| |
Last updated on November 15, 2020. This conference program is tentative and subject to change
Technical Program for Wednesday November 18, 2020
|
WeA31 |
L-1 |
C4: Circuits and Systems |
Regular Session |
|
11:00-11:15, Paper WeA31.1 | |
A Study on Shoot-Through Reduction of DC-DC Converter Pre-Driver Using Starving Resistor |
|
Sarkar, Sayan | HKUST |
Ki, Wing-Hung | HKUST |
Keywords: Circuits and Systems, Engineering Education, Power & Energy
Abstract: This research
studies the effect of a starving resistor in various pre-driver schemes
for shoot-through loss reduction in the buffer of an integrated DC-DC
converter and explores how the efficiency is affected. The starving
resistor (Bi-directional delay element) reduces the short circuit
current of an inverter by developing time skewed gate driving signals
for the driven stage NMOS and PMOS inside a buffer. The starving
resistor scheme enhances the efficiency if it is inside the buffer of a
switch, but is not as efficient if it is inside the buffer of an active
diode. The efficiency of the buffer can be further enhanced by adding
delay generator schemes within a buffer. Results are validated via
extensive SPICE simulations
|
|
11:15-11:30, Paper WeA31.2 | |
Making Sense of Occluded Scenes Using Light Field Pre-Processing and Deep-Learning |
|
Liyanage, Namalka | University of New South Wales |
Abeywardena, Kalana Gayal | University of Moratuwa |
Jayaweera, Sakila Sandeepani | University of Moratuwa |
Wijenayake, Chamith | University of Queensland |
U. S. Edussooriya, Chamira | University of Moratuwa |
Seneviratne, Suranga | University of Sydney |
Keywords: Circuits and Systems, Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: A combined
approach of low-complexity light field depth filtering and deep learning
is proposed for object classification in the presence of partial
occlusions. The proposed approach exploits depth information embedded in
multi-perspective four-dimensional (4-D) light fields via
low-complexity 4-D sparse depth filtering and deep-learning. The
proposed 4-D depth filter, designed using numerical optimization
techniques by formulating as a minimization problem, is shown to
outperform typical light field refocusing based on 4-D shift-sum
averaging filters. Experiments conducted using a light field dataset
acquired by a Lytro camera verify 45% and 27% better performance in
terms of object classification accuracy compared to the cases when no
depth filtering is employed and standard shift-sum refocusing is
employed, respectively.
|
|
11:30-11:45, Paper WeA31.3 | |
Development of an Automated Aquaponics System with Hybrid Smart Switching Power Supply |
|
Magwili, Glenn | Mapua University |
Egargue, Jerome Christian | Mapua University |
Pacaigue, Frederick | Mapua University |
Galicia, Raymund Glor | Mapua University |
Keywords: Circuits and Systems, Robotics, Control Systems & Theory
Abstract: This paper
shows the design, construction, and implementation of an Automated
Aquaponics system. The majority of the commercial aquaponics system in
the Philippines is grid-dependent thus making it cost-ineffective. The
design of the system has three-part; hydroponics, aquaculture, and
microcontrollers. The design consists of a hybrid power supply that
allows operation dependent on the grid or PV installations. Aside from
integrating it to be partially dependent on renewable energy, the system
was designed to adapt and adjust the monitored environment to be more
habitable for the aquaculture. Through the use of relays, dump energy is
also observed. Through the real-time monitoring system, the design
allows users to record and system痴 condition, power, energy
consumption, and power supply dependency simultaneously.
|
|
11:45-12:00, Paper WeA31.4 | |
WatAr: An Arduino-Based Drinking Water Quality Monitoring System Using Wireless Sensor Network and GSM Module |
|
Almojela, Irish Franz | FAITH Colleges |
Gonzales, Shyla Mae | FAITH Colleges |
Gutierrez, Karen | FAITH Colleges |
Santos, Adonis | FAITH Colleges |
Malabanan, Francis | FAITH Colleges |
Tabing, Jay Nickson | FAITH Colleges |
Escarez, Christopher | FAITH Colleges |
Keywords: Circuits and Systems, Signal and Image Processing
Abstract: This paper
presents an Arduino-based monitoring system that measures four
physicochemical parameters of water: pH, temperature, turbidity, and
electrical conductivity to identify possible water contamination. The
system is designed with two nodes: the sensor node and the sink node.
The sensor node performs the collection, pre-processing of data, relay
of sensed data wirelessly, data storage systems, data display in an LCD
and ThingSpeak channel, and SMS notifications. While the sink node
performs data reception from the sensor node, data display in an LCD,
and alert systems utilizing a buzzer whenever water is determined to be
unsafe for drinking.
|
|
12:00-12:15, Paper WeA31.5 | |
Novel Framework for Modelling High Speed Interface Using Python for Architecture Evaluation |
|
Katare, Siddharth | HCL Technologies Pvt Ltd |
Keywords: Circuits and Systems, Signal and Image Processing, Wireless Communications & Networks
Abstract: This paper
presents a framework for modelling Serdes system, SymbaPy, based on
Python scripting language along with efficient numerical computation
libraries. This paper discusses the building blocks of Serdes to create a
framework in Python for system models. The paper also discusses the
features of Python language which makes it an adequate tool for
modelling the Serdes. We also demonstrate application of this framework
by creating a model for MIPI DPHY and CPHY which generates the
eye-diagrams at different points in the communication chain.
|
|
WeA32 |
L-2 |
SS-3: Special Session - New Trends of Biometrics |
Invited Session |
Chair: Taguch, Akira | Tokyo City University |
|
11:00-11:15, Paper WeA32.1 | |
Classification of User Satisfaction Using Facial Expression Recognition and Machine Learning (I) |
|
Koonsanit, Kitti | Tokyo Metropolitan University |
Nishiuchi, Nobuyuki | Tokyo Metropolitan University |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Several papers
and articles regarding the measurement of UX (user experience) as the
satisfaction have been published. However, in the most approaches, UX
was measured by questionnaire or survey collection method, which may
lead to bias and a lack of exact feeling data of the target users. On
the other hand, soft biometric data such as gender, age and facial
expression can be used as the essential data for the user satisfaction
analysis. In this research, we assume that the facial expression is
essential in physical expressions and can be used as the accurate
satisfaction data. It may be possible to capture the user痴 facial
expression during the particular use of products or services without
usersconsciousness. However, in general cases, it is difficult to get
the final user satisfaction. This study aimed to propose a framework to
classify the final user satisfaction of products or services by the
facial expression recognition and machine learning. The proposed
framework consists of the three main steps. First, the data of facial
expression, gender, age and the final user satisfaction are
experimentally collected. Second, classification models are built by
machine learning algorithms using the data. Finally, the model
evaluation is employed to verify the accuracy of the model. After making
the classification model, it is possible to classify the final user
satisfaction only from the data of facial expression, gender and age.
|
|
11:15-11:30, Paper WeA32.2 | |
Introduction
of Fractal Dimension Feature and Reduction of Calculation Amount in
Person Authentication Using Evoked EEG by Ultrasound (I) |
|
Mukai, Kotaro | Tottori University |
Nakanishi, Isao | Tottori Univerisity |
Keywords: Signal and Image Processing
Abstract: The aim of this
study is to authenticate individuals using an electroencephalogram
(EEG) evoked by a stimulus. EEGs are highly confidential and enable
continuous authentication during the use of or access to the given
information or service. However, perceivable stimulation distracts the
users from the activity they are carrying out while using the service.
Therefore, ultrasound stimuli were chosen for EEG evocation. In our
previous study, an Equal Error Rate (EER) of 0 % was achieved; however,
there were some features which had not been evaluated. In this paper, we
introduce a new type of feature, namely fractal dimension, as a
nonlinear feature, and evaluate its verification performance on its own
and in combination with other conventional features. As a result, an EER
of 0 % was achieved when using five features and 14 electrodes, which
accounted for 70 support vector machine (SVM) models. However, the
construction of the 70 SVM models required extensive calculations. Thus,
we reduced the number of SVM models to 24 while maintaining an EER = 0
%.
|
|
11:30-11:45, Paper WeA32.3 | |
Wavelet Transform and Machine Learning Based Biometric Authentication Using EEG Evoked by Invisible Visual Stimuli (I) |
|
Miyake, Takahiro | Tottori University |
Kinjo, Nozomu | Tottori University |
Nakanishi, Isao | Tottori Univerisity |
Keywords: Signal and Image Processing
Abstract: We have
proposed to authenticate individuals using evoked electroencephalogram
(EEG) by invisible visual stimulation. In the previous study, we
introduced a wavelet transform, which is a time-frequency analysis
method, and extracted the features including time information to
discriminate individuals more accurately. By using the Euclidean
distance matching, Equal Error Rate (EER) was 9.4%. In this paper, to
further improve the verification performance, we introduce machine
learning. EER of 8.1% is achieved when neural networks trained by
ensemble learning using 30 networks.
|
|
WeA33 |
L-3 |
ML4: Machine Learning, Cloud and Data Analytics |
Regular Session |
Chair: Liu, Di | Yunnan University |
|
11:00-11:15, Paper WeA33.1 | |
Non Invasive Continuous Detection of Mental Stress via Readily Available Mobile-Based Help Parameters |
|
Samarasekara, Isuru Dananjaya | Sri Lanka Institute of Information Technology |
Wickramaarachchige, Champani Udayangani Hamy | Sri Lanka Institute of Information Technology |
Jayaweera, Gihan | Sri Lanka Institute of Information Technology |
Jayawardhana, Dinusha | Sri Lanka Institute of Information Technology |
Abeygunawardhana, Pradeep | Sri Lanka Institute of Information Technology |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: Mental stress
is a universal condition experienced by all humans alike at least once
in their lifespan. Stress can vary from person to person depending on
their age, gender, socioeconomic background and lifestyle. Although some
amount of stress act as a beneficial factor, accumulated stress levels
over a long period could lead to many other health problems. Hence,
early detection and diagnosis is the pre-eminent method in which this
damaging phenomenon can be managed. Vocal indices and facial expressions
of an individual disclose surfeit amounts of information including
emotions, and in turn stress. In this research two noninvasive and
dynamic mechanisms, in the form of speech emotion analysis and facial
expression analysis, are used in detecting stress, through emotion
analysis, of an individual in a mobile and real-life environment as
opposed to utilizing only one mechanism to detect stress in a controlled
environment. This study proposes a holistic approach in detecting
mental stress, through the categorization and identification of
fear/anxiety, sadness, anger and disgust as stress emotions via
extracted vocal and facial features. A finalized product is proposed to
recognize stress, averaged biased on the prediction probabilities of the
two detection mechanisms which then can be used to individually and
independently monitor stress in order to maintain it without relying on
physical medical checkups.
|
|
11:15-11:30, Paper WeA33.2 | |
Transfer Learning Based Method for COVID-19 Detection from Chest X-Ray Images |
|
Rashid, Nayeeb | Bangladesh University of Engineering and Technology |
Hossain, Md Adnan Faisal | Bangladesh University of Engineering & Technology |
Ali, Mohammad | Bangladesh University of Engineering & Technology |
Sukanya, Mumtahina Islam | Bangladesh University of Engineering and Technology |
Mahmud, Tanvir | Bangladesh University of Engineering and Technology |
Fattah, Shaikh Anowarul | BUET |
Keywords: Disasters and Humanitarian Technology, Biomedical Engineering, Machine Learning, Cloud and Data Analytics
Abstract: Radiology
examination of chest radiography or chest X-ray (CXR), is currently
performed manually by radiologists. With the onset of the COVID-19
pandemic, there is now a need to automate this process which is
currently one of the key methods of primary detection of the SARS-Cov-2
virus. This will lead to shorter diagnosis time and less human error. In
this study, we try to perform three-class image classification on a
dataset of chest X-rays of confirmed COVID-19 patients(408 images),
confirmed pneumonia patients(4273 images), and chest X-rays of healthy
people(1590 images). In total the dataset consists of 6271 people. We
aim to use a Convolutional Neural Network(CNN) and transfer learning to
perform this image classification task. Our model is based on a
pre-trained InceptionV3 network with weights trained on the ImageNet
dataset. We fine-tune the layers of the Inception network to train it to
our specific task. We try fine-tuning the network to different extents
by freezing a different number of layers and then comparing accuracy for
each variation of the network. To evaluate the performance of our
network we use several metrics which include Classification accuracy,
Precision, Sensitivity, and Specificity. Our proposed method achieves an
accuracy of 96.33% on a 3-class classification task (Normal, COVID-19,
Pneumonia) and an accuracy of 99.39% on a 2-class (COVID and Non-COVID)
classification task.
|
|
11:30-11:45, Paper WeA33.3 | |
A Multi-Model Based Ensembling Approach to Detect COVID-19 from Chest X-Ray Images |
|
Saha, Oishy | Bangladesh University of Engineering and Technology |
Tasnim, Jarin | Bangladesh University of Engineering and Technology |
Raihan, Md. Tanvir | BUET |
Mahmud, Tanvir | Bangladesh University of Engineering and Technology |
Ahmmed, Istak | PrimeSilicon Technology |
Fattah, Shaikh Anowarul | BUET |
Keywords: Disasters and Humanitarian Technology, Biomedical Engineering, Machine Learning, Cloud and Data Analytics
Abstract: Since the onset
of COVID-19, radiographic image analysis coupled with artificial
intelligence (AI) has become popular due to insufficient RT-PCR test
kits. In this paper, an automated AI-assisted COVID-19 diagnosis scheme
is proposed utilizing the ensembling approach of multiple convolutional
neural networks (CNNs). Two different strategies have been carried out
for ensembling: A feature level fusion-based ensembling method and a
decision level ensembling method. Several traditional CNN architectures
are tested and finally in the ensembling operation, MobileNet,
InceptionV3, DenseNet201, DenseNet121 and Xception are used. To handle
the computational complexity of multiple networks, transfer learning
strategy is incorporated through ImageNet pre-trained weight
initialization. For feature-level ensembling scheme, global averages of
the convolutional feature maps generated from multiple networks are
aggregated and undergo through fully connected layers for combined
optimization. Additionally, for decision level ensembling scheme, final
prediction generated from multiple networks are converged into a single
prediction by utilizing the maximum voting criterion. Both strategies
perform better than any individual network. Outstanding performances
have been achieved through extensive experimentation on a public
database with 96% accuracy on 3-class (COVID-19/normal/pneumonia)
diagnosis and 89.21% on 4- class (COVID-19/normal/viral
pneumonia/bacterial pneumonia) diagnosis.
|
|
11:45-12:00, Paper WeA33.4 | |
A Maximum Entropy Approach for Mapping Falcata Plantations in Sentinel-2 Imagery |
|
Marcial, Marcia Coleen | Caraga State University |
Santillan, Jojene | Caraga State University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: Mapping tree
species is essential for monitoring, planning, and better managing
industrial tree plantations (ITP). Due to the intensive procedure of
field sampling and multi-class manual training data collection for image
classification, an approach that allows fewer data would be efficient.
This study evaluated the performance of a one-class classifier called
Maximum Entropy (MaxEnt) for mapping Falcata (Paraserianthes falcataria)
in Sentinel-2 imagery. Two MaxEnt parameters were tested, namely sample
size and binary threshold. Using a default threshold of 0.5, MaxEnt can
provide classification accuracies ranging from 89.41-92.84% using
sample sizes as small as 30 and as high as 500. A 0.3 binary threshold
applied to MaxEnt logistic output with 500 samples were the best
parameter values for classifying Falcata using Sentinel-2 imagery.
|
|
12:00-12:15, Paper WeA33.5 | |
Web-Based Riverbank Overflow Forecasting and Monitoring System |
|
Soriano, Aldrin | Pamantasan Ng Cabuyao |
Lozas, Ma. Vienna | Pamantasan Ng Cabuyao |
Nuz, Carlo | Pamantasan Ng Cabuyao |
Zapanta Jr., Ricardo | Pamantasan Ng Cabuyao |
Bea, Mary Grace | Pamantasan Ng Cabuyao |
Magnate, Monica | Pamantasan Ng Cabuyao |
Medina, Oliver | Pamantasan Ng Cabuyao |
Keywords: Disasters and Humanitarian Technology, Software & Database Systems, Machine Learning, Cloud and Data Analytics
Abstract: River
overflowing is a common problem in the Philippines. And knowing the fact
that we lack proper devices and systems to monitor the water flow makes
it even more disturbing. Therefore, this project is to develop a
prototype that will measure, monitor, and forecast the water level and
the volume of water flowing through the riverbanks. The proponents used
Agile development method includes systematic process of designing,
developing the prototype, evaluating instructional programs, and system
that must meet the criteria of the effectiveness of the project. The
prototype consists of algorithms that is performed to have a reliable
data. In measuring the river parameters, Wireless Sensor Network (WSN)
Algorithm is used to interconnect the sensor nodes in different area of
the riverbank. In forecasting, the device performed a machine learning
by gathering raw data to run in Voting Algorithm. In monitoring, the
prototype provides Cabuyao River Monitoring System (CRMS) a web-based
application that uses a Decision Tree Algorithm that will give
information and warning to the community. This device and system aim to
give early warnings to the communities being both in a timely and
systematic way, providing advanced information on its behavior to better
prepare the disaster team and government.
|
|
WeA34 |
L-4 |
SD1: Software & Database Systems; Photonics; Disasters and Humanitarian
Technology |
Regular Session |
Chair: Okada, Minoru | Nara Institute of Science and Technology |
|
11:00-11:15, Paper WeA34.1 | |
Using Remote Sensing and GIS to Identify Alternative Water Sources for Butuan City, Philippines |
|
Galinato, Rachiel | Caraga State University |
Santillan, Meriam | Caraga State University |
Keywords: Software & Database Systems
Abstract: The Taguibo
River Watershed Forest Reserve TRWFR is its only major source of water
in Butuan City. The City of Butuan has experienced rapid growth and
becomes more progressive and urbanized community which leads to the
increase of water demand, thus, intermittent water supply was
experienced by the consumers, and the need to look for alternative water
source is inevitable. This study is focused on the identification of
possible alternative water sources for the city using remote sensing and
GIS-based approaches. Specifically, this study aims to locate and
delineate candidate watersheds within the proximity of the city using
GIS-based approaches, conduct hydrological modeling in each candidate to
determine physical characteristics and the quantity of water produced,
determine the water quality of the candidates, and to assess the number
of people in the city each candidate can supply. After the HEC-GeoHMS
pre-processing, five potential watersheds other than Taguibo watershed
that is within the proximity of Butuan City were identified. Considering
the different variables such as watershed area, river slope, soil type,
curve number, and water quantity, results showed that the most suitable
alternative watershed was Simbalan watershed.
|
|
11:15-11:30, Paper WeA34.2 | |
MATA: Mission, Attitude, and Telemetry Analysis Software for Micro-Satellites |
|
Tan, Vanessa | University of the Philippines Diliman |
Labrador, John Leur | University of the Philippines Diliman |
Talampas, Marc Caesar | University of the Philippines Diliman |
Keywords: Software & Database Systems, Aerospace Technology, Engineering Education
Abstract: With the rise
in popularity of small satellites, there has been an increasing demand
for a software tool that covers different stages of satellite
development. In this paper, we extend a small satellite simulation
software originally developed for earth-observation satellites
Diwata-1 and Diwata-2 to support other satellite missions. This support
covers various stages: from ideation, development, and up to post-launch
assessment. This paper focuses on the Mission, Attitude, and Telemetry
Analysis (MATA) software, which can simulate orbit, attitude, and camera
views from planned earth-observation missions. Satellite engineers can
also use MATA in a hardware-in-the-loop configuration, serving as
one of the last functionality checks before launching the
satellite. MATA can also read telemetry files from an orbiting satellite
and re-project it in a virtual environment for a more intuitive
assessment. This paper also covers the
implemented framework for the simulator. This framework would
help future developers to extend the simulator to other applications
like star tracking simulations, mixed reality satellite training, and
space educational software.
|
|
11:30-11:45, Paper WeA34.3 | |
Assessment of Heavy Metal Concentration in Soil Using Remotely Sensed Data |
|
Campana, Maria Belinda | Caraga State University |
Asube, Lorie Cris | Caraga State University |
Japitana, Michelle | Caraga State University |
Keywords: Disasters and Humanitarian Technology, Engineering Management
Abstract: Abstract
Remote Sensing has been used nowadays for environmental monitoring as it
offers a faster and less expensive way of monitoring the environment.
With various activities conducted around the Tubay catchment (e.g.,
mining, agriculture), monitoring the quality of its soil by determining
the heavy metal concentration (HMC) in soil, mainly its Lead (Pb)
content, became the main objective of this study. Remote sensing
technologies, together with field data, are used in this study to create
a model that would predict the lead content of the soil in Tubay
catchment through statistical analysis. The model created in this study
is used in an ArcGIS software. It resulted to a model-predicted value of
-263.993 ppm of Lead in minimum, and a model-predicted value of 308.482
ppm of Lead in maximum. Due to the soil test result, which yields a
majority of Not Detected values, the model created in this study is not
validated.
|
|
11:45-12:00, Paper WeA34.4 | |
Integrating
Geographic Information System, Remote Sensing Data, Field Surveys, and
Hydraulic Simulations in Irrigation System Evaluation |
|
Gagula, Arnaldo | Caraga State University |
Santillan, Jojene | Caraga State University |
Keywords: Disasters and Humanitarian Technology, Engineering Management
Abstract: Drought is
characterized by a deficiency or lack of rain in a specific or extended
period of time resulting to water shortage affecting animals, plants,
and people. In the occurrence of this phenomenon, agriculture is the
most affected industry. Agriculture plays a significant role in the
Philippines, considering that 32% of the country's total area is
agricultural lands; of these, 44% are permanent croplands. In the
absence of precipitation, irrigation systems are constructed to supply
water in agricultural areas. In Butuan City, the agriculture industry is
an essential contributor to the city's economy. Drought occurred
despite the presence of a vast network of irrigation systems. There is a
necessity to quantify the effectiveness of these irrigation systems. In
this study, irrigation systems were evaluated using an integrated
approach of geographic information system (GIS), remote sensing data
(RS), and field surveys at the farm level in Butuan City. The hydraulic
model simulation provides a map on the extent of water delivered by the
irrigation canal, including the discharge of water that was delivered.
Such maps were used to evaluate the effectiveness of the irrigation
system.
|
|
WeA35 |
L-5 |
W4: Wireless Communications & Networks |
Regular Session |
Chair: Duong, Quang-Thang | Nara Institute of Science and Technology |
|
11:00-11:15, Paper WeA35.1 | |
Positioning Outage Probability Analysis for Navigation Satellite Communication Over Fading Channels |
|
Bitragunta, Sainath | BITS Pilani, Rajasthan |
Keywords: Wireless Communications & Networks, Signal and Image Processing, Aerospace Technology
Abstract: In this paper,
the author investigates the positioning outage probability performance
of navigation satellite link. For the analysis, the author considers the
satellite downlink wherein the user has a mobile navigation receiver.
The author presents an insightful analysis which comprises of analytical
results for positioning outage probability (POP). Specifically, the
author derives tractable expressions for POP as functions of link
parameters in various fading scenarios, namely, small scale Rayleigh
fading, Rician fading, Shadow fading, and combined Rician and shadow
fading. To numerically evaluate the POP performance of the derived
analytical results, the author plots the POP for various simulation
parameters. From the numerical plots, the author observes that the POP
improves as the average signal power to interference plus noise power
ratio (SINR) and bandwidth. However, this dependence on model parameters
is not the same for all the fading scenarios. Finally, the author
suggests multi-antenna receive diversity and combining technique to
improve POP performance.
|
|
11:15-11:30, Paper WeA35.2 | |
STPAP: Source Transmit Power Adaptation Policy for Collaborative Wireless Systems |
|
Jha, Vidit | BITS Pilani, Rajasthan |
Bitragunta, Sainath | BITS Pilani, Rajasthan |
Keywords: Wireless Communications & Networks, Signal and Image Processing, Power & Energy
Abstract: For the design
of energy-efficient or green communication systems and networks, power
adaptation has been studied extensively in the literature. A vital
aspect of the same is to minimize the usage of resources wherever
possible. This research implements a Source Transmit Power Adaptation
Policy (STPAP) for a two hop collaborative wireless communication
system. Our objective is to optimize end-to-end fading averaged-energy
efficiency (FA-EE) when the source is subject to an average source power
constraint. Specifically, we derive an analytical expression for FA-EE
in terms of source power, which is adapted as a function of its local
channel state information (CSI). We compare optimal FA-EE results with
CSI-independent, fixed source power FA-EE and verify through Monte-Carlo
(MC) simulations and analytical results. We find that the proposed
STPAP delivers superior performance in terms of FA-EE. We further extend
our benchmarking to a scenario where a direct link between source and
destination is absent. We also compare optimal FA-EE with fixed power
FA-EE and quantify the performance gains achieved by the proposed
policy.
|
|
11:30-11:45, Paper WeA35.3 | |
A Smart Location-Aware Hand Sanitizer Dispenser System |
|
Loong, Jian Wen | University of Glasgow, Singapore |
Chan, Chee Leong | Singapore Institute of Technology |
Venkatarayalu, Neelakantam | Singapore Institute of Technology |
Lee, Jeannie | Singapore Institute of Technology |
Keywords: Disasters and Humanitarian Technology, Software & Database Systems, Wireless Communications & Networks
Abstract: The design,
development and results from the deployment of a hand hygiene monitoring
and reminder system is presented. The system is based on a dispenser
equipped with low-energy Bluetooth technology which when coupled with a
mobile application provides the basic location-awareness necessary to
track the proximity of health-care worker to the dispenser. The system
architecture provides the unique feature of selectively enabling the
dispenser action in the smart dispenser only when the intended user is
in its proximity. This feature is critical for deployment of hand
sanitizer dispensers in hospital wards where there is apprehension in
patients ingesting the sanitizer persists. The mobile application
maintains an online database of the hand hygiene event records. The
records are presented to administrators through a web-based dashboard
for assessment and improvement of organizational hand-hygiene compliance
levels. Preliminary quantitative results as well as qualitative results
are presented and demonstrate the effectiveness of the system to serve
as form of motivation for health care workers to improve their hand
hygiene compliance.
|
|
11:45-12:00, Paper WeA35.4 | |
Performance Evaluation of LDPC Coded Partial-Access IDMA Systems with SNR Evolution |
|
Yamagishi, Masaya | Doshisha University |
Cheng, Jun | Doshisha University |
Kimura, Tomotaka | Doshisha University |
Song, Guanghui | Singapore University |
Keywords: Wireless Communications & Networks
Abstract: The performance
of the quasi-cyclic low-density parity-check (QC-LDPC) coded
partial-access interleave division multiple access (IDMA) systems is
evaluated with the SNR (signal-to noise ratio) evolution algorithm. The
partial access IDMA system is the IDMA system in which the 0s, i.e.,
nonenergy transmission, are inserted into the chip sequence. The SNR
evolution algorithm is developed and employed to evaluate the systems.
Numerical and simulation results show that the partial access has better
BER (bit error rate) performance than that of the conventional full
access in a range of low Eb/N0, and the proposed IDMA system with the
3GPP NR QC-LDPC codes has a good error-floor performance.
|
|
WeA36 |
L-6 |
SOC1: Social Implications of Technology |
Regular Session |
Chair: Chen, Na | Nara Institute of Science and Technology |
|
11:00-11:15, Paper WeA36.1 | |
An Integrated Theory for Chatbot Use in Air Travel: Questionnaire Development and Validation |
|
Trapero, Hazel | De La Salle University Manila |
Ilao, Joel | De La Salle University Manila |
Lacaza, Rutcher | Far Eastern University |
Keywords: Social Implications of Technology
Abstract: Airline
industry is a major global leader in aviation. It even provides service
to almost every other sector, however, it does not receive significant
attention, despite its importance. Moreover, its service quality is an
aggregate of different interactions between the customers and airline
companies. This drove them to implement new business model to conform to
the new competitive atmosphere in the industry whose operation is
taking place in a completely globalized environment. Thus, the use of
chatbots is one of the avenues to meet this end. However, there is a
dearth of standardized and validated instrument that best fit to
evaluate the use of chatbots in the airline industry based on the
combined set of constructs as identified in the conceptual framework.
Thus, this study aims to develop and validate an instrument that will
evaluate the adoption of chatbots in a service industry, like the
airline industry, as well as its non-adoption. Based on the reliability
and internal consistency evaluation, only one item was deleted (PIIT
construct) since it has the lowest item-test correlation that caused the
reliability coefficient to be less than the suggested value of 0.70.
All statements in each of the constructs had positive signs, thus, were
not reversely worded. Lastly, all the scale reliability coefficient or
the overall alpha values are way higher than the suggested value, which
means that the internal consistency is either acceptable or highly
acceptable.
|
|
11:15-11:30, Paper WeA36.2 | |
Experimental Validation of Findings Using Brain Computer Interface in Autistic Children |
|
Ravindranathan, Reshmi | Tata Consultancy Services |
Tommy, Robin | Tata Consultancy Services |
Krishnan, Athira | Tata Consultancy Services |
Keywords: Social Implications of Technology
Abstract: Autism is a
developmental disorder that impairs the ability of affected to
communicate and interact. This disease impacts the nervous system,
resulting in poor emotional, social, cognitive and physical health.
Affected ones are however capable of excelling in some or other field of
their interest. To identify their interest, they need to be exposed to
wide range of activities on a daily basis. Manual interpretations can go
wrong as a person can complete a task with interest, fear, etc. Brain
Computer Interface (BCI), helps read and analyze the human brain
activity using brain waves. Attention values and brain waves from
samples are analyzed while performing activities as part of experiment.
So in this study using BCI, manually interpreted sample's interest to a
task is verified experimentally. It is learnt that, samples show an
improved percentage attention during sessions of their areas of
interest.
|
|
11:30-11:45, Paper WeA36.3 | |
AwareME: Public Awareness through Game Based Learning |
|
Dassanayake, Moditha | Sri Lanka Institute of Information Technology |
Jayasiri, Lisara | Sri Lanka Institute of Information Technology |
Wijesinghe, Sandali | Sri Lanka Institute of Information Technology |
Keenawinna, Ruwin | Sri Lanka Institute of Information Technology |
Rankothge, Windhya | Sri Lanka Institute of Information Technology |
Gamage, N.D.U | Sri Lanka Institute of Information Technology |
Keywords: Social Implications of Technology, Disasters and Humanitarian Technology
Abstract: It is widely
recognized that a nation with minimum problems relating to areas such as
health, environment, infrastructure, and technology is a developed
country [1]. However, the developing/ lower-middle income countries need
much improvements in the above-mentioned areas, as they are still
lacking in those areas [1]. Apart from the risk associated with these
problems, the main challenge faced by developing countries is, making
the public aware of these problems. In this paper, we are proposing a
mobile game-based learning platform: 鄭wareMEwhich focuses on
following problems: (1) health awareness (dengue fever), (2)
environmental awareness (garbage disposal), (3) cyber security awareness
(social media) and (4) safety awareness (road safety). The 鄭wareME
platform includes quizzes, 2D/3D puzzle games, and 3D action games with
activities to improve the cognitive skills and awareness of the public.
We have provided the results of an initial performance evaluation of
鄭wareMEplatform.
|
|
11:45-12:00, Paper WeA36.4 | |
E-Parakh: Unsupervised Online Examination System |
|
Pandey, Anoop Kumar | C-DAC Bangalore |
Pandey, Saubhik | IIT Patna |
Rajendran, Balaji | Centre for Development of Advanced Computing (CDAC), Bangalore |
B S, Bindhumadhava | C-DAC Bangalore |
Keywords: Social Implications of Technology, Engineering Education
Abstract: Online
examinations have become the norm, owing to the global Covid-19 pandemic
in various academic settings such as schools, colleges etc... and even
for job selection. The existing applications in this space, do not
assure against fraudulent practices, though some of them are highly
restrictive and constrain the candidates severely. We propose our system
e-Parakh, an online examination system that can be used by the
candidate even from his mobile phone app, which significantly reduces
the resource requirements and therefore the cost involved for the
candidate. The application also facilitates both supervised and
unsupervised remote monitoring of the examination, through a variety of
techniques including live video and audio streaming of not only the
candidate, but also the candidate's surrounding environment, liveliness
check of the candidate, facial comparison of the candidate with his/her
photograph etc.. This application provides the evaluator to cross-check
the candidate activity at any time during the examination as well as
after the examination by recording the whole video and audio.
|
|
12:00-12:15, Paper WeA36.5 | |
An Analysis of Patent Application in Pharmaceutical Industry in India |
|
Mitsumori, Yaeko | Osaka University |
Keywords: Social Implications of Technology, Engineering Management, Biomedical Engineering
Abstract: The Indian
pharmaceutical industry today is No. 3 in the world based on volume. Due
to the World Trade Organization痴 Agreement on Trade-Related Aspects of
Intellectual Property Rights (TRIPS), enforced in 1995, India revised
its patent law in 2005 and re-introduced product patents. Taking
advantage of TRIPS enforcement in 1995 and the re-introduction of
product patents in India in 2005, large foreign capital pharmaceutical
firms successively re-entered the Indian market; they began to engage in
R&D activities and produce formulations and active pharmaceutical
ingredients (APIs). Such foreign capital companies started to submit
patent applications to the Indian Patent Office (IPO), which began in
2005 to examine product patent applications under the new, revised
patent law. However, both IPO and IQVIA data show that the number of
patent applications in pharmaceuticals has been declining in past years.
|
|
WeB31 |
L-1 |
ML6: Machine Learning, Cloud and Data Analytics |
Regular Session |
|
14:45-15:00, Paper WeB31.1 | |
Genetic Algorithm-Based Visible Band Tetrahedron Greenness Index Modeling for Lettuce Biophysical Signature Estimation |
|
Concepcion II, Ronnie | De La Salle University |
Lauguico, Sandy | De La Salle University |
Tobias, Rogelio Ruzcko | Asia Pacific College |
Bandala, Argel | De La Salle University |
Dadios, Elmer | De La Salle University |
Sybingco, Edwin | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Software & Database Systems
Abstract: Lightness
signal and color reflectance constitute the reflected luminance spectra
from camera captured image to camera lenses. The intensity of lightness
and visible RGB signals deviates as the camera distance to object
varies. The presence of uneven distribution of photosynthetic light
causes angular light effect of shadowing on the focal object and light
emitting objects placed on the visually noisy background added a
challenge in materializing an efficient greenness index for crop
phenotyping. The proposed method in this study compensates excessive
relative brightness on the image by introducing lightness rectification
coefficient and employing genetic algorithm to derive a novel visible
tetrahedron greenness index (gvTeGI) based on normalized green waveband.
Hybrid neighborhood component analysis and Pearson痴 correlation
coefficient approach for feature selection resulted to retaining
photosynthetic canopy area, and correlation and homogeneity texture
features as highly important descriptors for biophysical signatures
considered in this study which are lettuce fresh weight, height and
number of spanning leaves. The selection, crossover and mutation rates
used to optimize the genetic algorithm model are 0.2, 0.8 and 0.01
respectively. Indoor and outdoor aquaponic system was deployed for
6-week full crop life cycle cultivation. Regression machine learning
models were used to estimate biophysical signatures from extracted
gvTeGI channels. Optimized Gaussian processing regr
|
|
15:00-15:15, Paper WeB31.2 | |
HelipadCat: Categorised Helipad Image Dataset and Detection Method |
|
Bitoun, Jonas | National University of Singapore |
Winkler, Stefan | National University of Singapore |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Software & Database Systems
Abstract: We present
HelipadCat, a dataset of aerial images of helipads, together with a
method to identify and locate such helipads from the air. Based on the
FAA痴 database of US airports, we create the first dataset of helipads,
including a classification by visual helipad shape and features, which
we make available to the research community. The dataset includes nearly
6,000 images with 12 different categories. We then train several
Mask-RCNN models based on ResNet101 using our dataset. Image
augmentation is applied according to learned augmentation policies. We
characterize the performance of the models on HelipadCat and pick the
best-performing configuration. We further evaluate that model on the
metropolitan area of Manila and show that it is able to detect helipads
successfully, with their exact geographical coordinates, in another
country. To reduce false positives, the bounding boxes are filtered by
confidence score, size, and the presence of shadows. Dataset and code
are available for download.
|
|
15:15-15:30, Paper WeB31.3 | |
Historical Places & Monuments Identification System |
|
Godewithana, Navod | Sri Lanka Institute of Information Technology |
Jayasena, Khema | Sri Lanka Institute of Information Technology |
Nagarawaththa, Chamodi | Sri Lanka Institute of Information Technology |
Croos, Praveenth | Sri Lanka Institute of Information Technology |
Harshanath, Buddika | Sri Lanka Institute of Information Technology |
Alosius, Jesuthasan | Sri Lanka Institute of Information Technology |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Software & Database Systems
Abstract: Sri Lanka,
which is known as "the pearl of the Indian ocean" provides great
survival and civilization history dating back to the 3rd century. Most
of the archaeological sites are attracted by not only Sri Lankans but
also by tourists. When searching for the information about the
archaeological sites, there are lack of trusted information sources and
smart online platforms. Even though some information is available, no
convenient and efficient ways to retrieve them. When trusted information
is provided in a user-friendly manner, the value will be added to the
Sri Lankan economy. Since the world is driving towards the 摘-Era
everything is involved with Information Technology. The proposed system
contributes to solve the above problems with Artificial Intelligence
& Machine Learning concepts. The system is assisted using four major
components namely, image identification, community platform,
conversational bot, and image visualization. The image Identification
component identifies the archaeological sites using image processing
techniques. The community platform gathers trusted information from
archaeologists and deep learning techniques are used to deliver that
content to the users. The artificial intelligence conversational bot is
established to communicate and retrieve available information in a
convenient manner. The image visualization component is used to provide
reality visualization on archaeological sites using the augmented
reality techniques.
|
|
15:30-15:45, Paper WeB31.4 | |
A Smart Space with Music Selection Feature Based on Face and Speech Emotion and Expression Recognition |
|
Maningo, Jose Martin | De La Salle University |
Bandala, Argel | De La Salle University |
Vicerra, Ryan Rhay | De La Salle University |
Dadios, Elmer | De La Salle University |
Bedoya, Karla Andrea | De La Salle University |
Carandang, Arramae Lauren | De La Salle University |
Maniaul, Paolo Joshua | De La Salle University |
Tabalan, Anna Rovia | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Software & Database Systems
Abstract: The
technological capabilities of computers in today's time continues to
improve in ways that seemed impossible before. It is common knowledge
that most people use computers to make everyday lives easier. Therefore,
it is vital to bridge the gap between humans and computers to provide
more suitable aid to the user. One way to do this is to use emotion
recognition as a tool to make the computer understand and analyze how it
can help its user on a much deeper level. This paper proposes a way to
use both face and speech emotion recognition as a basis for selecting an
appropriate music that can improve or relieve one's emotion or stress.
To accomplish this, Support Vector Machine with different kernels are
used to create the models for validation and testing on both the face
and speech emotion recognition. The final integrated system yielded an
accuracy rate of 78.5%.
|
|
15:45-16:00, Paper WeB31.5 | |
Crack Detection with 2D Wall Mapping for Building Safety Inspection |
|
Maningo, Jose Martin | De La Salle University |
Bandala, Argel | De La Salle University |
Bedruz, Rhen Anjerome | De La Salle University |
Dadios, Elmer | De La Salle University |
Lacuna, Ralph Joseph | De La Salle University |
Manalo, Andrea | De La Salle University |
Perez, Paolo Luis | De La Salle University |
Sia, Neil Patrick | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Software & Database Systems
Abstract: In the
Philippines, the number of earthquakes occurring has risen to an
alarming rate. 探he Big Oneis one of the biggest expected catastrophes
that is undoubtedly going to occur in the next decade as said by
various experts. Buildings that were able to withstand the upcoming
earthquakes, are to be inspected by engineers without knowing if the
safety of the building is compromised. Thus, there is a need for a
system that can inspect the cracks on the wall for faster and safer
inspection. The objective of this study is to develop a crack detecting
system capable of analyzing physical characteristics of cracks and
mapping the surface of the wall. The model to be used for classifying
and determining what cracks are, was trained with the use of Faster
R-CNN machine learning architecture. Trained using the SDNET2018
combined with actual data generated by the proponents, the resulting
system can detect cracks with an accuracy of 90% and classify the cracks
according to the shape The system also calculates its physical
properties, and has a recommender system that provides remarks on what
necessary actions can be done.
|
|
16:00-16:15, Paper WeB31.6 | |
Implementation of Automated Annotation through Mask RCNN Object Detection Model in CVAT Using AWS EC2 Instance |
|
Guillermo, Marielet | De La Salle University |
Billones, Robert Kerwin | De La Salle University |
Sybingco, Edwin | De La Salle University |
Dadios, Elmer | De La Salle University |
Fillone, Alexis | De La Salle University |
Bandala, Argel | De La Salle University |
Vicerra, Ryan Rhay | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Social Implications of Technology, Signal and Image Processing
Abstract: With machine
learning-based innovations becoming a trend, practical resolutions of
its implementation to large-scale data and computing problems must be
able to cope up as well. Currently, Graphic Processing Units (GPUs) are
being chosen over other available physical devices due to its powerful
computing capability and easier handling. Several cloud service
providers also made it possible for these to be accessible online
allowing higher serviceability and lower cost upfront for businesses.
With this said, the proponent would implement a common machine
learning-based application, automated annotation through Mask RCNN
Object Detection Model in CVAT, using AWS instance. The key purpose is
to showcase the viability of deploying data and computing intensive
system on the cloud.
|
|
WeB32 |
L-2 |
R10PG |
Regular Session |
|
14:45-15:00, Paper WeB32.1 | |
Semiconductor Wafer Surface: Automatic Defect Classification with Deep CNN |
|
Phua, Charissa, Han Ming | Swinburne University of Technology Sarawak, Malaysia |
Lau, Bee Theng | Swinburne University of Technology Sarawak, Malaysia |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: The rise of
artificial intelligence (AI) technologies and the increasing demand for
defect-free wafers encourage semiconductor manufacturers to pursue
automatic defect classification (ADC). The current ADC system classifies
wafer surface defects using optical and Scanning Electron Microscope
(SEM) images however manual classification is still a major part of the
process and it is not only labour-intensive and slow but also highly
prone to human error. This paper explores an ADC system based on deep
learning that automatically classifies wafer surface defects,
particularly from the metal layers, which brings consistency and speed,
allowing for better determination of wafer lifecycle as well as defect
root cause analysis in yield management. The proposed method adopts a
deep convolutional neural network (CNN) architecture for defect
classification using SEM images which can sub-classify defects into
respective sizing groups whereby defect size serves as an important
indicator of the origin of machine failure. This research observes that
the proposed ADC method achieves industrially pragmatic defect
classification performance based on experimentations with real
semiconductor datasets. This paper investigates the promise of transfer
learning for reducing computational cost and improving testing accuracy.
|
|
15:00-15:15, Paper WeB32.2 | |
TCP Over Satellite-To-Unmanned Aerial/Ground Vehicles Laser Links: Hybla or Cubic? |
|
Hoang, Le | The University of Aizu |
Anh, Pham | The University of Aizu |
Keywords: Photonics
Abstract: Satellite-based
Internet access for the whole globe, a newly emerging market, has
recently received much attention from both academia and industry. In
this paper, we present an analytical investigation of transmission
control protocol (TCP), which is the most popular protocol for various
Internet applications, in free-space optical (FSO) communications based
low earth orbit (LEO) satellite systems. Specifically, the throughput
performance of the potential deployed TCP variants for highspeed and
long-distance of FSO-based satellite networks, namely TCP Hybla and TCP
Cubic, are analyzed. Additionally, the incremental redundancy hybrid
automatic repeat request (IRHARQ) protocol is employed to enhance the
system performance over satellite-to-vehicles FSO links. The numerical
results quantitatively demonstrate the impact of atmospheric turbulence
on the TCP throughput and show that TCP Cubic outperforms Hybla in the
low error-rate conditions while Hybla provides the better performance
when the transmission errors happen more frequently. Monte Carlo
simulations are also performed to validate the accuracy of theoretical
derivations.
|
|
15:15-15:30, Paper WeB32.3 | |
An Efficient Approach for Paper Submission Recommendation |
|
Huynh, Son | University of Science, Ho Chi Minh City |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Nowadays, there
is a rapidly increasing number of conferences and journals in computer
science that make a lot of challenges for researchers to find an
appropriate venue to submit their scientific work. There is a need for a
recommendation system that can support researchers for a better process
of paper submission. In this paper, we present an efficient approach
for building such a recommendation model by using embedding methods,
Global Vector (GloVe) 1 created by Pennington et al. [1] and FastText 2
proposed by Facebook [2], Convolutional Neural Network (CNN) [3], and
LSTM. The experimental results show that the combination of CNNs and
FastText, CNN + FastText, can achieve the best performance in terms of
the Top 1 Accuracy compared with other techniques, including the S2RSCS
model, as presented in [4]. Moreover, the performance by using GloVe or
FastText is much better, faster, and more stable than S2RSCS in most
cases.
|
|
15:30-15:45, Paper WeB32.4 | |
An Evolutionary Algorithm for Data Aggregation Tree Construction in Three-Dimensional Wireless Sensor Networks |
|
Nguyen Thi, Tam | Hanoi University of Science and Technology |
Tran Son, Tung | Hanoi University of Science and Technology |
Keywords: Wireless Communications & Networks
Abstract: In wireless
sensor networks, sensor nodes send environmental data to the sink or
base station via a single hop or multiple hops. Due to limited
resources, constructing a good routing path to prolong the network
lifetime is critical to its effectiveness. One approach is using data
aggregation techniques, where sensors aggregate data through multiple
levels before reaching the base station, to reduce energy consumption. A
data aggregation tree describes the flow of data from each sensor node
to the sink or base station. In this paper, we study the problem of
constructing a data aggregation tree optimizing four objectives: total
energy consumption, network lifetime, latency and interference. This
problem was proven to be NP-hard. We propose a tree-based evolutionary
approach with edge-set representation, named KGASL, to solve the
problem. Experimental validation on our benchmarks have been carried out
to demonstrate proposed algorithm痴 performance.
|
|
WeB33 |
L-3 |
ML5: Machine Learning, Cloud and Data Analytics |
Regular Session |
Chair: Jia, Haohui | Nara Institute of Science and Technology |
|
14:45-15:00, Paper WeB33.1 | |
EyeSmell: Rice Spoilage Detection Using Azure Custom Vision in Raspberry Pi 3 |
|
Batugal, Christian Luzter | FAITH Colleges |
Gupo, Jewel Mark Perry | FAITH Colleges |
Mendoza, Kasandra Kimm | FAITH Colleges |
Santos, Adonis | FAITH Colleges |
Malabanan, Francis | FAITH Colleges |
Tabing, Jay Nickson | FAITH Colleges |
Escarez, Christopher | FAITH Colleges |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: Rice is the
staple food of the Filipinos. According to the Bureau of Agricultural
and Fisheries Product Standards, an average Filipino consumes 4-5
servings of rice per day. But because there is no accurate way of
detecting rice spoilage before consumption, Filipinos only rely on their
senses to know whether the rice is spoiled or not. This makes them at
risk of foodborne illness due to rice spoilage. But with the latest
technology advancements, machine learning could be used to help lessen
the risk and cases of food illness caused by rice spoilage. This study
focuses on the implementation of Azure Custom Vision API to detect rice
spoilage. Gas sensor readings and images captured during data gathering
were correlated with a resulting value of 1 which corresponds to a very
strong correlation. The system was tested by the researchers using 20
different rice samples that includes 10 samples of spoiled rice and 10
samples of not spoiled rice which resulted in a detection accuracy of
85%. The system is implemented with its own container using a Raspberry
Pi 3B with a camera module through Python programming language.
|
|
15:00-15:15, Paper WeB33.2 | |
Towards Tracking: Investigation of Genetic Algorithm and LSTM As Fish Trajectory Predictors in Turbid Water |
|
Palconit, Maria Gemel | De La Salle University; Cebu Technological University |
Almero, Vincent Jan | De La Salle University |
Rosales, Marife | De La Salle University |
Sybingco, Edwin | De La Salle University |
Bandala, Argel | De La Salle University |
Vicerra, Ryan Rhay | De La Salle University |
Dadios, Elmer | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: Monitoring the
dynamics of fish behavior is impactful both in the research for
fisheries and aquaculture production. One of the most explored
approaches to monitor the fish is tracking-by-detection along with
computer vision. Presently, there are several challenges in this field,
including underwater environment conditions and fish movement
complexity. This study presents an initial investigation towards
tracking the fish by predicting the trajectory 2D coordinates of fish
from the sequential sampled frames in underwater videos. Here, the
authors explored the Genetic Algorithm based on natural evolution
selection and the Long Short-Term Memory (LSTM) algorithm. Results have
shown tolerable trajectory prediction inaccuracies using the GA and
LSTM. Specifically, it obtained the Mean Absolute Percentage Error at
2.8% to 30.5% and 3.33% to 17.74% for GA and LSTM, respectively. These
results have allowed the authors and researchers to extend its study
towards tracking the fish using these approaches.
|
|
15:15-15:30, Paper WeB33.3 | |
Automated Detection of Helminth Eggs in Stool Samples Using Convolutional Neural Networks |
|
delas Pes, Kristofer | University of the Philippines |
Villacorte, Elena | University of the Philippines |
Rivera, Pilarita | University of the Philippines |
Naval, Prospero | University of the Philippines |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Biomedical Engineering
Abstract:
Schistosomiasis, trichuriasis, and ascariasis are few of the many
neglected tropical diseases that still affect populations in poor
countries. These diseases cause a variety of symptoms such as abdominal
pain, may lead to complications, and may even result in death in severe
schistosomiasis cases. To complement the efforts of governments and
health organizations in mitigating the morbidity and transmission of
neglected tropical diseases, several applications utilizing machine
learning techniques have been developed in recent years to automate the
detection of parasites in microscopy samples. In this paper, we explore
the use of YOLO, a convolutional neural network framework, in the
detection of helminth eggs in stool samples. We collected and labelled a
dataset with varying imaging conditions due to different staining
conditions and acquisition by smartphone cameras with different
parameters. We demonstrate that the approach works well despite this
variance in imaging conditions in the dataset, achieving high
sensitivity in the detection of helminth eggs and high accuracy in the
identification of egg species. The trained model operates in real-time,
making it suitable for automated diagnosis and real-time annotation.
|
|
15:30-15:45, Paper WeB33.4 | |
Automatic Diabetic Retinopathy Classification with EfficientNet |
|
Lazuardi, Rachmadio Noval | Institut Teknologi Bandung |
Abiwinanda, Nyoman | Institut Teknologi Bandung |
Suryawan, Tafwida Hesaputra | Bandung Institute of Technology |
Hanif, Muhammad | Institut Teknologi Bandung / Bandung Institute of Technology |
Handayani, Astri | Bandung Institute of Technology |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Biomedical Engineering
Abstract: Using the
recent known EfficientNet architecture of deep convolutional neural
network (CNN), we present an automatic detection of diabetic retinopathy
(DR) from given retinal images. We experiment with subsets of the
Kaggle diabetic retinopathy dataset consisting of retinal images with
varied diagnostic quality. To address the quality variation, we
incorporate two preprocessing steps, i.e. contrast limited adaptive
histogram equalization (CLAHE) and image central cropping. We trained
EfficientNet-B4 and EfficientNet-B5 model on two Kaggle subsets with
different class proportions. In this paper, we propose an automatic
early diagnosis of diabetic retinopathy which gained 0.7922 / 83.87% and
0.7931 / 83.89% of quadratic weight kappa and accuracy score on
EfficientNet-B4 and EfficientNet-B5 respectively.
|
|
15:45-16:00, Paper WeB33.5 | |
Unsupervised Abnormality Detection Using Heterogeneous Autonomous System |
|
Mejbaul Islam, Kazi | Head-Blocks |
Rouhan, Noor | Neural Semiconductor Limited |
Sharmin, Ruhi | Purdue University |
Ohi, Tafannum Tahiat | Ahsanullah University of Science and Technology |
Mohammad Redwan, Islam | Ahsanullah University of Science and Technology |
Chinmoy, Kumer Roy | Ahsanullah University of Science and Technology |
Nazmus, Sakib | Ahsanullah University of Science and Technology |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Social Implications of Technology
Abstract: Due to the rise
of autonomous vehicles like drones and cars anomaly detection for
better and robust surveillance becomes prominent for real-time
recognition of normal and abnormal states. But the whole system fails if
the unmanned device is unable to detect own device痴 anomaly in real
time. Considering the scenario, we can make use of various data of
autonomous vehicles like images, video streams and other digital or
analog sensor data to detect device anomaly. In this paper, we have
demonstrated a heterogeneous system that estimates the degree of an
anomaly in unmanned surveillance drone by inspecting IMU (Inertial
Measurement Unit) sensor data and real time image in an unsupervised
approach. We致e used AngleNet for detecting images taken in abnormal
state. On top of that, an autoencoder fed by the IMU data has been
ensembled with AngleNet for evaluating the final degree of the anomaly.
This proposed method is based on the result of the IEEE SP Cup 2020
which achieved 97.3 percent accuracy on provided dataset. Besides, this
approach has been evaluated on an in-house setup for substantiating its
robustness.
|
|
16:00-16:15, Paper WeB33.6 | |
Grape
Leaf Multi-Disease Detection with Confidence Value Using Transfer
Learning Integrated to Regions with Convolutional Neural Networks |
|
Lauguico, Sandy | De La Salle University |
Concepcion, Ronnie II | De La Salle University |
Tobias, Rogelio Ruzcko | De La Salle University |
Bandala, Argel | De La Salle University |
Vicerra, Ryan Rhay | De La Salle University |
Dadios, Elmer | De La Salle University |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing, Social Implications of Technology
Abstract: Identifying
variant diseases in leaves is a significant method for optimizing food
production. As the global population continues to arise and agricultural
space continues to decline, every possible way of increasing the supply
of food in any given condition and limited resources will address the
above-mentioned problems. This study proposes a way for detecting three
different diseases from grape leaves apart from the healthy leaves and
considers the confidence value of the system in correctly identifying
the classes. The diseases are namely: Black Rot, Black Measles, and
Isariopsis. The system conducted a comparative analysis to determine
which among the three pre-trained networks, AlexNet, GoogLeNet, and
ResNet-18 will be the most suitable network to be integrated with
Regions with Convolutional Neural Networks (RCNN) in performing multiple
object detection in a given image. The data used in training the models
comprised of annotated image data represented as a ground truth table
with image files and their corresponding bounding boxes coordinates. The
models evaluated resulted to AlexNet being the best pre-trained network
to be working on the RCNN with an accuracy of 95.65%. The other two
models from GoogLeNet and ResNet-18 only obtained accuracies of 92.29%
and 89.49% respectively.
|
|
WeB34 |
L-4 |
SIP3: Signal and Image Processing |
Regular Session |
Chair: Panicker, Mahesh | Indian Institute of Technology Palakkad |
|
14:45-15:00, Paper WeB34.1 | |
German Sign Language Translation Using 3D Hand Pose Estimation and Deep Learning |
|
Mohanty, Shruti | PES University |
Prasad, Supriya | PES University |
Sinha, Tanvi | PES University |
Krupa, Niranjana | PES University |
Keywords: Signal and Image Processing, Social Implications of Technology, Machine Learning, Cloud and Data Analytics
Abstract: Sign language
is the primary medium of communication for the majority of the world痴
population suffering from disabling hearing loss that creates a barrier
between the hearing and the hearing-impaired people. In this paper, sign
language translation is undertaken for German Sign Language (GSL)
characters from a single image by leveraging the technique of 3D object
detection. We make use of a three-network architecture that performs
segmentation, keypoint localization, and elevation from a
two-dimensional plane to the three-dimensional space, from a single RGB
image containing the signed gesture. Thirty gestures have been used and
the best results were obtained using a combination of pose
representation coordinates, joint angles, and pool layer features of
AlexNet for classification. The system gives a character error rate of
0.29, a reduction of error rate by 12.12% when compared to the
state-of-the-art approach.
|
|
15:00-15:15, Paper WeB34.2 | |
Automatic Bowel Sound Detection under Cloth Rubbing Noise |
|
Kodani, Kazuma | Tokyo University of Science |
Sakata, Osamu | Tokyo University of Science |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: Conventionally,
bowel sound is considered an important index for understanding a
patient痴 intestinal condition. At present, bowel sound is determined by
a doctor痴 auscultation with a stethoscope. The auscultation is based
on experience and intuition, and is short-term. Therefore, research has
been conducted to enable a long-term and quantitative measurement of
bowel sound. However, these studies measured bowel sound for bedridden
patients only, and no study has yet measured them for moving patients.
To measure bowel sound even for a moving patient, a portable bowel sound
detection device needs to be developed. For this purpose, a new sensor
that is smaller than the conventional stationary prototype, with the
addition of noise resistance, is developed in this study. The noise
resistance is added through signal processing conducted on a computer.
This study focuses on the rubbing sound of clothes, which is the most
influential noise generated when moving. In addition, a notch filter,
wavelet filter, and low-pass filter are used to extract only the cloth
rubbing and bowel sounds. In addition, the difference in the number of
peaks and the enhancement of the bowel sound spectrum characteristics
are used to distinguish between the two sounds. As a result,
automatically, only the bowel sound is detected.
|
|
15:15-15:30, Paper WeB34.3 | |
Shunt Sound Decomposition by Empirical Mode Decomposition |
|
Otake, Yuki | Tokyo University of Science |
Sakata, Osamu | Tokyo University of Science |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: Unpredictable
disequilibrium syndrome and blood pressure fluctuations can occur during
hemodialysis therapy. We have proposed a method for analyzing shunt
sounds using EMD to predict these symptoms. The shunt sound is the sound
of turbulent blood flow generated in the shunt, which can be measured
from the puncture needle of the dialyzer. This shunt sound may contain
elements that identify these symptoms. To identify these elements, it is
necessary to decompose the shunt sound into a minimum number of
components, assuming that the shunt sound is composed of a plurality of
basic components. Therefore, in this report, how to decompose the shunt
sound into the minimum components by dividing the shunt sound into beats
and by empirical mode decomposition is explained.
|
|
15:30-15:45, Paper WeB34.4 | |
Delay Multiply and Sum Based Selective Compounding for Enhanced Ultrasound Imaging |
|
Malamal, Gayathri | Indian Institute of Technology Palakkad |
Panicker, Mahesh | Indian Institute of Technology Palakkad |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: In ultrasound
imaging, a non-linear beamforming algorithm called filtered delay
multiply and sum (F-DMAS) has been demonstrated to provide improved
contrast and resolution compared to the commonly employed delay and sum
(DAS) algorithm. In F-DMAS, the delay compensated radio-frequency
narrowband signals from the transducer channels is pairwise multiplied
to generate baseband and higher-order harmonic components in the output
spectrum. The final image is reconstructed by filtering the second
harmonic component to provide better contrast and resolution. However,
other generated harmonic components, which are not utilized in the
standard F-DMAS could be employed for improved contrast and resolution.
In this work, a modification to standard F-DMAS is proposed where the
different frequency bands generated through pairwise multiplications are
selectively combined through additive or difference compounding
techniques to form the final image. The results show that the proposed
approach outperforms the standard F-DMAS in terms of contrast and
resolution.
|
|
15:45-16:00, Paper WeB34.5 | |
Towards Bone Aware Image Enhancement in Musculoskeletal Ultrasound Imaging |
|
Singh, Mohit | R V College of Engineering |
Panicker, Mahesh | Indian Institute of Technology Palakkad |
K V, Rajagopal | Kasturba Medical College |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: Musculoskeletal
(MSK) ultrasound imaging aims to provide pictures of tissues and bones
such as muscles, tendons, ligaments, joints and soft tissues throughout
the body. One of the major landmarks in MSK ultrasound are the bones,
and segmentation of bone surface has numerous applications in
computer-aided orthopedic diagnosis. In this work, a novel method of
bone aware image enhancement of MSK ultrasound images is presented. A
combination of fundamental and harmonic US images is used for bone
segmentation. The method for bone segmentation takes into account the
acoustic characteristics of the intensity of bones used for computing
their acoustic shadows, local phase-based features such as local energy,
local phase, and feature symmetry based on a reported work in
literature. It is combined with integrated backscattering of the bone to
provide a probability map of the bone. Bone location in probability map
was found based on the centroid of the intensity distribution. Further,
image enhancement of the extracted region of interest based on the bone
for distinctive visualization of the muscular and tendon region above
the bone structure is presented. The image enhancement techniques
employed are gamma correction, histogram equalization, adaptive
histogram equalization and an improved frequency based superresolution
of ultrasound images.
|
|
16:00-16:15, Paper WeB34.6 | |
A Study on fNIRS-Based Working Memory Load Assessment and Potential Issues with Extracerebral Artifacts |
|
Lim, Lam Ghai | Universiti Teknologi PETRONAS |
Tang, Tong Boon | Universiti Teknologi PETRONAS |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: Functional
near-infrared spectroscopy (fNIRS) has gained interest in the
development of brain-computer interface (BCI) for working memory (WM)
training. Amplitude averaging of oxygenated hemoglobin (oxy-Hb) signal
over the predefined region of interest (ROI) is typically used to
compute WM load. It is unclear to what extent extracerebral artifacts
can affect WM assessment. To examine this, a technique adopting
multi-distance probe configuration and independent component analysis
(MD-ICA) was applied to split the original fNIRS signals into
hemodynamic signals originating from the deep (cerebral) and shallow
(extracerebral) tissue layers. Twenty-five healthy participants
performed letter 1- and 2-back tasks, symbolizing low and high WM load
respectively. In the bilateral dorsolateral prefrontal cortex (DLPFC),
increasing WM load evoked significant changes in both original and deep
oxy-Hb activation, but not in the shallow oxy-Hb. Under low WM load, the
bilateral DLFPC activation was significantly higher than that of the
middle prefrontal cortex (mPFC), only seen through the deep signal.
Conversely, under high WM load, the significant difference in brain
activation between the bilateral DLPFC and mPFC were observed in both
original and deep oxy-Hb. This highlights extracerebral artifacts
correction might be useful when searching for activation regions.
However, when activation areas are known, the signal intensities in
original oxy-Hb are sufficiently profound to quantify and
|
|
WeB35 |
L-5 |
CAS1: Computer Architecture & Systems |
Regular Session |
Chair: Yoshimoto, Junichiro | Nara Institute of Science and Technology |
|
14:45-15:00, Paper WeB35.1 | |
Design and Implementation of a Pipelined RV32IMC Processor with Interrupt Support for Large-Scale Wireless Sensor Networks |
|
Neri, Michael Joseph | University of the Philippines |
Ridao, Redentor Immanuel | University of the Philippines Diliman |
Baylosis, Victor Emmanuel | University of the Philippines Diliman |
Chua, Phoebe Meira | University of the Philippines Diliman |
Tan, Allen Jason | University of the Philippines Diliman |
De Leon, Maria Theresa | University of the Philippines |
Hizon, John Richard | University of the Philippines, Diliman |
Rosales, Marc | University of the Philippines |
Sabino, Maria Patricia Rouelli | University of the Philippines Diliman |
Santos, Christopher | University of the Philippines |
Alvarez, Anastacia | University of the Philippines |
Keywords: Computer Architecture & Systems
Abstract: With the rise
of IoT and its many applications, the capabilities of sensor nodes in
wireless sensor networks have increased due to the large amounts of
sensed data that incur a significant amount of workload at the network
core. As such, edge computing applications, which take computing away
from the network core into the network edge, become more widely used.
This paper presents a pipelined RISC-V RV32IMC processor with interrupt
support as a solution to this challenge. For communication with
peripherals, the processor supports the protocols I^2C, SPI, and UART.
Design optimizations, delay balancing and clock gating, resulted in a
13.3% maximum operating frequency increase and a 23.3% reduction in the
dynamic power consumption of the core processor. The implemented
processor utilizes an average core power of 30.752 mW while operating at
a frequency of 50 MHz on a Digilent Arty A7 Board with a Xilinx Artix-7
FPGA.
|
|
15:00-15:15, Paper WeB35.2 | |
TRETA - a Novel Heuristic Based Efficient Task Scheduling Algorithm in Cloud Environment |
|
Jayasena, Kudamaduwage Pubudu Nuwanthika | Sabaragamuwa University of Sri Lanka |
Bandaranayake, K.M.Sathera Umesh | Sabaragamuwa University of Sri Lanka |
Kumara, B. T. G. S. | Sabaragamuwa University of Sri Lanka |
Keywords: Computer Architecture & Systems
Abstract: Cloud computing
is a computing platform that allows users to access various kinds of
computing services over the internet. Cloud provides on-demand, scalable
and highly available resources on pay-per-usage subscriptions. Cloud is
an optimum solution for executing a large number of different size
tasks as for the computing capability it offers. Task scheduling is one
of the major open challenges that need to be addressed. The Task
scheduling problem in the cloud is known to be an NP-complete problem.
Hence heuristics can be used to get an optimal solution. There have been
many heuristics proposed for the task scheduling problem in the cloud.
None of them has considered the total execution time of the virtual
machine as a factor for finding a better schedule. In this paper, we
proposed a new task scheduling algorithm named Total Resource Execution
Time Aware Algorithm (TRETA) which takes into account the total
execution time of computing resources in obtaining an optimal schedule.
The algorithm is compared with Min-Min, Min-Max, FCFS, and MCT
heuristics for Makespan, Degree of Imbalance and System Throughput. The
proposed algorithm shows a significant amount of improvement in Makespan
compared to other heuristics. The algorithm also outperforms other
heuristics with respect to System Throughput and Degree of Imbalance
which results in better workload distribution among the cloud resources.
|
|
15:15-15:30, Paper WeB35.3 | |
Bit-Selection Control for Energy-Efficient Hand Written Digits Recognition Hyperdimensional Computing Architecture |
|
Antonio, Ryan Albert | Analog Devices Inc |
Alvarez, Anastacia | University of the Philippines |
Keywords: Computer Architecture & Systems, Circuits and Systems, Machine Learning, Cloud and Data Analytics
Abstract:
Hyperdimensional computing (HDC) is a brain-inspired computing framework
that provides simple and convenient methods to perform cognitive tasks
like classification. Its foundation lies in the properties of very high
dimensional vectors called hypervectors (HV). HDC is a promising
alternative to the conventional von-Neumann architectures, but its
high-dimensional processes still contain massive bit-wise operations.
Current optimizations often sacrifice accuracy for better
energy-efficiency. This work finds redundant bits in the associative
memory that do not contribute any information during classification. A
proposed bit-selection control trims these redundant bits leading to
improved throughput and energy-savings without sacrificing accuracy. For
the handwritten digits recognition problem, this simple control results
in a 44.62% energy reduction at the cost of 8.34% increase in area.
|
|
15:30-15:45, Paper WeB35.4 | |
Rail System Anomaly Detection via Machine Learning Approaches |
|
Lee, Zi Shan | National University of Singapore |
Guo, Huaqun | Institute for Infocomm Research, A*STAR Research Entities |
Zhou, Luying | Institute for Infocomm Research, A*STAR Research Entities |
Keywords: Computer Architecture & Systems, Machine Learning, Cloud and Data Analytics, Robotics, Control Systems & Theory
Abstract: Supervisory
Control and Data Acquisition (SCADA) system which monitors and controls
physical processes/operations within a rail infrastructure is critical.
SCADA system痴 accessing to key components and infrastructure
information make it a promising attack target. This paper explores
building machine learning models to detect anomalies in a rail SCADA
system through the usage of network traffic data. The attack scenarios
designed based on domain expertise are epoch time attack and TCP payload
length attack in this paper. Data pre-processing is done before passing
into machine learning approaches for training. The anomaly detection
machine learning models are evaluated using several metrics such as true
positive rate and precision. Results show that supervised learning
approaches (K-Nearest Neighbours (KNN), Linear Support Vector
Classification (LinearSVC), Random Forest, Gaussian Bayes) outperform
unsupervised learning approach (K-Means). Exploration into the use of
the full original network traffic versus a subset of network traffic for
model training has shown that the latter performed better in precision
due to the presence of overfitting to specific alarm network traffic.
Finally, our experiment results show that supervised learning approach
KNN is effective to detect the attacks with high precision.
|
|
15:45-16:00, Paper WeB35.5 | |
Signature-Based and Behavior-Based Attack Detection with Machine Learning for Home IoT Devices |
|
Visoottiviseth, Vasaka | Mahidol University |
Sakarin, Pranpariya | Mahidol University |
Thongwilai, Jetnipat | Mahidol University |
Choobanjong, Thanakrit | Mahidol University |
Keywords: Computer Architecture & Systems, Software & Database Systems, Wireless Communications & Networks
Abstract: Currently,
Internet of Things (IoT) becomes pervasive and widely deployed. However,
the lack of developer and user cyber security awareness leaves IoT
devices become the new target of cyber attacks. Therefore, we design and
develop "A System for Preventing IoT Device Attacks on Home Wi-Fi
Router" (SPIDAR) in order to protect home Wi-Fi networks. This system
consists of SPIDAR home Wi-Fi router, SPIDAR Raspberry Pi, and SPIDAR
web application to prevent attacks and display the attack statistics to
home users. It also helps saving costs from purchasing expensive
intrusion prevention software and hardware to install at home. For the
prevention method, we provide both the signature-based method using
Snort software and the behavior-based method which learns and analyzes
IoT devicesbehavior by using either the baseline or the machine
learning in order to increase the system performance. SPIDAR can prevent
five major attack types specified in the OWASP IoT Top 10
vulnerabilities 2018.
|
|
WeB36 |
L-6 |
P4: Power & Energy |
Regular Session |
Chair: Duong, Quang-Thang | Nara Institute of Science and Technology |
|
14:45-15:00, Paper WeB36.1 | |
Optimization of Voltage Tolerance Curve against Voltage Sag Using Cuckoo Search Algorithm |
|
Suliva, Kevin | Polytechnic University of the Philippines |
Keywords: Power & Energy, Devices, Materials & Processing
Abstract: Industrial
plants utilize sensitive equipment for the past years to increase their
efficiency to yield the required needs of their customers. Power quality
disturbances such as voltage sag causes this equipment to operate
poorly and even malfunction due to its nonlinear characteristic and
thus, affecting the performance of the whole process to produce an
output product. To address this, manufacturers sought to find means to
determine its equivalent response through its voltage tolerance curve to
improve the equipment immunity under this disturbance. The objective of
this research study is to determine the possibility of adding optimized
boundaries to the voltage tolerance curve for the protection of
sensitive equipment and to improve their ride through capability to
voltage sags by using Cuckoo search algorithm. The voltage tolerance
curve of each equipment is plotted against voltage sag events to
determine its possible response and optimized using its parameters and
sag events as constraints and boundaries using MatLAB. The simulation
shows that an equipment can have a significant improved performance
against voltage sags by setting up optimized boundaries to the voltage
tolerance curve in addition to the conventional upper and lower
boundaries.
|
|
15:00-15:15, Paper WeB36.2 | |
Design of IMC & IMC Derived PID Controller for Interleaved Boost Converter |
|
Sarkar, Sayan | HKUST |
Ghosh, Aayushman | Wecare Medservice LLP |
Ghosh, Shiuli Subhra | Jindal Stainless Limited |
Keywords: Power & Energy, Engineering Education, Devices, Materials & Processing
Abstract: This paper
gives the design of IMC and IMC derived biphasic Interleaved Boost
Converter (IBC) in voltage mode control technique. Small-signal based
modelling of IBC in continuous conduction mode (CCM) of operation shows a
right half plane zero (RHPZ) in control to output plant transfer
function (TF) of the IBC. IBC produces substantially low output voltage
ripple compared to boost converter due to the emergence of multiple
power switches in the parallel path. Subsequently, the size and output
filter losses of IBC can be substantially reduced in comparison to the
Boost Converter (BC). Execution of the converter-controller system is
validated by SISO tool-based step response analysis. Developed IMC and
IMC dependent PID controllers are performing better than highly cited
Type III controller-based IBC in line, load regulation, and reference
tracking study. They have comparable performance in parametric
uncertainty (variation) study, validated using MATLAB/SIMULINK. IMC
derived PID is performing better than the IMC controller in line
regulation, load regulation, and parametric variations, but in step
response checking, they have nearly equal settling time.
|
|
15:15-15:30, Paper WeB36.3 | |
Decentralised Fault Tolerant Model Predictive Control for a Class of Interconnected System |
|
Gatavi, Ehsan | Western Sydney University |
Hellany, Ali | Western Sydney University |
Rizk, Jamal | Western Sydney University |
Nagrial, Mahmood Hussain | Western Sydney University |
Keywords: Power & Energy, Robotics, Control Systems & Theory
Abstract: A decentralised
fault tolerant control is presented in this paper for a class of
interconnected system. The bounded control technique is applied to
address the interconnection effects and the dynamic changes due to the
faults. Multiple local controllers are designed as part of decentralised
algorithm to guarantee the system stability during the fault period. In
this case, the system can deal with the fault with large magnitude. To
illustrate the effectiveness the proposed scheme, the system is tested
for the case that multiple fault occurred in different local subsystems.
|
|
15:30-15:45, Paper WeB36.4 | |
Battery Management System with Temperature Monitoring through Fuzzy Logic Control |
|
Calinao, Hilario | De La Salle University |
Bandala, Argel | De La Salle University |
Gustilo, Reggie | De La Salle University |
Dadios, Elmer | De La Salle University |
Rosales, Marife | De La Salle University |
Keywords: Power & Energy, Robotics, Control Systems & Theory, Devices, Materials & Processing
Abstract: Batteries are
very important in many different applications. In the solar energy
system, the batteries are used as power storage when solar energy is not
available especially during night time. Batteries need to be maintained
and closely monitor their condition. Battery management systems are
normally used for this application but many of them are not monitoring
the battery痴 temperature. This study will use a fuzzy logic-controlled
system to manage the operation of the battery. This system will maintain
the operation of the battery in the allowed operating temperature to
prevent it from damaged caused by excessive internal temperature.
|
|
15:45-16:00, Paper WeB36.5 | |
Distribution Efficiency and 10 Year Projection of Water Availability of Cabuyao Water District in Cabuyao Area |
|
Domingo, Bernie | College of Engineering, Pamantasan Ng Cabuyao |
Jarilla, Joefaustus | College of Engineering, Pamantasang Ng Cabuyao |
Labampa, Francis Jerome | College of Engineering, Pamantasan Ng Cabuyao |
Marcelino, Marbien John | College of Engineering, Pamantasan Ng Cabuyao |
Papa, Angelica | College of Engineering, Pamantasan Ng Cabuyao |
Alcantara, Ramonchito | College of Engineering, Pamantasan Ng Cabuyao |
Andaya, Florante | College of Engineering, Pamantasan Ng Cabuyao |
Beano, Mary Grace | College of Engineering, Pamantasan Ng Cabuyao |
Sigue, Anna-liza | College of Engineering, Pamantasan Ng Cabuyao |
Vanguardia, Sarah | College of Engineering, Pamantasan Ng Cabuyao |
Keywords: Power & Energy, Engineering Management
Abstract: The aim of the
study is to know the efficiency of Cabuyao Water District (CABWAD) in
their service of distributing water to their customers and to know what
will be their plans for the next 5 to 10 years regarding water
projection and water availability. After conducting surveys and
interviews, the researchers found out that the service efficiency of
CABWAD is moderately efficient. In terms of water pressure efficiency,
it is also rated moderately efficient with mean of 2.2 with the highest
rating of 1. Their plans for the next 5 and 10 years are; first, to
increase the number of pumping stations from other sources of water like
surface water, underground water and rainwater. Second, to put
additional water sources located strategically within the districts
jurisdiction. And last, to invest applicable water quality equipment
required in the PNSDW parameters. It was concluded that the water
availability may be affected by the location of the customers from the
water source and the number of member in every household may also affect
by a high demand on water consumption. Regardless of demographic
profile, the respondents opt to stand that CABWAD needs improvement
specially to the barangays suffering water shortage.
|
|
WeC31 |
L-1 |
ML8: Machine Learning, Cloud and Data Analytics |
Regular Session |
|
16:30-16:45, Paper WeC31.1 | |
JavaScript Malware Behaviour Analysis and Detection Using Sandbox Assisted Ensemble Model |
|
Kishore, Pushkar | Nit Rourkela |
Barisal, Swadhin Kumar | Nit Rourkela |
Mohapatra, Durga Prasad | NIT Rourkela |
Keywords: Software & Database Systems, Machine Learning, Cloud and Data Analytics
Abstract: Whenever any
internet user visits a website, a scripting language runs in the
background known as JavaScript. The embedding of malicious activities
within the script poses a great threat to the cyber world. Attackers
take advantage of dynamic nature of the JavaScript and embed malicious
code within the website to download malware and damage the host.
JavaScript developers obfuscate the script to keep it shielded from
getting detected by the malware detectors. In this paper, we propose a
novel technique for analysing and detecting JavaScript using sandbox
assisted ensemble model. We extract the payload using malware-jail
sandbox to get the real script. Upon getting the extracted script, we
analyse it to define the features that is needed for creating the
dataset. We compute Pearson's r between every features for feature
extraction. An ensemble model consisting of Sequential Minimal
Optimization (SMO), Voted Perceptron and AdaBoost algorithm is used with
voting technique to detect malicious JavaScript. Experimental results
show that our proposed model can detect obfuscated and de-obfuscated
malicious JavaScript with an accuracy of 99.6% and 0.03s detection time.
Our model performs better than other state-of-the-art models in terms
of accuracy and least training and detection time.
|
|
16:45-17:00, Paper WeC31.2 | |
A Ride Sharing System Based on an Expansive Search-Based Algorithm |
|
Escalona, Josh Angelo | University of the Philippines - Diliman |
Manalo, Benjamin | University of the Philippines - Diliman |
Limjoco, Wilbert Jethro | University of the Philippines - Diliman |
Dizon, Carl | University of the Philippines - Diliman |
Keywords: Software & Database Systems, Machine Learning, Cloud and Data Analytics
Abstract: Ride sharing is
one of the several transportation alternatives used to ease and skip
traffic problems worldwide. A platform of interest is GrabShare, where
its ride sharing algorithm was empirically found to be simple. However,
the algorithm has several limitations, such as it being not truly
optimal due to catering to user experiences, and only able to handle up
to two bookings. Hence, there is a need to develop a ride sharing system
that is scalable, fast, and efficient especially in terms of finding
matches and recommending routes. A Modified Search-based Ride Sharing
algorithm, which uses an expansion-based method, was developed as a
response to these requirements. Results showed that the Modified
Search-based Ride Sharing algorithm generally outperforms the
empirically-derived GrabShare algorithm in terms of route length, shared
route percentage, and processing time. However, GrabShare performs
better when there are few passengers in the area while the Modified
Search-based Ride Sharing algorithm runs relatively slower when the
sources and destinations are far from each other.
|
|
17:00-17:15, Paper WeC31.3 | |
A Comparative Study of Pretrained Language Models for Automated Essay Scoring with Adversarial Inputs |
|
Wangkriangkri, Phakawat | Chulalongkorn University |
Viboonlarp, Chanissara | Chulalongkorn University |
Thamrongrattanarit, Attapol | Chulalongkorn University |
Chuangsuwanich, Ekapol | Chulalongkorn University |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Automated Essay
Scoring (AES) is a task that deals with grading written essays
automatically without human intervention. This study compares the
performance of three AES models which utilize different text embedding
methods, namely Global Vectors for Word Representation (GloVe),
Embeddings from Language Models (ELMo), and Bidirectional Encoder
Representations from Transformers (BERT). We used two evaluation
metrics: Quadratic Weighted Kappa (QWK) and a novel "robustness", which
quantifies the models' ability to detect adversarial essays created by
modifying normal essays to cause them to be less coherent. We found
that: (1) the BERT-based model achieved the greatest robustness,
followed by the GloVe-based and ELMo-based models, respectively, and (2)
fine-tuning the embeddings improves QWK but lowers robustness. These
findings could be informative on how to choose, and whether to
fine-tune, an appropriate model based on how much the AES program places
emphasis on proper grading of adversarial essays.
|
|
17:15-17:30, Paper WeC31.4 | |
Personalised Food Classifier and Nutrition Interpreter Multimedia Tool Using Deep Learning |
|
M, Sundarramurthi | Dayananda Sagar College of Engineering |
M, Nihar | BMS Institute of Technology and Management |
Anandi, Giridharan | Indian Institute of Science (IISc) |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Food plays a
vital role in our day-to-day life to get all the required nutrients for a
healthy lifestyle. In recent years, obesity has become one of the major
concerns among humans. Therefore, it is necessary for each individual
to keep track of the nutrition intake in order to have a balanced diet.
This has scaled up the implementation of automatic food analysis and
semantic food detection using different image classification approaches,
among which Deep Learning has brought a series of breakthroughs in this
field. We have proposed the Food Classifier and Nutrition Interpreter
(FCNI), a user-friendly tool that classifies various food types with a
different graphical representation of food nutrients values in terms of
calorie estimation along with a multimedia audio response. FCNI improves
state-of-the-art food detection by a considerable margin on achieving
about 96.81% accuracy.
|
|
17:30-17:45, Paper WeC31.5 | |
Density Based Clustering Methods for Road Traffic Estimation |
|
D N, Jagadish | Indian Institute of Information Technology Dharwad |
Mahto, Lakshman | Indian Institute of Information Technology Dharwad |
Chauhan, Arun | Indian Institute of Information Technology, Dharwad |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Multiple object
detection using deep neural networks can lead to transportation
vehicles estimate, a necessary requirement for prediction and management
of road traffic and parking lot. Highly overlapped objects that look
similar and objects that are there at far distances have lesser
probability of detection by state-of-art techniques. We propose
techniques to estimate the traffic at regions of poor detection
probability in the image based on (i) density based clustering and (ii)
exclusive object detection in the regions of poor detection. The
proposed techniques lead to better estimation in comparison to
state-of-art by approximately 12 %. We have utilized RetinaNet and
YOLOv3 networks for object detection.
|
|
17:45-18:00, Paper WeC31.6 | |
Blackbox Trojanising of Deep Learning Models : Using Non Intrusive Network Structure and Binary Alterations |
|
Pan, Jonathan | Home Team Science and Technology Agency |
Keywords: Machine Learning, Cloud and Data Analytics
Abstract: Recent
advancements in Artificial Intelligence namely in Deep Learning has
heightened its adoption in many applications. Some are playing important
roles to the extent that we are heavily dependent on them for our
livelihood. However, as with all technologies, there are vulnerabilities
that malicious actors could exploit. A form of exploitation is to turn
these technologies, intended for good, to become dual-purposed
instruments to support deviant acts like malicious software trojans. As
part of proactive defense, researchers are proactively identifying such
vulnerabilities so that protective measures could be developed
subsequently. This research explores a novel blackbox trojanising
approach using a simple network structure modification to any deep
learning image classification model that would transform a benign model
into a deviant one with a simple manipulation of the weights to induce
specific types of errors. Propositions to protect the occurrence of such
simple exploits are discussed in this research. This research
highlights the importance of providing sufficient safeguards to these
models so that the intended good of AI innovation and adoption may be
protected.
|
|
WeC32 |
L-2 |
A1: Antenna & Microwave |
Regular Session |
Chair: Hirano, Takuichi | Tokyo City University |
|
16:30-16:45, Paper WeC32.1 | |
Characterization of PLA-Based Quad-Ridged Horn Antenna |
|
Oktafiani, Folin | Indonesian Institute of Sciences |
Hamid, Effrina Yanti | Institut Teknologi Bandung |
Munir, Achmad | Institut Teknologi Bandung |
Keywords: Antenna & Microwave
Abstract: Fabrication of
PLA-based horn antenna has a drawback that produces imperfect prototype
such as an air gap between parts, surface roughness and impure
conductivity. Characterization of PLA-based quad-ridged horn antenna is
presented in this paper to observe the effect of imperfect fabrication
to the horn antenna performance. The research is carried out by
investigating the antenna parameter in terms of reflection coefficient
and antenna gain of QRHA with an imperfect fabrication. The
investigation is performed by using 3D simulation software. The result
shows that an air gap and surface roughness influence the antenna
bandwidth and impure conductivity decrease the antenna gain.
|
|
16:45-17:00, Paper WeC32.2 | |
Effect of Finite Ground Plane on Performance of Compact Air-Suspended Rectangular Microstrip Antenna for 5G Applications |
|
Solanki, Rajbala | Indian Institute of Technology Bombay |
Srivastava, Anuj | Space Application Centre, Ahmedabad |
Keywords: Antenna & Microwave
Abstract: This paper
presents details of the effects of shorting along the width of the
air-suspended rectangular microstrip antenna (RMSA). The entire width of
the patch is shorted using a number of shorting pins and as the number
of shorting pins increases, the gain, bandwidth, and resonance frequency
of the antenna increase. By decreasing the shorting width, the antenna
can be made more compact. For the shorted compact air-suspended RMSA the
effects of the finite ground plane on its performance have been
analyzed. When the geometric parameters of the ground plane are changed,
it affects the gain, bandwidth, resonance frequency, and back lobe
radiation. Various graphs have been presented to choose the optimum
performance depending on the size constraints.
|
|
17:00-17:15, Paper WeC32.3 | |
Circular Patch Antenna with Comb-Shaped Slot for NR-79/Wi-Fi Applications |
|
Kulkarni, Neeta | Sanjay Ghodawat University |
Kulkarni, Jayshri | Vishwakarma Institute of Information Technology |
Bahadure, Nilesh | Sanjay Ghodawat University |
Patil, Prasenjeet | Sanjay Ghodawat University |
Keywords: Antenna & Microwave
Abstract: A novel, wide
band circular patch antenna with symmetrical coplanar waveguide (S-CPW)
fed is proposed for wireless access point operating in
NR-79/Wi-Fi-5/Wi-Fi-6 frequency bands. To attain multiband operation, a
circular patch is loaded with an intersecting of two slots namely
vertical slot and comb shaped slot. The complete structure resonates at
5.3 GHz to produce wide band with fractional bandwidth of 55.77% in the
frequency range (4.37-7.75GHz). The nearly omnidirectional 3D patterns
followed by stable gain of 2.2 dBi throughout the functioning bands
confirm the appropriateness of the proposed antenna for wireless access
point operating in NR-79/Wi-Fi-5/Wi-Fi-6 frequency bands.
|
|
17:15-17:30, Paper WeC32.4 | |
Design and Assembly of Textile Microstrip Antenna for Global Positioning System Application |
|
Budiastuti, Desi | Universitas Indonesia |
Ilyas, Ardine Khairunisa | Universitas Indonesia |
Rahardjo, Eko Tjipto | Universitas Indonesia |
Keywords: Antenna & Microwave
Abstract: The antenna
proposed in this study is a wearable microstrip patch antenna that
utilizes jeans (permittivity: 1.77) as its substrate for GPS
application. Tests shows that the antenna has frequency range of 1.57
1.61 GHz. Resonant frequency of the antenna is 1.595 GHz, with return
loss value of -14.18 dB. The antenna achieved its desired specification
with truncated edge, quarter wave transformator, and slot utilization.
The antenna is safe to be used on thigh, chest, and arm as simulation
shows that SAR value of the antenna is under the maximum standard
allowed. However, when the antenna is moved further away from the
phantom, the axial ratio value decreases and goes > 3 dB when antenna
is placed over the distance recommendation.
|
|
17:30-17:45, Paper WeC32.5 | |
Effect of Textile Substrate on Antenna Performance for GPS Application |
|
Ilyas, Ardine Khairunisa | Universitas Indonesia |
Budiastuti, Desi | Universitas Indonesia |
Rahardjo, Eko Tjipto | Universitas Indonesia |
Keywords: Antenna & Microwave
Abstract: Wearable
antennas made from textile materials for GPS (Global Positioning System)
applications has been widely developed. However, textile materials have
properties that can absorb water and be bent which will affect the
performance of the antenna. Therefore, the testing of GPS antennas made
from textile materials with five different substrates has been carried
out to determine the effect of textile use on the antenna. Five
substrate materials were felt, spun bond, cotton, drill, and denim. All
antennas were designed to work on the GPS L1 frequency of 1,575 GHz with
a value of S11 <- 10 dB, bandwidth > 10 MHz, and axial ratio
<3 dB to achieve circular polarization. The study shows when affected
by water absorption, there are 4 antennas that remain successfully work
at GPS L1 frequency. When the antenna is tested in bending conditions,
there are several antennas that can still work at GPS L1 frequency but
are not stable for every bend condition.
|
|
17:45-18:00, Paper WeC32.6 | |
Transmission
Phase-Shift Method for Complex Permittivity Determination of Biological
Sample Performed Using X-Band Rectangular Waveguide |
|
Effendi, Mohammad Ridwan | Institut Teknologi Bandung |
Prastio, Rizky Putra | Institut Teknologi Bandung |
Munir, Achmad | Institut Teknologi Bandung |
Mengko, Tati | Biomedical Engineering Program, School of Electrical Engineering |
Keywords: Biomedical Engineering, Antenna & Microwave
Abstract: Determination
of material properties is one of essential stages to more understanding
the characteristics of biological sample especially in biomedical
research. In this paper, a method of transmission phase-shift is
proposed to determine complex permittivity of biological sample which is
performed using a WR90 type X-band rectangular waveguide. Some samples
of chicken meat, liver, and skin are applied as biological materials for
the experimentation. The irregular shape of biological sample is
examined by placing it into a thin container to obtain a flat surface
and putting the container in inside of the rectangular waveguide. The
complex relative permittivity of each sample is extracted from measured
S-parameters and then determined using the method. The results show that
the method could successfully determine the complex permittivity of
biological sample. In addition, the water content in the material has
become a critical issue to be considered in the examination especially
for the biological sample with high permittivity.
|
|
WeC33 |
L-3 |
ML7: Machine Learning, Cloud and Data Analytics |
Regular Session |
Chair: Okada, Minoru | Nara Institute of Science and Technology |
|
16:30-16:45, Paper WeC33.1 | |
A Survey on Convolution Neural Networks |
|
Sarker, Goutam | Computer Science and Engineering Department, National Institute |
Keywords: Machine Learning, Cloud and Data Analytics, Software & Database Systems
Abstract: Major tools to
implement any Artificial Intelligence and Machine Learning systems are
Symbolic AI and Artificial Neural Network (ANN) AI. ANN has made a
dramatic improvement in the versatile area of Machine Learning (ML). ANN
is a gathering of vast number of weighted interconnected artificial
neurons, initially invented with the inspiration of biological neurons.
These models are much better than previous models implemented with
Symbolic AI so far as their performance is concerned. One revolutionary
change in ANN is Convolution Neural Network (CNN). These structures are
mainly suitable for complex pattern recognition tasks within images.
Here we would discuss basics of ANN as a tool for complex pattern
recognition and image processing task. Also as some applications of the
CNN tool, we will present OCR based text translation and biometric based
uni modal and multimodal person identification systems.
|
|
16:45-17:00, Paper WeC33.2 | |
Designing of Urban Air Pollution Monitoring System and Notify Traffic Police to Their Personal Exposure in Urban Air Pollution |
|
Jain, Harshita | Davv Indore |
Saini, Anil Kumar | CSIR-CEERI Pilani |
Nigam, Himanshu | CSIR-CEERI Pilani |
Keywords: Machine Learning, Cloud and Data Analytics, Wireless Communications & Networks
Abstract: Urban air
pollution has significant effects in living beings and nature.
Automobile exhaust emissions are the main cause of air pollution.
Moreover, the major contribution of Air pollution is by static vehicle
traffic over a long period when vehicles stop at a traffic crossing This
article purposed a framework for managing traffic police duty hours
based on the recommended time exposure to the pollutants. Air Pollution
Monitoring System measures concentration value of harmful gases like CO,
CO2, NO2, SO2 and particulate matters in real-time and send these value
wirelessly to ThingSpeak IoT cloud through ESP8266 Wi-Fi module. An
analysis of personal exposure to pollution of traffic police
individually and total Air Quality Index (AQI) calculated in MATLAB
environment. An alert email has been sent to traffic police control room
about apprise duty hour of traffic police to aware less affected
exposure time of urban air pollution for that particular crossing.
|
|
17:00-17:15, Paper WeC33.3 | |
Image Search System Based on Feature Vectors of Convolutional Neural Network |
|
Diana, Mery | Agency for Assessment and Application of Technology (BPPT) |
Amagasaki, Motoki | Kumamoto University |
Iida, Masahiro | Kumamoto University |
Keywords: Machine Learning, Cloud and Data Analytics, Wireless Communications & Networks, Computer Architecture & Systems
Abstract: Edge computing
offers real-time applications because the edge device closes with the
data source such as the end device. This condition gives the challenge
to implement deep learning in the edge device. Unfortunately, deep
learning requires high computing resources, but often edge-side devices
have limitations. In this study, we built an image search system based
on CNN (Convolutional Neural Network)痴 feature vectors to address the
challenges by enlarging the implementation of CNN in the edge device
such as Raspberry Pi 3. The image search system applied these
informative features vector to get similar images in the image searching
task by using cosine similarity. We used a 102-flower categories
dataset and we prepared a light database to run the system as an
off-line system in the edge device. The MobileNetV2 as CNN痴 model
reached 70.02% of the top 1 accuracy and 92.84 % for the top 5 accuracy.
As a result, the image search system showed five images result with the
most similar image from the same image category. Image resolution,
model complexity, and hardware capability give the significant time in
this image search system. The framework of this system can be simply
used for other deep learning models and applications by updating the
model, dataset, database, and hardware.
|
|
17:15-17:30, Paper WeC33.4 | |
Implementation
of Image Processing and Machine Learning in High Resolution Aerial
Image Datasets for Lake Resource Usage, Aquaculture, and Coastal
Community |
|
Belarmino, Mark Daniel | Ateneo De Manila University |
Keywords: Marine and Offshore Engineering, Disasters and Humanitarian Technology, Machine Learning, Cloud and Data Analytics
Abstract: Last May 2019,
fish farms in Taal Lake suffer from fish kill resulting in an estimated
loss of 405 tons of fish. It was reported that the measured water sample
from the lake shows significant loss of dissolved-oxygen due to
over-crowding of fish farm. With the crisis mentioned, recent studies
utilize satellite remote sensors to map and monitor the aquaculture
inside the lake. The maps are being used as reference material for
progress monitoring, as decision-support and lake management tool by the
local government and regulatory agencies. Aerial maps were captured
using Unmanned Aerial Vehicle (UAV) as it has better resolution than
satellite imagery. This study implements image processing and Mask
Regional Convolutional Neural Network (Mask RCNN) on high resolution
images to create an object detection and segmentation model for
aquaculture structures and coastal settlement. To create the detection
model, the image dataset undergoes preprocessing before feeding into the
training process. Finally, an analytical software was developed to
utilize segmented maps for zone management plan implementation, lake
resource usage calculation, and gauge the population of settlers along
the coastline. This provides meaningful visual and statistical data
regarding aquaculture population, lake resource usage, local settlement
population and zone development plan status.
|
|
17:30-17:45, Paper WeC33.5 | |
Using
Stacked Long Short Term Memory with Principal Component Analysis for
Short Term Prediction of Solar Irradiance Based on Weather Patterns |
|
de Guia, Justin | De La Salle University |
Alejandrino, Jonnel | De La Salle University |
Concepcion, Ronnie II | De La Salle University |
Calinao, Hilario | De La Salle University |
Dadios, Elmer | De La Salle University |
Sybingco, Edwin | De La Salle University |
Keywords: Power & Energy, Machine Learning, Cloud and Data Analytics
Abstract: Energy
production of photovoltaic (PV) system is heavily influenced by solar
irradiance. Accurate prediction of solar irradiance leads to optimal
dispatching of available energy resources and anticipating end-user
demand. However, it is difficult to do due to fluctuating nature of
weather patterns. In the study, neural network models were defined to
predict solar irradiance values based on weather patterns. Models
included in the study are artificial neural network, convolutional
neural network, bidirectional long-short term memory (LSTM) and stacked
LSTM. Preprocessing methods such as data normalization and principal
component analysis were applied before model training. Regression
metrics such as mean squared error (MSE), maximum residual error (max
error), mean absolute error (MAE), explained variance score (EVS), and
regression score function (R2 score), were used to evaluate the
performance of model prediction. Plots such as prediction curves,
learning curves, and histogram of error distribution were also
considered as well for further analysis of model performance. All models
showed that it is capable of learning unforeseen values, however,
stacked LSTM has the best results with the max error, R2, MAE, MSE, and
EVS values of 651.536, 0.953, 41.738, 5124.686, and 0.946, respectively.
|
|
17:45-18:00, Paper WeC33.6 | |
Uniform Recognition-Activated Gate for Dress Code Implementation of Pamantasan Ng Cabuyao |
|
Mariveles, Edgardo Manuel | College of Engineering, Pamantasan Ng Cabuyao |
Porcare, Jimwell | College of Engineering, Pamantasan Ng Cabuyao |
Regonay, Jovelyn | College of Engineering, Pamantasan Ng Cabuyao |
Cruz, Meryll | College of Engineering, Pamantasan Ng Cabuyao |
Bea, Mary Grace | Pamantasan Ng Cabuyao |
Andaya, Florante | Pamantasan Ng Cabuyao |
Mandayo, Ericson | Pamantasan Ng Cabuyao |
Domingo, Bernie | Pamantasan Ng Cabuyao |
Keywords: Machine Learning, Cloud and Data Analytics, Signal and Image Processing
Abstract: Wearing of
improper uniform has been one of the problems being faced by Pamantasan
ng Cabuyao due to a massive number of students entering the university.
The security guards do not have the ability to monitor the student痴
attire all the time. There are also some students who do not wear
Identification Cards (ID) upon entering the school premise which is also
important for the student痴 or staff痴 identification as well as the
school痴 security and integrity. This paper aims to plan and built a
device whose main function is to monitor student痴 attire for most of
the time. Uniform recognition-activated gate for dress code
implementation of Pamantasan ng Cabuyao focused on improving the
security system upon entering the gate of the university. This device
used biometrics, barcode scanner of the Identification (ID) card and
image recognition for uniform to open the gate. The mechanism to open
the gate uses a servo motor which is connected to the gate structure.
Based on the evaluation done by the professionals and preferred users,
the device has been considered very good for each criteria provided of
its scores. The device will be available for further improvement to
develop more functions necessary to the workplace of its application.
|
|
WeC34 |
L-4 |
SIP4: Signal and Image Processing |
Regular Session |
Chair: Sasaoka, Naoto | Tottori University |
|
16:30-16:45, Paper WeC34.1 | |
Skin Cancer Classification from Dermoscopic Images Using Feature Extraction Methods |
|
Gautam, Anjali | Women Institute of Technology, Dehradun |
Raman, Balasubramanian | Indian Institute of Technology Roorkee |
Keywords: Biomedical Engineering, Signal and Image Processing
Abstract: Melanoma is a
type of skin cancer that is mainly caused by intense UV exposure. If
melanoma is identified at an early stage, then it is generally
remediable. However, if it is not diagnosed properly, cancer can grow to
rest of the body which then makes it difficult to cure and can be
lethal. Conventionally, melanoma is diagnosed through visual methods and
biopsies but their accuracy may not be reliable for all the cases.
Hence, the risks involved for such a diagnosis have emerged
identification and classification of melanoma as benign or malignant a
very important research problem in medical imaging. This paper employs
various feature descriptors like local binary pattern (LBP), complete
LBP (CLBP) and their variants, which are based on histogram mapping such
as uniform, rotation invariant and rotation invariant uniform patterns.
The extracted features are then used to train different classifiers
such as decision tree, random forest (RF), support vector machine (SVM)
and k nearest neighbour (kNN). A comparative study of the various
feature descriptors and classifiers are analyzed for accurate
identification and classification of melanoma as benign or malignant. An
image dataset which has been used in our work has been downloaded from
ISIC-Archive, which consists of 947 dermoscopic images and the dataset
is made freely available online by realizing the importance of the
research. The best accuracy has been obtained by using RF in CLBP with
an accuracy of 80.3%.
|
|
16:45-17:00, Paper WeC34.2 | |
Interference Reduction Using Bispectrum Estimation in Non-Contact Heart Rate Measurement by Doppler Radar |
|
Tazen, Moushumi | Tottori University |
Sasaoka, Naoto | Tottori University |
Fujita, Kasumi | Tottori University |
Itoh, Yoshio | Tottori University |
Keywords: Biomedical Engineering, Signal and Image Processing, Antenna & Microwave
Abstract: In recent
years, the interest in utilizing non-contact Doppler radar for vital
sign detection is growing. In case that there is another person around a
subject, the influence due to the obstructive person is treated as a
fundamental problem for the estimation of heart rate (HR) in non-contact
heart rate (HR) monitoring 25-GHz Doppler radar. This paper
investigates the suitability of bispectrum estimation in extinguishing
the influence in the received signal. The bispectrum represents the
dependency between two different frequency spectra. Assuming that the
heart-beat component from the subject has a strong phase coupling, the
bispectrum estimation of a received signal enhances the heart-beat
component, and then the influence can be reduced. The experimental
results showed the bispectrum estimation improves the estimation
accuracy of heart rate.
|
|
17:00-17:15, Paper WeC34.3 | |
On the Differences between Song and Speech Emotion Recognition: Effect of Feature Sets, Feature Types, and Classifiers |
|
Atmaja, Bagus Tris | JAIST |
Akagi, Masato | JAIST |
Keywords: Signal and Image Processing, Machine Learning, Cloud and Data Analytics, Social Implications of Technology
Abstract: In this paper,
we argue that singing voice (song) is more emotional than speech. We
evaluate different features sets, feature types, and classifiers on both
song and speech emotion recognition. Three feature sets: GeMAPS,
pyAudioAnalysis, and LibROSA; two feature types, low-level descriptors
and high-level statistical functions; and four classifiers: multilayer
perceptron, LSTM, GRU, and convolution neural networks; are examined on
both songand speech data with the same parameter values. The results
show no remarkable difference between song and speech data on using the
same method. Comparisons of two results reveal that song is more
emotional than speech. In addition, high-level statistical functions of
acoustic features gained higher performance than low-level descriptors
in this classification task. This result strengthens the previous
finding on the regression task which reported the advantage use of
high-level features.
|
|
17:15-17:30, Paper WeC34.4 | |
Identification of Corn Plant Leaf Diseases through Web Server Using Image Processing and Artificial Neural Network |
|
Macasaet, Dailyne | De La Salle University |
Sybingco, Edwin | De La Salle University |
Bandala, Argel | De La Salle University |
Illahi, Ana Antoniette | De La Salle University |
Dadios, Elmer | De La Salle University |
Keywords: Signal and Image Processing, Machine Learning, Cloud and Data Analytics, Software & Database Systems
Abstract: This study
centers on the design and development of a microcontroller based
hardware interface that connects the serial camera, the processor, the
WiFi module, and the LCD screen and identification software for corn
plant diseases through web-server using image processing and artificial
neural network. This is done by capturing and displaying the image of
the leaf inside the box and transmits it to the web server as an input
image; process, analyze and interpret the data through image processing.
The result of the processed image will be sent to the displaying
microcontroller based hardware interface through the web-server and
display the Pest Management Recommendations.
|
|
17:30-17:45, Paper WeC34.5 | |
Automated Stitching of Coral Reef Images and Extraction of Features for Damselfish Shoaling Behavior Analysis |
|
Pineda, Riza Rae | Nara Institute of Science and Technology |
delas Pes, Kristofer | University of the Philippines |
Manogan, Dana | University of the Philippines Diliman |
Keywords: Signal and Image Processing, Marine and Offshore Engineering
Abstract: Behavior
analysis of animals involves the observation of intraspecific and
interspecific interactions among various organisms in the environment.
Collective behavior such as herding in farm animals, flocking of birds,
and shoaling and schooling of fish provide information on its benefits
on collective survival, fitness, reproductive patterns, group
decision-making, and effects in animal epidemiology. In marine ethology,
the investigation of behavioral patterns in schooling species can
provide supplemental information in the planning and management of
marine resources. Currently, damselfish species, although prevalent in
tropical waters, have no adequate established base behavior information.
This limits reef managers in efficiently planning for stress and
disaster responses in protecting the reef. Visual marine data captured
in the wild are scarce and prone to multiple scene variations, primarily
caused by motion and changes in the natural environment. The gathered
videos of damselfish by this research exhibit several scene distortions
caused by erratic camera motions during acquisition. To effectively
analyze shoaling behavior given the issues posed by capturing data in
the wild, we propose a pre-processing system that utilizes color
correction and image stitching techniques and extracts behavior features
for manual analysis.
|
|
17:45-18:00, Paper WeC34.6 | |
Monitoring of Abiotic Factors in Outdoor Aquaponics with Fuzzy Logic for Growing of Costus Igneus |
|
Banjao, John Patrick | Mapua University |
Villafuerte, Kyle | Map俉 University |
Villaverde, Jocelyn | Mapua University |
Keywords: Signal and Image Processing, Wireless Communications & Networks
Abstract: Aquaponics is
an integration of aquaculture and hydroponics and the naked eye cannot
predict and distinguish abiotic factors specifically in the water. The
study used a Costus Igneus (insulin plant) to discover if it will grow
successfully in the Aquaponics setup rather than traditional soil setup
and Nile tilapia for cultivating fish to promote urban farming. With the
objectives of the study are to develop an array of sensors using a
fuzzy logic algorithm to know the aqueous state ideal value of the
system such as water temperature, electrical conductivity, pH content,
dissolved oxygen and water level of the tank and sending notification
and updates through Global System Communication (GSM). In the result of
weekly data gathering plant height between two environments, the
statistical value result to 3.728 which exceeds t-critical values of
2.228 proved monitoring of abiotic factors of Aquaponics is
significantly greater than traditional soil farming.
|
|
WeC35 |
L-5 |
CAS2: Computer Architecture & Systems |
Regular Session |
Chair: Yoshimoto, Junichiro | Nara Institute of Science and Technology |
|
16:30-16:45, Paper WeC35.1 | |
Application and Assessment of Click Modular Firewall vs POX Firewall in SDN/NFV Framework |
|
Monir, Md Fahad | Faculty Member, Independent University, Bangladesh |
Pan, Dan | Telenor |
Keywords: Computer Architecture & Systems, Wireless Communications & Networks, Software & Database Systems
Abstract: The evolution
of Software Defined Networks (SDN) and Network Function Virtualization
(NFV) introduced a revolutionary development in network architecture.
SDN together with NFV provides users a platform to design flexible
virtual networks (VNs) on a shared computer infrastructure. However,
network administrators have specific requirements to secure this
network. There are new security demands for VN such as flexible network
function migrations and user-focused security system, which may not be
supported by traditional firewalls. In our work we have implemented SDN
and NFV based firewalls on an open source platform mininet. POX module
and Click Modular Router are used to develop our firewall modules. Then
we evaluated the performance of both firewalls with packet loss and
throughput measurement.
|
|
16:45-17:00, Paper WeC35.2 | |
Teaching Programming: An Evidence Based and Reflective Approach |
|
Ercan, Muhammet | Singapore Polytechnic |
Keywords: Engineering Education, Computer Architecture & Systems
Abstract: Programming is
an essential skill that an electrical and electronics engineering
student should possess. With the advances made in technology such as
IoT, low cost embedded systems, even the simplest electrical devices
become intelligent and connected. In electrical engineering curriculum,
introduction to programming is traditionally taught though without
rigor. Computer programming is a challenging task since it requires
abstract thinking, logic and mathematics skills. Novice students rapidly
develop a disliking and avoid tasks/projects that involves programming
in future. In order to overcome these issues and get students interested
in programming, we took an evidence based approach for teaching
computer programming. The method involves combining a number of proven
best practices in teaching, together with a reflective tool for the
instructor when planning and delivering the course. We experimented with
novice students who are taking the basic computer programming for the
first time and found out its highly effective. This paper describes the
evidence based practices used and our observations on the outcome.
|
|
17:00-17:15, Paper WeC35.3 | |
Individual Learning Effectiveness Based on Cognitive Taxonomies and Constructive Alignment |
|
Huu Nguyen, Phat | Mahidol University |
Tangworakitthaworn, Preecha | Mahidol University |
Gilbert, Lester | Southampton University |
Keywords: Engineering Education, Computer Architecture & Systems, Software & Database Systems
Abstract: Online learning
is becoming increasingly popular and used in many academic disciplines
due to its advantages, where learners can access courses from anywhere
and at any time. Besides benefits, online learning may have limitations,
such as slow response times when bandwidth is limited, or inflexible
one-size-fits-all content without regard for the learner痴 background or
knowledge state. This paper presents an approach to more flexible
online learning, where recommended learning paths are derived from the
results of learning activities and assessment tasks. The proposed paths
comprise multiple intended learning outcome (ILO) nodes based upon and
sequenced according to Bloom痴 taxonomies and Biggsprinciples of
constructive alignment (PCA).
|
|
WeC36 |
L-6 |
P5: Power & Energy |
Regular Session |
Chair: Vo, Quoc Trinh | Nara Institute of Advanced Science and Technology |
|
16:30-16:45, Paper WeC36.1 | |
Influence of Defective Bypass Diodes on Electrical and Thermal Properties of Photovoltaic String and Array |
|
Torihara, Ryo | University of Miyazaki |
Latt, Nay Zaw | University of Miyazaki |
Khin, May Oo | University of Miyazaki |
Lwin, Yu Mar | University of Miyazaki |
Sakoda, Tatsuya | University of Miyazaki |
Hayashi, Noriyuki | University of Miyazaki |
Keywords: Power & Energy
Abstract: The intent of
this paper is to analyze the power consumption or heat dissipation of
defective bypass diode (BPD) at open circuit (OC) and maximum power
point (MPP) load conditions when the BPD turns to have resistive
behavior in a photovoltaic (PV) string and array. We also analyze the
thermal impact of defective BPD in a PV string under different
irradiances and cell temperatures. It was observed that the power
consumption of defective BPD largely depends on load condition and the
thermal impact is more severe in OC condition. It was also observed that
the thermal impact of defective BPD is larger under either high
irradiance level for the same cell temperature or lower cell temperature
on the same irradiance. This study indicates that it is necessary to
monitor the heat dissipation of BPDs and to evaluate the electrical
properties of the BPDs to realize the reliable PV systems.
|
|
16:45-17:00, Paper WeC36.2 | |
Optimal
Control and Placement of Step Voltage Regulator for Voltage Unbalance
Improvement and Loss Minimization in Distribution System |
|
Nakadomari, Akito | University of the Ryukyus |
Shigenobu, Ryuto | University of Fukui |
Senjyu, Tomonobu | University of Ryukyus |
Keywords: Power & Energy
Abstract: This paper
describes optimal voltage control and optimal placement of the
three-phase individual step voltage regulator 3ΦSVR considering voltage
unbalance improvement. As a result of active efforts to promote
renewable energy, there is a concern that voltage unbalance will
increase due to an increase in distributed power sources. Therefore,
this paper proposes the optimal control and placement method for 3ΦSVR
for voltage unbalance improvement and loss minimization. Simulations
verified that all the voltage unbalanced indices satisfied the
constraint value and the objective function improved. These results
confirmed that the effectiveness of the optimal control and placement
method for 3ΦSVR.
|
|
17:00-17:15, Paper WeC36.3 | |
Optimal Sizing and Operation of Distributed Energy Resources in Micro-Grid with Fuel Cells |
|
Sugimura, Makoto | University of the Ryukyus |
Tetsuya, Yabiku | University of the Ryukyus |
Nakadomari, Akito | University of the Ryukyus |
Takahashi, Hiroshi | Fuji Electric Co, Ltd |
Senjyu, Tomonobu | University of Ryukyus |
Keywords: Power & Energy
Abstract: This study
proposes an optimal installed capacity of Distributed Energy Resources
(DERs) for a small remote island (Aguni-Island) is belongs to Okinawa
Prefecture in Japan. Photovoltaic (PV), Wind Generator (WG), Battery
Energy Storage System (BESS), and Fuel Cell (FC) are considered to be
installed for optimal sizing. The simulation conducted in this study has
been simplified to account seasonal load and weather variations. This
simulations aims to minimize the fuel and total cost of the system as it
resulted in a total cost, which is lower than it was before DERs to be
implemented. In addition, carbon dioxide emissions from diesel
generators have been reduced.
|
|
17:15-17:30, Paper WeC36.4 | |
Short-Term Unit Commitment Using Advanced Direct Load Control |
|
Isomura, Ryota | University of the Ryukyus |
Tetsuya, Yabiku | University of the Ryukyus |
Tamashiro, Kanato | Univercity of the Ryukyu |
Jalloh, Ibrahim | University of the Ryukyus |
Senjyu, Tomonobu | University of Ryukyus |
Keywords: Power & Energy
Abstract: In recent
years, there is a tendency to reduce greenhouse gas emissions
internationally in consideration of environmental problems. In the field
of electric power systems, the introduction of renewable energy power
generation facilities centered on photovoltaic power generation is being
promoted in order to reduce greenhouse gas emissions. However, if these
power generation facilities are introduced excessively, a duck curve
phenomenon occurs in which the operating efficiency of the thermal power
generator is poor. Currently, we are reducing the output of
photovoltaic power generation equipment to avoid the duck curve
phenomenon. In order to suppress the output, it is not possible to
further install renewable energy power generation equipment, and the
limit of introduction comes with a fixed amount. Therefore, this paper
proposes a new load demand control method that improves the duck curve
phenomenon without hindering the introduction of renewable energy power
generation equipment. In addition, in order to make the proposed method
more active, the usual unit commitment has a time interval of 1 hour,
but at the same time, we also devised a time interval of 30 minutes. We
show that by performing a short-term unit commitment using the proposed
method, the optimal operation can be performed even when a large amount
of renewable energy power generation is introduced.
|
|
17:30-17:45, Paper WeC36.5 | |
Shunt VSC Based Subsynchronous Damping Control for DFIG-Based Wind Farms Connected to an MMC-HVDC System |
|
Zhang, Fan | China Southern Power Grid |
Yin, Congqi | Tsinghua University |
Li, Haozhi | Tsinghua University |
Xie, Xiaorong | Tsinghua University |
Hong, Chao | China Southern Power Grid |
Yuan, Hao | China Southern Power Grid |
Liu, Yongjun | China Southern Power Grid |
Keywords: Power & Energy
Abstract: An emerging
subsynchronous oscillation (SSO) associated with wind generators and
voltage-sourced converter (VSC) based HVDC has been observed around the
world. It is revealed that this new type of SSO is caused by the
subsynchronous control interaction among power electronic converters and
the grid. In this paper, the stability criterion of SSO is examined
using frequency-dependent impedance models. Then a shunt VSC based
subsynchronous damping control (SVSDC) has been proposed to reshape the
impedance characteristic of the whole system and thus mitigate the SSO.
The stability criterion and the control has been applied to a typical
system with DFIG-based wind farms connected to a modular multilevel
converter (MMC) based HVDC transmission. Impedance model based analyses
as well as electromagnetic simulations have verified the effectiveness
of the criterion and the control scheme. For its flexibility of capacity
and deployment, the proposed SVSDC offers a promising option to address
the SSO issues associated with wind generators and/or VSC-HVDCs.
|
| |