cover
Contact Name
Dahlan Abdullah
Contact Email
dahlan@unimal.ac.id
Phone
+62811672332
Journal Mail Official
ijestyjournal@gmail.com
Editorial Address
Jl. Tgk. Chik Ditiro, Lancang Garam, Lhokseumawe, Aceh - Indonesia, 24351
Location
Kota lhokseumawe,
Aceh
INDONESIA
International Journal of Engineering, Science and Information Technology
ISSN : -     EISSN : 27752674     DOI : -
The journal covers all aspects of applied engineering, applied Science and information technology, that is: Engineering: Energy Mechanical Engineering Computing and Artificial Intelligence Applied Biosciences and Bioengineering Environmental and Sustainable Science and Technology Quantum Science and Technology Applied Physics Earth Sciences and Geography Civil Engineering Electrical, Electronics and Communications Engineering Robotics and Automation Marine Engineering Aerospace Science and Engineering Architecture Chemical & Process Structural, Geological & Mining Engineering Industrial Mechanical & Materials Science: Bioscience & Biotechnology Chemistry Food Technology Applied Biosciences and Bioengineering Environmental Health Science Mathematics Statistics Applied Physics Biology Pharmaceutical Science Information Technology: Artificial Intelligence Computer Science Computer Network Data Mining Web Language Programming E-Learning & Multimedia Information System Internet & Mobile Computing Database Data Warehouse Big Data Machine Learning Operating System Algorithm Computer Architecture Computer Security Embedded system Coud Computing Internet of Thing Robotics Computer Hardware Information System Geographical Information System Virtual Reality, Augmented Reality Multimedia Computer Vision Computer Graphics Pattern & Speech Recognition Image processing ICT interaction with society, ICT application in social science, ICT as a social research tool, ICT in education
Articles 80 Documents
Search results for , issue "Vol 5, No 3 (2025)" : 80 Documents clear
Failure of Preventive Security Controls in Cloud-Native Systems: Revisiting Governance Enforcement Ramadhan, Muhammad Daffa; Fajar, Ahmad Nurul
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1294

Abstract

Cloud-native architectures have introduced a fundamental shift in how security and governance are applied within modern IT environments. While traditional preventive IT General Controls (ITGCs) were designed for static, centralised systems, their application in dynamic, decentralised, and automated cloud-native systems remains ambiguous and often ineffective. This study investigates the patterns of failure in preventive controls across cloud-native environments and analyses the extent to which governance frameworks fail to enforce security proactively. Employing a meta-synthetic approach, this research reviews documented cloud breach incidents from 2021 to 2024 to extract recurring failure patterns. These incidents were analysed and mapped against major security control domains, including identity and access management, configuration hardening, and observability. The findings highlight systemic gaps in the implementation of preventive measures, particularly in areas where infrastructure is governed as code, and runtime dynamics alter control effectiveness. Furthermore, the study examines how existing governance frameworks such as ISO 27001, COBIT, and NIST CSF are often too abstract or outdated to directly translate into executable policies within CI/CD pipelines and cloud-native infrastructures. The study reveals that misconfigurations, inadequate identity management, and runtime blind spots are among the most common contributors to control failures. These issues are compounded by the lack of real-time enforcement mechanisms and the misalignment between policy design and operational realities. Based on these findings, the paper proposes a shift toward Governance-as-Code and continuous control validation as critical strategies for modern preventive governance. In conclusion, the paper demonstrates that traditional ITGCs, while still conceptually relevant, require operational reengineering to remain effective in cloud-native ecosystems. A governance model that is executable, context-aware, and runtime-integrated is essential for proactive security and sustained compliance in modern digital infrastructure.
Towards Self-Healing Cloud Infrastructures: Predictive Maintenance with Reinforcement Learning and Generative Models Kunal Shah, Jyoti; Matam, Prashanthi
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1185

Abstract

Reinforcement Learning (RL) is quickly becoming a powerful way to predict failures and improve systems in large cloud environments before they happen. Unlike traditional reactive methods, RL lets smart agents learn the best actions by interacting with changing environments and using reward signals to improve system uptime, resource use, and reliability. As cloud-based big data systems get bigger and more complicated, they also become more likely to have problems that slow them down or cause them to fail at random times. To deal with these problems, we need more than just advanced failure prediction algorithms. We also need adaptive, explainable systems that help people understand what's going on and step in when necessary. This paper looks into how to use RL to help predict and manage failures in cloud-based big data systems. We suggest a layered architecture that uses RL agents and generative explanation models to predict failures and take steps to stop them. We focus on real-time feedback loops, autonomous learning, and outputs that can be understood. This is especially important in anomaly detection pipelines, where explanations need to be detailed but short. We show how reinforcement learning agents can find patterns of risk and take steps to avoid them by using examples from real-world hyperscale data centers. We also look at how generative models, like transformer-based language generators, can turn complicated telemetry data into information that people can understand. At the end of the paper, the authors suggest areas for future research, such as safe RL deployment, multi-agent coordination, and explainable policy design.
Leveraging Kafka for Event-Driven Architecture in Fintech Applications Modadugu, Jaya Krishna; Venkata, Ravi Teja Prabhala; Venkata, Karthik Prabhala
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1074

Abstract

 The volume of payment transactions has grown exponentially, creating a high demand for high-throughput payment processing systems. These systems must be capable of handling a large number of transactions with minimal delay while also being highly scalable and resilient to failures. To overcome this challenge, leveraging kafka for event-driven architecture in fintech applications (LK-EDA-FA-BSCNN) is proposed. At first, input data is gathered from kafka streams. Then, the input data are pre-processed using adaptive two-stage unscented kalman filter (ATSUKF is used to clean the data to ensure high-quality input for downstream analysis. Then, the pre-processed data are fed into binarized simplicial convolutional neural network (BSCNN) is used to predict the future transactions from historical trends. The proposed LK-EDA-FA-BSCNN method is implemented using python and the performance metrics like accuracy, precision, sensitivity, specificity, F1-score, and computational time. The LK-EDA-FA-BSCNN method achieves the best performance with 98.5% accuracy, 95.3% precision and 1.150 seconds runtime with existing methods, like a DRL-based adaptive consortium blockchain sharding framework for supply chain finance (DRL-ACSF-SCF), a blockchain-based secure storage and access control scheme for supply chain finance (BC-SS-ACS-SCF), and analysis of banking fraud detection methods through machine learning strategies in the era of digital transactions respectively.
Safety Function Model for Requirement Specification in Critical Systems: A Case Study of Generic Patient Controlled Analgesia Pump Model (CGPA) Abdullah, Azma; Abu Bakar, Rohani; Abdul Farid, Fairus; Abdulhak, Mansoor
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1370

Abstract

Developing safety-critical systems (SCS) involves a systematic method for assuring and providing safety and dependability. Conventional approaches rely on expert intervention, which can introduce bias, cause delays, and promote inconsistency. This work proposes a model that enhances efficiency and accuracy by extracting safety functions from requirements specifications. The model is made up of three main steps: (1) preprocessing, which involves getting rid of stop words; (2) string selection and matching using a database of safety properties variables based on literature and expert knowledge; and (3) putting safety and non-safety functions into a structured safety function log. The model was trained and tested with the CGPA insulin pump and got a 94% F1 measure score, which means it was 91% accurate, 96% accurate, 92% precise, and 96% recall. This shows that it is good at making things clearer and less biased when finding functions for safety against failures, malfunctions, operational hazards, and inconsistencies in safety-critical specifications. All these enhancements contribute towards Sustainable Development Goal (SDG) 11: Sustainable Cities and Communities, aiming to develop safer, resilient, and sustainable infrastructure in safety-critical regions.
Federated Learning Architectures for Privacy-Preserving Smart Grid Data Processing Abdulkareem, Sarah Ali; M. Kallow, Sabah; Bako, Imad Matti; Abdullah, Salima Baji; T.Y. Alfalahi, Saad; Batumalay, M.
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1423

Abstract

The use of smart data in smart grid infrastructure has lately become essential for efficient power distribution, instantaneous?decision-making and overall system protection. Nonetheless, the application of centralized machine-learned models is impeded by?privacy issues, nonhomogeneous distributed data sources, and communication constraints. In this paper, we propose a federated learning framework to handle these challenges and support decentralized, privacy-preserving?model training across a wide range of smart grid components such as residential meters, substations, and electric vehicle charging stations. The proposed method develops a multi-staged framework, which includes adaptive differential privacy, gradient compression, and topology-aware aggregation to improve?the model's performance in the meanwhile of data privacy. The robustness of the system is demonstrated by energy profiling, cross-domain generalization test and temporal?stability analysis. Findings indicate the model has good prediction performance across different grid setups and customer profiles and that energy use and privacy?noise are within acceptable limits for operational use. Furthermore, the architecture shows?strong generalization to unseen domains, and robust performance through many federated training rounds. By considering?computational efficiency, privacy limitations and topological heterogeneity, this work provides a scalable and secure real-time energy intelligence approach. Results suggest that federated?learning with adaptations to the smart grid is a promising approach for robust privacy-preserving analytics applied to critical infrastructures. This work will support energy efficiency in the future which will be a process innovation. 
Gamification Design in Assisting Master's Students in Learning Readiness of XYZ University Stanley Salim, Sebastian; Wang, Gunawan
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.974

Abstract

This paper discusses how to design and assess a gamification framework to increase the learning preparedness of postgraduate students at XYZ University. Academic success at the master's level largely depends on learning readiness, and most students have to face numerous challenges, including poor time management, thesis composition, a lack of motivation, and insufficient social interaction with peers. Such obstacles inevitably result in low productivity and low engagement, which eventually influence the quality of their academic performance. In order to solve these problems, the concept of gamification is proposed as a new approach to pedagogy that incorporates the elements of a game into the learning process. The system included features like experience points (XP), leagues, leaderboards, and guided challenges to make the system more motivational, maintain engagement, and collaborate with students. The quantitative research design was chosen, and approximately 50 respondents who are enrolled in the program and participated in the gamified learning activities were used in the study. The results prove that gamification is a powerful tool that promotes learning preparedness by motivating success through reward systems and an opportunity to interact with peers through group activities and online discussion forums. The students claimed to be more motivated, better concentrated on the milestones of the thesis, and more disciplined in managing their time than they are using the traditional approaches. In addition, the system provides a more organised, interactive, and fun learning experience that allows participants to resolve academic difficulties more successfully. According to the assessment, the research indicates that gamification is an emerging tool that can be used to increase postgraduate learning preparedness. It suggests additional design improvements to the user interface, personalisation, and differentiation of reward systems to ensure the highest student engagement and effectiveness in the long term.
Optimizing Supply Chain Logistics with Predictive Analytics: Using Data Science to Improve Cost Efficiency and Operational Performance Mehta, Rushabh
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1078

Abstract

Traditional reactive approaches to supply chain logistics are inadequate because global supply chains are consistently confronted with demand volatility, geopolitical risks and operation inefficiencies. This paper examines how predictive analytics, a fundamental field in data science, can be applied to streamline logistics to make operations not only more cost-efficient but more efficient. The study utilizes machine learning algorithms, time-series forecasting, optimization models, and simulation toolsets to implement a mixed methodology based on literature synthesis, case analysis, and model evaluation on the most important logistics functions. The secondary sources such as industry reports, peer-reviewed articles, and validated case studies were used as a source of data. The results show that predictive analytics produce quantifiable benefits in various areas. Machine learning adoption in demand forecasting and inventory optimization in companies like Amazon and Walmart cut stockouts to less than 5% and lower the number of overstocks by 2050 to up to 25% inventory holding costs. Optimization in transportation: DHL announced that through dynamic route optimization based on AI models, fuel expenses were cut by 15% and delivery times in cities were shortened by 12 percent. Predictive modeling ensured a greater efficiency of the warehouse and resulted in a 15-percent decrease in the variability of order processing and labor allocation optimization. By identifying supplier delays, quality risks and geopolitical threats proactively, risk management applications posted a 45.3 percent reduction in supply chain disruption. Further, the predictive variance analysis delivered 10 percent procurement cost savings to a firm like Nestle, demonstrating the advantages of supplier performance. This study concludes that predictive analytics promotes an active, robust and cost effective supply chain. Predictive analytics is a groundbreaking direction toward the creation of agile logistics systems oriented to Industry 4.0 requirements despite the difficulties in data integration, technical complexity, and upfront costs.
Harnessing Backflow: AI-Optimized Hybrid Fan Systems for Micro-Scale Energy Regeneration and Smart Efficiency Control Kumar V, Bhuvana; Yedukondalu, N.; Rao Appini, Narayana; Suresh Babu, Siddabathuni; Sreenu, Karnam
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1411

Abstract

The interest in sustainable energy applications is driven by the desire to improve hybrid systems that can consume and simultaneously recover energy in a closed-loop situation. This research examines the possibility of an AI-based, self-reproducing fan that can recover and convert some of its own generated airflow, and convert that to usable electrical energy. Electric fans are inherently bound by their architecture to use their entire input energy for ventilation with no feedback for energy. However, the system here proposes a new fully integrated energy regeneration system by utilizing miniaturized axial turbines, or piezoelectrics, placed within the momentum of the airflow to utilize any remaining kinetic energy as usable electrical energy. The proposed research study utilizes deep reinforcement learning (DRL) and multi-objective approaches based on evolutionary algorithms (MOEA). The proposed DRL and MOEA utilize adaptable meta-level optimization and real-time optimization of its geometric arrangement and turbine geometric arrangement and energy routing. The study's computational fluid dynamics (CFD) models will be validated by utilizing AI-supported simulation environments, iterates through the design space for the various configurations that optimize net energy and axial turbine efficiency without sacrificing their airflow efficiency, and use exhaust volumetric flow rates from the CFD. Energy recovery ratio, effect on fan impact and system sustainability index will be the indicators of success to evaluate the study's sustainable and energy-efficient application. This research takes a significant step in the area of micro-scale regenerative energy systems and suggests an intelligent control system that can respond to changing usage conditions. The implications provide significant opportunities that support developing next-generation smart fans, autonomous operation ventilation systems, and low-power AIoT (Artificial Intelligence of Things) devices. This research is a significant first step in trying to re-engineer airflow systems not as passive consumers of energy, but as active participants in energy recycling, that can contribute to drive innovation for green engineering and intelligent systems.
Cotton Disease Prediction Using Deep Transfer Learning: Comparative Analysis of Resnet50, VGG16 and Inceptionv3 Models Gupta, Sandeep; Hamid, Abu Bakar Abdul; Nyamasvisva, Tadiwa Elisha; Jain, Vishal; Tyagi, Nitin; Mun, NG Khai; Ather, Danish
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1116

Abstract

Cotton is among the most critical crops in the world textile industry, but it is highly susceptible to a vast array of infections that have a tremendous impact on output and fiber quality. Traditional cotton disease diagnosis is mostly based on manual inspection by farmers and experts and is time consuming, labor intensive and inaccurate due to similarity of symptoms. The high rate at which artificial intelligence, especially computer vision and deep learning (DL), have advanced has provided effective alternatives to auto-detecting plant diseases. As a subdivision of the DL approach, transfer learning allows adapting existing convolutional neural networks to the agricultural domain using smaller datasets to guarantee higher performance. This work introduces comparative analysis of three popular deep transfer learning (DTL) models ResNet50, VGG16, and InceptionV3 that are used in the classification of cotton leaf diseases. The training, validation, and testing were performed on a dataset of 1,991 labelled images that included four categories of normal and diseased cotton leaves and plants. All models were optimized and assessed with standard measures, such as validation and test accuracy. The experimental results show that InceptionV3 had the highest accuracy of 95.28, VGG16 had 85.85, and ResNet50 had the lowest accuracy of 69.81. The high accuracy of InceptionV3 is also a testament to its ability in the extraction of multi-scale features, and the trade-off between accuracy and computational efficiency. The results affirm the feasibility of DTL frameworks to revolutionize precision agriculture by facilitating diagnosis of cotton diseases in a timely and reliable manner. This development can help in ensuring that farming activities are sustainable, pesticides are used efficiently and the economy does not suffer economic losses and helps in ensuring that productivity and environmental protection are maintained in cotton farming.
Screen Reader AI: A Conversational Web-Accessibility Assistant for Blind and Low-Vision Users Patel, Rushilkumar
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1562

Abstract

Blind and low-vision users continue to face significant challenges when interacting with modern dynamic and visually complex web applications. Traditional screen readers often fall short due to the rapid changes in content, single-page applications, and intricate layouts. This paper introduces Screen Reader AI, a novel conversational web accessibility assistant implemented as a browser extension, designed to provide adaptive and context-rich support for non-visual navigation. Unlike conventional screen readers, Screen Reader AI constructs and continuously updates a live semantic scene graph by integrating the Document Object Model (DOM) and the Accessibility Object Model (AOM). Leveraging multimodal vision-language reasoning powered by GPT-4o, it generates detailed visual interpretations, detects interface structures and interactive elements, and conveys this information through natural, conversational dialogue. This approach allows users to request clarifications, discover relationships between interface components, and receive proactive notifications about dynamic content updates. The system features a modular architecture that ensures compatibility with evolving AI models and web standards, while maintaining an intuitive user interface. Core capabilities include adaptive task guidance, an interactive dashboard with contextual summaries, nested menus, live feeds, and predictive navigation assistance across diverse content types such as forms and multimedia. An evaluation framework outlines expected improvements in user experience, including reduced task completion times, enhanced understanding of page layouts, and greater autonomy during browsing. Initial findings suggest that conversational interaction can decrease cognitive load by reducing repetitive commands and streamlining information retrieval. Screen Reader AI represents a paradigm shift in digital accessibility by embedding adaptive intelligence into assistive technology, empowering independence and inclusivity while making accessibility an integral part of web innovation.