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

30,185 Article Results

Image feature extraction for road surface damage classification

10.11591/ijai.v15.i2.pp1578-1592
Octaviani Hutapea , Sarifuddin Madenda , Hustinawaty Hustinawaty , Iffatul Mardhiyah
Road surface deterioration poses a critical risk to driving safety and comfort, necessitating timely and accurate detection to support effective maintenance. Manual inspection methods are often inefficient, underscoring the need for automated approaches based on computer vision. This study investigates the integration of feature extraction techniques histogram of oriented gradients (HOG) and local binary pattern (LBP) with convolutional neural network (CNN) architectures ResNet50 and InceptionV3 for the classification of road damage. A dataset of 1,580 images was categorized into five damage types: alligator crack, longitudinal crack, other crack, patching, and potholes. Experimental results indicate that HOG–ResNet50 achieved 79% accuracy, while LBP–InceptionV3 yielded the best performance at 97%. The contributions of this study are threefold: i) an automated framework is proposed that combines texture-based features with deep learning for road damage detection, ii) the LBP–InceptionV3 combination is shown to provide superior accuracy compared to conventional pairings, and iii) the approach offers a scalable and reliable alternative to manual inspection methods, supporting more efficient road maintenance planning.
Volume: 15
Issue: 2
Page: 1578-1592
Publish at: 2026-04-01

An exploratory review on conceptualizing generative artificial intelligence literacy

10.11591/ijai.v15.i2.pp1023-1035
Mohammed Afandi Zainal , Mohd Effendi Mohd Matore , Siti Mistima Maat
Generative artificial intelligence (AI) has rapidly evolved, demanding new forms of literacy that go beyond traditional AI concepts. However, current definitions of generative AI literacy often overlook its unique challenges, including prompt engineering, critical evaluation of AI-generated outputs, and complex ethical considerations. This study addresses these gaps through an exploratory review of 20 peer-reviewed articles. These articles were identified using systematic searches across major academic databases and selected based on predefined inclusion criteria. The analysis reveals conceptual limitations in existing frameworks, particularly their lack of structure and their generalization of AI literacy. To overcome these issues, we propose a new competency framework adapted from Bloom’s taxonomy. The framework integrates three essential dimensions: technical proficiency, ethical responsibility, and societal awareness. It is organized into five progressive cognitive stages: understand, apply, analyze, evaluate, and create. This framework clarifies the distinct demands of generative AI literacy and can be implemented to guide curriculum design, professional training, and the development of generative AI literacy across sectors.
Volume: 15
Issue: 2
Page: 1023-1035
Publish at: 2026-04-01

MNetNCR: MobileNet model for efficient traditional Nusantara script character recognition

10.11591/ijai.v15.i2.pp1513-1528
Untari Novia Wisesty , Aditya Firman Ihsan , Mahmud Dwi Sulistiyo , Donni Richasdy , Prasti Eko Yunanto , Gamma Kosala , Arfive Gandhi , Febryanti Sthevanie
Preservation of traditional Nusantara scripts is very important because these traditional scripts are part of the cultural heritage that reflects the identity and history of the nation. This research proposed MobileNet for Nusantara character recognition (MNetNCR) model based on MobileNetV3 architecture to recognize traditional Nusantara scripts with lightweight, efficient architecture, and accurate recognition. The novel and comprehensive datasets for traditional Nusantara scripts have been curated in this research, that will later be stored digitally and can be used in further research. This novel dataset includes handwritten Balinese, Batak, Javanese, Lontara, and Sundanese scripts, each with unique visual characteristics. The proposed MNetNCR model is highly effective in recognizing characters, achieving F1-scores of 0.9934 for Balinese, 0.9450 for Batak, 0.9788 for Javanese, 0.9936 for Lontara, and 0.9961 for Sundanese scripts, according to the experimental results. The MNetNCR model built in this research has been proven to be effective and efficient in recognizing traditional scripts accurately. It also supports the preservation and promotion of the nation's cultural and historical heritage.
Volume: 15
Issue: 2
Page: 1513-1528
Publish at: 2026-04-01

TunDC: a public benchmark dataset for sentiment analysis and language modeling in the Tunisian dialect

10.11591/ijai.v15.i2.pp1891-1908
Ahmed Khalil Boulahia , Mourad Mars
The development of natural language processing (NLP) applications has increasingly focused on dialectal variations of languages. The Tunisian dialect (TD), a widely spoken variant of Arabic, poses unique linguistic challenges due to its lack of standardized writing conventions and influences from multiple languages, including French, Italian, Turkish, and Berber. In this work, we introduce TunDC, a dataset of 20,044 labeled comments designed to advance NLP research on the TD. The dataset covers diverse linguistic forms (Arabic, Latin, and mixed scripts), and each comment was manually annotated for positive or negative sentiment by native speakers, achieving high inter-annotator agreement. To evaluate its effectiveness, we fine-tuned various models on TunDC. The bert-base-arabic-TunDC-mixed model achieved an accuracy of 0.84 and a macro-averaged F1-score of 0.83, demonstrating strong generalization across sentiment categories and writing systems. A stratified data-splitting strategy considering both sentiment and script type further improved accuracy by approximately 8% compared to standard splits. As a publicly available resource, TunDC contributes to the computational linguistics community, fostering advancements in language modeling and applications tailored to the TD.
Volume: 15
Issue: 2
Page: 1891-1908
Publish at: 2026-04-01

The effects of data imbalance on fraud detection model accuracy

10.11591/ijai.v15.i2.pp1402-1408
Rusma Anieza Ruslan , Nureize Arbaiy , Pei-Chun Lin
Machine learning (ML) model performance is often assessed by accuracy, but the quality and balance of data also play crucial roles. Imbalanced datasets, where the minority class has fewer samples than the majority class, can lead to biased predictions favoring the majority class. This study addresses the issue of class imbalance through resampling techniques, including random undersampling (RUS) and random oversampling (ROS), specifically applied to a fraud detection dataset. We classify the resampled datasets using random forest (RF) and gradient boosting (GB) models. Our findings indicate that the RF model, when combined with ROS, achieves an accuracy of 97.4%, surpassing the 96.1% accuracy of the GB model with RUS. This approach demonstrates the importance of addressing class imbalance to improve prediction accuracy in ML.
Volume: 15
Issue: 2
Page: 1402-1408
Publish at: 2026-04-01

A hybrid model for enhanced aspect-based sentiment analysis using large language models

10.11591/ijai.v15.i2.pp1825-1838
Mohammed Ziaulla , Arun Biradar
Aspect-based sentiment analysis (ABSA) is a crucial task within natural language processing (NLP), enabling fine-grained opinion mining by identifying sentiments associated with specific aspects of a product or service. While transformer-based models like bidirectional encoder representations from transformers (BERT) have improved sentiment classification, they still struggle with limited contextual adaptability, especially in customer reviews containing complex expressions. Most existing approaches rely heavily on benchmark datasets such as semantic evaluation (SemEval) and multi-aspect multi-sentiment (MAMS), which do not fully capture the diversity of real-world review scenarios. Hence, this research addresses these limitations by proposing a novel hybrid model, called as hybrid-BERT (H-BERT), that integrates span-aware BERT (SpanBERT) with bidirectional long short-term memory (BiLSTM), conditional random field (CRF), and large language models (LLMs). The objective is to enhance aspect extraction and sentiment classification performance using both annotated and synthetic data. The methodology includes preprocessing, hybrid model training, and evaluation using the SemEval 2014 dataset. Experimental results show that H-BERT achieved 90.58% accuracy and 90.56% F-score in the laptop domain and 91.21% accuracy with a 92.03% F-score in the restaurant domain. These results outperform existing models, confirming H-BERT’s robustness and effectiveness. In conclusion, H-BERT improves sentiment understanding in customer reviews.
Volume: 15
Issue: 2
Page: 1825-1838
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

Student activity recognition from classroom video: a survey

10.11591/ijeecs.v42.i1.pp149-163
Phuong-Dung Nguyen , Khanh-Huyen Bui , Thi-Lan Le
Student behavior and activity play a crucial role in shaping the classroom atmo sphere and influencing the quality of a learning session. Recently, vision-based student activity recognition has gained significant attention. However, recog nizing student activities from classroom videos presents unique challenges due to the nature of the classroom environment, such as the presence of multiple students and severe occlusions. As a result, research in this area has often over looked these challenges. This study provides a detailed and comprehensive re view of student activity recognition from classroom videos. First, we formalize the problem of student activity recognition from videos and categorize existing methods into three distinct approaches: frame-level, clip-level, and continuous recognition. We then provide a detailed analysis of representative methods for each approach. In addition, we present a comprehensive overview of publicly available datasets for student activity recognition and discuss key open chal lenges, together with potential future research directions. Our analysis reveals that: (1) Most existing studies focus on frame-level recognition, while clip-based and continuous activity recognition remain relatively underexplored; (2) there is still a lack of large-scale, standardized benchmark datasets for vision-based stu dent activity recognition; and (3) existing research primarily emphasizes recog nition accuracy, whereas real-time performance and computational efficiency are rarely addressed.
Volume: 42
Issue: 1
Page: 149-163
Publish at: 2026-04-01

Attribute optimization to improve breast cancer prediction using machine learning techniques

10.11591/ijai.v15.i2.pp1327-1338
Raghavendra Srinivasaiah , Santosh Kumar Jankatti , Niranjana Shravanabelagola Jinachandra , Manjunath Ramanna Lamani , Bellam Vijaya Lakshmi , Rishita Bhelwa
Breast cancer (BC) arises when cells grow out of control. It affects women more than men. Seeking cancer treatment can be both costly and time consuming, with test results spanning from a few hours to several weeks. The duration of these tests depends on the number of attributes within the dataset. This research paper endeavors to optimize the dataset attributes and find the accuracy of the optimized dataset. The primary goal is to reduce features using recursive feature elimination to minimize the time taken for the test result. This work discusses the machine learning technique and the random forest (RF) algorithm, which helps determine the parameter accuracy on the Wisconsin BC diagnostic dataset. The method achieves an accuracy of 96.49% with only eighteen attributes. It has aided the healthcare industry in finding BC in less time and improving the treatment.
Volume: 15
Issue: 2
Page: 1327-1338
Publish at: 2026-04-01

Comparative deep learning study for downy mildew detection in vegetables

10.11591/ijai.v15.i2.pp1719-1732
Supreetha Shivaraj , Manjula Sunkadakatte Haladappa
Several vegetable crops are affected by downy mildew, a major foliar disease resulting in notable reductions in yield. For sustainable agriculture and disease prevention, early and precise detection is crucial. To be able to detect downy mildew in five varied vegetables—bitter gourd, bottle gourd, cauliflower, cucumber (Rashid), and cucumber (Sultana)—this study evaluates three deep learning architectures: VGG19, DenseNet201, and MobileNetV2. This work focuses on imbalanced datasets collected from several sources, in opposition to prior work that depended on balanced laboratory datasets. Accuracy, precision, recall, and F1-score metrics were used to evaluate the models shortly after they were trained using transfer learning, data augmentation, and 5-fold cross-validation. Model focus regions were assessed by using gradient-weighted class activation mapping (Grad-CAM) visualizations, and statistical reliability was assessed based on paired t-tests and Wilcoxon signed-rank tests. By achieving mean accuracies above 98% and statistically significant results (p <0.05) on cucumber datasets, DenseNet201 accomplished superior performance. Despite attaining slightly lower accuracy (89.6–100%), MobileNetV2 offered the smallest model size (12.9 MB) and minimum inference time (85 ms). The proposed approach demonstrated a transparent, generalizable, and computationally efficient deep learning pipeline for precision agriculture’s real-time downy mildew detection.
Volume: 15
Issue: 2
Page: 1719-1732
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

IoT-enabled digital twin with renewable energy for sustainable mudless eel aquaculture

10.11591/ijeecs.v41.i3.pp912-923
Muhammad Ferdiansyah , Lika Mariya , Taufik Rahman , Sugeng Dwiono
This research develops and tests a digital twin (DT)-based smart aquaculture system for mud-free eel farming through the integration of IoT sensing, artificial intelligence (AI)-based prediction, edge computing, and solar energy-based automation. The approach used is experimental systems engineering, which includes system design, hardware and software implementation, virtual replication, and physical-digital two-way synchronization. The system utilizes ESP32-based pH, temperature, dissolved oxygen (DO), ammonia (NH₃), and turbidity sensors, MQTT communication, and Raspberry Pi edge computing. Water quality prediction is performed using long short-term memory (LSTM) and random forest regression. The dataset consists of 30 days of real-time data covering water quality, actuator activity (aerator, pump, feeder), and energy production and consumption by IoT sensors and energy meters. Results show that LSTM excels by R² = 0.94; RMSE = 0.14; MAPE <5% and synchronization latency <1.5 seconds. Solar energy integration reduces energy consumption by 54 67%, whilst automation increases eel survival rate by 78% to 91%. The novelty of this research lies in the first integrated implementation of DT, AIoT, and solar energy-based automation in mud-free eel farming. The proposed framework provides a precise, scalable, and sustainable solution for the development of modern aquaculture.
Volume: 41
Issue: 3
Page: 912-923
Publish at: 2026-03-10

Overvoltage assessment of wind energy integration in low voltage distributed grids

10.11591/ijeecs.v41.i3.pp859-872
Farid Merahi , Badoud Abd Essalam
Large-scale integration of renewable energy (RE) resources into the electrical grid has increased significantly over the last decade, affecting the network at various nodes even at considerable distances from the common connection point. This paper presents an overvoltage assessment caused by the integration of two wind generators (WGs) into a low voltage distribution grid, which is structured into three zones. Two scenarios are studied, the first one considers the low voltage grid without WGs, representing its natural operating condition. In the second scenario, two WGs are connected in zone 3, inducing voltage rises at different nodes within the same zone, by reaching 7.9%, and affecting nodes located in other zones (Zone 1 and Zone 2). The simulation is performed using MATLAB/Simulink (R2025a), and the results obtained are compared to the standards test feeder IEEE 33-bus network, showing the overvoltage caused by WGs integration at nodes close to the connection point while improving voltage quality at distant nodes.
Volume: 41
Issue: 3
Page: 859-872
Publish at: 2026-03-10

Level of detail in UML models and its impact on model comprehension: a replication study

10.11591/ijeecs.v41.i3.pp1095-1104
Ariadi Nugroho , Michel R.V Chaudron
This replication study examines the impact of level of detail (LoD) in unified modeling language (UML) on model comprehension, replicating a controlled experiment, which involved 53 MSc students at Eindhoven University of Technology. Using the same UML model and experimental design, we conducted the study with 23 MSc Computer Science students at Bina Nusantara University, Indonesia. Consistent with the original findings, higher LoD was found to enhance comprehension correctness. However, the effect on comprehension efficiency was weaker and not statistically significant, likely due to the smaller sample size and contextual differences in subjects’ backgrounds. Furthermore, we found a potential disconnect between perception and actual comprehension performance in the subjects receiving UML model with low LoD. Specifically, while they viewed the model favourably, their actual understanding may have been impaired by the limited information and therefore the perceived clarity and ease of comprehension are not reflective of the true comprehension. Overall, this study reinforces the importance of LoD in UML modeling and highlights the need for further replication, particularly in contexts involving professional software engineers.
Volume: 41
Issue: 3
Page: 1095-1104
Publish at: 2026-03-10
1 2 3
...
2012 2013
Show 34 of 2013

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