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

31,456 Article Results

Predicting trapped victims in debris using signal analysis ensemble classification

10.11591/ijai.v15.i1.pp493-505
Enoch Adama Jiya , Ilesanmi B. Oluwafemi , Olayinka O. Ogundile , Oluwaseyi P. Babalola
One major difficulty in pervasive computing is trapped human detection in search and rescue (SAR) scenarios. Accurately identifying trapped individuals is challenging due to noisy data and the curse of dimensionality. When non-line-of-sight (NLOS) conditions are present during catastrophic occurrences, the curse of dimensionality can result in blind spots in detections because of noise and uncorrelated data. Because machine learning algorithms are incredibly accurate, this work focuses on using ultra wideband (UWB) radar waves to detect individuals in NLOS scenarios and leveraging wireless communication to harmonize information. The paper uses ensemble methods to extract features using independent component analysis (ICA) and evaluate classification performance on both static and dynamic datasets. The testing results confirm the effectiveness of the proposed strategy, with classification accuracies of 87.20% for dynamic data and 88.00% for static data. Lastly, during SAR operations, our approach can assist engineers and scientists in making quick decisions.
Volume: 15
Issue: 1
Page: 493-505
Publish at: 2026-02-01

Optimizing Javanese script recognition using fine-tuned ResNet-18 and transfer learning

10.11591/ijai.v15.i1.pp443-453
Nur Fateah , Subhan Subhan , Yahya Nur Ifriza
Javanese script, known as Aksara Jawa, is an ancient script used in historical and cultural texts. However, its complex character structure poses challenges for accurate recognition in modern digital applications. This study proposes an optimized classification approach for Aksara Jawa using a fine-tuned ResNet-18 model combined with the Adam optimization algorithm and transfer learning on the Hanacaraka image dataset. By leveraging the residual learning framework of ResNet-18, the model effectively captures deep spatial features of the script while reducing vanishing gradient issues. Fine-tuning is applied to enhance model adaptability, ensuring robust feature extraction specific to Javanese characters. Experimental results demonstrate that the fine-tuned ResNet-18 outperforms conventional deep learning architectures in recognizing Aksara Jawa characters, achieving 93% precision, 91% recall, 91% F1-score, and 91% accuracy. The study further explores the impact of hyperparameter tuning, data augmentation, and dropout regularization on model performance. The findings highlight the effectiveness of transfer learning in resource-limited scenarios, making it a feasible solution for optical character recognition (OCR) applications in Javanese script digitization. This research contributes to the preservation of cultural heritage through advancements in deep learning-based script recognition.
Volume: 15
Issue: 1
Page: 443-453
Publish at: 2026-02-01

Energy-efficient AI-enhanced secure routing for protecting IoT networks from advanced attacks

10.11591/ijeecs.v41.i2.pp731-739
Leelavathi R. , Vidya A.
This paper proposes artificial intelligence-enhanced secure routing (AIRS), a lightweight AI-enhanced secure routing protocol for internet of things (IoT) networks operating under advanced routing attacks. Unlike existing approaches that treat intrusion detection and routing separately, AIRS tightly integrates anomaly scoring into trust-aware routing decisions using a compact random forest model designed for constrained nodes. The anomaly detector is trained offline on simulated IoT traffic features and deployed for real-time inference during routing. Extensive Cooja simulations demonstrate that AIRS improves intrusion detection accuracy and packet delivery while reducing energy consumption compared to secure-RPL and trust-LEACH. The current validation is limited to simulation environments, and real-world testbed evaluation is left for future work.
Volume: 41
Issue: 2
Page: 731-739
Publish at: 2026-02-01

Adversarial examples in Arabic language

10.11591/ijai.v15.i1.pp941-952
Safae Laatyaoui , Mohammed Saber
Adversarial attacks have a great popularity in the artificial intelligence (AI) domain. In the natural language processing (NLP) field, various techniques have been used to evaluate the vulnerability of deep learning (DL) models. It is observed that while most studies focused on generating adversarial examples in English language, Arabic adversarial attacks have received little attention. This paper presents a two-step method to create adversarial examples in Arabic language: first, the most important words are identified. Then, the proposed transformation algorithm is applied. Only small and imperceptible manipulations based on common mistakes in Arabic writing mislead the popular pre-trained language model (PLM) bidirectional encoder representations from transformers (BERT) retrained on the book reviews in Arabic dataset (BRAD) on the sentiment analysis (SA) task and decrease its performance: the classification accuracy was reduced by an average of 3.44%. This drop in accuracy shows that the model was successfully attacked.
Volume: 15
Issue: 1
Page: 941-952
Publish at: 2026-02-01

Stroke prediction using data balancing method and extreme gradient boosting

10.11591/ijai.v15.i1.pp655-671
Abd Mizwar A. Rahim , Anna Baita , Firman Asharudin , Wahid Miftahul Ashari , Walidy Rahman Hakim , Andriyan Dwi Putra , Supriatin Supriatin , Eko Pramono
Stroke is one of the leading causes of death worldwide, creating an urgent need for effective early detection systems, particularly because conventional methods often struggle with class imbalance and produce biased evaluations. Previous studies have primarily focused on accuracy while overlooking model consistency, data pre-processing quality, and probability-based evaluation. This study evaluates model performance under three conditions: original data using extreme gradient boosting (XGBoost) with scale_pos_weight, original data using the easy ensemble classifier, and class-balanced data generated using random oversampling (ROS), adaptive synthetic sampling (ADASYN), and synthetic minority over-sampling technique (SMOTE). Each model underwent missing value handling, normalization, feature preparation, and hyperparameter optimization using grid search. Performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), confidence intervals, calibration curves, Shapley additive explanations (SHAP), decision curve analysis (DCA), and external validation. The results demonstrate that data resampling significantly improves performance, with the XGBoost-SMOTE combination achieving the best results, including an accuracy of 0.99, AUROC of 0.998, and AUPRC of 0.986, outperforming the other approaches. This method provides more consistent and balanced predictions, supporting the application of artificial intelligence for early stroke risk identification.
Volume: 15
Issue: 1
Page: 655-671
Publish at: 2026-02-01

Automated ergonomic sitting postures detection for office workstation using XGBoost method

10.11591/ijai.v15.i1.pp506-514
Theresia Amelia Pawitra , Farida Djumiati Sitania , Anindita Septiarini , Hamdani Hamdani
Sedentary office work increases musculoskeletal risk, underscoring the need for non-intrusive, real-time posture monitoring. This study presents a computer vision approach that classifies ergonomic versus non-ergonomic sitting postures using upper body key points extracted by MoveNet thunder. Images from 30 participants were captured from frontal and side views, and labeled according to SNI 9011:2021 criteria. Seventeen key points were detected, with head-to-hip landmarks retained, then normalized and centered. Three classifiers—adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and a multi-layer perceptron (MLP)—were trained and evaluated with 10-fold stratified cross-validation. XGBoost achieved the best performance, with accuracy 93.0%±1.9%, precision 94.6%, recall 91.4%, F1-score 92.9%, and area under the receiver operating characteristic curve (ROC-AUC) 0.974±0.010, outperforming MLP and AdaBoost. The method supports privacy-preserving, on-device inference and is suitable for integration into smart office systems to reduce exposure to high-risk postures. Limitations include controlled capture conditions and an upper body focus; future work will expand posture taxonomy and real-world deployment.
Volume: 15
Issue: 1
Page: 506-514
Publish at: 2026-02-01

Multi-scale features assisted knowledge distillation vision transformer for land cover segmentation and classification

10.11591/ijai.v15.i1.pp361-373
Sujata Arjun Gaikwad , Vijaya Musande
The most significant problem in remote sensing interpretation is semantic segmentation, which attempts to give each pixel in the image a particular class. This research work follows the various steps, such as pre-processing, segmentation, and classification. Initially, high spatial resolution remote sensing images (RSI) are collected from the open-source dataset. In the pre processing stage, an improved guided filter (Imp-GF) is used to remove various noises from images. Next, the segmentation is done by using a knowledge distillation-based vision transformer approach integrated with an atrous spatial multi-scale pyramidal module (KD-MuViTPy). Based on the segmented image, land cover classes such as vegetation, urban areas, forest, water bodies, and roads are classified. The proposed method outperformed the Bhuvan satellite dataset, achieving better accuracy, precision, recall, F1 score, Dice score, intersection over union (IoU), and Kappa score at values of 98.01%, 98.99%, 97.49%, 98.23%, 98.23%, 96.55%, and 95.91%, respectively.
Volume: 15
Issue: 1
Page: 361-373
Publish at: 2026-02-01

Explainable rice yield from Sentinel-1 and Sentinel-2 satellite data for food security

10.11591/ijai.v15.i1.pp615-627
Dhimas Tribuana , Usman Sattar , Baharuddin Mide , Dayanti Dayanti
Reliable, explainable crop-yield estimates are essential for food-security planning in data-sparse regions. We present a transparent pipeline for district-level (regency) rice yield prediction in Indonesia that fuses Sentinel-1 synthetic aperture radar (SAR), Sentinel-2 normalized difference vegetation index (NDVI), and weather/reanalysis features. The system standardizes inputs per province, fixes a 16-day temporal key, and uses a small, auditable ensemble of tree models (gradient boosting+light gradient-boosting machine (LightGBM)). Trained on ≤2023 data and evaluated on a 2024 temporal hold-out, a joint West Java ∪ South Sulawesi model achieves root mean square error (RMSE)≈0.80 t/ha, mean absolute error (MAE)≈0.48 t/ha, and R-squared (R²)≈0.33 at regency scale. Feature importances and Shapley additive explanations (SHAP) confirm that phenology (NDVI peak, integral, green-up/senescence), SAR backscatter (vertical transmit-vertical receive/vertical transmit-horizontal receive (VV/VH)), and wind/pressure are consistent drivers under monsoon conditions. The workflow supports routine, one-click provincial updates and produces parity maps and error bars for actionable diagnostics. These results demonstrate that combining Sentinel-1, Sentinel-2, and basic meteorology delivers accurate, interpretable, and operational yield signals suited to Indonesia’s food security needs, while providing a clear recipe for scaling to additional provinces.
Volume: 15
Issue: 1
Page: 615-627
Publish at: 2026-02-01

Anefficient ensemble tree-based framework for intrusion detection in industrial internet of things networks

10.11591/ijai.v15.i1.pp481-492
Mouad Choukhairi , Oumaima Chentoufi , Ouail Choukhairi , Youssef Fakhri
The increasing complexity of cyber threats in industrial internet of things (IIoT) environments necessitates robust, scalable, and efficient intrusion detection systems (IDS). This study presents a novel ensemble tree-based framework that integrates gradient boosting-based machine learning models, including XGBoost, LightGBM, AdaBoost, and CatBoost, with mutual information (MI) feature selection and synthetic minority over-sampling technique (SMOTE) to enhance multiclass intrusion detection performance. The framework is designed to handle large-scale, imbalanced datasets efficiently while maintaining high classification accuracy. Performance evaluation using the telemetry of network (ToN)-IoT benchmark dataset demonstrates that the proposed models achieve a high accuracy of 99.43%, with a strong precision-recall balance and an F1-score, ensuring minimal false positive rates of 0.08%. By leveraging MI for optimal feature selection and SMOTE for data balancing, this approach effectively enhances detection capabilities in highly dynamic network environments. The lightweight architecture and reduced execution time make the framework well-suited for deployment in edge or fog nodes within smart industrial environments. The proposed solution provides a scalable and adaptable methodology for securing IIoT networks, making it applicable for real-time intrusion monitoring and further cybersecurity advancements in industrial systems.
Volume: 15
Issue: 1
Page: 481-492
Publish at: 2026-02-01

An efficient method to improve machine learning decoders using automorphisms group

10.11591/ijai.v15.i1.pp547-558
Imrane Chemseddine Idrissi , Said Nouh , El Mehdi Bellfkih , Mohammed El Assad , Abdelaziz Marzak
The decoding of error-correcting codes (ECCs) is a critical aspect of communication systems, yet traditional decoding techniques can often be computationally demanding or ineffective for certain codes, necessitating innovative approaches. In this study, we introduce a hybrid approach that combines machine learning and automorphism techniques to optimize the decoding process. Specifically, we train multilayer perceptron (MLP) models to learn the mapping between error syndromes and their corresponding errors. While these models exhibit robust learning capabilities, their performance sometimes does not reach 100%. To mitigate this limitation, we exploit the automorphism group of the code—a set of structure-preserving transformations—to convert the errors that the MLP struggles to decode into ones it can process more effectively. We use a minimum number of p permutations, pre-calculating and storing all possible automorphisms to ensure computational efficiency. Our experimental results reveal that this hybrid approach substantially enhances the decoding performance of the MLP model, presenting a promising avenue for decoding ECCs. Importantly, this approach is not limited to MLP models and can be applied to any machine learning model with a learning score less than 100%, broadening its applicability and impact. By integrating machine learning with traditional algebraic coding theory, we propose a new paradigm that holds the potential to revolutionize the design of decoding systems, making them more efficient and effective.
Volume: 15
Issue: 1
Page: 547-558
Publish at: 2026-02-01

Scalable resume screening using large language model Meta AI version 3

10.11591/ijai.v15.i1.pp953-961
Asmita Deshmukh , Anjali Raut , Vedant Deshmukh
This research paper explores the use of large language model Meta AI 3 (LLaMA 3) for automating the resume screening process. Traditional resume screening methods that rely on keyword searching and human review can be inefficient, biased, and fail to identify qualified candidates. LLaMA 3, trained on large-scale text datasets, has the potential to accurately analyze resumes by understanding context and semantic details beyond simple keyword matching.The study presents a system that converts resume PDFs to text, inputs the text along with the job description into the LLaMA 3 model, and generates a ranked list of candidates with reasoning for their job fit. This discusses the data preparation, model setup, and performance evaluation of this system. Results show LLaMA 3 can rapidly process batches of resumes while reducing human bias in the screening process. The system aims to streamline hiring by automating the initial resume screening stage to surface top candidates for further in-depth evaluation. Key benefits include improved accuracy in identifying relevant skills, reduced bias compared to human screeners, and significant time savings for recruiters. The paper also examines ethical considerations around using AI for hiring decisions. Overall, this work demonstrates the promising application of large language models (LLMs) like LLaMA 3 to transform and enhance resume screening practices.
Volume: 15
Issue: 1
Page: 953-961
Publish at: 2026-02-01

The Bender’s decomposition model to optimize temporary waste disposal sites based on general algebraic modeling system

10.11591/ijeecs.v41.i2.pp666-679
Sisca Octarina , Fitri Maya Puspita , Endro Setyo Cahyono , Evi Yuliza , Pebriyanti Simanjuntak , Siti Suzlin Supadi
Waste constitutes a substantial problem in urban and residential locales, as the volume of refuse escalates in tandem with population increase, deteriorating community quality of life. One solution to this problem is to provide temporary waste disposal sites (TWDS). This research discussed optimizing TWDS in the Sukarami Subdistrict, Palembang City, which consists of seven villages. The current TWDS in the Sukarami Subdistrict is irregular, with some sites located close together and others far apart. The optimization problem is solved by formulating the set covering problem (SCP) model, namely the set covering location problem (SCLP), the p-Median problem, and the Bender’s decomposition model. All models were solved using the general algebraic modeling system (GAMS) software. The research introduces a Bender’s decomposition model based on the SCLP model. The Sukarami Subdistrict has 29 TWDS located in only five villages. Using the SCLP and Bender’s decomposition models, the study identified 19 optimal TWDS in the Sukarami Subdistrict. Based on the solution of the p-Median problem, there are seven TWDS that can meet each village’s demand. This study recommends the optimal TWDS obtained from the Bender’s decomposition model. Additionally, two TWDS are recommended to be added, each in Sukodadi and Talang Betutu villages.
Volume: 41
Issue: 2
Page: 666-679
Publish at: 2026-02-01

Botnet detection: a system for identifying DGA-based botnets using LightGBM

10.11591/ijeecs.v41.i2.pp833-844
Mumtazimah Mohamad , Nazirah Abd Hamid , Sanaa A. A. Ghaleb , Siti Dhalila Mohd Satar , Suhailan Safei , Wan Mohd Amir Fazamin Wan Hamzah , Lim En En
Botnets present a major challenge to detecting anomalies in domain generation algorithms (DGAs). Botmasters use DGAs to create numerous domain names to communicate with command-and-control servers, complicating the detection process. Traditional blacklisting methods struggle to effectively identify anomalous DGA domain names amid the vast number of randomly generated domains, leading to a greater risk of detection being evaded. The proliferation of DGA-based botnets has created an urgent need for robust detection methods. Various techniques and attributes have been utilised to categorise different DGA families, yet the dynamic nature of DGA domain names renders the current blacklisting algorithms ineffective. Additionally, the dynamic characteristics of DGAs further complicate classification, emphasising the need for machine learning models to improve detection accuracy and enhance cyber defence. This study proposes a robust solution to address the challenges posed by DGA-based botnets by developing an innovative machine learning-based model for domain name classification. The model leverages the light gradient boosting algorithm (LightGBM) and integrates n-gram features to enhance the detection of malicious DGA domains. This approach offers superior accuracy, adaptability, and efficiency in identifying and classifying anomalous domain names, achieving 96% precision when detecting true DGA domains. This system represents a significant advancement in cybersecurity and anomaly detection.
Volume: 41
Issue: 2
Page: 833-844
Publish at: 2026-02-01

Contextualized clinical anomaly detection with explainable AI and patient modeling

10.11591/ijeecs.v41.i2.pp614-623
Amel Elketroussi , Bachir Djebbar , Ibtissem Bekkouche
This study aims to reduce alarm fatigue and improve the clinical relevance of alerts in intensive care by combining sequential modeling, patient contextualization, explainable artificial intelligence (XAI), and probability calibration. To this end, we leverage the adult cohorts from MIMIC-III/IV, segmented into four-hour windows, explicitly handling missing data and constructing a context vector that integrates demographics, comorbidities, and therapeutic interventions. The approach relies on a tabular autoencoder, an long short-term memory (LSTM) autoencoder, and a transformer, complemented by an adjustment layer based on auditable clinical rules, local explanations (LIME/SHAP), and post-hoc calibration (temperature scaling). Evaluation involves receiver operating characteristic (ROC)/precision–recall (PR) area under the curve (AUC), F1-score, sensitivity and specificity, as well as calibration metrics (ECE, Brier score), alert burden, ablation studies, robustness tests, and subgroup fairness analyses. Across all experiments, the complete model (+Context+XAI+Calibration) outperforms baselines in AUPRC and F1, reduces alert burden, and improves calibration while providing understandable explanations. Specifically, the proposed model improves ROC AUC from 0.74 to 0.89 and reduces alert burden by approximately one third compared to clinical thresholds.
Volume: 41
Issue: 2
Page: 614-623
Publish at: 2026-02-01

An investigation of different low-power circuits and enhanced energy efficiency in medical applications

10.11591/ijeecs.v41.i2.pp478-493
Prabhu R , Sivakumar Rajagopal
This research investigates the application of low-power circuits in medical devices and imaging systems. The primary goal is to address the growing demand for energy-efficient solutions in medical applications. There is an increasing need for energy-efficient solutions due to the development of medical technologies, particularly implanted and battery-operated medical devices. This paper explores the integration of adiabatic logic as a critical enabler for achieving low power consumption in medical applications. The study looks into different low-power circuit designs and technologies that optimize power usage without sacrificing performance. Adiabatic circuits offer a promising substitute for conventional circuitry in low-energy design. The research examines several low-power circuit designs and technologies that maximize power efficiency without compromising functionality. In low-energy design, adiabatic circuits present a possible alternative to traditional circuitry. Adiabatic logic aims to create energy-efficient digital circuits that consume significantly less power than conventional complementary metal-oxide-semiconductor (CMOS) circuits. We accomplish this by recovering and recycling energy that would otherwise be lost as heat and carefully controlling energy flows during switching events. Adiabatic logic is precious in battery-operated and energy-constrained devices.
Volume: 41
Issue: 2
Page: 478-493
Publish at: 2026-02-01
1 2 3
...
2097 2098
Show 141 of 2098

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