Masrullizam Mat Ibrahim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Masrullizam Mat Ibrahim has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Meizano Ardhi Muhammad
Universiti Teknikal Malaysia Melaka,Department of Computer Engineering,Melaka,Malaysia
2 shared publications - Muhammad Noorazlan Shah Zainudin
Universiti Teknikal Malaysia Melaka
2 shared publications - Nik Mohd Zarifie Hashim
Fakulti Teknologi dan Kejuruteraan Elektronik dan Komputer, Universiti Teknikal Malaysia Melaka
2 shared publications - Ahmad Fauzan Kadmin
Universiti Teknikal Malaysia Melaka
1 shared publication - Ameer Farhan Roslan1 shared publication
- Dikpride Despa
University of Lampung
1 shared publication
Latest Publications
- Open Access
- 1 October 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (5) , 4096-4104
Assessing corn quality classification with deep-learning module
This study presents a new classification framework for corn quality assessment using the you only look once version 8 (YOLOv8) deep learning architecture. Traditional corn-sorting methods are labor-intensive, time-consuming, and prone to human error. To address these challenges, this study proposes the corn quality classification (CQC) algorithm, an artificial intelligence (AI)-driven approach for automatically recognizing and categorizing pest- and disease-related defects. The proposed model uses YOLOv8, which integrates a convolutional neural network (CNN) backbone for feature extraction and object detection. The system was trained on labelled corn images to classify them into three categories: healthy, water rot, and bug. The model achieved an overall classification accuracy of 92.7%, with class-specific accuracies of 88.9% for healthy, 70% for water rot, and 100% for bug. Key performance metrics included a recall of 93%, an F1-score of 62%, a mean average precision (mAP) of 92.7%, and an intersection over union (IoU) of 52.3%. Additionally, the F1-confidence and recall-confidence curves provided further insights into the model’s performance. The proposed classification framework and CQC algorithm demonstrate the feasibility of AI-powered agricultural monitoring systems, offering a reliable and efficient approach to corn quality assessment. By enabling consistent and accurate classification, the proposed system has the potential to reduce labor requirements and support precision agriculture practices for improved crop quality management.
- 1 October 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (5) , 4096-4104
Open AccessAssessing corn quality classification with deep-learning module
This study presents a new classification framework for corn quality assessment using the you only look once version 8 (YOLOv8) deep learning architecture. Traditional corn-sorting methods are labor-intensive, time-consuming, and prone to human error. To address these challenges, this study proposes the corn quality classification (CQC) algorithm, an artificial intelligence (AI)-driven approach for automatically recognizing and categorizing pest- and disease-related defects. The proposed model uses YOLOv8, which integrates a convolutional neural network (CNN) backbone for feature extraction and object detection. The system was trained on labelled corn images to classify them into three categories: healthy, water rot, and bug. The model achieved an overall classification accuracy of 92.7%, with class-specific accuracies of 88.9% for healthy, 70% for water rot, and 100% for bug. Key performance metrics included a recall of 93%, an F1-score of 62%, a mean average precision (mAP) of 92.7%, and an intersection over union (IoU) of 52.3%. Additionally, the F1-confidence and recall-confidence curves provided further insights into the model’s performance. The proposed classification framework and CQC algorithm demonstrate the feasibility of AI-powered agricultural monitoring systems, offering a reliable and efficient approach to corn quality assessment. By enabling consistent and accurate classification, the proposed system has the potential to reduce labor requirements and support precision agriculture practices for improved crop quality management.
- 2 August 2026
- Published by Springer Nature
- p. 531-541
Energy-Efficient Image Compression for Business Intelligence: Comparative Insights on Wavelet-Based Methods
- 2 August 2026
- Published by Springer Nature
- p. 531-541
Energy-Efficient Image Compression for Business Intelligence: Comparative Insights on Wavelet-Based Methods
- Open Access
- 1 February 2026
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 41 (2)
Assessment of detection methods for back-end process defects in equipment and devices in semiconductor manufacturing
Defect detection plays a pivotal part in the manufacturing process of semiconductors. Defects can be rooted in the product on its own, as well as the tools used to process and make the product, particularly the equipment and machinery used. Defect detection is crucial in semiconductor manufacturing, where even minor flaws can compromise product performance. Defect detection in the backend process of semiconductor manufacturing, specifically in die attach and die bonding, is critical for ensuring product quality and reliability. Die attach involves securing semiconductor chips onto substrates, while die bonding involves connecting wires to the chip. Detecting defects during these processes is vital to prevent issues such as misalignment, inadequate bonding, or contamination, which can lead to malfunctioning chips or devices. Various techniques such as visual inspection, automated optical inspection (AOI), and X-ray imaging are utilized to identify defects like cracks, voids, or irregularities in bond formation. By employing rigorous defect detection measures, manufacturers can uphold stringent quality standards and produce reliable semiconductor devices for various applications.
- 1 February 2026
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 41 (2)
Open AccessAssessment of detection methods for back-end process defects in equipment and devices in semiconductor manufacturing
Defect detection plays a pivotal part in the manufacturing process of semiconductors. Defects can be rooted in the product on its own, as well as the tools used to process and make the product, particularly the equipment and machinery used. Defect detection is crucial in semiconductor manufacturing, where even minor flaws can compromise product performance. Defect detection in the backend process of semiconductor manufacturing, specifically in die attach and die bonding, is critical for ensuring product quality and reliability. Die attach involves securing semiconductor chips onto substrates, while die bonding involves connecting wires to the chip. Detecting defects during these processes is vital to prevent issues such as misalignment, inadequate bonding, or contamination, which can lead to malfunctioning chips or devices. Various techniques such as visual inspection, automated optical inspection (AOI), and X-ray imaging are utilized to identify defects like cracks, voids, or irregularities in bond formation. By employing rigorous defect detection measures, manufacturers can uphold stringent quality standards and produce reliable semiconductor devices for various applications.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 195-200
Wrist-Worn sEMG Interface Design Framework for One-Handed Typing in Mixed Reality
This paper proposes a general design framework for a wrist-worn surface electromyography (sEMG) device to support one-handed typing in Mixed Reality (MR) environments. Current MR interaction methods-such as midair gestures, gaze input, and handheld controllers-are inaccessible to users with motor limitations due to their physical demands and limited feedback. To address this, we present a compact and battery-powered sEMG system that detects thumb-to-finger gestures and maps them to a virtual T9inspired keyboard layout distributed across the user's palm and fingers. The proposed system uses six sEMG sensors placed beneath the palmar side of the fingers, combined with an embedded nRF52840 module for wireless signal acquisition and filtering. Each gesture corresponds to one of twelve anatomical zones representing character groups. Signals are preprocessed with bandpass and notch filters, segmented with sliding windows, and transformed using time-domain features such as RMS, MAV, and waveform length. A lightweight convolutional neural network (CNN) is employed to classify gestures with realtime capability. The framework supports per-user calibration to address signal variability and includes a structured plan for collecting gesture data from both healthy and disabled participants. This approach enables tactile, efficient, and accessible typing in MR using a single hand. It reduces physical fatigue and enhances usability for individuals with reduced dexterity. The system is designed in alignment with United Nations Sustainable Development Goal 10.2, promoting inclusive access to digital environments. Future work includes prototyping, model training, and usability testing under realworld MR scenarios.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 195-200
Wrist-Worn sEMG Interface Design Framework for One-Handed Typing in Mixed Reality
This paper proposes a general design framework for a wrist-worn surface electromyography (sEMG) device to support one-handed typing in Mixed Reality (MR) environments. Current MR interaction methods-such as midair gestures, gaze input, and handheld controllers-are inaccessible to users with motor limitations due to their physical demands and limited feedback. To address this, we present a compact and battery-powered sEMG system that detects thumb-to-finger gestures and maps them to a virtual T9inspired keyboard layout distributed across the user's palm and fingers. The proposed system uses six sEMG sensors placed beneath the palmar side of the fingers, combined with an embedded nRF52840 module for wireless signal acquisition and filtering. Each gesture corresponds to one of twelve anatomical zones representing character groups. Signals are preprocessed with bandpass and notch filters, segmented with sliding windows, and transformed using time-domain features such as RMS, MAV, and waveform length. A lightweight convolutional neural network (CNN) is employed to classify gestures with realtime capability. The framework supports per-user calibration to address signal variability and includes a structured plan for collecting gesture data from both healthy and disabled participants. This approach enables tactile, efficient, and accessible typing in MR using a single hand. It reduces physical fatigue and enhances usability for individuals with reduced dexterity. The system is designed in alignment with United Nations Sustainable Development Goal 10.2, promoting inclusive access to digital environments. Future work includes prototyping, model training, and usability testing under realworld MR scenarios.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 189-194
Machine Learning in Electromyography Finger Recognition: Current Trends and Future Opportunities
Finger movement recognition based on muscle signals has gained increasing attention in recent years. Machine learning approaches have enabled accurate, non-invasive decoding of voluntary motor activity. Recent advances in deep learning have improved signal interpretation, generalization, and classification performance. However, finger-level applications remain underexplored, particularly in regressionbased estimation and real-time deployment. This study presents a systematic analysis of research trends regarding Machine Learning in Electromyography Finger Recognition over the past decade from 2014 until 2024. A total of 968 documents were collected using a structured search strategy and analyzed using bibliometric tools. The results highlight major developments in signal classification, neural network architecture, and wearable control systems. Co-occurrence and thematic mapping identify emerging research clusters and conceptual structures. Research themes increasingly reflect practical challenges, including signal variability, device integration, and system interpretability. Key gaps were found benchmarking protocols, cross-subject generalizability, and real-time implementation. The limitations restrict translation to assistive, clinical, or commercial domains. This review supports future development of robust, adaptive, and low-latency systems for finger movement recognition. 20142019 focus on feature extraction, classification, and surface EMG signals. 2020-2022 emphasis shifted toward deep learning, CNN, and gesture recognition. 2023-2024 research began targeting real-time control, wearable deployment, and neuromorphic models. Through convergence of machine learning and physiological modeling, EMG systems may soon achieve intuitive and practical finger movement recognition. Such systems will play a critical role in shaping future humanmachine interfaces, prosthetic devices, and neuroadaptive technologies.
- 22 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 189-194
Machine Learning in Electromyography Finger Recognition: Current Trends and Future Opportunities
Finger movement recognition based on muscle signals has gained increasing attention in recent years. Machine learning approaches have enabled accurate, non-invasive decoding of voluntary motor activity. Recent advances in deep learning have improved signal interpretation, generalization, and classification performance. However, finger-level applications remain underexplored, particularly in regressionbased estimation and real-time deployment. This study presents a systematic analysis of research trends regarding Machine Learning in Electromyography Finger Recognition over the past decade from 2014 until 2024. A total of 968 documents were collected using a structured search strategy and analyzed using bibliometric tools. The results highlight major developments in signal classification, neural network architecture, and wearable control systems. Co-occurrence and thematic mapping identify emerging research clusters and conceptual structures. Research themes increasingly reflect practical challenges, including signal variability, device integration, and system interpretability. Key gaps were found benchmarking protocols, cross-subject generalizability, and real-time implementation. The limitations restrict translation to assistive, clinical, or commercial domains. This review supports future development of robust, adaptive, and low-latency systems for finger movement recognition. 20142019 focus on feature extraction, classification, and surface EMG signals. 2020-2022 emphasis shifted toward deep learning, CNN, and gesture recognition. 2023-2024 research began targeting real-time control, wearable deployment, and neuromorphic models. Through convergence of machine learning and physiological modeling, EMG systems may soon achieve intuitive and practical finger movement recognition. Such systems will play a critical role in shaping future humanmachine interfaces, prosthetic devices, and neuroadaptive technologies.