cover
Contact Name
Muhammad Luthfi Hamzah
Contact Email
muhammad.luthfi@uin-suska.ac.id
Phone
+6282385405905
Journal Mail Official
editor.jaets@gmail.com
Editorial Address
Jl. Amanah, No. 17 B Kec. Marpoyan Damai, Pekanbaru, Riau
Location
Kota pekanbaru,
Riau
INDONESIA
Journal of Applied Engineering and Technological Science (JAETS)
ISSN : 27156087     EISSN : 27156079     DOI : -
Journal of Applied Engineering and Technological Science (JAETS) is published by Yayasan Pendidikan Riset dan Pengembangan Intelektual (YRPI), Pekanbaru, Indonesia. It is academic, online, open access, peer reviewed international journal. It aims to publish original, theoretical and practical advances in Computer Science & Engineering, Information Technology, Electrical and Electronics Engineering, Electronics and Telecommunication, Mechanical Engineering, Civil Engineering, Textile Engineering and all interdisciplinary streams of Engineering Sciences. Journal of Applied Engineering and Technological Science (JAETS) is published annually 2 times every June and Desember.
Articles 576 Documents
Hand Gesture Recognition Using Optimized Hyperparameters of CNN for Real-Time Control of a Multi-Servo Hand Noor M. Naser; Kian R. Qasim; Zinah J. Jabbar
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v7i1.8740

Abstract

Gesture recognition has emerged as a promising approach to enhance human-machine interaction, especially in robotics and assistive devices. This study presents a real-time gesture-controlled robotic system that combines deep learning and machine learning techniques to recognize hand gestures and map them to servo motor movements. A convolutional neural network (CNN) was used to classify six predefined hand gestures: a closed fist and five individual finger extensions. To enhance classification accuracy and generalization, CNNs are tuned using hyperparameter tuning techniques, such as Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO), and Brown Bear Optimization (BBO). These methods efficiently explore the hyperparameter space—such as learning rate, filter size, and batch size—reducing manual trial and error in control. Among these proposed models tested, the BBO-CNN has been achieved the highest performance with a classification accuracy of 99.98%, outperforming both PSO-CNN (99.89%) and GWO-CNN (99.44%). The model CNN without optimization achieved an accuracy of 97.50%. The combination of advanced deep learning models and embedded control demonstrates the feasibility and effectiveness of gesture-based robotics applications.
Enhancing Cybersecurity Threat Detection Using Machine Learning: A Comprehensive Review Somasundari P; Kavitha V
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v7i1.8814

Abstract

Cybersecurity forms the backbone of digital infrastructure that protects overstretched payment systems, governmental operations, and business continuity today. With machine learning (ML) techniques, it can help analyze a large amount of data and improve cyber-security. It’s tough to quantify how effective the ML-based cybersecurity system is, especially when we theorize it. This review paper talks about the significant role of ML in security, threat detection and security measures. Using machine learning algorithms helps in cybersecurity as they make the system automatic and fast. We can implement a threat detection security model using widely used ML algorithms. For classification purposes, we have Support Vector Machines (SVM), Decision Trees (DT), Random forests (RF), and Adaptive and Extreme gradient boosting (XGBoost). This review paper proposes ML algorithms for the implementation of cybersecurity with some practical application demonstrations. Machine learning algorithms can provide valuable analytics to help bolster security and reduce threats. We assess the accuracy of threat detection in network security by utilizing a set of formulas based on confusion, recall, F1-score, time complexity, accuracy and precision. This review synthesizes algorithmic performance across benchmark datasets (CICIDS2017 NSL-KDD UNSW-NB15) to identify significant gaps in previous ML-based cybersecurity frameworks. The results demonstrate the superior precision (90. 8 percent) and scalability of XGBoost.
Enhancing Intrusion Detection System Performance Using Reinforcement Learning : A Fairness-Aware Comparative Study on NSL-KDD and CICIDS2017 Yudhi Arta; Suzani Mohamad Samuri; Nesi Syafitri
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Conventional Intrusion Detection Systems (IDS) often fail to generalize in dynamic network environments, facing challenges with evolving attack patterns and class imbalance. This study aims to evaluate and compare the effectiveness of three Reinforcement Learning (RL) paradigms to enhance IDS adaptability and accuracy against these challenges. This research employs a comparative experimental design, implementing Q-Learning, Deep Q-Networks (DQN), and Proximal Policy Optimization (PPO). These algorithms were systematically evaluated using the NSL-KDD and CICIDS2017 benchmark datasets to represent both legacy and modern network traffic. A fairness-aware evaluation framework was applied, prioritizing the Matthews Correlation Coefficient (MCC) as a primary metric alongside accuracy to ensure robust performance assessment against skewed class distributions. Experimental results demonstrate that PPO significantly outperforms value-based algorithms such as Q-Learning and DQN. On the high-dimensional CICIDS2017 dataset, PPO achieved the highest detection accuracy (96.3%) and MCC (0.913). Confusion matrix analyses confirmed PPO’s capability to simultaneously minimize false positives and false negatives. Conversely, Q-Learning exhibited poor generalization on complex data, while DQN showed improved performance due to deep value approximation but remained less stable than PPO. These findings imply that policy-gradient methods like PPO are superior for real-world IDS deployments where scalability, adaptability, and low error rates are critical. Theoretically, the results suggest that stochastic policy optimization handles complex, continuous state spaces more effectively than traditional value-estimation approaches. This study contributes a rigorous head-to-head comparative analysis of RL algorithms across multiple standard datasets using fairness-aware metrics. It bridges the research gap found in previous studies that often evaluated algorithms in isolation or relied on accuracy metrics that can be misleading in imbalanced security contexts.
Blockchain-Enhanced Framework for Ensuring Data Consistency, Transparency and Privacy in Cloud Computing Kavitha T; Kavitha V
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v7i1.8851

Abstract

The Impact of Virtual Laboratories on Student Motivation and Academic Performance: An Integrated Fuzzy-Sem and Machine Learning Study Tabriz Osmanli
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v7i1.9146

Abstract

This study explored the impact of virtual laboratories (VLs) on university learning and seeks to fill a gap in the literature: most VL research reports positive outcomes, but rarely explains why they occur or whether psychological mechanisms generalize predictively. The solution comes from a synthetic model combining Fuzzy-SEM, which is great for modelling uncertainty within Likert-based motivation and engagement constructs, with supervised machine learning models that provide causal explanation combined with predictive validation. We analyzed data from 432 undergraduates combining VL usage logs, motivation–engagement surveys, and official academic records. Fuzzy-SEM confirmed a mediated motivation–engagement–performance pathway, which confirms that VLs significantly boost performance primarily by converting motivational activation to sustained engagement. Predictively, the 1D CNN better fitted the classical ML models (AUC-ROC = 0.94) suggesting the possibility of early identification of at-risk students through behavioural and affective proxies. Practical implications should be to apply VLs as complementary motivational approaches to training practice and to monitor prediction weekly for intervention. In theory, the study bolsters engagement frameworks by elucidating how VLs exert their effect. Methodologically, it presents an integrated Fuzzy-SEM + ML pipeline that facilitates both explanatory context and potentially deployable prediction, although it recognizes the limitation of single-institution and self-report.
Leveraging Intranet Quality for University Financial Sustainability: The Mediating Role of Enterprise Risk Management Ummu Ajirah Abdul Rauf; Ragnar Löfstedt; Paul Bracken; Astri Ayu Purwati
Journal of Applied Engineering and Technological Science (JAETS) Vol. 7 No. 1 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v7i1.9188

Abstract

This study examines how intranet quality affects the financial performance of Malaysian public universities, filling a crucial gap in understanding how internal digital infrastructure supports institutional sustainability. It highlights Enterprise Risk Management (ERM) as a mediating factor translating intranet quality into measurable performance results. A cross-sectional survey was conducted with 210 participants, including risk committees, internal auditors, and top management from 20 public universities in Malaysia. This study used purposive, stratified, and census sampling methods. Intranet quality was evaluated across six key areas: collaboration tools, risk management application, access to proper risk data, interaction in risk problem-solving, communication among the risk committee, and risk management controls. ERM implementation was measured using ISO 31000-aligned standards, while university financial performance was assessed through five income sources: research projects, consultancies, public and private funding, commercialisation, and program offerings. Covariance-based structural equation modelling (CB-SEM) was employed for analysis. Findings reveal that intranet quality significantly improves ERM implementation, positively impacting financial performance. ERM partially mediates this relationship, with more substantial indirect effects than direct ones. This study emphasises the strategic importance of digital infrastructure and risk governance in boosting institutional effectiveness. It proposes a socio-technical model that helps university leaders leverage intranet systems to enhance risk resilience and long-term financial sustainability.