Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

30,547 Article Results

Predicting student academic outcomes from e-learning interaction data using hybrid machine learning models

10.11591/ijres.v15.i2.pp259-268
Sajithunisa Hussain , Jayachandran Jeyachidra
The rapid growth of digital learning platforms has generated large volumes of student interaction data, providing opportunities for intelligent prediction of academic outcomes. Beyond educational analytics, such prediction tasks are relevant for reconfigurable systems, embedded platforms, very large scale integration (VLSI) accelerators, and internet of things (IoT)-enabled edge devices in smart learning environments. This study proposes a hybrid machine learning framework for predicting student performance using the e-learning student reactions dataset, which captures engagement patterns, behavioral responses, and interaction dynamics. Eight classifiers— eXtreme gradient boosting (XGBoost), K-nearest neighbors (KNN), decision tree (DT), random forest (RF), support vector machine (SVM), multilayer perceptron (MLP), radial basis function (RBF), and deep neural network (DNN)—are evaluated using both an 80–20 train–test split and K-fold cross-validation to assess accuracy and generalization. Results show the RBF model achieves the highest accuracy of 1.00, demonstrating its ability to capture complex, nonlinear behavior. From a systems perspective, the framework can be mapped onto field programmable gate arrays (FPGAs) or embedded devices, leveraging parallel computation for low-latency inference, and integrated with IoT-enabled smart classrooms for real-time edge analytics. These findings confirm that hybrid machine learning models not only improve student performance prediction but also serve as practical workloads for reconfigurable, embedded, and VLSI-based intelligent systems in digital education.
Volume: 15
Issue: 2
Page: 259-268
Publish at: 2026-07-01

Revolutionizing night-time object detection in autonomous vehicles with SCL-YOLOv11 and ROA optimization

10.11591/ijres.v15.i2.pp534-552
Kondapalli Sri Vijaya , Gokula Krishnan Vasudevan , Pinagadi Venkateswara Rao , Therasa Michael , Balasubramanian Lalithambigai , Boddula Prathusha Laxmi
Accurate object detection under low-light conditions is a critical requirement for reliable perception in autonomous driving systems. However, night-time environments often suffer from poor illumination, noise, and reduced feature visibility, which significantly degrade the performance of conventional object detection models. To address this challenge, this paper proposes spatial contrast learning (SCL)-you only look once version 11 (YOLOv11), an enhanced object detection framework designed for night-time scenarios. The proposed approach integrates SCL to improve feature discrimination in dark regions and employs the revolution optimization algorithm (ROA) for effective model parameter optimization. The framework is evaluated on three benchmark night-time datasets, ExDark, LLVIP, and BDD100K, to assess its detection performance. Experimental results demonstrate that the proposed model achieves a mAP@50 of 72.9%, improving the baseline YOLOv11 by 9.5% while also reducing inference latency by 18.3%. Comparative evaluations with existing detectors further confirm that the proposed method provides improved accuracy and efficiency for night-time object detection. These results indicate that the proposed framework can enhance perception reliability for autonomous driving applications operating in low-light environments.
Volume: 15
Issue: 2
Page: 534-552
Publish at: 2026-07-01

An IoT-enabled vision-aid for the blind integrating ultrasonic obstacle detection and GPS-based location tracking

10.11591/ijres.v15.i2.pp386-395
Varuna Kumara , Akshatha Naik , Ashwini Ashwini , Navilgone Krishna Vaishnavi , Ruchitha Kamath Subhashchandra , Trapthi Trapthi
Visual impairment significantly affects independent mobility and personal safety, creating a need for affordable and reliable assistive navigation technologies. This paper presents the design and implementation of a low-cost wearable Vision-Aid system to support visually impaired individuals during outdoor navigation. The primary objective of the study is to enhance obstacle awareness, location tracking, and emergency communication using accessible embedded technologies. The proposed system integrates ultrasonic sensors for real-time obstacle detection, an Arduino microcontroller for data processing, a global positioning system (GPS) module for location tracking, and a global system for mobile communication (GSM) module for emergency alert transmission. Audio feedback is provided through a voice module to guide the user safely. Experimental evaluations were conducted under various environmental conditions to assess obstacle detection accuracy, response time, and location reliability. The results demonstrate accurate obstacle detection, timely audio alerts, and reliable real-time location sharing with caregivers. The proposed system improves user confidence, mobility, and safety while maintaining low implementation cost. This work highlights the potential of embedded and internet of things (IoT)–based assistive devices to enhance autonomy for visually impaired individuals and provides a foundation for future integration of artificial intelligence (AI)-based object recognition.
Volume: 15
Issue: 2
Page: 386-395
Publish at: 2026-07-01

Implementation and design of GPS tracker monitoring system on car rental vehicles based on internet of things using Nodemcu ESP-32

10.11591/csit.v7i2.p214-223
Indah Purnama Sari , Al-Khowarizmi Al-Khowarizmi , Asrar Aspia Manurung
Internet of things (IoT) based vehicle tracking system is an effective solution to overcome various problems in the vehicle rental industry, such as asset loss, route misuse, and late returns. This study aims to design and implement a real-time vehicle position monitoring system using the NodeMCU ESP-32 module integrated with the NEO-6M GPS module and Wi-Fi connectivity to send data to a cloud-based server. This system is designed to display the vehicle position directly through a web-based digital map interface, which can be accessed by vehicle owners anytime and anywhere. The methodology used includes hardware and software design, location accuracy testing, and data integration with a web-based visualization platform using a map API. The test results show that the system is capable of sending vehicle location data with a position accuracy level of up to ±5 meters and data updates every 10 seconds under stable network conditions. In addition, the system has good power efficiency, with an average current consumption of 80–100 mA when active. All data was successfully stored and visualized in real-time using the Google Maps API, and the system was able to operate stably for 24 hours of non-stop testing. Based on these results, the IoT-based GPS tracker system with NodeMCU ESP-32 can be effectively implemented on rental vehicles as a modern monitoring solution that is cost-effective, flexible, and easily accessible. This system provides added value in fleet monitoring and supports faster and data-based decision making.
Volume: 7
Issue: 2
Page: 214-223
Publish at: 2026-07-01

Performance evaluation of the deep learning system for weed recognization

10.11591/csit.v7i2.p167-178
Abd Abrahim Mosslah , Reyadh Hazim Mahdi , Hassan Kassim Albahadily
Numerous approaches based on machine learning have emerged in recent years to enhance crop protection efficiency. One example is the utilization of deep neural networks (DNNs) to differentiate between various weed types in actual events scenarios. Nevertheless, these methods often need substantial input from experts who work iteratively to design the robust deep learning system. To simplify such process and conserve resources, researchers have explored a fresh method known as automated deep learning our technology’s recognization of weeds through the use of machine learning was evaluated using plant seedlings and weed collections from plants dataset to address a issue of weed recognization. The study compared various configurations, including plant segmentation, using a collection of classifiers in place of Softmax, and training with datasets that contain noise. The findings indicated ensuring performance, with F1-scores of 93.1% and 90.2% based on the dataset utilised. These results align together with automated machine learning (AutoML-linked) studies, while fall short of manually fine-tuned deep-learning-based systems created through human specialists. To conclude, exploring the potential of combining manual expert work and automated deep learning could be a promising direction for enhancing efficiency in plant defence.
Volume: 7
Issue: 2
Page: 167-178
Publish at: 2026-07-01

Fuzzy logic–based consensus protocol for educational blockchain networks

10.11591/csit.v7i2.p131-140
Igor Ivanov , Svetlana Zhdanova
This paper addresses the growing challenge of ensuring trust, authenticity, and transparency in the management and verification of educational credentials within modern, digitally oriented learning ecosystems. Rapid expansion of e-learning, lifelong learning, and global mobility has intensified document fraud, revealing the limitations of traditional verification mechanisms. To respond to these systemic risks, the study proposes a socially oriented block-validation protocol integrated into a distributed blockchain environment designed specifically for educational data security. The protocol forms the core of the EduBLOCK system, developed by the authors, and introduces an innovative consensus mechanism that incorporates human-centered reputation assessments rather than computational or financial power. The approach employs fuzzy-set theory to evaluate user activity, institutional credibility, and delegate reputation, enabling a more nuanced and context-sensitive model of trust. Delegates responsible for validating blocks are selected through a dynamic, reputation-driven procedure that excludes financial contributions and subjective parameter tuning. The proposed algorithm combines cryptographic guarantees, peer-to-peer (P2P) communication, and soft-computing methods to ensure fairness, prevent manipulation, and maintain stable system functioning. Block validity is determined through open voting, requiring approval by more than two-thirds of elected delegates.
Volume: 7
Issue: 2
Page: 131-140
Publish at: 2026-07-01

Multi-objective task scheduling in large-scale distributed systems using a Lévy flight-based hybrid Bat-Whale optimization algorithm

10.11591/ijeecs.v42.i3.pp913-926
Ali Mohammed Ahmed , Manar Younis Kashmola
The rapid growth of cloud computing demands efficient task scheduling strategies capable of handling heterogeneous resources, dynamic workloads, and multiple conflicting objectives. Existing approaches often optimize a single criterion, limiting their effectiveness in large-scale distributed systems. This paper proposes hybrid Bat–Whale optimization algorithm (BWOA), a hybrid scheduling algorithm combining the Bat algorithm and Whale optimization algorithm, enhanced with Lévy flight-based exploration, adaptive crossover, and a smart local search mechanism. The framework balances global exploration and local exploitation while preserving population diversity and intensifying search around promising solutions. A problem-aware local search reallocates long-duration tasks to high performance virtual machines and selectively swaps tasks with poor response times. Experiments on a heterogeneous cloud environment with 300 tasks and 50 virtual machines, using min–max scaling for workload normalization, demonstrate that BWOA outperforms classical methods, including first come, first served (FCFS) and Min-Min scheduling algorithms, achieving superior makespan (≈32.77 s) while maintaining competitive utilization, throughput, and energy efficiency. These results highlight the effectiveness of hybrid metaheuristic approaches integrating multiple optimization strategies for multi-objective task scheduling in large scale cloud systems, providing a robust and scalable solution for both academic research and practical deployment.
Volume: 42
Issue: 3
Page: 913-926
Publish at: 2026-06-10

Fine-tuned IndoBERT for stock market sentiment analysis: evidence from CNBC Indonesia news

10.11591/ijeecs.v42.i3.pp774-785
Tri Agung Jiwandono , MS Hendriyawan Achmad , Suhirman Suhirman
Financial sentiment analysis in Indonesian markets faces significant accuracy challenges, with existing models achieving only 78-81% accuracy. We present a fine-tuned IndoBERT-Large model for classifying sentiment in Indonesian stock market news headlines, trained on 9,819 CNBC Indonesia headlines (January 2024-March 2025). Through systematic hyperparameter optimization and stratified vocabulary-balanced splitting, our model achieved 94.20% accuracy, surpassing previous baselines by 4-16 percentage points. These results demonstrate IndoBERT's effectiveness for Indonesian financial NLP and its potential for real-time market monitoring and investment decision support systems.
Volume: 42
Issue: 3
Page: 774-785
Publish at: 2026-06-10

Seasonal and diurnal variations of wet scintillation in tropical region Malaysia

10.11591/ijeecs.v42.i3.pp721-728
Ibtihal Fawzi El-Shami , Jafri Din , Ali I. Elgayar , Ahlaam Miftah Saed
This paper investigates the seasonal and diurnal variations of wet tropospheric scintillation in a tropical region to support the design and optimization of fade margin in satellite communication systems. A one-year Ku-band propagation measurement campaign was conducted in Johor Bahru, Malaysia, using a direct broadcast receiver (DBR) and an automatic weather station (AWS) to capture both signal and meteorological data. A comprehensive signal processing technique was applied to separate scintillation effects from rain attenuation, enabling accurate statistical characterization. The analysis was performed based on monsoon seasons and different time intervals of the day. The results indicate that higher scintillation fades are most likely to occur during the afternoon period, particularly between 3:00 pm and 6:00 pm. In addition, the inter-monsoon season exhibits a higher rate of variation in scintillation intensity due to increased convective activity, whereas the southwest monsoon shows relatively lower variability under drier conditions. The findings also demonstrate that diurnal scintillation behavior is strongly influenced by seasonal patterns, with peak intensity typically observed in the late afternoon across different monsoon periods. Unlike many existing models developed for temperate regions, this study provides experimental insights into scintillation characteristics under equatorial climatic conditions. These results offer valuable guidelines for system designers to improve fade margin allocation and enhance the reliability of satellite links in tropical environments.
Volume: 42
Issue: 3
Page: 721-728
Publish at: 2026-06-10

Design procedure and digital control of a DCM flyback converter: component sizing and experimental validation

10.11591/ijeecs.v42.i3.pp688-698
Nabil Abouchabana , Mohammed Benmiloud , Khaled Ameur , Aboubakeur Hadjaissa
Flyback converters are widely used in low-power switch-mode power supplies (SMPS) due to their simple structure, galvanic isolation capability, and cost effectiveness. This paper presents a systematic design methodology and digital Proportional–Integral (PI) control implementation for a discontinuous conduc tion mode (DCM) flyback converter using a dSPACE 1104 control platform. The proposed approach integrates magnetic component sizing, semiconductor stress evaluation, and RCD snubber design into a unified workflow. A 30 W prototype operating at 30 kHz with an input range of 20–30 V and a regulated 12 V output was developed and experimentally validated. The digital PI con troller was tuned using Takahashi’s method to ensure stable voltage regulation. Experimental results demonstrate proper DCM operation and stable output regulation under input voltage variation (20–30 V), load variation (48 Ω–12 Ω), and reference changes (10–14 V). The measured efficiency exceeded 90% at nominal operating conditions. The results confirm the effectiveness of the proposed design methodology for low-power isolated DC–DC applications.
Volume: 42
Issue: 3
Page: 688-698
Publish at: 2026-06-10

Resilient artificial intelligence, secure digital ecosystems, and intelligent computing for a connected future

10.11591/ijeecs.v42.i3.pp631-636
Tole Sutikno
This editorial introduces the articles published in Volume 42, Number 3, June 2026 of the Indonesian Journal of Electrical Engineering and Computer Science (IJEECS), highlighting recent advances and emerging research directions in artificial intelligence, cybersecurity, intelligent computing, and digital transformation. The published studies span a broad range of topics, including machine learning, intelligent analytics, healthcare technologies, computer vision, cryptography, privacy-preserving systems, Internet of Things (IoT) security, cloud computing, distributed optimization, blockchain applications, and decentralized digital platforms. Emerging trends highlighted throughout this issue include foundation and multimodal AI models, AI-enabled cybersecurity, privacy-preserving machine learning, Zero-Trust architectures, edge intelligence, decentralized computing, and digital trust ecosystems. Collectively, these contributions underscore the growing importance of resilient artificial intelligence and secure digital infrastructures in enabling adaptive, efficient, and trustworthy connected environments. The increasing integration of intelligence, security, resilience, and human-centered design principles reflects the evolving requirements of next-generation technologies that support sustainable innovation, economic development, and societal well-being. The research presented in this issue provides valuable perspectives on the opportunities and challenges associated with building secure, resilient, and intelligent digital ecosystems for an increasingly interconnected future.
Volume: 42
Issue: 3
Page: 631-636
Publish at: 2026-06-10

Emulation-based evaluation of dust-aware automated cleaning system for aggregated solar panels on electric vehicles

10.11591/ijeecs.v42.i3.pp637-648
Mohamed Abubakr Mahgoub Hassan , Belal Ahmed Hamida , El-Sayed Soliman A. Said , Muhammed Zaharadeen Ahmed
The integration of photovoltaic (PV) panels into electric vehicles (EVs) provides a complementary energy source capable of extending driving range and reducing reliance on grid-based charging. However, the practical contribution of vehicle-mounted PV systems is significantly constrained by dust accumulation, which can induce power losses exceeding 20% under prolonged urban and roadside exposure. This study presents a low-power; sensor-driven, automated dust detection and cleaning system specifically designed for aggregated EV-mounted solar panels. Hybrid series–parallel panel aggregation architecture is employed to mitigate mismatch and partial shading effects associated with non-uniform dust deposition. A MATLAB/Simulink-based emulation framework is developed to model dust-induced attenuation, capacitive sensor response, cleaning subsystem energy consumption, and net energy recovery under static parking, urban driving, and mixed-use operating conditions. Results demonstrate that the proposed system maintains panel performance within 95%–98% of clean baseline output and recovers approximately 12%–15% of the dust-induced lost energy per cleaning cycle, while sustaining a positive net energy balance with minimal operational overhead. The main contributions of this work include the development of a quantitative energy trade-off model linking dust density, sensor response, and cleaning cost, the design of an EV specific hybrid aggregation strategy for dust-resilient power extraction, and a reproducible emulation framework for evaluating autonomous cleaning systems under realistic vehicular conditions. These findings confirm the technical feasibility and energy efficiency of intelligent dust mitigation as an enabling mechanism for solar-assisted electric mobility.
Volume: 42
Issue: 3
Page: 637-648
Publish at: 2026-06-10

Grasshopper sound acoustic signal analysis using FFT and Butterworth filter

10.11591/ijeecs.v42.i3.pp708-720
Khairunnisa Khairunnisa , Sarifudin Sarifudin , Annisa Maulidia Damayanti
Grasshoppers are among the most destructive agricultural pests, making early detection essential to reduce crop losses while limiting excessive pesticide use. Acoustic monitoring provides a non-invasive and environmentally friendly approach for pest detection; however, its effectiveness is often constrained by strong environmental noise in open field conditions. This study proposes a structured acoustic signal analysis framework for grasshopper detection based on fast fourier transform (FFT) and Butterworth bandpass filtering. Grasshopper sound recordings were collected in rice field environments and pre-processed using Butterworth filters with empirically determined cutoff frequencies to suppress out-of band noise. FFT was applied to extract dominant spectral features, and signal quality was evaluated using both direct signal-to-noise ratio (SNR) and power spectral density (PSD)-based SNR estimated via the Welch method. Results indicate that grasshopper acoustic energy is consistently concentrated within the frequency range of approximately 5.8–9 kHz. Although direct time-domain SNR slightly decreases after filtering due to attenuation of out-of-band components, PSD-based SNR improves significantly, reaching 25–28 dB, demonstrating effective spectral concentration and noise suppression. The proposed approach is computationally efficient, interpretable, and suitable as a foundational module for low-cost, real-time acoustic pest detection systems in precision agriculture.
Volume: 42
Issue: 3
Page: 708-720
Publish at: 2026-06-10

A multicriteria collaborative decision support system for multidisciplinary medical coordination meetings

10.11591/ijeecs.v42.i3.pp753-766
Souad Madouri , Kaouter Labed , Kawther Makhlouf , Djamila Hamdadou , Anis Ayoub Amara , Aya Aouimer
Multidisciplinary team meetings (MDTMs) are central to cancer care. However, consensus can be hard to reach because specialists rely on diverse expertise and uncertain, multi-criteria clinical data. In this paper, we propose a group decision support system (GDSS) that integrates a multi-agent system (MAS) with multi-criteria decision making (MCDM) to structure interactions, aggregate expert preferences, enable real-time evaluation of options based on criteria, and transparently prioritize patients for discussion and intervention. Each specialist is represented by an agent that evaluates cases against shared criteria, while an embedded negotiation protocol enables exchanges and concessions to resolve conflicts and build consensus. We evaluated the GDSS using simulated breast cancer MDTM scenarios generated from a synthetic dataset of MDTM records. Experimental results demonstrate rapid convergence toward a consensual patient prioritization within a few negotiation iterations; in our experiments, agreement on the highest risk patient was reached after four rounds. Sensitivity analysis on subjective inputs, including criteria weights and preference profiles, produced minor changes in the resulting ranking, indicating robustness and stability to preference variations. The system maintains low computational complexity and short execution times, improving the transparency and consistency of MDTM recommendations. These outcomes confirm effectiveness and scalability for complex multidisciplinary clinical decisions.
Volume: 42
Issue: 3
Page: 753-766
Publish at: 2026-06-10

Metaheuristic optimization of wind turbine farm siting in power grids: a comparative study of PSO and GA

10.11591/ijeecs.v42.i3.pp666-677
Taha Rachdi , Yahia Saoudi , Larbi Chrifi-Alaoui , Ayachi Errachdi
This paper addresses the optimal integration of wind turbines into distribution networks with the aim of reducing active power losses and improving voltage stability. Two metaheuristic optimization methods genetic algorithm (GA) and particle swarm optimization (PSO) are applied to determine the optimal siting and sizing of wind turbines in the IEEE 14-bus system. The problem is formulated as a multi-objective function combining loss minimization and voltage profile enhancement under standard network constraints. Simulation results using MATLAB/PSAT show that both algorithms improve system performance compared to the base case, with PSO providing superior loss reduction and voltage stability. Wind variability is represented through a Weibull distribution to reflect realistic operating conditions. The study demonstrates the effectiveness of metaheuristic optimization for renewable integration and highlights PSO’s stronger robustness. The work contributes a comparative evaluation of GA and PSO, supported by stability analysis and realistic wind modelling.
Volume: 42
Issue: 3
Page: 666-677
Publish at: 2026-06-10
1 2 3
...
2036 2037
Show 3 of 2037

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration