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

30,033 Article Results

Machine learning-based solar power prediction for major Indian metro cities

10.11591/ijai.v15.i2.pp1362-1370
Komal Kumar Napa , Rajkumar Govindarajan , J. Senthil Murugan , Billa Manindhar
The growing reliance on renewable energy has intensified the need for accurate solar power forecasting to support efficient grid operation and energy planning. However, reliable prediction remains challenging due to the strong dependence of solar power output on dynamic meteorological conditions. This study proposes a data-driven machine learning (ML) framework for high-precision solar power prediction across several major Indian metro cities. Using hourly weather and power generation data for the year 2023, a random forest regressor was developed to model complex non linear relationships between environmental variables and solar energy output. The proposed model achieved exceptional predictive performance, with an R² score of 0.9999 and a mean absolute error (MAE) of 0.15 kW, significantly outperforming conventional regression approaches. Feature contribution analysis revealed solar radiation as the dominant factor influencing power generation, while cloud cover and elevated temperatures exhibited negative effects. The key contribution of this work lies in demonstrating the robustness and generalizability of ensemble learning for urban-scale solar forecasting under diverse climatic conditions. The findings provide actionable insights for policymakers, grid operators, and energy planners to optimize solar integration and resource management.
Volume: 15
Issue: 2
Page: 1362-1370
Publish at: 2026-04-01

Sentiment-aware user-item recommendation combining weighted XGBoost and optimized similarity metrics

10.11591/ijai.v15.i2.pp1851-1862
Snehal Bhogan , Vijay S. Rajpurohit , Sanjeev S. Sannakki
User-item recommendation systems play a vital role in enhancing personalized digital experiences across e-commerce and social media platforms. Traditional recommendation approaches, such as collaborative filtering (CF) and content-based filtering (CBF), often suffer from challenges like data sparsity, cold-start issues, and limited contextual understanding. Sentiment-aware recommendation systems have emerged as a promising solution by incorporating emotional insights extracted from user reviews, thereby improving recommendation accuracy and personalization. This study proposes a novel sentiment-aware user-item recommendation system (SAUIRS) framework that integrates optimized term frequency inverse document frequency (O-TF-IDF), parameterized bidirectional encoder representations from transformers (P-BERT), weighted extreme gradient boosting (WXGBoost), and an optimized similarity metrics model. The optimized TF-IDF enhances feature selection, reducing dimensionality while preserving relevant textual information. P-BERT, a fine-tuned BERT model, improves sentiment classification accuracy by leveraging deep contextual embeddings. WXGBoost further refined sentiment predictions, addressing class imbalance and enhancing model robustness. The extracted sentiment information is incorporated into an optimized similarity metrics model to improve recommendation precision by aligning user preferences with sentiment-driven insights. Extensive experiments conducted on Amazon benchmark datasets demonstrate the superior performance in terms of accuracy, root mean square error (RMSE), and mean absolute error (MAE) of the proposed framework compared to state-of-the-art recommendation models.
Volume: 15
Issue: 2
Page: 1851-1862
Publish at: 2026-04-01

Accurate stroke area classification using extreme gradient boosting with multi-feature extraction

10.11591/ijai.v15.i2.pp1390-1401
Kavikondala Praveen Kumar Rao , Maha Lakshmi Bondla , Bommaraju Srinivasa Rao , Ambidi Naveena , K. V. Balaramakrishna , Srinivasarao Goda
Stroke, one of the most common neurological disorders leading to long-term disability and mortality, requires accurate detection of affected brain regions for timely treatment planning. However, conventional deep learning models face challenges in achieving precise segmentation and robust classification due to noisy inputs, weak feature representation, and poor generalization. To address these gaps, this study introduces a hybrid framework that integrates the ConvNeXt architecture for stroke region segmentation with XGBoost based classification, strengthened through three complementary feature extraction methods: local binary patterns (LBP), adaptive threshold directional binary gradient matrix (AT-DBGM), and wavelet packet transform (WPT). These methods capture textural, directional, and multi resolution features, which are concatenated into a stacked vector and classified using XGBoost. Preprocessing steps, including normalization and resizing, ensure improved input consistency. Experimental evaluations on benchmark stroke imaging datasets show that the proposed framework achieves 98.56% Dice similarity coefficient (DSC), 12.96 mm Hausdorff distance (HD), 99.12% accuracy, 98.69% sensitivity, 99.06% specificity, 98.98% precision, and 98.85% F1-score.
Volume: 15
Issue: 2
Page: 1390-1401
Publish at: 2026-04-01

Deep learning for early detection of cardiovascular diseases via auscultation sound classification

10.11591/ijai.v15.i2.pp1746-1761
Shreyas Kasture , Sudhanshu Maurya , Amit Kumar Sharma , Santhosh Chitraju Gopal Varma , Kashish Mirza , Firdous Sadaf Mohammad Ismail
Heart diseases are one of the most prominent causes of death globally, which requires immediate and accurate diagnosis. The auscultation methods used in conventional medical practice, where the doctor listens to the sounds produced by the body without intervention is very ineffective because of the limitations in the actual skills and perception of the doctor. The main goal of this project will be designing a mobile-based system for the early detection of cardiovascular disease (CVD) by utilizing deep learning for auscultation sound classification. The approach involves the use of deep learning structures to classify cardiac sounds into normal and abnormal patterns on its own. Wavelet transformations, time-frequency representations, and Mel frequency cepstral coefficients (MFCC) have been used in feature extraction. The ResNet152V2 model showed high classification performance with area under the receiver operating characteristic curve (AUROC) of 0.9797 and 0.9636 on two datasets. Contrary to that, data augmentation, hyperparameter optimization, attention mechanisms, as well as input-output residual connections, led to better functionality and interpretability. This research seeks to overcome the limitations of traditional stethoscope use through the incorporation of sophisticated algorithms and the availability of mobile technology that could result in early diagnosis and prevention of CVDs, especially in underprivileged areas.
Volume: 15
Issue: 2
Page: 1746-1761
Publish at: 2026-04-01

An intelligent and explainable IoT-Edge-Cloud architecture for real-time water quality monitoring

10.11591/ijai.v15.i2.pp1109-1120
Sara Bouziane , Badraddine Aghoutane , Aniss Moumen , Anas El Ouali , Ali Essahlaoui , Abdellah El Hmaidi
Continuous and reliable monitoring of water quality is critical for early detection of environmental deterioration, yet conventional monitoring approaches are often slow and lack timely data availability. This study proposes an intelligent and explainable internet of things (IoT)–Edge–Cloud architecture to monitor water quality in real time, using IoT sensing, edge based artificial intelligence (Edge AI), cloud-stream processing, and explainable artificial intelligence (XAI). The system calculates the water quality index (WQI) directly at the edge and predicts its evolution using a stacking ensemble model trained on physicochemical measurements taken from the Moulouya River Basin in Morocco. An explainability module based on Shapley additive explanations (SHAP) values gives a clearer image of the contribution of various parameters to WQI predictions, providing transparency of the features, which builds trust in the model’s output. The proposed architecture was implemented as an end-to-end prototype and validated using a simulation-based experimental that mimicked realistic sensor dynamics and connectivity interruptions. The experimental results show strong predictive performance (R² =0.945), stable system operations, and reliable interpretability highlighting the potential of the proposed approach for scalable, intelligent, and transparent environmental monitoring.
Volume: 15
Issue: 2
Page: 1109-1120
Publish at: 2026-04-01

Fetal organ detection using feature enhancement with attention and residual block

10.11591/ijai.v15.i2.pp1593-1604
Nuswil Bernolian , Siti Nurmaini , Ade Iriani Sapitri , Annisa Darmawahyuni , Muhammad Naufal Rachmatullah , Bambang Tutuko , Firdaus Firdaus
The rapid advancements in fetal ultrasonography have significantly enhanced prenatal diagnosis in recent years. Deep learning (DL) architectures have further streamlined the process of organ detection, improved diagnostic accuracy, and reduced observer dependency. This study proposes a computer-aided DL approach for fetal organ segmentation using the you only look once (YOLO) algorithm, a state-of-the-art method for object detection and image segmentation. This study identified and classified 15 fetal organs, including the umbilical vein, stomach, abdomen, brain (trans-cerebellum, trans-thalamic, and trans-ventricular regions), femur, head, thorax (chest cavity), heart (circumference, left atrium, left ventricle, right atrium, right ventricle), and aorta. We compared the performance of YOLOv7, YOLOv8, YOLOv9, and YOLOv11 architectures. The results showed that YOLOv9 outperformed YOLOv7, YOLOv8, and YOLOv11 achieving mAP50 and mAP95 scores of 91.90% and 94.50%, respectively. This performance surpasses previous studies that focused on classifying only a limited number of fetal organs.
Volume: 15
Issue: 2
Page: 1593-1604
Publish at: 2026-04-01

Enhanced long-term recurrent convolutional network for video classification

10.11591/ijeecs.v42.i1.pp174-182
Manal Benzyane , Mourade Azrour , Said Agoujil
Video classification is essential in computer vision, enabling automated understanding of dynamic content in applications such as surveillance, autonomous systems, and content recommendation. Traditional long-term recurrent convolutional network (LRCN) models, however, often struggle to capture complex spatio-temporal patterns, limiting classification performance across diverse video datasets. To address this limitation, we propose an enhanced LRCN with architectural refinements, optimized filter sizes, and hyperparameter tuning, improving both temporal modeling and spatial feature extraction. Experimental results on three benchmark datasets DynTex, UCF11, and UCF50 demonstrate that the proposed model achieves accuracies of 0.90 on DynTex (+26.8% over standard LRCN), 0.92 on UCF11 (+19.5%), and 0.94 on UCF50 (+1.1%), consistently outperforming ConvLSTM, LRCN, and other state-of-the-art approaches. These findings indicate that the enhanced LRCN effectively captures spatial and temporal dynamics in video sequences, setting a new benchmark for video classification. The study highlights the impact of architectural innovation and parameter optimization, providing a solid foundation for future research on scalable and efficient deep learning models for dynamic content analysis.
Volume: 42
Issue: 1
Page: 174-182
Publish at: 2026-04-01

Towards greener telecom: energy-efficient hybrid solar–grid systems for remote base station operations

10.11591/ijeecs.v42.i1.pp93-104
Hasanah Putri , Rendy Munadi , Sofia Naning Hertiana , Alfin Hikmaturokhman
Efficient and environmentally friendly energy use for base transceiver stations (BTS) in remote areas is essential for telecommunication network development. This study simulates and compares two BTS configurations: a conventional grid-powered system and a hybrid solar-grid system, focusing on energy efficiency, operational cost, and carbon emissions. The simulation was conducted over a one-year operational period using Python-based modeling with realistic input parameters. The results indicate that the hybrid system can supply approximately 74% of the annual energy demand using solar power, achieving 24.4% operational cost savings and reducing carbon emissions by 73% compared to the grid-only system. These findings confirm that the hybrid BTS system is a feasible and sustainable solution to support telecommunication expansion in remote areas with lower cost and environmental impact.
Volume: 42
Issue: 1
Page: 93-104
Publish at: 2026-04-01

Enhancing AODV protocol for black hole attack detection and mitigation in VANETs: a lightweight dual-confirmation approach

10.11591/ijeecs.v42.i1.pp252-262
Ahmed Abderraouf , Ramdane Taglout , Sofiane Boukli-Hacene
Vehicular ad hoc networks (VANETs) represent a specialized category of Mobile ad hoc networks that are specifically designed to enable communication among autonomous (self-driving or partially self-driving) vehicles. These vehicles are equipped with onboard computers, network interfaces, and sophisticated sensors for data capture and processing. Within a VANET, vehicles have the ability to communicate with each other as well as with surrounding infrastructure, thereby exchanging critical messages aimed at enhancing road safety, reducing traffic congestion, and enabling new services and applications for drivers and passengers. Due to its unique characteristics, VANETs have succeeded in enhancing transportation efficiency and safety. However, VANETs are vulnerable to black hole attacks, where malicious nodes discard packets, compromising safety. Existing solutions suffer from high overhead or infrastructure dependence. We propose a lightweight enhancement to AODV using dual-confirmation (RepAck/Info packets) to detect and isolate attackers in real time. Simulations show a 98% improvement in packet delivery ratio under attack, with minimal protocol modifications. While routing overhead increases by 25%, this trade-off ensures reliable communication in dynamic VANETs.
Volume: 42
Issue: 1
Page: 252-262
Publish at: 2026-04-01

ViHateT5 with LoRA: efficient vietnamese toxic news classification on social media

10.11591/ijeecs.v42.i1.pp123-130
Tran Duc Duong , Hai Hoan Do
We propose an efficient transformer-based approach to detect toxic or misleading news in Vietnamese social media. Motivated by the societal harm of viral misinformation in Vietnam, we fine-tune a Vietnamese T5 model (ViHateT5) on a new dataset of 2,962 social-media news snippets labeled as toxic vs. non-toxic. We use low-rank adaptation (LoRA) to inject trainable layers into ViHateT5, allowing high accuracy with minimal additional parameters. Our model achieves 97.5% macro-F1 on a held-out test set, significantly higher than a PhoBERT baseline by 2.7 points. By focusing on Vietnamese data and a parameter-efficient method, we demonstrate a practical pipeline for low-resource fake-news detection. These results suggest that transformer pretraining on social-media text can effectively capture the subtle cues of deceptive or defamatory news. Limitations: the current model is trained on a specific labeled dataset and may not generalize to all domains; future work should evaluate its fairness and biases in deployment.
Volume: 42
Issue: 1
Page: 123-130
Publish at: 2026-04-01

Trophallactic optimization algorithm with markov random field refinement for stroke lesion segmentation

10.11591/ijeecs.v42.i1.pp131-141
Hayet Berkok , Karima Kies , Nacera Benamrane
Cerebrovascular accidents (strokes) represent a critical medical emergency re quiring rapid and accurate diagnosis. Automated segmentation of stroke lesions from computed tomography (CT) images remains challenging due to low con trast, image noise, and high anatomical variability between ischemic and hem orrhagic subtypes. This paper introduces a novel hybrid approach combining the trophallactic optimization algorithm (TOA), inspired by cooperative nectar exchange in bee colonies, with markov random fields (MRF) for spatial coher ence modeling. The proposed TOA-MRF method operates semi-automatically from a single user-defined seed point, leveraging bio-inspired collective intel ligence to progressively explore and refine regions of interest. The algorithm simulates the enzymatic transformation of nectar into honey through iterative information exchange between virtual bees, followed by MRF-based regulariza tion to ensure anatomical consistency. Evaluated on a clinical CT dataset, the method achieves a Dice similarity coefficient of 87.3% for ischemic strokes and 91.2% for hemorrhagic strokes, with an overall detection accuracy exceeding 89%. Comparative analysis demonstrates the complemen tary strengths of TOA exploration and MRF refinement, offering a robust and efficient solution for clinical stroke assessment with minimal user intervention.
Volume: 42
Issue: 1
Page: 131-141
Publish at: 2026-04-01

A sub-threshold CMOS temperature sensor circuit core with 2.41 mV/°C sensitivity for ultra-low-power applications (-100°C to 100°C)

10.11591/ijeecs.v42.i1.pp40-47
Abdelhakim Megueddem , Khaled Bekhouche
This paper presents a sub-threshold complementary metal-oxide semiconductor (CMOS) temperature sensor core for ultra-low-power applications, with the key advantage of reliable operation over an exceptionally wide temperature range from –100 °C to 100 °C, which is rarely reported in existing CMOS-based designs. The proposed architecture operates entirely in the sub-threshold region and is evaluated using circuit level simulations, with validation through comparison to a previously reported temperature sensor. Simulation results show excellent linearity across the full temperature range, achieving a coefficient of determination of R² = 0.99997 and a sensitivity of approximately 2.41 mV/°C. At a supply voltage of 1.4 V and 25°C, the sensor core consumes only 22 nW, highlighting its suitability for energy-constrained applications. These results demonstrate the potential of sub-threshold CMOS temperature sensing for wide-range, ultra-low-power sensing systems.
Volume: 42
Issue: 1
Page: 40-47
Publish at: 2026-04-01

Towards decision-making and task planning modules for autonomous mini-UAV mission planning in civil applications

10.11591/ijeecs.v42.i1.pp48-61
Asmaa Idalene , Sophia Faris , Hicham Medromi , Khalifa Mansouri
Autonomous mini unmanned aerial vehicles (UAVs) for civilian applications face a critical challenge: during flight, their mission planning cannot break down complex goals into real-time actions. It’s like having a brilliant strategy with no way to execute it in the moment conditions change. While current solutions can handle basic navigation, they often fail when conditions change. This lack of adaptability seriously limits autonomy in real-world applications, like infras tructure inspection or emergency response. The core problem? Nobody has yet built a system that can think in both layers, combining hierarchical goal decom positions with dynamic tasks without overloading the onboard computer. Our work addresses this gap by introducing an integrated mission planning system with two complementary modules. First: the decision-making module employs recursive goal tree construction to transform high-level mission goals into hier archical sub-goal structures in a systematic manner. Second: the task planning module converts these structured goals into concrete MAVLink command se quences. Together, these modules bridge the gap between abstract mission spec ifications and low-level flight operations while enabling dynamic replanning. To verify if our system actually works, we validated the framework through simulation-based experiments using a Python UAV mission simulator across 50 test runs. The results showed a 94% mission completion rate, with an average planning time of 1.8 seconds for missions with 5 to 8 waypoints. It adapted well to surprises: new targets (100% success), no-fly zones (92% success), and priority changes (96% success). Compared to traditional reactive baseline ap proaches, the framework reduced replanning time by 67%. This tells us that the modular approach is not just theoretically sound but it’s also practically viable for real-world civilian operations.
Volume: 42
Issue: 1
Page: 48-61
Publish at: 2026-04-01

Comparison of adaptive tuning fuzzy PID and Ziegler-Nichols PID for photovoltaic cooling system

10.11591/ijece.v16i2.pp1063-1074
Yusnan Badruzzaman , Aggie Brenda Vernandez , Septiantar Tebe Nursaputro , Pangestuningtyas Diah Larasati
Renewable energy, particularly solar power, is widely recognized as a clean and sustainable resource, with rooftop photovoltaic (PV) systems playing a vital role in electricity generation. However, high temperatures can significantly reduce their efficiency, making effective cooling systems essential. This study proposes a proportional-integral-derivative (PID) based cooling control system for rooftop PV panels, integrating an adaptive Mamdani fuzzy logic controller to optimize PID parameters dynamically. The methodology includes system modeling, hardware and software implementation, and comparative testing between the Mamdani fuzzy-PID controller and the Ziegler-Nichols PID method. Experimental results show that both controllers effectively regulate PV panel temperature at 36 °C. The Ziegler-Nichols PID achieves faster settling time of 6.45 minutes with a steady-state error of 1.345%, whereas the Mamdani fuzzy-PID reduces the steady-state error to 0.93% but with a longer settling time of 9.15 minutes. These results indicate that the fuzzy-PID controller offers better accuracy and system stability, making it a promising solution for maintaining PV performance under varying environmental conditions. The key novelty of this study lies in its adaptive approach, where the Mamdany fuzzy-PID controller continuously adjust control parameters (Kp,Ki,Kd) in real time, resulting in more consistent and precise temperature regulation than conventional PID tuning methods.
Volume: 16
Issue: 2
Page: 1063-1074
Publish at: 2026-04-01

Smartphone data privacy and security awareness among university students in Malaysia

10.11591/ijece.v16i2.pp850-862
Ahmed Al-Rassas , Zaheera Zainal Abidin
This study examines the level of data privacy and security awareness (DPSA) among Malaysian university students who depend on smartphones for academic activities. An enhanced cybersecurity education (CE) technological proficiency–perceived control (CTP) model is proposed, incorporating technological innovation and cultural norms (TICN) as a mediating factor between technological proficiency (TP) and awareness. A total of 356 students from public and private institutions in Melaka participated. The Krejcie and Morgan table was used to determine the sample size. Descriptive analysis was conducted using IBM SPSS 27, and SmartPLS-SEM was used to evaluate both measurement and structural models. Reliability and validity were confirmed through a pilot study with 50 respondents. Findings show that TICN significantly strengthens the translation of technical skills into protective behavior, outperforming the original model that used frequency of smartphone usage (FSU) as a mediator. The enhanced model provides a deeper understanding of the socio-technical determinants of smartphone privacy awareness. Implications, limitations, and directions for future research are also discussed.
Volume: 16
Issue: 2
Page: 850-862
Publish at: 2026-04-01
1 2 3
...
2002 2003
Show 19 of 2003

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