Program Book EECCIS 2024
Program Book EECCIS 2024
Program Book EECCIS 2024
i-1
Welcome Message by General Chair
It is our pleasure to welcome all participants to the 12th Electrical Power, Electronics,
Communications, Controls, and Informatics Seminar (EECCIS) 2024, being held in
Malang, East Java Province, Indonesia from October 16-18, 2024. The EECCIS 2024 is
an international conference organized by the Electrical Engineering
Department, Faculty of Engineering, Universitas Brawijaya, in collaboration with
Universiti Tun Hussein Onn Malaysia (UTHM) – Malaysia.
On behalf of the EECCIS Committee, I would like to take this opportunity to address
our sincere thanks to all the keynote speakers for having accepted our invitations to
share their experience and expertise through the keynote speeches they deliver.
Their expertise sharing will surely enrich the knowledge of and be greatly appreciated
by the audience of the EECCIS 2024.
We would also like to express our deepest gratitude to our generous sponsors. Their
unwavering support has been instrumental in making this event possible. Their
contributions not only help in bringing together experts, scholars, and industry
leaders but also ensure that the EECCIS 2024 runs smoothly and successfully. Thanks
to their sponsorship, we are able to create a platform that fosters meaningful
exchanges of ideas and the sharing of cutting-edge innovations.
There are 40 research papers coming from 11 countries to be presented in parallel
session programs, after following rigorous double blind-review processes with >50%
rejection rate. The papers will proceed to the last checking and review before the
final submission to IEEE Xplore. Today, conference organized by hybrid scheme, 18
person attendance by virtual meeting and 22 participants will presentation on site.
Finally, we really wish that the conference will provide an opportunity for all
participants to establish a scientific network and to discuss new ideas and
developments in the converging technology and educations of electrical and
electronics engineering in general.
Dr. TRI NURWATI, ST., MT
General Chair
EECCIS 2024
i-2
Message from the Dean of Faculty of Engineering, Universitas Brawijaya
Prof. Ir. Hadi Suyono, S.T., M.T., Ph.D., IPU., ASEAN Eng.
Dean of Faculty of Engineering
Universitas Brawijaya
i-3
Organizing Committee
GENERAL CHAIR
Dr. Ir. TRI NURWATI, ST., MT.
PUBLICATION CHAIR
MUHAMMAD FAUZAN EDY PURNOMO, S.T., M.T., Ph.D
SECRETARIAT
Ir. ZAINUL ABIDIN, ST., M.Eng., MT., Ph.D
ANGGER ABDUL RAZAK, ST., M.Eng., MT., Ph.D
FITRI AMALIA RAHMAWATI, S.Si.
HENNY SARASWATI, A.Md., S.Pd
CONTACT DETAILS:
Department of Electrical Engineering
Faculty of Engineering, Universitas Brawijaya, 65145
Phone: (+62 341) 554166
Email: eeccis@ub.ac.id
Website: http://eeccis.ub.ac.id/
i-4
EECCIS 2024 Technical Program Committee and Reviewer
i-5
Table of Contents
i-6
EECCIS 2024 Title List
A. Electrical Power
[1571028669] Design Analysis of Floating Solar Plant Development in Lake Toba: Study on
Engineering, Economic and Environmental Aspects 12
William Sutan Nainggolan; Unggul Wibawa; Wijono
[1571029461] Improvement Of Power Losses and Voltage Drops 20kV Distribution Network
at Intako Feeder Porong Sidoarjo 12
Deny Fatkhur Rohman; Unggul Wibawa; Teguh Utomo
[1571030345] Low-cost BLE based Indoor Localization using RSSI Fingerprinting and Machine
Learning
13
Balaji Ramachandran; Rizwan Mohammed Hussain; Vinod Subramanian; Jayakumar Vandavasi
Karunamurthy
[1571042522] Optimizing Preventive Maintenance of Generator Excitation Systems to
Improve Power Plant Reliability and Performance
13
Hartawan Abdillah; A.N. Afandi; Alief Muhammad; Abdul Haris; Mas Ahmad Baihaqi; Dani Hari
Tunggal Prasetyo; Moh Zainul Falah
[1571048406] Wave Height Monitoring and Security System on Oscillating Water Column
Using ESP32 Microcontroller 14
Kholistianingsih; Isra’ Nuur Darmawan; Banyumas Dzanzar Panza Bakti
i-7
B. Electronic Systems
[1571030355] Reducing Crosstalk of SiC MOSFET Gate Driver using a Negative Driving
Voltage 17
Intan Anggraeni Maryanda Putri; Waru Djuriatno; Tri Nurwati; Soltana Guesmi
[1571049748] Step Length Classification using Decision Tree based on IMU Sensors and Body
Height 18
Ilham Ari Zaeni; Dyah Lestari; Soraya Norma Mustika; Dessy Rif’a Anzani; Muhammad Khusairi
Osman; Khairul Azman Ahmad
[1571058434] Optimizing The Sensor Array In The Electronic Nose For Coffee Aroma 19
Denda Dewatama; Erni Yudaningtyas; Muhammad Fauzan Edy Purnomo; Setyawan P. Sakti
[1571059173] Smart Vest for Palliative Therapy of Metastatic Cancer Patients Using TENS
Integrated with Thermotherapy, Aromatherapy, and Multimedia Based on the Internet of
Things 20
Nurussa'adah; Muhamad Asyir Zarkasih; Aryo Nabil Maulana; Akmal Mulki Majid; Christalenta
Renata Dwi Aristawati; Shalihat Azka Sabrina; Dauletbay Sarsenbaev; Ayaz Ali Soomro
i-8
C. Telecommunication
[1571048360] Vegetation Density Profiling Using FMCW Radar for Plant Population
Estimation 22
Virginia Rosaline Zefanya Iskandar; Budi Prasetya; Aloysius Adya Pramudita
[1571048484] Soil Nitrogen Content Estimation Using SFCW Radar with Interpolated
Look-Up Table Inference Technique 23
Nurul Febri Annisa; Levy Olivia Nur; Restu Wulansari; Aloysius Adya Pramudita
[1571059184] Impact of Traffic Increase on Quality of Service for Internet, IPTV, and VoIP in
FTTH Networks: A Case Study at Brawijaya University 24
Sigit Kusmaryanto; Rusmi Ambarwati; Ali Mustofa; Endah Budi Purnomowati; Gaguk Asmungi;
Najya Putri Herfita
i-9
D. Controls System
[1571047836] On the Design and Analysis of Discrete-Time Plug-in Repetitive Controller with
Three Different Internal Models 25
Muhammad Aziz Muslim; Edi Kurniawan; Rahmadwati; Ronald Edward
[1571048385] YOLOv8 based Multi Object Detection for BTS Asset Monitoring 27
Lukman Hakim; Asep Suhendi; Aloysius Adya Pramudita
[1571048423] Stress Detection Using EEG Signals: A SVM-Based Classification and Feature
Selection Approach 27
Fi Imanur Sifaunnufus Ms; Fitra Abdurrachman Bachtiar; Barlian Henryranu Prasetio
i-10
[1571048497] Engagement Level Detection Using Facial Extraction Using Multi-stacked
Convolutional Neural Network in e-Learning Settings 29
Fitra Abdurrachman Bachtiar; Al’Ravie Mutiar Mahesa; Eric Wallace Cooper
[1571061478] Leveraging Deep Learning Vision for Real-Time Monitoring and Counting of
Online Motorcycle Taxi Traffic 30
Raden Arief Setyawan; Zainul Abidin; Ratno Wahyu Widyanto
i-11
Keynote Speakers 1
--------------------------------------------------------------------------------------------------------------------------------------
1
Keynote Speakers 2
--------------------------------------------------------------------------------------------------------------------------------------
Biography
Asmarashid Bin Ponniran received the bachelor's degree in electrical engineering from
Universiti Tun Hussein Onn Malaysia, Parit Raja, Malaysia, in 2002, and the master's degree in
electrical engineering (power) from Universiti Teknologi Malaysia, Johor Bahru, Malaysia, in 2005. He
is currently working toward the Ph.D. degree at the Nagaoka University of Technology, Nagaoka,
Japan. He is a lecturer with Universiti Tun Hussein Onn Malaysia (UTHM). His research interests
include DC–DC converter and its application, Power Electronic and Drives, Power Converters and
Control, Industrial Batteries Capacity Restoration (Regeneration Technology, Demand Side
Management (DSM) of Electric Power Consumption, and Underground Power Cable System.
2
Keynote Speakers 3
--------------------------------------------------------------------------------------------------------------------------------------
Biography
Nanang Sulistiyanto received the bachelor's degree in electrical engineering from Brawijaya,
Malang in 1993, and the master's degree in electrical engineering from Universitas Indonesia, in
2012. Then he got the Ph.D. degree at the National Sun Yat Sen University, Taiwan. He is a Lecturer
with Universitas Brawijaya Malang. His research interests include microelectronics, embedded
systems and FPGA.
3
Session Schedule
(Western Indonesia Time (WIB), UTC + 7)
Keynote Speaker 1
08.40 - 09.20 Speaker: Prof. Ichijo Hodaka
University of Miyazaki, Japan
Keynote Speaker 2
Prof. Ir. Suryono Hall
09.20 - 10.00 Speaker: Asmarashid bin Ponniran, Ph.D.
Faculty of Engineering Building
Universiti Tun Hussein Onn Malaysia, Malaysia
Universitas Brawijaya
Keynote Speaker 3 Moderator: Waru Djuriatno,
10.00 - 10.40 Speaker: Dr. Nanang Sulistiyanto ST., MT.
Universitas Brawijaya, Indonesia
4
Thursday – October 17, 2024
TIME AGENDA VENUE
08.30 - 09.10 Plenary Speaker 1 : Derry Aditya (Huawei) Prof. Ir. Suryono Hall
Faculty of Engineering
09.10 - 09.20 Question and Answer Session 1 Building
Universitas Brawijaya
09.20 - 10.00 Plenary Speaker 2 : Krishna Moorthy (Technical Moderator: Dr.
Director MITS ASIA) Fakhriy Hario
Partiansyah
10.00 - 10.10 Question and Answer Session 2
11.50 - 12.00 Closing Session and Photo Session Prof. Ir. Suryono Hall
Faculty of Engineering
Building
Universitas Brawijaya
5
Technical Session Online Presentation
(Western Indonesia Time (WIB), UTC + 7)
6
12.55 - 13.15 1571059173 1571030345 1571030355
Smart Vest for Palliative Therapy IoT Enabled Power Reducing Crosstalk of SiC
of Metastatic Cancer Patients Quality Monitoring in MOSFET Gate Driver using
Using TENS Integrated with Substations through a Negative Driving
Thermotherapy, Aromatherapy, LoRa LEO Satellite Voltage
and Multimedia Based on the Communication Intan Anggraeni Maryanda
Internet of Things Balaji Ramachandran Putri, Waru Djuriatno, and
Nurussa'adah, Muhamad Asyir (Research and Tri Nurwati (Universitas
Zarkasih, Aryo Nabil Maulana, Development Centre & Brawijaya, Indonesia);
Akmal Mulki Majid, Shalihat Azka Dubai Electricity and Soltana Guesmi (National
Sabrina and Christalenta Renata Water Authority, United Engineering School of Sfax,
Dwi Aristawati (Universitas Arab Emirates); Tunisia)
Brawijaya, Indonesia); Dauletbay Jayakumar Vandavasi
Baktybaevich Sarsenbaev (Ministry Karunamurthy, Rizwan
of Energy of Republic of Mohammedhussain and
Uzbekistan, Uzbekistan); Ayaz Ali Vinod Subramanian
Ali Soomro (Sindh Agriculture (Dubai Electricity and
University Sub Campus Umerkot, Water Authority, United
Pakistan & INNER Mangolia Arab Emirates)
University, Pakistan)
7
13.55 - 14.15 1571030250 1571038519 1571043721
Utilization of U-Slot on 30-Star Analysis of a Boost-Fed Comparison Of Vehicular
Microstrip Antenna for CP-SAR Full-Bridge Converter Traffic Emissions And Fuel
Antenna Performance as a Voltage Stabilizer Consumption Under
Enhancement for a Fuel Cell Source Full-Actuated And Fixed
Ajeng Kusuma Dewi, Muhammad Mochammad Rusli, Timing Traffic Light
Fauzan Edy Purnomo, and Fakhriy Taufik Iqbal Miftaks Iqbal Zulfa Fahrunnisa,
Hario (Universitas Brawijaya, Miftaks, and Rahmadwati Rahmadwati,
Indonesia) Muhammad Aziz and Raden Arief Setyawan
Muslim (Brawijaya (Universitas Brawijaya,
University, Indonesia); Indonesia)
Taufik Taufik (California
Polytechnic State
University, San Luis
Obispo, USA); Stephania
N Angelica (Universitas
Brawijaya, Indonesia)
8
Technical Session Offline Presentation
(Western Indonesia Time (WIB), UTC + 7)
Western
OFFLINE TECHNICAL SESSION ( in-Person Seminar )
Indonesian
Time
(WIB), UTC Room 1 (Computer & Room 2 (Controls; Room 3 (Computer & Room 4 (Electronics;
+7 Informatics) Computer & Informatics; Controls; Computer & Informatics;
Session Chair : Panca Informatics; Electronics; Electrical Electrical Power)
Mudjirahardjo Electronics; Power; Session Chair : Rizki
Telecommunications) Telecommunications) Mendung Ariefianto
Session Chair : Angger Session Chair :
Abdul Razak Primatar Kuswiradyo
9
12.55 - 13.15 1571048470 1571061478 1571048360 1571048406
Detection of Leveraging Deep Vegetation Density Design And Build A
Empoasca Pest Learning Vision for Profiling Using FMCW Wave Height Monitoring
Attacks on Tea Leaves Real-Time Monitoring Radar for Plant And Security System On
Based on and Counting of Online Population Estimation Owc Column Based On
Multispectral Camera Motorcycle Taxi Traffic Virginia Rosaline Esp32
Using ResNet-50 Raden Arief Setyawan, Zefanya Iskandar, Budi Isra Nuur Darmawan and
Bella Khairunnisa Zainul Abidin, and Prasetya and Aloysius Kholistianingsih
Kurniawan and Fiky Ratno Wahyu Widyanto Adya Pramudita (Telkom Kholistianingsih
Suratman (Telkom (Universitas Brawijaya, University, Indonesia) (Universitas
University, Indonesia); Indonesia) Wijayakusuma
Fani Fauziah (Research Purwokerto, Indonesia)
Institute for Tea and
Cinchona, Indonesia);
Aloysius Adya
Pramudita (Telkom
University, Indonesia)
10
Gratitude for Participants
We would like to thank all participants for having given their invaluable contribution:
1. Universitas Brawijaya (Indonesia)
2. Academy of Applied Studies Sumadija (Serbia)
3. Tokyo University of Science (Japan)
4. BRIN (Indonesia) - National Research and Innovation Agency
5. Bina Nusantara University (Indonesia)
6. Indonesian Institute of Sciences (LIPI) (Indonesia)
7. Waseda University (Japan)
8. Nobel Institute of Technology and Business (Indonesia)
9. PT. Perusahaan Listrik Negara (PLN) (Indonesia)
10. Universiti Teknologi Malaysia (Malaysia)
11. Telkom University (Indonesia)
12. Universitas Mercu Buana (Indonesia)
13. Universitas Siber Asia (Indonesia)
14. Institute Technology Bandung (Indonesia)
15. Universiti Tun Hussein Onn Malaysia (Malaysia)
16. Universitas Negeri Malang (Indonesia)
17. Dubai Electricity and Water Authority (United Arab Emirates)
18. National Engineering School of Sfax (Tunisia)
19. California Polytechnic State University, San Luis Obispo (USA)
20. Kumamoto University (Japan)
21. University of Miyazaki (Japan)
22. Charles Darwin University (Australia)
23. Technical University of Cluj-Napoca (Romania)
24. Polytechnic University of the Philippines (Philippines)
25. Universitas Panca Marga (Indonesia)
26. University of Indonesia (Indonesia)
27. Research Institute for Tea and Cinchona (Indonesia)
28. Ritsumeikan University (Japan)
29. Universiti Teknologi Mara (Malaysia)
30. UIN Maulana Malik Ibrahim (Indonesia)
31. Odhisa University of Technology and Research (India)
32. Sindh Agriculture University Sub Campus Umerkot (Pakistan)
33. INNER Mongolia University (Pakistan)
34. Ministry of Energy of Republic of Uzbekistan (Uzbekistan)
11
EECCIS 2024 Abstracts
A. ELECTRICAL POWER
(Electrical Power)
Paper ID : 1571028669
Title : Design Analysis of Floating Solar Plant Development in Lake Toba: Study on
Engineering, Economic and Environmental Aspects
Authors : William Sutan Nainggolan; Unggul Wibawa; Wijono
Abstract : High level of solar radiation throughout the year makes solar photovoltaic systems
(PV) as one of the options for clean energy sources in Indonesia. Indonesia
possesses significant potential for utilizing floating solar plants, given its 3,091 water
resources. Lake Toba, situated in the North Sumatra province, stands as Indonesia's
largest lake, covering an expansive area of 1,145 km2. With solar irradiation levels
reaching 1757.1 kWh/m2/yr, the lake presents promising potential as a suitable
location for floating solar plant installations. The study focused on the technical
design of floating solar power plant, covering electrical components and civil
structures like floaters, anchors, and moorings. Two scenarios were analyzed to
determine plant capacity: maximum water surface area and peak load data of North
Sumatra. Inverter capacity was restricted by a ratio of 1.15 to 1.25. Graphical
simulations using Matlab software were conducted to assess PV module generation
characteristics at various solar radiation levels. Economic analysis included Cost of
Energy, Net Present Value, Profitability Index, and Payback Period over a 30-year
project lifetime. Environmental analysis addressed GHG emissions reduction
assuming a 1% yearly power depreciation. This study outlines the technical design
for the Lake Toba floating solar plant with a capacity of 583 MWp covering 3,57 km2
water surface. The plant uses 988,080 PV modules 590 Wp and 48 inverters 10,000
kW, mounted on HDPE floaters with a taut mooring system. Estimated energy
production stands at 854 GWh/year. Economic analysis reveals a positive NPV of Rp
5.8 trillion, PI exceeding 1 at 1.774, and a Payback Period of 10 years and 2 months,
demonstrating the feasibility of constructing the 583 MW Lake Toba Floating Solar
Plant. Environmental analysis indicates a reduction in GHG emissions on Sumatra
Island by 18.68 kilotons of CO2 over the project's lifetime.
(Electrical Power)
Paper ID : 1571029461
Title : Improvement Of Power Losses and Voltage Drops 20kV Distribution Network at
Intako Feeder Porong Sidoarjo
Authors : Deny Fatkhur Rohman; Unggul Wibawa; Teguh Utomo
Abstract : Electrical energy is required for almost all activities in life, it can be said that
electricity is the main support of human life. A reliable and efficient electrical energy
distribution system is needed to fulfill this, but power losses and voltage drops will
definitely occur. Solutions that can be provided to reduce losses and voltage drops
are by setting tap changers on substation transformers and also up-rating overload
transformers. The method used in this research is simulation in the ETAP application
with the data obtained and focuses on calculating and improving power losses and
voltage drops in the 20 kV distribution system of PT PLN (Persero) ULP Intako
12
Porong. Based on the results of load flow analysis, there are 8 overload
transformers, namely PC415 (108.7%), PC18 (91.3%), PC82 (89.7%), PC122 (89.3%),
PC194 (99.2%), PC533 (81.9%), PC589 (137%), PC671 (87%). There are 3 buses that
experience voltage drops exceeding SPLN standards (-10% and +5%) while when
referring to IEC standards (-5% and +5%) there are 24 buses that experience voltage
drops not according to standards. The total active power loss is 58,8 kW and the
total reactive power loss is 285 kVAR. Conditions after setting the tap changer on
the substation transformer by -2.5 on the primary side can reduce the critical
voltage drop on several buses, but the transformer overload bus has not met the IEC
standard of nominal voltage. Conditions after up-rating the transformer
experiencing overload conditions can reduce the voltage drop value so that all buses
are in accordance with IEC standards (-5% and +5) of the nominal voltage. The value
of active power losses has decreased from 58,8 kW to 51.0 kW and the value of
reactive power losses has decreased from 285 kVAR to 273.2 kVAR.
(Electrical Power)
Paper ID : 1571030345
Title : Low-cost BLE based Indoor Localization using RSSI Fingerprinting and Machine
Learning
Authors : Balaji Ramachandran; Rizwan Mohammed Hussain; Vinod Subramanian; Jayakumar
Vandavasi Karunamurthy
Abstract : This paper explores the convergence of Internet of Things (IoT) technology with Low
Earth Orbit (LEO) satellite communication for power quality monitoring in
substations. A 7-day experiment utilizing a LEO satellite, exemplified by DEWASAT-1,
demonstrates the viability of this approach. The findings highlight the potential for
continuous monitoring of critical substation assets with a multi-satellite
constellation. The system leverages LoRa (Long Range) communication technology,
which is a low-power, long-range wireless protocol ideal for IoT applications. LoRa
enables efficient and reliable data transmission from substation sensors to satellites,
ensuring seamless connectivity even in remote or challenging environments.The
integration of IoT, LoRa, and satellite communication technology enhances the
efficiency of power quality monitoring and ensures data connectivity resilience. This
research paves the way for developing robust and responsive power quality
monitoring systems, contributing to the evolution of smart infrastructure and
resilient IoT applications in power systems.
(Electrical Power)
Paper ID : 1571042522
Title : Optimizing Preventive Maintenance of Generator Excitation Systems to Improve
Power Plant Reliability and Performance
Authors : Hartawan Abdillah; A.N. Afandi; Alief Muhammad; Abdul Haris; Mas Ahmad Baihaqi;
Dani Hari Tunggal Prasetyo; Moh Zainul Falah
Abstract : Generators are key components in power plants that convert mechanical energy
into electrical energy through the interaction between the magnetic field and the
rotor windings. The excitation system of a generator, responsible for providing the
initial magnetic field, plays a crucial role in this process. Preventive maintenance of
the excitation system is essential to maintain reliability and optimal performance.
13
Insulation resistance (IR) testing and brush length measurements are important
indicators in evaluating the condition of the exciter. The test results indicate that
routine cleaning can significantly improve resistance values, bringing them closer to
or exceeding the expected standards. Additionally, brush length measurements
suggest the need for special attention to brushes that have reached or exceeded the
minimum threshold of 65 mm, as per the 1995 First Year Inspection (FYI) standards.
Four brushes identified with the note "Replace" must be replaced immediately to
prevent serious disruptions in the power generation system. With proper routine
maintenance, the generator excitation system can remain in optimal condition,
preventing serious issues in the future and ensuring the reliable performance of the
power plant.
(Electrical Power)
Paper ID : 1571047567
Title : Optimizing Power Delivery in Inductive Wireless Power Transfer Systems Utilizing
SPICE-Python Integration
Authors : Sabriansyah Rizqika Akbar; Agung Setia Budi; Achmad Basuki; Ichijo Hodaka
Abstract : The quality factor (Q factor) and the coupling coefficient (K) are important
parameters in optimizing power delivery in Inductive Wireless Power Transfer
(IWPT) systems. The Q factor measures the efficiency and performance of resonant
circuits, indicating how effectively a coil can store energy relative to the energy lost
per cycle. This efficiency is crucial for determining the power transfer between
transmitter and receiver coils. Similarly, the coupling coefficient quantifies the
magnetic coupling between these coils, influencing the mutual inductance and
being affected by distance and misalignment. Our study proposes Wireless Power
Transfer Optimization utilizing SPICE-Python integration, a tool and method to
optimize IWPT parameters by utilizing SPICE and Python. The developed methods
effectively demonstrate the maximum power absorbed by the load under varying Q
factors and K coupling coefficients. Our findings indicate that higher K coefficients
require smaller Q values for optimal power delivery. These insights enable IWPT
designers to select appropriate capacitors, frequencies, and inductance parameters
to achieve maximum power transfer efficiency.
(Electrical Power)
Paper ID : 1571048406
Title : Wave Height Monitoring and Security System on Oscillating Water Column Using
ESP32 Microcontroller
Authors : Kholistianingsih; Isra’ Nuur Darmawan; Banyumas Dzanzar Panza Bakti
Abstract : This research aims to develop a wave height monitoring and security system for an
oscillating water column (OWC) system using the ESP32 microcontroller. The system
is capable of collecting real-time wave height data with high accuracy through
ultrasonic sensors and is equipped with an automatic security mechanism to ensure
the safe operation of the OWC. Testing results show an average sensor error rate of
3% inside the column, 1% outside the column, and an average delay time of 3.3
seconds to open the gate and 1 second to close it. The monitoring device has an
error rate below 5%, indicating sufficient accuracy in handling wave fluctuations,
and the security mechanism has proven reliable. This research contributes to
14
improved operational sustainability, reduced risk of damage from excessive waves,
and optimized renewable energy production from the OWC system.
(Electrical Power)
Paper ID : 1571048409
Title : Experimental Testing of 48 V Hybrid System of Solar-Wind Power Modul at Baru
Beach Pandansimo and Mount Buthak Bantul Special Region of Yogyakarta
Authors : Isra’ Nuur Darmawan; Kholistianingsih; Ghozy Awal Ramadani
Abstract : Electrical energy is an essential requirement for all life on Earth today, and energy
demands for electricity continue to rise. Meanwhile, Hybrid Power Moduls are being
created to fulfill the growing demand for extra electrical energy derived from
renewable energies. The purpose of this study is to assess the potential electrical
energy in a new location based on the design analysis of a hybrid generator
prototype that uses solar panels and windmills. According to the findings of this
study, the average intensity of sunshine at Baru Beach Pandansimo is 69,777 Cd,
while Mount Buthak Bantul has an average of 53,885 Cd, indicating a high potential
for good based on the standard average of 59,000 Cd. Baru Beach has an average
wind speed of 5.8 m/s, which is higher than Mount Buthak's average of 3.38 m/s,
with the average throughout Indonesia being 4 - 5 m/s. The average electrical
energy produced by a Solar Power Modul (SPM) on the Pantai Baru coast is 49.50
Watts, whereas on Mount Buthak it is 44.58 Watts. The average power energy at the
Wind Power Modul (WPM) on the Baru coast is 34.19 Watts, whereas Mount Buthak
receives just 5.02 Watts. Meanwhile, SPM's highest power output reaches 94 Watts
with a solar panel specification of 120W. The highest power of the WPM is 143W
while utilising a 200 Watt generator. This hybrid generator is stated to be capable of
charging a 20 Ah battery for 6 - 7 hours with a charging current of 3.0 - 3.5A.
(Electrical Power)
Paper ID : 1571051246
Title : Design of Wind Turbine Battery Charging Control Using a Buck-Boost Converter
with PID Control Optimized by Ant Colony Optimization
Authors : Ni Wayan Budiantari; Rini Nur Hasanah; Hadi Suyono
Abstract : This research proposes a voltage control strategy for battery voltage in wind turbine
battery charging systems. Changes in wind speed in wind turbine systems can cause
the generated voltage to be non-optimal, which in turn can affect the life of the
battery. A buck-boost DC-DC converter can be used to regulate the battery charging
mode. This converter is controlled by PID to keep the battery voltage constant. In
this study, the PID parameters are optimized using Ant Colony Optimization (ACO) to
achieve optimal control. This study will use a comparison of 2 methods, viz: System
using PID tuning control method and system controlled by PID with Ant Colony
Optimization. The results obtained in this study are the battery voltage generated by
the PID tuning system of 51.87 V and the battery voltage generated by the ACO
system of 51.95 V. While the battery SOC generated by the tuning system is 50.02
and the SOC generated by the ACO system is 50.12, The time required for the tuning
system is 0.53 and the time required for the ACO system is 0.42. It can be seen that
the ACO system is better and more efficient than the tuning system. This research
was designed using MATLAB/Simulink.
15
(Electrical Power)
Paper ID : 1571057388
Title : Implementation of the Enlargement Law on Rod-Rod Electrodes
Authors : Moch Dhofir; Rini Nur Hasanah; Aulia Angkasa; Corina Martineac
Abstract : Increasing the capacity and voltage of an electrical equipment will have implications
for increasing the dimensions of the equipment. According to Ohm's Law, increasing
the dimensions between two live conductors can reduce the dielectric strength of
the insulation between the two live conductors. In this paper, the results of research
are reported on the effect of increasing the cross-sectional area of the rod-rod
electrodes. The electrodes, namely A, 2A, 3A, 4A, and 5A, with A equal to
172.6mm2 or with a radius of 7.5mm.
(Electrical Power)
Paper ID : 1571062724
Title : An MPPT Strategy Based on Gravitational Search Optimization (GSO) for Improving
PV System Applications in Isolated Areas
Authors : Rizki Mendung Ariefianto; Indra Setyawan; Tri Nurwati; Rini Nur Hasanah; Makbul
Anwari Muhammad Ramli
Abstract : Solar energy converted by PV systems is very promising as the primary electricity
source in rural areas. However, the varying characteristics of nature make the
optimal efficiency of PV systems hard to achieve. Maximum Power Point Tracking
(MPPT), as a strategy to help PV systems extract solar power efficiently, faces an
issue in reaching the Global Maximum Power Point (GMPP). Many
metaheuristic-based algorithms have been developed to ensure the maximum
power of PV systems can be achieved. This study aims to evaluate the performance
of a metaheuristic-based MPPT called Gravitational Search Optimization (GSO),
which is applied to PV systems. As a comparison, Particle Swarm Optimization (PSO),
another MPPT strategy, was employed. The results show that the GSO exhibits
superior tracking ability and convergence rate compared to the PSO. This means
that GSO has proven its capability to reach GMPP, leading to beneficial
improvements in overall PV system performance.
B. ELECTRONIC SYSTEMS
(Electronic Systems)
Paper ID : 1570990854
Title : Design of Water Purification System Integrated with Real-Time Quality Monitoring
System Using Internet of Things
Authors : Zainul Abidin; Aldo Ricardo; Akhmad Zainuri; Agwin Fahmi Fahanani; Miroslav
Markovic; Ryoichi Miyauchi
16
Abstract : This paper presents the development of an advanced water purification system
utilizing reverse osmosis and real-time monitoring, powered by the Internet of
Things (IoT). The integration of IoT technology allows for continuous monitoring and
control of key water quality parameters, ensuring efficient and effective purification.
The system employs sensors to track metrics such as pH, Total Dissolved Solids
(TDS), water temperature, water flow rate, and water level, providing instant
feedback and automated adjustments to maintain optimal water quality.
Experiment results indicate significant improvements in water purity and
operational efficiency, demonstrating the potential of IoT-enhanced reverse osmosis
systems in addressing water quality challenges.
(Electronic Systems)
Paper ID : 1571015798
Title : IoT Based Precision Irrigation for Indoor Maize Cultivation
Authors : Rizqi Andry Ardiansyah; Mohamad Shukri Zainal Abidin; Hanif Fakhrurroja
Abstract : Due to the critical issues of water and climate change challenges, conserving water
in agriculture is becoming more and more crucial. These days, the goal of
agricultural research is to maximize agricultural productivity while minimizing water
usage. This study present IoT based automatic irrigation system for greenhouse
maize cultivation. A weather station equipment, soil moisture sensor and a
timer-based system were applied to accurately calculate the timing of irrigation
operations and to determine the volume of water needed by the plants. Error
(MAPE) of water need and water used value is 3.18%.
(Electronic Systems)
Paper ID : 1571030355
Title : Reducing Crosstalk of SiC MOSFET Gate Driver using a Negative Driving Voltage
Authors : Intan Anggraeni Maryanda Putri; Waru Djuriatno; Tri Nurwati; Soltana Guesmi
Abstract : This study examines the enhancement of reliability in Silicon Carbide (SiC) MOSFETs
in a half-bridge configuration through the use of an Active Gate Driver (AGD). SiC
MOSFETs offer higher efficiency, power density, and reliability compared to Silicon
(Si) MOSFETs due to their wider band gap, faster electron mobility, and better
thermal conductivity. However, SiC MOSFETs suffer challenges such as high dv/dt
and di/dt, oscillation, ringing, leading to Electromagnetic Interference (EMI), and
voltage overshoot, as well as crosstalk that disrupts control signals and MOSFET
stability. To address these issues, an AGD with a negative voltage technique
(NVTAGD) was designed to suppress crosstalk effects and reduce shoot-through
without requiring an additional negative power supply. Test results indicate that the
AGD significantly reduces voltage overshoot by 6.97 V or 21.02 dB compared to a
Conventional Gate Driver (CGD). Also, it suppresses positive crosstalk by 1.019 V or
9.59 dB and negative crosstalk by 1.69 V or 12.19 dB, maintaining the stability of the
gate-source voltage (VgsH). Although the AGD has a longer rise time compared to
the CGD, this increase is considered a reasonable trade-off for crosstalk suppression.
Drain current (Id) waveforms indicate no sudden current spikes, suggesting no
shoot-through occurrence with the AGD. In conclusion, the AGD outperforms in
enhancing MOSFET reliability by reducing overshoot and crosstalk, despite a slight
increase in rise time that may contribute to switching losses.
17
(Electronic Systems)
Paper ID : 1571038519
Title : Analysis of a Boost-Fed Full-Bridge Converter as a Voltage Stabilizer for a Fuel Cell
Source
Authors : Mochammad Rusli; Taufik Iqbal Miftaks; Muhammad Aziz Muslim; Taufik; Stephania
Angelica
Abstract : Fuel cells are an environmentally friendly form of energy source. However, their use
as an energy source must consider inherent decreasing and non-constant output
voltage characteristics. In this research, a full bridge circuit whose input is a fuel cell
with the addition of a boost DC-DC converter is proposed to minimize output voltage
ripple. The main objective is to obtain output voltage with minimal ripple by
reducing the current density and voltage drop at the fuel cell’s output. Modeling of
the full bridge DC-DC Converter was carried out with the addition of a PID controller
on the boost converter considering the linearity of boost output voltage and the
SMC on the full bridge converter considering the non-linearity of the full bridge’s
output voltage. In this study, a comparative evaluation was conducted between
circuits with and without the boost converter. Results show that the circuit with the
boost converter has slower system response than that without the boost converter.
The circuit with the boost converter was able to reach an output voltage of 600V in
0.116 seconds, while without the boost converter the response was at 0.083
seconds. However, the addition of the boost converter allows for less ripple and
better efficiency than that without the boost converter.
(Electronic Systems)
Paper ID : 1571049748
Title : Step Length Classification using Decision Tree based on IMU Sensors and Body
Height
Authors : Ilham Ari Zaeni; Dyah Lestari; Soraya Norma Mustika; Dessy Rif’a Anzani;
Muhammad Khusairi Osman; Khairul Azman Ahmad
Abstract : The ability to walk independently contributes significantly to the protective health
benefits and complications reduction in stroke rehabilitation. Task-oriented training
involves the repetition of functional activities to improve walking ability and is
considered a critical strategy. Human gait analysis, especially step length
measurement, plays an important role in monitoring mobility and rehabilitation
progress, though practical application in everyday life can seldom be achieved by
means of conventional methods. This paper presents the confirmation that step
length classification is achievable using Inertial Measurement Unit sensors. Feature
extraction, filtering, and preprocessing were done on the data from the
accelerometer to enhance the accuracy of the classification model. A decision tree
algorithm was used for its simplicity and interpretability to classify the step lengths
into short (22 cm), medium (33 cm), and long (44 cm). Three confusion matrices are
presented, showing the performance of three different models in classifying data
into classes 0, 1, and 2. For example, the first model is most accurate for class 0, at
an accuracy of 34.88%, but has difficulties classifying classes 1 and 2 at an accuracy
of 12.40% and 15.50%, with considerable misclassifications each. Then, the second
18
model yields higher results for both classes 1 and 2 with accuracy of 19.38% each,
though it still shows high misclassifications. The third model is the most accurate
and balanced; class 0 is classified at 24.07%, class 1 at 25.93%, and class 2 at
27.16%, with low misclassification rates. On the whole, this model is outstanding
since it offers the most reliable classification results of all the models.
(Electronic Systems)
Paper ID : 1571058434
Title : Optimizing The Sensor Array In The Electronic Nose For Coffee Aroma
Authors : Denda Dewatama; Erni Yudaningtyas; Muhammad Fauzan Edy Purnomo; Setyawan
P. Sakti
Abstract : Gas sensors are a key component in developing an electronic nose (e-nose) for
coffee volatile compounds (aroma) applications. This study aims to optimize the use
of sensors in e-nose based on three evaluation indicators: sensitivity, selectivity, and
sensor correlation. The research was conducted experimentally using nine types of
MQ Series sensors with coffee grown near Malang, specifically Robusta-Gedangan,
Robusta-Tirtoyudo, Arabica-Semeru, and Arabica-Gunung Kawi Gayo coffee varieties
roasted and ground to medium consistency by Alir.co Coffee and Roastery.
(Electronic Systems)
Paper ID : 1571059165
Title : Designing a Synchronous Automatic Transfer Switch for An on-grid Solar System
Authors : Akhmad Zainuri; Nurussa'adah; Onny Setyawati; Zainul Abidin; Panca Mudjirahardjo;
Renaldi Putra Pratama; Puput Dani Prasetyo Adi; Robeth Viktoria Manurung;
Dauletbay Baktybaevich Sarsenbaev
Abstract : The world is currently at a crucial point in energy transition due to the rapid
depletion of fossil fuels and growing concerns about climate change. The reliance on
non-renewable energy is becoming increasingly concerning, necessitating the
utilization of renewable energy sources. The on-grid solar system operates by
feeding the electrical energy generated by solar panels into the grid using a Grid Tie
Inverter (GTI). The on-grid solar system offers the advantage of being cheaper
because it does not require batteries. Most industrial users require energy from
on-grid solar energy to carry out production during the day. Despite their
advantages, on-grid systems have a notable limitation. When the grid provider an
electricity outage, the on-grid system cannot function, even during the day. This is
because the system relies on a trigger from PLN to activate its inverter. This paper
aims to design a trigger inverter for on-grid solar systems to address this issue
during a PLN power outage. The design will incorporate a Synchronous Automatic
Transfer Switch. The main goal of this investigation is to ensure uninterrupted
operation of the on-grid solar system in the event of a power outage from the grid.
The switch from PLN to GTI occurs without delay and without waveform differences
in the load, although there is a slight, insignificant voltage drop with a time interval
of 61ms. This study successfully demonstrates that the ATS and GTI systems can
function as designed to support the availability of renewable energy in Indonesia.
19
(Electronic Systems)
Paper ID : 1571059173
Title : Smart Vest for Palliative Therapy of Metastatic Cancer Patients Using TENS
Integrated with Thermotherapy, Aromatherapy, and Multimedia Based on the
Internet of Things
Authors : Nurussa'adah; Muhamad Asyir Zarkasih; Aryo Nabil Maulana; Akmal Mulki Majid;
Christalenta Renata Dwi Aristawati; Shalihat Azka Sabrina; Dauletbay Sarsenbaev;
Ayaz Ali Soomro
Abstract : There are 19.292.789 global cancer cases, with 9.958.133 fatalities. Lung cancer is
the leading cause of death among men with 1.796.144 cases, and breast cancer is
most prevalent in women with 684.996 cases. In Indonesia, there were 396.914 new
cases and 234.511 deaths [1][2]. Metastatic cancer or stage 4 cancer, is
characterized by highly aggressive cancer cells that have spread to other areas of
the body. Approximately 60% of advanced cancer patients with pain struggle with
daily activities, impacting sleep, and exacerbating emotional distress. Depression
rates among cancer patients are three times higher than the general population.
Addressing these challenges without medication, PALIAVEST integrates therapies like
TENS, thermotherapy, aromatherapy, and multimedia with real-time ECG monitoring
via IoT. Validated trials show high accuracy of ECG sensors more than 95% with 0.8%
error and TENS therapy (2 Hz and 100 Hz) at over 95% with 0.52% error. PALIAVEST
ensures consistent therapeutic temperatures, enhancing care reliability and
promising better patient quality of life through comprehensive palliative
approaches.
C. TELECOMMUNICATION
(Telecommunication)
Paper ID : 1571005792
Authors : Puput Dani Prasetyo Adi; Fairuz Iqbal Maulana; Pradeka Brilyan Purwandoko; Tjahjo
Adiprabowo; Yudi Yulius Maulana; Sofyan Mufti Prasetyo; Yuyu Wahyu; Arief
Suryadi Satyawan; Muhammad Yassir
20
allows devices to check the channel before transmission, reducing the risk of
interference and data collisions. The results show that LBT significantly reduces the
collision rate compared to ADR and ALOHA, with a collision rate of 10% for LBT, 20%
for ADR, and 40% for ALOHA. These findings reinforce the potential of LBT in
improving the performance of LoRaWAN, especially in applications that require
reliable data delivery without data loss.
(Telecommunication)
Paper ID : 1571028838
Paper ID : 1571030250
Authors : Ajeng Kusuma Dewi; Muhammad Fauzan Edy Purnomo; Fakhriy Hario Partiansyah
Abstract : CP-SAR (Circularly Polarized Synthetic Aperture Radar) utilizes circularly polarized
signals, enabling penetration through obstacles such as fog, clouds, and rain. One
type of antenna that can be used in CP-SAR applications is the microstrip antenna,
which generates circularly polarized signals due to its advantages of compact size,
simplicity, lightweight construction, low production cost, and ease of fabrication.
This research chose the 30-star microstrip antenna because its performance aligns
with the desired parameters. The U-slot method is proposed to demonstrate its
impact on circular polarization. U-slot is a U-shaped gap in the main antenna
element, which enhances bandwidth, modifies radiation patterns, and reduces the
antenna's dependency on the center frequency. The analyzed performance
21
parameters for the antenna include VSWR < 3 dB, return loss < -12 dB, gain > 3 dB,
efficiency > 80%, and axial ratio < 3 dB. Simulations were conducted using CST
Studio Suite 2019 with an FR-4 substrate. The simulation results show that the
30-star microstrip antenna with the U-slot achieved an axial ratio of < 3 dB,
confirming the presence of circular polarization. This finding is crucial for effective
signal transmission in CP-SAR.
(Telecommunication)
Paper ID : 1571042923
Abstract : The Internet of Things (IoT) relies on efficient data communication protocols like
CoAP and HTTP. This study compares the performance of these protocols using an
ESP32 microcontroller with MQ7 and DHT11 sensors for air quality monitoring. Key
metrics assessed include network performance, power consumption, and memory
usage. Wireshark analysis reveals CoAP has 80% higher delay and consumes 4%
more power than HTTP, though CoAP offers 3% better storage efficiency. HTTP, on
the other hand, provides 27% higher throughput. Both protocols show similar
reliability and memory usage.
(Telecommunication)
Paper ID : 1571048360
Title : Vegetation Density Profiling Using FMCW Radar for Plant Population Estimation
Authors : Virginia Rosaline Zefanya Iskandar; Budi Prasetya; Aloysius Adya Pramudita
22
(Telecommunication)
Paper ID : 1571048390
Abstract : Topsoil is essential for agriculture, storing nutrients and water necessary for plant
growth, but is susceptible to erosion from rainfall and human activities, reducing its
thickness and productivity. Unlike conventional methods, this research utilizes
Stepped Frequency Continuous Wave (SFCW) Radar as a non-destructive method to
estimate topsoil thickness with high resolution without damaging the soil structure.
This research investigates the effect of soil dielectric properties such as conductivity
on the radar signal and the impact of signal-to-noise ratio (SNR) on measurement
accuracy. Simulation results show that higher SNR values result in more accurate
estimates, with moderate conductivity values providing better accuracy than very
low or high values. For example, at a soil thickness of 20 cm, the thickness estimate
at a conductivity value (σ) of 0.1 S/m, the accuracy is 99.5%, but it decreases to
88.7% at σ = 1 S/m. Similarly, at a thickness of 40 cm, the estimate at σ = 0.1 S/m,
the accuracy is 99.8%, but it decreases to 88.93% at σ = 1 S/m. In addition, with a
topsoil thickness of 20 cm, the estimated thickness at SNR = 13 dB is 19.85 cm with
an accuracy of 99.25%, and at a thickness of 40 cm, the estimate is 40.46 cm with
an accuracy of 98.85%, with an overall average accuracy of 99.043% at SNR = 13 dB.
(Telecommunication)
Paper ID : 1571048484
Title : Soil Nitrogen Content Estimation Using SFCW Radar with Interpolated Look-Up
Table Inference Technique
Authors : Nurul Febri Annisa; Levy Olivia Nur; Restu Wulansari; Aloysius Adya Pramudita
Abstract : The availability of soil nitrogen content is a very important substance for plant
growth. Nitrogen plays a role in the formation of chlorophyll and proteins that are
essential for photosynthesis and plant development. In this paper, a
non-conventional method was used with Stepped Frequency Continuous Wave
(SFCW) radar. The SFCW radar is known for detecting the soil surface with high
resolution. The value of soil nitrogen content can be estimated using the reflection
coefficient obtained from the results of SFCW radar measurements. SFCW radar
data can help see the correlation between peak-to-peak values and the nitrogen (N)
element obtained from the SEM2252 soil speedometer sensor. When the nitrogen
value obtained from the sensor is high, the peak-to-peak value on the SFCW radar
also shows relatively high results. The results obtained from the radar are used to
find the shape of the curve fitting. This paper uses an inference technique to
interpret the soil nitrogen content from the reflected signal obtained from the
SFCW radar
23
(Telecommunication)
Paper ID : 1571059184
Title : Impact of Traffic Increase on Quality of Service for Internet, IPTV, and VoIP in
FTTH Networks: A Case Study at Brawijaya University
Authors : Sigit Kusmaryanto; Rusmi Ambarwati; Ali Mustofa; Endah Budi Purnomowati; Gaguk
Asmungi; Najya Putri Herfita
Abstract : The use of digital internet-based services has become a primary need, especially in
academic environments such as campuses. Triple Play services, which include
internet, IPTV, and VoIP, are increasingly used to support daily activities such as
teaching, research, and administration. However, an increase in the number of
users or traffic can pose a problem that potentially disrupts service quality.
Therefore, this study was conducted to understand how the increase in traffic
affects Quality of Service (QoS). The research methodology includes predicting
incoming traffic, which involves estimating the number of users, calculating traffic
intensity, and determining traffic volume over a day. Network quality testing
involves calculating the power link budget. Service quality testing includes
measuring throughput, packet loss, delay, and jitter using Ettercap and Wireshark
software. The results of the study show that the daily traffic volume is 669,600 Mbit
for internet services, 201,600 Mbit for IPTV services, and 787.2 Mbit for VoIP
services. The traffic intensity over a day is 18.6 Mbps for internet services, 5.6 Mbps
for IPTV, and 0.262 Mbps for VoIP, with peak traffic activity occurring at 12:00 PM,
1:00 PM, and 2:00 PM. The calculated attenuation of 21.65 dB and receiver power
of -17.66 dBm indicate that the network can provide good service quality. An
increase in traffic will lead to higher throughput, no packet loss, and a reduction in
delay and jitter. High traffic can cause strain on the network capacity, particularly if
the capacity is insufficient to handle the volume of traffic. Insufficient network
capacity will result in decreased service quality, characterized by reduced
throughput and increased packet loss, delay, and jitter. In such conditions, the
services that experience significant quality degradation are VoIP and IPTV.
(Telecommunication)
Paper ID : 1571060364
Title : Scalable Resource Management for Latency-Sensitive Applications in Edge
Computing
Authors : Wahyu Adi Prijono; Primatar Kuswiradyo; Dipak Kumar Sahoo; Sigit Kusmaryanto;
Endah Budi Purnomowati; Ali Mustofa
Abstract : Edge computing is crucial for latency-sensitive Internet of Things (IoT) applications,
providing reduced latency and enhanced computational efficiency. However,
ensuring low latency while maintaining scalability presents significant challenges.
This paper proposes a scalable resource management algorithm using heuristic
methods to optimize resource allocation and workload distribution in edge
computing environments. The algorithm dynamically adjusts to real-time demands,
ensuring minimal latency and efficient utilization of computational resources.
Extensive simulations were conducted to evaluate the performance of the proposed
algorithm compared to the Greedy Algorithm and the First-Come, First-Served (FCFS)
24
Algorithm. The results demonstrate that the proposed heuristic algorithm
significantly outperforms the baseline algorithms in terms of number of packet
losses, decreased average latency by up to 38%, and better resource utilization
efficiency by up to 27%. The inclusion of buffers at edge nodes to handle
non-real-time traffic allows the system to prioritize real-time traffic effectively,
resulting in reduced packet drops and improved overall performance. These results
highlight the algorithm’s potential for improving the performance and scalability of
edge computing for real-time IoT applications. Future research directions include
exploring advanced optimization techniques, integrating energy efficient resource
management strategies, addressing security and privacy challenges, and conducting
real-world deployment and validation of the proposed algorithm.
D. CONTROLS SYSTEM
(Control System)
Paper ID : 1571039394
Title : Investigation of PI-Controller With A Sinusoidal Function And Feedforward Control
On Traction Motor Of High Speed Train
Authors : Mochammad Rusli; Unggul Wibawa; Razzan Naufal Rianta
Abstract : Direct torque control of three-phase induction motor based on constant voltage per
frequency control preserves the conventional direct torque control transient merits,
furthermore, produces better quality steady-state performance in a wide speed
range. In this paper, the simple PI Plus Sinusoidal Function controller is introduced
to substitute the original PI controller for speed controller, torque and stator flux
magnitude controller using an On-Off controller. The simulation results have
confirmed the validity of the proposed controller as well as shown good dynamic
and steady-state responses of this control system. In the traction drive system for
high-speed trains, a substantial ripple of DC bus voltage may negatively affect the
performance of the traction drives. A new method to reject the torque and current
ripple (beat components) in induction motor, which resulted from the DC effects of
sampling accuracy to the ripple-eliminating common methods, the introduced
method is economical and easy to implement. In this paper, a PI Plus Sinusoidal
Function controller is derived and simulated using the parameters of the traction
motor of high-speed Train. Feedforward control was also considered.
(Control System)
Paper ID : 1571047836
Title : On the Design and Analysis of Discrete-Time Plug-in Repetitive Controller with
Three Different Internal Models
Authors : Muhammad Aziz Muslim; Edi Kurniawan; Rahmadwati; Ronald Edward
Abstract : This research provides a design strategy of a plug-in repetitive control (RC) method
with three internal models for a class of linear minimum phase systems. The part of
the RC that is used in stabilizing the closed-loop system is the compensator. In this
paper, we present the design of RC compensator and internal model. The
effectiveness of the proposed design is demonstrated through simulations on a
minimum phase plant model with a periodic reference signal. The simulation results
25
show that the plug-in RC method achieves precise tracking and convergence,
confirming the effectiveness of the proposed approach.
Paper ID : 1571030268
Title : Development of Indonesia Sign Language Learning Media based on YoloV8
Authors : Kartika Candra Kirana; Frans Achmad Hendra Winata; Wahyu Nur Hidayat; Muis
Muhtadi; Heru Wahyu Herwanto; Slamet Wibawanto
Abstract : Previous research has used YOLO as a computer vision technique to recognize sign
language translation systems. Nevertheless, there is no research focusing on
optimizing the model's hyperparameters. However, hyperparameters are crucial
keys to optimizing the Yolo model. The goal of this study is to optimize YOLOv8
model hyperparameters to develop Indonesian sign language learning media. The
best possible hyperparameter configuration was found through testing, including
YOLOv8m pre-trained weights, 150 epochs, the Stochastic Gradient Descent (SGD)
optimizer function, and a batch size of 16. The result shows 100% for Precision,
Recall, and F1 Score for 4 real-time videos, as well as a measure indicating that the
proposed model could recognize sign language movements as learning media.
Paper ID : 1571040661
Title : A Systematic Approach of Hyperparameter Optimization to Improve Neural
Network Model Performance
Authors : Muhammad Yusuf Rizaldy; Mochammad Rusli; Muhammad Aziz Muslim
Abstract : This study investigates the effectiveness of different hyper-parameter optimization
methods for a neural network model predicting solar array voltage peak Vmp. The
performance of four methods is compared: Trial and Error, GS, RS, and PSO. Mean
Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE),
and R-squared were used to evaluate model performance. PSO achieved the best
performance (MAE = 4.52, MSE = 90.63, RMSE = 9.52, and R2 = 0.81) compared to
other methods. PSO also achieved the fastest search time (60.46 second) compared
to other methods. This study highlights PSO's potential as an effective
hyper-parameter optimization algorithm, producing to a model with superior
performance metrics. This study also explores the impact of varying search space
dimensions and swarm population on model performance, emphasizing the
importance of selecting an appropriate population size, and investigates the effects
of adjusting PSO cognitive and social parameters, highlighting the necessity of
balancing these parameters for optimal PSO performance.
26
Paper ID : 1571043721
Title : Comparison Of Vehicular Traffic Emissions And Fuel Consumption Under
Full-Actuated And Fixed Timing Traffic Light
Authors : Zulfa Fahrunnisa; Rahmadwati; Raden Arief Setyawan
Abstract : This study analyzes and compares the emissions and fuel consumption of vehicles
operating under full-actuated and fixed-timing traffic light systems. The analysis is
based on experiments conducted using traffic simulation models. Results indicate
that vehicles under full-actuated control, which adjusts signal timings based on
real-time traffic conditions, show significantly lower emissions and fuel
consumption than those under fixed-timing traffic light, which operates on a
predetermined schedule. Additionally, the study reveals notable differences in
emission levels and fuel consumption between different traffic density scenarios
within each control system. This research underscores the environmental and
efficiency benefits of implementing full-actuated traffic signal systems in urban
traffic management.
Paper ID : 1571048385
Title : YOLOv8 based Multi Object Detection for BTS Asset Monitoring
Authors : Lukman Hakim; Asep Suhendi; Aloysius Adya Pramudita
Abstract : The security of Base Transceiver Stations (BTS) is a critical priority due to the
significant material losses caused by theft of components such as cables and
receivers. Traditional human-based monitoring systems are impractical for 24-hour
surveillance due to high costs and logistical challenges. Object detection using deep
learning algorithms, specifically the YOLO architecture, potentially offers an effective
solution for automated monitoring. YOLO is known for its real-time processing
capabilities and was studied for its application in detecting sectoral and microwave
antennas on BTS from image data collected by remote camera. In this research, the
performance of YOLOv8 in identifying BTS components was investigated through
comprehensive experimentation. The result show that this model is quite effective
in detecting microwave and sectoral antennas, this shows by 61% overall accuracy.
Paper ID : 1571048423
Title : Stress Detection Using EEG Signals: A SVM-Based Classification and Feature
Selection Approach
Authors : Fi Imanur Sifaunnufus Ms; Fitra Abdurrachman Bachtiar; Barlian Henryranu Prasetio
Abstract : Stress is a problem with various adverse effects, such as mental disorders and
suicide. With these problems arising, a stress detection system is needed as an
initial examination of the level of stress experienced. Generally, stress detection is
done with a stress test at a hospital. However, medical examinations done in the
hospital require high costs. Another alternative to examine stress levels is by using a
biosignal electroencephalogram (EEG), which provides more objective and accurate
results. In addition, there is a need to develop a portable device that can be used to
detect stress. This study tries to detect stress levels using EEG Signals. The data used
27
in this study is primary data that simulates several stress-level activities. In total, 55
subjects participated in this stress detection research. The received signal goes
through preprocessing to clean it from noise and artifacts. The data will be extracted
using Power Spectral Density (PSD) into power value for each signal frequency. The
preprocessed input signals are then classified into indications of stress levels. This
study uses Random Forest, SVM, and Decision Tree. The model is stored on a
portable system with Raspberry Pi as the main component. EEG signals are taken
using electrodes on Muse 2 and sent to the system. The classification model
generates predicted stress levels and is displayed on a 16×2 LCD. SVM as the best
model test result achieved a testing accuracy of 1, and an average computation time
of 0.92.
Paper ID : 1571048470
Title : Detection of Empoasca Pest Attacks on Tea Leaves Based on Multispectral Camera
Using ResNet-50
Authors : Bella Khairunnisa Kurniawan; Fiky Yosef Suratman; Fani Fauziah; Aloysius Adya
Pramudita
Abstract : Tea is one of the important plantation commodities in the Indonesian economy.
However, some challenges during cultivation can cause a decrease in production,
including the attack of Empoasca pests on tea leaves. Inappropriate use of
pesticides to combat this pest can reduce the quality of tea leaves. Accurate
diagnosis of plant diseases and proper use of plant protection systems can help
prevent production losses. This research proposes to detect Empoasca-infested tea
leaves using multispectral cameras, with ResNet-50 architecture used for data
processing to achieve high accuracy. The main indicator of Empoasca infestation is
leaf curl-up, which can lead to leaf death. Multispectral cameras were chosen for
this study because of their ability to provide different spectral features. Among the
four spectra tested, the green spectrum gave the best results, graphically showing
no overfitting and underfitting. This spectrum makes it easy to identify the
characteristics of Empoasca-infested tea leaves based on their shape, which can
facilitate data processing using the ResNet-50 architecture.
Paper ID : 1571048492
Title : Comparisson of Q&A Classification Using Bi-LSTM Based on Closed Domain
Knowledge
Authors : Alifi Lazuardi Gunawan; Fitra Abdurrachman Bachtiar; Budi Darma Setiawan
Abstract : The Faculty of Computer Science, Universitas Brawijaya (Filkom UB) is committed to
providing quality services for the users especially internal and external stakeholders,
one of which is through the HaloFilkom service. HaloFilkom services have limitations
in terms of time. HaloFilkom services are not available 24 hours due to limited
working hours. Questions asked by users are not answered directly. This weakness in
the HaloFilkom system can be overcome by using a chatbot system. Chatbot is an
interactive system that works with natural human language and can work 24 hours.
Thus, the current study explores the basic chatbot model by classifying the Q&A in
the closed domain knowledge. The dataset in this research is in the form of pairs of
28
questions and answers regarding various topics at the Filkom UB. The knowledge is
preprocessed using text preprocessing which includes case folding, tokenization,
padding, and tensorization. One of the chatbot models is a generative model.
Creating a generative chatbot model can be done using the Seq2Seq model
mechanism which consists of an encoder and decoder. The model created consists
of four different architectures, namely a model with an LSTM encoder without
attention and with attention and a BiLSTM model encoder without attention and
with attention. Hyperparameter tuning was conducted to obtain the best
hyperparameter combination. The experiment results show the best
hyperparameter combination obtained is hidden size 448, drop out rate 0.5,
learning rate 0.001, batch size 64, and teacher force 0. The model with the best loss
is obtained with a BiLSTM encoder architecture without an attention mechanism
with a train loss of 0.120. The model with the highest BLEU Score was obtained by a
model with a BiLSTM encoder architecture without an attention mechanism with a
BLEU Score of 0.8587 on the training data. Testing using prompt testing obtained an
average BLEU Score of 0.3745 on the BiLSTM encoder without an attention
mechanism model. Finally, the best model architecture obtained in this research is
BiLSTM encoder without an attention mechanism.
Paper ID : 1571048497
Title : Engagement Level Detection Using Facial Extraction Using Multi-stacked
Convolutional Neural Network in e-Learning Settings
Authors : Fitra Abdurrachman Bachtiar; Al’Ravie Mutiar Mahesa; Eric Wallace Cooper
Abstract : Engagement in learning is crucial in maintaining student eagerness as fuel for
student learning to achieve learning success. In e-Learning settings, engagement
also plays an important role as a factor influencing student learning success as
students are regulating themselves during learning one-on-one using computer
devices. Failing to detect student engagement may result in a decline in learning. In
extreme cases, students may disengage and learning purpose cannot be achieved.
This research aims to detect user engagement in e-Learning settings by using a deep
learning approach with a feature extraction method. The dataset used in this study
is the DAiSEE dataset. The dataset is in the form of videos and is extracted into
frames and specific facial features. The facial area was extracted using the
Mediapipe Library. The features include 1434 3D landmark features, 52 action unit
features, one depth estimation feature, and three head pose estimation features.
This research also conducts image selection, which selecting frames with an interval
of 15 in the train, validation, and test folders. The multi-stacked Convolutional
Neural Network model was used to classify four levels of engagements. The results
were compared to the existing approach in engagement detection. The untuned
proposed model achieved an accuracy of 48.95%, while the tuned proposed model
achieved an accuracy of 52.94%. The proposed model is able to compete with
state-of-the-art methods using a less complex model. Even so, the model still cannot
learn labels perfectly due to a very imbalanced dataset and a possibility of model
overfitting. This research is expected to be useful for educational institutions and
the e-Learning field in the future.
29
Paper ID : 1571051253
Title : Building Detection Using Convolutional Neural Network (CNN) U-Net Architecture
on Satellite Imagery
Authors : Panca Mudjirahardjo; Rahmadwati; Vicky Firmansyah
Abstract : This research aims to detect buildings in satellite images using the U-Net
architecture CNN model. The dataset is a satellite image of the Araya area, Malang
City extracted through Google Earth Engine with the Python programming language,
consisting of 4 band channels: Red, Green, Blue, and NIR. The data is processed into
2 types of sizes, namely 128x128 pixels and 64x64 pixels, then divided into train,
validation, and test data. Training uses Keras Tensorflow, and testing is done in three
stages: model performance testing with layer addition and parameter changes,
building detection testing, and comparison of prediction results with manual
measurements. The best model was obtained by a model with a training dataset of
128x128 pixels that achieved 93% accuracy with a prediction time of 2 seconds.
Paper ID : 1571061478
Title : Leveraging Deep Learning Vision for Real-Time Monitoring and Counting of Online
Motorcycle Taxi Traffic
Authors : Raden Arief Setyawan; Zainul Abidin; Ratno Wahyu Widyanto
Abstract : The expansion of online motorcycle taxi services has rapidly changed the transport
systems in cities, especially in developing countries with high traffic density. This
paper proposes a new method using deep learning and computer vision to monitor
30
and count motorcycle taxis on the internet in real-time. The proposed system uses
state-of-art convolutional neural networks (CNNs) for object detection and tracking,
which the YOLOv5 model is chosen based on the combination of the accuracy and
speed. The efficiency of the proposed system was evaluated in a real environment at
the main gate of Universitas Brawijaya with the detection accuracy of 91,4% and
reasonable time to complete the processes suitable for real time application. The
versatility of the system was also demonstrated in different lighting and weather
conditions with slight reductions in performance during low light and rainy
environments. These promising results show the potential of the proposed system
for improving traffic management in cities and supporting urban infrastructure
development for smarter cities.
31