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

31,291 Article Results

Dual view explainability-aware log preprocessing for robust anomaly detection toward ER-CyRIS

10.11591/ijeecs.v43.i3.pp871-879
Fathoni Mahardika , Ema Utami , Kusrini Kusrini , Ferry Wahyu Wibowo
Machine learning based intrusion detection can achieve strong benchmark performance yet remain fragile under operational telemetry changes. This paper proposes a dual-view, explainability-aware log preprocessing layer for robust anomaly detection toward ER-CyRIS. The novelty is the use of dynamic-token preservation together with feature stability score (FSS), which turns SHapley additive exPlanations (SHAP)-ranking stability into a preprocessing-level evaluation criterion rather than a post-hoc explanation only. The layer preserves structural log patterns and contextual dynamic tokens, and is evaluated through detection performance, noise degradation, and SHAP-ranking stability. A leakage-controlled ablation on HDFS, BGL, CICIDS2018, and UNSW-NB15 shows that the CICIDS2018 baseline reached F1 = 0.9999 but degraded by 68.1% for XGBoost and 93.9% for random forest under small Gaussian noise. Contextual preprocessing reduced degradation to 58.7%, 54.9%, and 53.6% in selected settings. FSS reached 100% for XGBoost on HDFS and CICIDS2018. The results show that preprocessing mitigates, but does not eliminate, operational brittleness.
Volume: 43
Issue: 3
Page: 871-879
Publish at: 2026-09-01

Automated recognition of Thai fabric patterns using transfer learning with ResNet-50

10.11591/ijeecs.v43.i3.pp847-856
Kittiya Poonsilp , Pijitra Jomsri , Dulyawit Prangchumpol , Thammarat Panityakul
Traditional Thai fabric patterns are valuable cultural heritage, but expert knowledge of these patterns is declining. This study uses a convolutional neural network (CNN) with transfer learning (ResNet-50) to classify traditional Thai fabric patterns automatically. We collected 961 images across 19 pattern categories, split into training (57%), validation (11%), and test (32%) sets. Using ImageNet pre-trained weights and progressive fine-tuning, the model achieved 99.68% test accuracy with macro-averaged F1-score of 99.35%. Ablation studies validated our approach: augmentation improved accuracy by 2.26%, fine-tuning outperformed frozen backbone by 4.84%, and backbone comparison showed ResNet-50 achieves higher F1-score than MobileNetV2 while MobileNetV2 offers 90% parameter reduction for mobile deployment. Controlled stress tests demonstrated robustness under image degradations typical of smartphone photography. Unlike previous studies using controlled conditions, our dataset includes real-world variations. These results show that transfer learning with small datasets can match expert-level pattern recognition for cultural heritage preservation.
Volume: 43
Issue: 3
Page: 847-856
Publish at: 2026-09-01

Low-cost BLDC drive with PBBO-tuned FOPID controller for enhanced speed regulation and torque ripple reduction

10.11591/ijeecs.v43.i3.pp956-964
Pandi Maharajan M. , Rohini G. , Ravindran Ramkumar , Dharani Kumar Narne
Torque ripple (TR) minimization in brushless DC (BLDC) motors has become a critical research focus due to its direct impact on drive performance, efficiency, and reliability. Conventional BLDC drives typically employ large DC-link capacitors, which increase system cost and weight and are highly sensitive to operating temperature, thereby reducing lifetime. To address these limitations, this work proposes a low-cost capacitor-based BLDC drive integrated with a torque ripple compensation (TRC) technique and optimized control using the probabilistic biogeography-based optimization (PBBO) algorithm. The PBBO method is employed to tune the parameters of a fractional-order proportional-integral-derivative (FOPID) controller, ensuring effective speed regulation and TR reduction. By probabilistically refining migration and emigration rates, PBBO enhances convergence and eliminates redundant species movements, leading to superior controller parameter optimization. Simulation studies validate the proposed PBBO-FOPID approach, demonstrating significant improvements in TR reduction and speed control compared to conventional controllers such as DGOA-FOPID and spider web-based controller (SWC). Results confirm that the PBBO-FOPID controller achieves smoother torque response, reduced ripple, and enhanced speed regulation, establishing it as a cost effective and high-performance solution for BLDC motor drives.
Volume: 43
Issue: 3
Page: 956-964
Publish at: 2026-09-01

Automated smart handbag with enhanced women's safety using cutting edge technology

10.11591/ijra.v15i3.pp669-677
Vijayaraja Loganathan , Dhanasekar Ravikumar , Ashish Ragavendra Nattamai Uthayakumar , Arulmurugan Nagarajan Renukadevi , Rishikeshwaran Balamurugan Rani , Rupa Kesavan
Women’s safety has been an area of concern, especially in public places where timely assistance cannot be provided. To mitigate this problem, this paper proposes an intelligent handbag-based women’s safety system that utilizes the concept of biometric identification, location tracking, and edge computing-based AI threat verification. The proposed system, unlike other traditional women’s safety devices that rely on GPS-GSM for emergency alerts and are more likely to send false alarms, utilizes fingerprint identification for secure and authorized use, along with YOLO v3 vision model on an ESP32-CAM for threat verification. Upon failure in the authentication process or threat detection, the system sends an SOS message with the current location via GSM with the help of GPS coordinates. The system achieves an emergency response time of 33 seconds, primarily limited by GPS acquisition delay. The results confirm the effectiveness and applicability of the proposed system in providing an intelligent emergency response system for women’s safety.
Volume: 15
Issue: 3
Page: 669-677
Publish at: 2026-09-01

URL-based phishing detection using XGBoost with engineered features

10.11591/ijeecs.v43.i3.pp908-927
Jawaher Alharbi , Manal Bayousef , Hind Almisbahi
URL-based phishing involves fake uniform resource locators (URLs) created by attackers to trick users into believing they are visiting a legitimate website and thereby steal their confidential information. While several powerful machine learning (ML) and deep learning (DL) studies exist to detect phishing, they still face limitations. Many studies rely on third-party intervention to extract features, which introduces delays that make them unsuitable for fast detection. Another limitation is that existing studies often use small datasets, and traditional features hinder models' ability to learn new phishing techniques, resulting in poor generalization. Therefore, developing new features is crucial to ensure that anti-phishing tools can keep pace with evolving phishing tactics. In addition, the existing studies do not report detection time, which is important for fast detection, and reduces methodological clarity. This paper aims to address these limitations by applying a neural network model and traditional ML classification algorithms to support browser-based phishing detection that balances high accuracy with fast detection. Our XGBoost model achieved 98% accuracy on the test set, utilizing 40 third-party-independent features. Additionally, we achieved an average response time of 0.026225 seconds and an average computation time of 1.6977×10⁻6 seconds per URL, which demonstrates competitive speed. We provided a table of features from recent studies, together with their documented sources, to support future research and analyze key URL-based features.
Volume: 43
Issue: 3
Page: 908-927
Publish at: 2026-09-01

Optimal robust control for self-balancing robot-based feedback linearization and Atom Search Optimization

10.11591/ijra.v15i3.pp519-528
Alaa Jumaah Al-Maiahy , Yahya Ghufran Khidhir , Adnan Jabbar Attiya , Hisham H. Jasim
In this paper, a robust control method is suggested for attitude control of the two-wheeled self-balancing robot by combining feedback linearization with sliding mode control techniques. The proposed method takes into account important challenges such as external disturbance and system uncertainty. Feedback linearization cancels the nonlinearities in the dynamics of the robotic system, while the sliding mode control handles the uncertainties and the external disturbance. The parameters of the proposed controller are selected by tuning the controller with the Atom Search Optimization algorithm. MATLAB is used to simulate the proposed controller. Simulation results indicate a good performance of the presented controller with high robustness compared with the proportional-integral-derivative (PID) controller. Moreover, the proposed method reduces the rise time by approximately 40% and 50% with respect to PID. These results illustrate the feasibility of the presented control method to be used for real-time implementation in autonomous robotic balancing systems.
Volume: 15
Issue: 3
Page: 519-528
Publish at: 2026-09-01

Amaranthus dubius seeds oil extraction using green solvent approach with terpenes

10.11591/ijaas.v15.i3.pp964-974
Rachma Tia Evitasari , Gita Indah Budiarti , Endah Sulistiawati , Adi Permadi , Ika Dyah Kumalasari , Nazira Mahmud , Nor Adila Mhd Omar
This research will explore the potential for utilizing wild amaranth (Amaranthus dubius) seeds, which are abundant and have not been utilized in Indonesia. This research will focus on optimizing the amaranth seed oil extraction process using the response surface method and the characteristics of the oil produced from amaranth seeds. The solvent used in this research is a biobased green solvent, terpenes. This research aims to explore the potential of utilizing wild amaranth seeds by optimizing the oil extraction process using a biobased green solvent, terpenes, through the response surface methodology (RSM). Fourier transform infrared spectroscopy (FTIR) results indicate that the terpenes solvent contains various terpenoids such as α-pinene, β-pinene, and camphene. By applying ultrasound-assisted extraction (UAE) and optimizing the critical process parameters (liquid-to-solid ratio, extraction temperature, and extraction time) through a Box-Behnken RSM design, the maximum oil yield was achieved under environmentally friendly conditions. The optimum condition was reached at a solvent-to-solid ratio of 5.13 ml/0.1 g, a temperature of 49.39 °C, and an extraction time of 47 minutes. With these optimal parameters, the predicted oil yield was 2.04%. The optimized extraction not only delivered a high-quality oil-rich extract but also minimized solvent residue, energy consumption, and hazardous emissions.
Volume: 15
Issue: 3
Page: 964-974
Publish at: 2026-09-01

Multilevel local region sparse shape composition model for liver cancer classification

10.11591/ijaas.v15.i3.pp932-943
Balasubramanian Sakthisaravanan , Ramakrishnan Meenakshi , Thirugnanasambandam Akila , Saravanan Durga Devi , Subbiah Murugan
Machine learning and computer-assisted disease detection are two technological innovations that have significantly improved medical advancement, and recent research has demonstrated their effectiveness. Liver cancer is one of the important causes of cancer-related deaths internationally. Tumor detection in the liver and its classification is challenging due to poor accuracy and high processing requirements available in the existing techniques. In these, there is a loss of edge information and the quality of the images considered. To address these issues in the segmentation and classification of liver cancer, a novel feature extraction method and algorithm called the novel multilevel local region (MLR)-based sparse shape composition model (NMLR-SSC) were developed. This innovative technique identifies the existence of tumors on abdominal computed tomography (CT) images. The input images were obtained from the 3D-IRCADb-01 dataset. The algorithm showed an improvement of 0.22%. When compared to other classifiers. The proposed algorithm showed 100% specificity, sensitivity, and a 98% accuracy rate in detecting the liver tumor.
Volume: 15
Issue: 3
Page: 932-943
Publish at: 2026-09-01

Interpreting potato disease classification using explainable artificial intelligence

10.11591/ijaas.v15.i3.pp1123-1130
Rakesh Kumar Gumasta , Ajay Somkuwar
Timely and accurate crop diseases detection is most important for ensuring global food security. For detecting diseases in crops, many different machine learning (ML) models were proposed. These models work as a black-box, and without proper explanation of these models’ decisions, farmers may find it difficult to trust these systems. For this, many model explainability methods were also proposed. All these methods have been evaluated qualitatively, but their quantitative and cross-comparison are missing. This study addresses this gap by emphasizing quantitative validation of models’ explanations. This study investigates the interpretability and performance of two approaches for potato leaf disease classification: i) manual feature engineering with relief-based feature selection and artificial neural network (ANN) classification with local interpretable model-agnostic explanations (LIME) and ii) deep convolutional neural networks (CNNs) based on mobile network version 2 (MobileNetV2) with gradient-weighted class activation mapping (Grad-CAM). Quantitative assessment of explanation quality was performed using fidelity and robustness metrics. While LIME achieved a lower average fidelity drop 10.90% and higher robustness 84.27% compared to Grad-CAM 18.68% fidelity drops and 79.38% robustness, Grad-CAM provided clearer visual explanations. These findings suggest that explanation effectiveness is influenced by model design and data characteristics, highlighting the need for careful selection of interpretability techniques in precision agriculture applications.
Volume: 15
Issue: 3
Page: 1123-1130
Publish at: 2026-09-01

Quantification and traceability of mango by-products in the Hauts-Bassins and Cascades regions of Burkina Faso

10.11591/ijaas.v15.i3.pp1059-1071
Wendkouni Marguerite Bamogo , Hyacinthe Kante-Traore , Bakary Tarnagda , Boureima Kagambèga , Charles Parkouda , Aly Savadogo
This study provides a regional analysis of mango by-product generation and traceability in the Hauts-Bassins and Cascades regions of Burkina Faso. Through field surveys conducted in samples of 89 processing units and stakeholder mapping, the study quantifies the volume and flow of mango residues and identifies key stakeholders and bottlenecks in the post-harvest chain. Although traceability practices remain largely manual, the study identifies opportunities for digital integration and the added value of utilizing by-products in agro-industrial applications. A total of 52,691 tons of fresh mangoes were processed, primarily from seven varieties. Five types of by-products were identified, with peels, kernels, and sorting waste being the most prevalent. These by-products represented 49.66% of the total processed mango mass. Most by-products were discarded indiscriminately, with only minimal portions allocated to livestock feed (1%) and agriculture (2%). Physical analyses conducted in drying units and laboratories revealed that processing methods significantly increased by-product generation, resulting in pulp losses of up to 31.8%. These results provide a foundation for optimizing the utilization of mango by-products in Burkina Faso through technological innovations. The findings support strategic planning for sustainable resource management and lay the groundwork for the future deployment of traceability systems in tropical agricultural contexts.
Volume: 15
Issue: 3
Page: 1059-1071
Publish at: 2026-09-01

Predicting perceived information overload from social media use: a machine learning approach

10.11591/ijaas.v15.i3.pp1147-1154
Mohamad Noorman Masrek , Endang Fitriyah Mannan , Zulfatun Sofiyani , Atiqa Nur Latifa Hanum
The rapid growth of social media has intensified users’ exposure to large volumes of information, increasing the risk of perceived information overload. While prior studies have primarily examined this phenomenon using explanatory models, limited attention has been given to its prediction. This study aims to predict perceived information overload from social media use using a machine learning approach. Data were collected through a survey of 349 university students in Malaysian higher education institutions. Social media use across multiple platforms was used as input features, while perceived information overload was treated as a binary target variable. Several machine learning algorithms were evaluated, including decision tree, random forest, k-nearest neighbor, support vector machine, neural network, naïve Bayes, and logistic regression. The results indicate that social media usage patterns contain predictive value for identifying information overload, with the support vector machine demonstrating the strongest discriminative performance. The study contributes to the literature by complementing existing explanatory research with a predictive perspective and highlights the potential of machine learning techniques for early identification of information overload in social media environments.
Volume: 15
Issue: 3
Page: 1147-1154
Publish at: 2026-09-01

Hybrid lightweight encryption and searchable security framework for secure VANET image and text data sharing

10.11591/ijaas.v15.i3.pp1006-1014
Fairouz Sherali , Falah Hasan Sarhan
The increasing reliance on vehicular ad hoc networks (VANETs) for instantaneous traffic orchestration and data exchange highlights the need for robust, efficient, and privacy preserving security solutions. Classical encryption methods often fail to meet the low-latency and lightweight requirements of vehicular environments. In this study, a hybrid cryptographic framework was designed that integrates searchable encryption (SE) with the Spritz stream cipher, targeting secure keyword-based access to encrypted data. By leveraging bilinear pairing for identity-based key management, the system enables flexible authentication and secure updates. Both text and image data are supported, with minimal computational overhead. Experimental results validate the feasibility of the approach in dynamic, resource-limited vehicular networks.
Volume: 15
Issue: 3
Page: 1006-1014
Publish at: 2026-09-01

Optimization-enabled machine learning with feature selection for phishing detection system

10.11591/ijaas.v15.i3.pp1131-1146
Lukman Adebayo Ogundele , Julius Temitayo Adepoju , Femi Emmanuel Ayo , Idayat Abike Akano , Abidemi Emmanuel Adeniyi , Halleluyah Oluwatobi Aworinde , Oluwasegun Julius Aroba , Gbohunmi Ajibesin
The rapid evolution of phishing methods has long been a threat to cybersecurity that demands adaptive and intelligent detection techniques. This current work envisions an improved phishing detection system that involves the integration of machine learning (ML) with feature selection for improving the performance of real-time classification. A comprehensive dataset was optimized and preprocessed through Chi-square (CHI) feature selection to reduce dimensionality while preserving the most discriminative features. Random forest (RF) algorithm, selected for its robustness, interpretability, and high computational efficiency for binary classification, was employed and achieved an accuracy of 96.25%, effectively identifying sophisticated phishing attacks. The architecture is designed to operate on large datasets with minimal computational overhead but with high precision and scalability. Experimental results also indicate the dependability of the system with an area under the curve (AUC)-receiver operating characteristic (ROC) score of 1.0, indicating perfect separation of phishing from normal cases. In addition, an adaptive classification model was used to accommodate unknown data sets with a 100% accuracy score. The results above identify the potential of adaptive, feature-optimized ML systems in the ability to handle dynamic phishing attacks and enable proactive cybersecurity defense.
Volume: 15
Issue: 3
Page: 1131-1146
Publish at: 2026-09-01

Space vector control for multilevel static synchronous compensator in wind energy systems

10.11591/ijaas.v15.i3.pp1270-1285
Gundala Muni Reddy , Ammapalli Hema Sekhar , Selika Narasimha Rao , Kuruna Divakar , Kola Murali Kumar , Nathella Munirathanm Giri Kumar , Gunti Kishor Babu , Vayyala Jyothsna Priya
To meet the higher demand for energy, fossil fuels have been the leading energy source. These fuels produce greenhouse gases (GHG) and these gases are the reason for climate change, and the fossil fuel resources are also running out quickly. Because of this, lawmakers need to switch to clean and renewable energy sources, including solar, geothermal, wind, tidal, and biomass. The wind energy industry has developed a lot because of new technologies, which has led to more wind turbines (WTs) being connected to the grid. Integrating a lot of WTs into the grid has caused challenges like power quality (PQ), grid stability, and reactive power correction. This study utilizes a multilevel inverter-based static synchronous compensator (STATCOM) with a space vector hysteresis current controller (SVHCC) to mitigate the impacts of WTs. The proposed control strategy improves PQ by reducing total harmonic distortion (THD) and maintaining unity power factor (UPF) even in the presence of nonlinear load and induction generator (IG). The desired results are obtained with a lower switching frequency, thereby improving efficiency and reducing stress on power electronic devices. The proposed SVHCC-based STATCOM is modelled and evaluated using MATLAB/Simulink, and its performance is compared with both uncompensated system and a simple hysteresis current controller (SHCC)-based STATCOM.
Volume: 15
Issue: 3
Page: 1270-1285
Publish at: 2026-09-01

Novel bat algorithm for short-term peak load forecasting in Sulselrabar electricity system

10.11591/ijaas.v15.i3.pp1334-1346
Muhammad Rais , Rosihan Aminudin , Asnefi Asnefi , Andi Nur Putri , Irwan Syarif , Muhammad Ruswandi Djalal
This study addresses short-term load forecasting (STLF) in the South, Southeast, and West Sulawesi (Sulselrabar) power system, Indonesia, using interval type-2 fuzzy logic (IT2FL) optimized by the proposed novel bat algorithm (NBA). The NBA is employed to optimize the footprint of uncertainty (FOU) of the fuzzy membership functions for both antecedent (X and Y) and consequent (Z) variables. The forecasting model utilizes daily peak load data from the previous four days (d−4 to d−1) to predict the peak load of the forecast day (d). To evaluate the effectiveness of the proposed approach, NBA is benchmarked against particle swarm optimization (PSO), firefly algorithm (FA), and cuckoo search algorithm (CSA). The results demonstrate that the proposed IT2FL–NBA model provides the highest forecasting accuracy among the evaluated methods, achieving a mean absolute percentage error (MAPE) of 1.5650%. In comparison, IT2FL–PSO, IT2FL–FA, and IT2FL–CSA achieve MAPEs of 1.6353%, 1.6451%, and 1.6353%, respectively. For type-1 fuzzy logic (IT1FL), the NBA, PSO, FA, and CSA optimization methods produce MAPEs of 1.6668%, 1.6842%, 1.6805%, and 1.6768%, respectively. These findings demonstrate that optimizing the FOU of IT2FL using the proposed NBA significantly improves forecasting accuracy and provides a robust and reliable approach for STLF in power systems.
Volume: 15
Issue: 3
Page: 1334-1346
Publish at: 2026-09-01
1 2 3
...
2086 2087
Show 19 of 2087

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