Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Teddy Surya Gunawan
ECE Department, Faculty of Engineering, International Islamic University Malaysia
Computer Science & IT Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Enhanced Emotion Recognition in Videos: A Convolutional Neural Network Strategy for Human Facial Expression Detection and Classification Arselan Ashraf; Teddy Surya Gunawan; Fatchul Arifin; Mira Kartiwi; Ali Sophian; Mohamed Hadi Habaebi
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 1: March 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i1.4449

Abstract

The human face is essential in conveying emotions, as facial expressions serve as effective, natural, and universal indicators of emotional states. Automated emotion recognition has garnered increasing interest due to its potential applications in various fields, such as human-computer interaction, machine learning, robotic control, and driver emotional state monitoring. With artificial intelligence and computational power advancements, visual emotion recognition has become a prominent research area. Despite extensive research employing machine learning algorithms like convolutional neural networks (CNN), challenges remain concerning input data processing, emotion classification scope, data size, optimal CNN configurations, and performance evaluation. To address these issues, we propose a comprehensive CNN-based model for real-time detection and classification of five primary emotions: anger, happiness, neutrality, sadness, and surprise. We employ the Amsterdam Dynamic Facial Expression Set – Bath Intensity Variations (ADFES-BIV) video dataset, extracting image frames from the video samples. Image processing techniques such as histogram equalization, color conversion, cropping, and resizing are applied to the frames before labeling. The Viola-Jones algorithm is then used for face detection on the processed grayscale images. We develop and train a CNN on the processed image data, implementing dropout, batch normalization, and L2 regularization to reduce overfitting. The ideal hyperparameters are determined through trial and error, and the model's performance is evaluated. The proposed model achieves a recognition accuracy of 99.38%, with the confusion matrix, recall, precision, F1 score, and processing time further quantifying its performance characteristics. The model's generalization performance is assessed using images from the Warsaw Set of Emotional Facial Expression Pictures (WSEFEP) and Extended Cohn-Kanade Database (CK+) datasets. The results demonstrate the efficiency and usability of our proposed approach, contributing valuable insights into real-time visual emotion recognition.
Development and Evaluation of a High-Performance Electrochemical Potentiostat-Based Desktop Application for Rapid SARS-CoV-2 Testing Faisal Ahmed Assaig; Teddy Surya Gunawan; Anis Nurashikin Nordin; Rosminazuin Ab. Rahim; Zainihariyati Mohd Zain; Rozainanee Mohd Zain; Fatchul Arifin
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 2: June 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i2.4645

Abstract

The COVID-19 pandemic has necessitated the development of rapid and trustworthy diagnostic tools. Reverse transcription-polymerase chain reaction (RT-PCR) is the gold standard for detecting SARS-CoV-2 but has cost and time constraints. The sensitivity, specificity, and low cost of electrochemical biosensors make them an attractive alternative for virus detection. This study aims to develop and evaluate a high-performance desktop application for an electrochemical potentiostat-based SARS-CoV-2 test device, with a user-friendly interface that automatically interprets results, to expedite the testing process and improve accessibility, particularly in resource-limited settings. The application was built with the Electron framework and the HTML, CSS, and JavaScript programming languages. Our findings indicate that the developed electrochemical potentiostat-based desktop application demonstrates high accuracy compared to commercial software, achieving rapid detection within 30 seconds. The graphical user interface was found to be straightforward and user-friendly, requiring minimal training for efficient system operation. Our electrochemical potentiostat-based desktop application represents a valuable tool for rapid SARS-CoV-2 testing, particularly in settings with limited resources. This research contributes to developing rapid and reliable diagnostic tools for SARS-CoV-2 and potentially other pandemic-causing viruses, addressing the pressing need for improved public health surveillance and response strategies.
Voltage Instability and Voltage Regulating Distribution Transformer Assessment Under Renewable Energy Penetration For Low Voltage Distribution System Nur Syazana Izzati Razali; Teddy Surya Gunawan; Siti Hajar Yusoff; Mohamed Hadi Habaebi; Saerahany Legori Ibrahim; Siti Nadiah Mohd Sapihie
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 3: September 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i3.4857

Abstract

The Voltage Regulating Distribution Transformer (VRDT) is a tap-changing transformer that regulates the voltage across all three phases. However, its application in the context of renewable energy penetration into low-voltage grids remains understudied. This paper addresses this research gap by presenting a refined voltage drop model tailored for the International Islamic University Malaysia (IIUM) distribution network. Based on a derived mathematical equation, the model is validated and analyzed using Simulink's modeling platform. Simulations are performed without and with the VRDT, revealing that renewable energy penetration can cause instability, leading to voltage deviations proportional to the injected renewable energy. Incorporating the VRDT in the low-voltage grid allows for voltage adjustment under loaded conditions, ensuring uninterrupted renewable energy injection. Voltage stability analysis is conducted using actual load consumption data from the IIUM network for 2020 and 2021, offering valuable insights despite assuming equal energy consumption across buildings. Most hostels exhibit stable distribution systems with solar energy, but instability arises when solar energy comprises 100% of the input for the Safiyyah and Zubair hostels' 11kV distribution transformers. Implementing the VRDT regulates this instability, restoring system stability. This study highlights the importance of VRDT integration in high renewable energy proportion low-voltage grids, enabling voltage regulation and stability under variable renewable energy injection scenarios. The findings demonstrate that VRDTs mitigate voltage instability caused by renewable energy, providing a reliable solution for incorporating renewables into low-voltage distribution networks. It contributes to understanding renewable energy's impact on distribution system stability and offers guidance for VRDT implementation in similar contexts. 
Optimizing U-Net Architecture with Feed-Forward Neural Networks for Precise Cobb Angle Prediction in Scoliosis Diagnosis Mohamad Iqmal Jamaludin; Teddy Surya Gunawan; Rajendra Kumar Karupiah; Suriza Ahmad Zabidi; Mira Kartiwi; Zamzuri Zakaria
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 3: September 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i3.5009

Abstract

In the burgeoning field of Artificial Intelligence (AI) and its notable subsets, such as Deep Learning (DL), there is evidence of its transformative impact in assisting clinicians, particularly in diagnosing scoliosis. AI is unrivaled for its speed and precision in analyzing medical images, including X-rays and computed tomography (CT) scans. However, the path does not lack obstacles. Biases, unanticipated outcomes, and false positive and negative predictions present significant challenges. Our research employed three complex experimental sets, each focusing on adapting the U-Net architecture. Through a nuanced combination of feed-forward neural network (FFNN) configurations and hyperparameters, we endeavored to determine the most effective nonlinear regression model configuration for predicting the Cobb angle. This was done with the dual purpose of reducing AI training time without sacrificing predictive accuracy. Utilizing the capabilities of the PyTorch framework, we meticulously crafted and refined the deep learning models for each of the three experiments, focusing on an FFFN dropout rate of p=0.45. The Root Mean Square Error (RMSE), the number of epochs, and the number of nodes spanning three hidden layers in each FFFN were utilized as crucial performance metrics while a base learning rate of 0.001 was maintained. Notably, during the optimization phase, one of the experiments incorporated a learning rate scheduler to protect against potential pitfalls such as local minima and saddle points. A judiciously incorporated Early Stopping technique, triggered between the patience range of 5-10 epochs, ensured model stability as the Mean Squared Error (MSE) plateau loss approached approximately 1. Consequently, the model converged between 50 and 82 epochs. We hypothesize that our proposed architecture holds promise for future refinements, conditioned on assiduous experimentation with an array of medical deep learning paradigms.
Co-Authors Ali Sophian Anis Nurashikin Nordin Arselan Ashraf Faisal Ahmed Assaig Fatchul Arifin Mira Kartiwi Mira Kartiwi Mohamad Iqmal Jamaludin Mohamed Hadi Habaebi Mohamed Hadi Habaebi Nur Syazana Izzati Razali Rajendra Kumar Karupiah Rosminazuin Ab. Rahim Rozainanee Mohd Zain Saerahany Legori Ibrahim Siti Hajar Yusoff Siti Nadiah Mohd Sapihie Suriza Ahmad Zabidi Zainihariyati Mohd Zain Zamzuri Zakaria