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

31,377 Article Results

Comparison of machine learning algorithms to identify muscular atrophy and muscular dystrophy

10.11591/ijai.v15.i4.pp3505-3517
Ganga Bhavani Billa , Venkateswara Rao Peddada
Muscular dystrophy is a genetic disorder characterized by progressive muscle weakness and degeneration, while muscular atrophy involves the loss of muscle tissue due to pathological conditions. Accurate differentiation between these neuromuscular disorders is critical for effective clinical diagnosis and treatment planning. This study presents a machine learning– based framework for classifying muscular dystrophy and muscular atrophy using surface electromyography (sEMG) signals. sEMG data were acquired and processed to extract informative features with low computational complexity. Several machine learning classifiers several techniques were used and assessed, such as random forest (RF), support vector machine (SVM), gradient boosting (GB), and extreme gradient boosting (XGBoost). To further enhance classification performance, a novel ensemble learning approach combining multiple machine learning models was proposed. Experimental results exhibit that the suggested ensemble model completes significantly higher grouping accurateness and robustness compared to individual classifiers and existing methods reported in the literature. The results of this investigation indicate that ensemble-based machine learning techniques integrated with sEMG analysis provide a reliable and non-invasive diagnostic aid, with strong potential for early detection and improved clinical management of neuromuscular disorders.
Volume: 15
Issue: 4
Page: 3505-3517
Publish at: 2026-08-01

Performance evaluation of YOLOv11-based vehicle detection and tracking for urban intelligent transportation systems

10.11591/ijai.v15.i4.pp3518-3527
Thang C. Vu , Dung T. Nguyen , Minh T. Nguyen , Long Q. Dinh , Mui D. Nguyen
This paper proposes and evaluates an integrated vehicle detection and tracking framework based on you only look once (YOLO)v11 for intelligent transportation systems (ITS). The combination of the deep simple online and real-time tracking (DeepSORT) algorithm helps maintain vehicle identity across consecutive frames, thereby enhancing the stability of the multi-object tracking system. Additionally, the slicing-aided hyper inference (SAHI) technique is integrated to improve the detection efficiency of small vehicles in remote sensing imagery and urban surveillance video data collected in Thai Nguyen, Vietnam. The system's performance is comprehensively evaluated through several key quantitative indicators, including mean average precision (mAP), multiple objects tracking accuracy (MOTA), and identification F1-score (IDF1), across realistic urban traffic scenarios. The results show that the framework significantly improves detection accuracy, tracking consistency, and small object recognition efficiency in real-world urban traffic scenarios. This paper provides useful insights for selecting appropriate detection and tracking configurations in ITS applications.
Volume: 15
Issue: 4
Page: 3518-3527
Publish at: 2026-08-01

A novel embedded approach to face recognition using multi-threaded controller based on weightless neural network

10.11591/ijai.v15.i4.pp3903-3918
Ahmad Zarkasi , Hadipurnawan Satria , Anggina Primanita , Deris Stiawan
This research presents a high efficiency embedded face recognition system based on the weightless neural network-face recognition algorithm (WNN-FRA) integrated with a multi-thread controller to enhance execution time and recognition accuracy under limited hardware resources. The system implements a center-scan feature alignment model to address resolution discrepancies between reference and input facial images. The multi-threaded architecture divides processing into three concurrent threads front, left, and right facial orientations each handling approximately 20 facial patterns. Experimental evaluation on a dataset of 60 facial images demonstrated a maximum recognition accuracy of 96.83% and an average execution time ranging from 16 to 34 milliseconds per dataset, confirming real-time performance. Comparative analysis shows that the multi-threaded approach reduced the execution time by over 67% compared to single-thread processing 0.09 second vs. 0.271 second, while maintaining balanced workload distribution across threads. Memory analysis revealed that the entire system required only 24 KB from the available 512 KB flash capacity, indicating efficient resource utilization. The results confirm that integrating WNN-FRA with multi-threading provides a robust, low-cost, and scalable solution for real-time facial pattern recognition in embedded environments.
Volume: 15
Issue: 4
Page: 3903-3918
Publish at: 2026-08-01

Forecasting income inequality in Vietnam’s regions using machine learning

10.11591/ijai.v15.i4.pp3464-3475
T. Thai-Phuong , L. Nguyen-Son
This study applies artificial neural networks (ANN) and support vector regression (SVR) to forecast the Gini coefficient across Vietnam’s seven socio-economic regions using limited data from 2014–2022 (N = 63). Despite the small dataset, robust techniques including repeated cross-validation, temporal backtesting, regularization, and bootstrapping were employed to mitigate overfitting. The results show a modest continued decline in income inequality through 2025, with faster improvements in urban regions (Red River Delta and Southeast) than in rural and highland areas. ANN outperformed SVR with an average cross-validation coefficient of determination (R²) of 0.93. The novelty lies in its granular regional forecasting and region-specific policy recommendations beyond national-level analyses. Key drivers—per capita income and simple housing—support targeted interventions such as housing credits in the Mekong River Delta and agricultural investments in the Central Highlands. The findings provide an evidence-based foundation for regionally tailored strategies to reduce income disparities in Vietnam.
Volume: 15
Issue: 4
Page: 3464-3475
Publish at: 2026-08-01

Enhancing pedestrian detection in adverse conditions using YOLOv5s with adaptive weighted fusion efficient channel attention module

10.11591/ijai.v15.i4.pp3299-3308
Oumayma Rachidi , Badr Bououlid Idrissi , Chafik Ed-dahmani
Pedestrian detection constitutes a critical task within advanced driver assistance systems (ADAS), where reliable identification of pedestrians is essential for ensuring vehicular safety. Although deep learning has substantially improved detection performance, existing state-of-the-art models continue to exhibit notable degradation in adverse weather conditions and low-light. To mitigate these challenges, this study introduces an enhanced pedestrian detection framework based on you only look one version 5 (YOLOv5s), retrained on an augmented common object in context (COCO) dataset focused on the person class. Additionally, a novel, lightweight, and adaptive attention mechanism called: the weighted fusion efficient channel attention (WF-ECA) module is incorporated into the detection architecture. The WF-ECA module selectively focusses on important features without compromising computational efficiency or inference speed. Comparative experiments demonstrate a 5% increase in mean average precision (mAP) in comparison to the baseline model, thereby demonstrating the efficacy of the proposed attention module in improving detection robustness under challenging environmental conditions. These findings highlight the potential of attention-based mechanisms to enhance pedestrian detection performance in real-world ADAS applications.
Volume: 15
Issue: 4
Page: 3299-3308
Publish at: 2026-08-01

Comparative performance analysis of lightweight face identification algorithm

10.11591/ijece.v16i4.pp2042-2060
Wuyun Wang , Suchada Sitjongsataporn
With the wide application of face recognition in resource-constrained scenarios like mobile and embedded devices, lightweight algorithms have become a research focus, but existing studies lack multi-dimensional, scenario-based performance comparisons. This paper studies the performance evaluation and application adaptation of lightweight face recognition algorithms, innovatively builds a scenario-based evaluation system, verifies the performance improvement of combining traditional algorithms with MobileNet, and constructs an efficient, stable and low-cost system. It elaborates on face recognition principles, including key links of face detection, feature extraction and matching, introduces traditional algorithms such as Eigenfaces, Fisherfaces and LBPH, and focuses on MobileNet’s characteristics: reducing computation and parameters via depthwise separable convolution, and adjustable width and resolution. Four comparative experiments verify the "traditional algorithms + MobileNet" hybrid strategy. Results show the combination achieves 98.1% accuracy, 4.3 percentage points higher than single MobileNet; LBPH + MobileNet balances performance and resource consumption best, with 110MB memory, 40% CPU usage and 315ms processing time. The hybrid strategy improves accuracy and efficiency in different scenarios, aiming to provide a scientific basis for the engineering application and subsequent optimization of lightweight face recognition algorithms, and supporting algorithm selection and performance improvement in resource-constrained scenarios.
Volume: 16
Issue: 4
Page: 2042-2060
Publish at: 2026-08-01

Image-based estimation of surface roughness in Al-7075 drilling

10.11591/ijai.v15.i4.pp3492-3504
Shilpa M. Karegoudra , Vamsidhar Yendapalli
Surface roughness is an important quality parameter that affects the performance, durability, and reliability of machined components. Measuring the internal surface roughness of drilled holes using conventional contact-based methods is often difficult. Accessibility of the internal surface is complicated due to the diameter of the drilled hole and the need to interrupt the machining process. To overcome these limitations, the proposed work offers a non-contact method for estimating the surface roughness of drilled Al-7075 using image-based analysis. Drilled surfaces are machined using different speeds and feed rates. High-resolution images of the drilled surface are captured using a custom-built image-capturing setup. Texture and frequency features were extracted using gray-level co-occurrence matrix (GLCM), discrete Fourier transform (DFT), and discrete wavelet transform (DWT) techniques. Surface arithmetic average roughness (Ra) was measured using these extracted features. The estimated roughness parameters were then validated by comparing them against roughness parameters obtained by means of the contact stylus technique. According to the experimental results, the accuracy of the wavelet technique is higher, with mean absolute errors of 0.32 μm compared to those obtained using GLCM and DFT techniques. The findings demonstrate that the proposed image-based framework is a reliable and practical solution for non destructive surface roughness prediction.
Volume: 15
Issue: 4
Page: 3492-3504
Publish at: 2026-08-01

Simulation of a frequency-reconfigurable multiband antenna for 5G and Wi‑Fi 6E/7 applications

10.11591/ijeecs.v43.i2.pp439-449
Ismahane Refsi , Miloud Benchehima , Mohammed Hicham Hachemi , Salah Eddine Brezini
This paper presents a compact frequency-reconfigurable multiband antenna design suitable for 5G and Wi‑Fi 6E/7 applications. Designed on a low-cost FR4 substrate, the antenna occupies a compact footprint of 28×15×1.6 mm, making it one of the smallest designs reported and suitable for integration into space-constrained devices. Its simple geometry enables easy design and integration across platforms. Frequency reconfigurability is achieved using PIN-diode-controlled reactive elements that manipulate current distribution to shift resonant frequencies. The design and optimization were performed using CST Microwave Studio to ensure accurate electromagnetic performance. Simulation results demonstrate that the proposed design supports up to eight distinct operating modes, highlighting its versatile frequency-reconfigurable capability. Among these modes, some achieve excellent performance at specific frequency bands including Wi‑Fi 6E/7 (2.4, 5 and 6 GHz) and 5G sub-6 GHz (3.5 GHz). These findings are confirmed with simulation results showing clearly that the antenna exhibits S_11 below –20 dB across the targeted frequency bands. The antenna also demonstrates satisfactory gain, with values above 1.5 dBi across the desired frequency bands. The antenna reveals a voltage standing wave ratio (VSWR) below 1.5 across the intended frequency bands. These characteristics make the proposed antenna a compact, versatile and efficient solution for current and future wireless communication systems.
Volume: 43
Issue: 2
Page: 439-449
Publish at: 2026-08-01

Coordinated multi-battery control for single-stage islanded AC microgrids

10.11591/ijeecs.v43.i2.pp384-399
Adhi Kusmantoro , Lukman Harun
Reliable power management is essential for islanded AC microgrids integrating photovoltaic (PV) generation and battery energy storage, particularly under variable solar irradiance and load conditions. This paper proposes a coordinated multi-battery control strategy using a single-stage AC-coupled configuration to ensure uninterrupted power supply while improving system reliability. The proposed topology employs two PV arrays: one directly connected to a battery inverter to supply the AC load and another dedicated to battery charging. Four battery units are coordinated through a fuzzy logic controller (FLC), which sequentially regulates battery discharge based on PV generation and load demand. Simulation studies were conducted under two operating scenarios. In the first scenario, at a solar irradiance of 1000 W/m², the PV system generated approximately 1200 W, and the proposed controller maintained power balance as the load demand increased. In the second scenario, when PV output decreased due to reduced solar irradiance or complete source interruption, the FLC coordinated battery operation at 0.07 s, 0.34 s, 0.64 s, and 0.93 s, ensuring continuous power delivery to the load. The simulation results demonstrate that the proposed coordinated control strategy effectively enhances power continuity, operational stability, and energy management in single-stage islanded AC microgrids.
Volume: 43
Issue: 2
Page: 384-399
Publish at: 2026-08-01

Factors that influence social media interaction among university students: emotional and mental well-being

10.11591/ijeecs.v43.i2.pp607-617
Nur Anis Mohd Jasmi , Fauziah Redzuan , Jasber Kaur Gian Singh
Social media usage is becoming popular among students, which is used both for academic and entertainment. However, the excessive use of social media can increase the level of stress, anxiety, and depression. The social media interaction can also lead the students to compare themselves with influencers. This study aims to identify the factors and the significant relationship between the factors of social media interaction and emotional and mental well-being. This research used a quantitative research and hypothesis-driven approach. The existing theories, such as social capital theory and social comparison theory were adapted for the online survey questionnaires. The collected data were analysed using partial least square-structural equation modelling (PLS-SEM) to analyse the two objectives of this research. Based on the findings, twelve (12) constructs were identified as the factors that contribute to social media interaction on university students' emotional and mental well-being by assessing and validating the constructs using PLS-SEM. Then, there are thirteen (13) out of twenty-three (23) hypothesis were significant relationships based on the final model testing using PLS-SEM bootstrapping method. Ten (10) paths of direct effect, two (2) paths of mediating analysis, and one (1) path of moderating analysis were significant relationships and supported the alternative hypothesis. It is recommended for future studies to also explore other analysis techniques, theories, or models, and the changes to other group such as older generations or working adults.
Volume: 43
Issue: 2
Page: 607-617
Publish at: 2026-08-01

OCTModNet: a deep learning-based framework for optical coherence tomography image multi-class classification

10.11591/ijeecs.v43.i2.pp495-506
Saja Ataallah Muhammed , Abbas M. Ali , Dler Salih Hasan
Sight is one of the most significant senses in human beings. Losing sight can change a human’s life dramatically. Early diagnosis and detection of retinal diseases will prevent sight loss. Optical coherence tomography (OCT) imaging is helpful in ocular imaging with its high resolution and non invasive imaging for diagnosing retinal diseases. This study proposes OCTModNet, a novel multi-class hybrid classification model that is capable of classifying seven different retinal diseases using a combination of publicly available datasets, Kaggle OCT-C8, and OCTDL datasets. For effective extraction of the significant features, the collected data is resized and normalized. Augmentation techniques are used to improve the training and learning process. For model development, we applied transfer learning and fine-tuned several state-of-the-art deep learning models, ResNet50, InceptionV3, DenseNet121, VGG16, and EfficientNetV2S. Two models that performed best, VGG16 and EfficientNetV2S, were selected as the model backbones with integration of a squeeze and excitation block. The results showed that the OCTModNet achieved an outstanding performance with 99% test accuracy, 99% precision, 99% recall, 99% F1-score, and an area under the curve (AUC) as 99% across the unseen data. These results point out the robustness and reliability of the proposed model to classify OCT images and have the potential to enhance clinical decision-making and assist ophthalmologists in the early detection of diseases.
Volume: 43
Issue: 2
Page: 495-506
Publish at: 2026-08-01

A comprehensive review of memory BIST algorithms for SRAM static fault detection

10.11591/ijeecs.v43.i2.pp400-412
Aiman Zakwan Jidin , Razaidi Hussin , Mohd Syafiq Mispan , Lee Weng Fook , Loh Wan Ying
Memory built-in self-test (MBIST) has become an essential design-for testability technique for ensuring the reliability and quality of embedded memories in modern integrated circuits. The effectiveness of an MBIST implementation is largely determined by its test algorithm, which defines the sequence of memory operations, directly influencing both test complexity and fault coverage. Designing an efficient test algorithm requires balancing low test complexity with comprehensive fault detection. This paper presents a comprehensive review of MBIST test algorithms for static fault detection in static random-access memory (SRAM). The review first summarizes the characteristics of major SRAM static faults and their corresponding detection requirements. It then compares representative test algorithms in terms of test sequence, computational complexity, fault coverage, and design methodology. Furthermore, the evolution of MBIST test algorithm development is discussed, ranging from conventional ad hoc approaches to enhanced algorithms derived from existing March tests. The comparative analysis indicates that an 18N-complexity test algorithm is generally required to achieve complete detection of all unlinked static faults in SRAM, whereas optimized 14N-complexity algorithms provide an effective trade-off between test time and fault coverage. Finally, the review identifies current research challenges, including efficient detection of dynamic and linked memory faults and the development of MBIST algorithms for emerging memory technologies such as magnetic random-access memory (MRAM), highlighting promising directions for future research.
Volume: 43
Issue: 2
Page: 400-412
Publish at: 2026-08-01

Affine-invariant feature learning for accurate ulcer detection in wireless capsule endoscopy images

10.11591/ijeecs.v43.i2.pp595-606
S. Bhuvaneswari , M. Sulthan Ibrahim
Ulcers are lesions that develop in the lining of the gastrointestinal (GI) tract, particularly in the stomach and small intestine, and may lead to severe complications such as Crohn’s disease and ulcerative colitis if not detected at an early stage. Conventional endoscopic procedures are often uncomfortable for patients and may provide limited visualization of the entire small intestine. Wireless capsule endoscopy (WCE) has emerged as a non-invasive alternative for comprehensive GI tract examination; however, automated ulcer detection from WCE images remains challenging due to image noise, complex tissue structures, and computational requirements. To address these issues, this paper proposes a Camargo’s Indexive Kuwahara filtering-based affine-invariant sliced regression (CIKF-AISR) framework for accurate and efficient ulcer detection. The proposed framework consists of image acquisition, preprocessing, segmentation, and feature extraction stages. Adaptive CIKF is employed to suppress noise while preserving edge information. Subsequently, Von Neumann locality segmentation combined with the Canberra distance measure is utilized to identify regions of interest (ROIs). Finally, affine-invariant saliency sliced regression extracts discriminative shape, color, and texture features for ulcer detection. Experimental evaluation on the Hyper-Kvasir dataset demonstrates that the proposed method achieves higher ulcer detection accuracy, improved precision, enhanced peak signal-to-noise ratio (PSNR), and lower detection time compared with existing deep CNN and VAE-GAN approaches. These results confirm the effectiveness of the proposed framework for computer-aided GI diagnosis.
Volume: 43
Issue: 2
Page: 595-606
Publish at: 2026-08-01

Evaluation of hybrid parallelism for scalable training of DenseNet-121 in diabetic retinopathy classification

10.11591/ijeecs.v43.i2.pp662-671
Indar Sugiarto , Djoni Haryadi Setiabudi , Darrell Cornelius Rivaldo , Taweesak Kijkanjanarat , Resmana Lim
Training large and complex deep learning models is often constrained by GPU memory limitations and prolonged training times. While several parallelism strategies have been proposed, this study specifically evaluates hybrid parallelism—a combination of data parallelism and pipeline parallelism—to address both challenges simultaneously. Using a case study on diabetic retinopathy (DR) classification with the DenseNet-121 architecture, we analyze the trade-off between computational efficiency and memory scalability. Results show that although hybrid parallelism does not yet provide speedup compared to a single-GPU setup—due to communication overhead and pipeline fragmentation—it enables training of large models that exceed the memory capacity of a single GPU. The trained model achieved a validation accuracy of 0.737, a quadratic weighted kappa (QWK) of 0.861, and a weighted F1-score of 0.749. In contrast, pure data parallelism showed a potential speedup of up to 1.9× in scenarios where the model still fits within a single GPU. These findings highlight the critical role of hybrid parallelism in overcoming the memory wall in large-scale model training, though optimization to reduce overhead remains a key challenge.
Volume: 43
Issue: 2
Page: 662-671
Publish at: 2026-08-01

An artificial neural network-based decision support model for early prediction of mathematics learning challenges using the CRISP DM framework

10.11591/ijeecs.v43.i2.pp618-627
Harry Dhika , Surajiyo Surajiyo , Lasia Agustina , Abdul Muchlis
Identifying mathematics learning difficulties remains a challenge for educators due to the subjectivity and inefficiency of conventional methods in capturing psychological factors. To address this limitation, this study proposes an artificial neural network (ANN)-based decision support model developed within the cross-industry standard process for data mining (CRISP-DM) framework. The model integrates 16 academic indicators (quizzes, exams, remedial frequency, online activity) and psychological factors (motivation, anxiety, self-confidence, interest) from 163 student records at SMA Muhammadiyah 16 Jakarta. Synthetic minority over-sampling technique (SMOTE) and focal loss are applied to handle class imbalance and improve reliability. The proposed model achieves 98% accuracy and a 0.97 F1-score in classifying students into three difficulty levels: Easy, moderate, and difficult. These findings demonstrate the model’s effectiveness in capturing complex relationships between cognitive and affective features. Unlike prior studies that rely solely on academic performance, this work contributes a robust, comprehensive data-driven framework that enhances multiclass classification for early educational intervention within the Indonesian context.
Volume: 43
Issue: 2
Page: 618-627
Publish at: 2026-08-01
1 2 3
...
2091 2092
Show 42 of 2092

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