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

29,905 Article Results

Deep learning ensembles for lung cancer detection in thoracic CT scans leveraging generative adversarial network technology

10.11591/ijai.v15.i2.pp1605-1612
Bineesh Moozhippurath , Jayapandian Natarajan
Effective treatment of lung cancer depends on early and accurate detection, which continues to be a major cause of cancer-related fatalities globally. Conventional diagnostic techniques are useful, but their efficacy in handling large amounts of thoracic computed tomography (CT) scan data is limited by their time-consuming nature and susceptibility to human error. The research here suggests a new deep learning model that integrates generative adversarial networks (GANs) for data improvement with a sophisticated ensemble approach to classification. GANs are employed to generate realistic synthetic CT images, addressing the challenges of limited datasets. The backbone of the proposed approach is a consensus-guided adaptive blending (CGAB) ensemble model that learns to dynamically combine the predictions of three top-performing convolutional neural networks (CNNs): ResNet-152, DenseNet-169, and EfficientNet-B7. The CGAB model improves prediction accuracy through model contribution weighting based on confidence scores and inter-model consensus, while a conflict-resolving auxiliary decision model is used. The approach was tested using the lung image database consortium and the image database resource initiative (LIDC-IDRI) dataset with a detection rate of 97.35%, surpassing single model and traditional ensemble methods. The current work provides a solid and scalable approach to lung cancer detection with better generalization, increased diagnostic consistency, and applicability for clinical use.
Volume: 15
Issue: 2
Page: 1605-1612
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

Automated bacteria and fungi classification using convolutional neural network on embedded system

10.11591/ijai.v15.i2.pp1132-1142
Tarik Bouganssa , Maryem Ait Moulay , Samar Aarabi , Abedelali Lasfar , Abdelatif EL Afia
In this study, we created and applied novel concepts for hardware-based image identification and categorization. For artificial intelligence (AI) and image recognition applications, this includes putting algorithms for recognizing colors, textures, and shapes into practice. Our contribution uses an embedded device with a camera and a microcomputer (Raspberry-Pi4 type) to replace the optical assessment of Petri dishes. Our object recognition system processes images efficiently by using a state-of-the-art kernel function and a new neighborhood architecture. Using the well-known convolutional neural network (CNN) architecture, YOLOv8, as a pre-trained model, we evaluated the proposed CNN-based method for object recognition in a number of demanding scenarios. Several Petri plates, uncontrolled settings, and different backgrounds and illumination were used to evaluate the technology. Our dynamic mode integrates a CNN network with an attention mask to highlight the traits of bacteria and fungi, ensuring robust recognition. We implemented our algorithm on a Raspberry Pi 400, connected to a CMOS 3.0 camera sensor and a human-machine interface (HMI) for instant display of results.
Volume: 15
Issue: 2
Page: 1132-1142
Publish at: 2026-04-01

Performance assessment of an adaptive model predictive control with torque braking for lane changes

10.12928/telkomnika.v24i2.27167
Zulkarnain; Universitas Sriwijaya Zulkarnain , Irwin; Universitas Sriwijaya Bizzy , Armin; Universitas Sriwijaya Sofijan , Mohd Hatta Mohammed; Universiti Teknologi Malaysia Ariff
The growing demand for autonomous vehicles requires robust control systems that can maintain safety during complex maneuvers like lane changes. However, a significant research gap exists in developing controllers that effectively manage the combined challenges of steering and braking across diverse and unpredictable driving conditions, such as varying speeds and low-friction road surfaces. This research addresses this gap by proposing and evaluating an adaptive model predictive control (MPC) system integrated with a torque braking distribution strategy. The key advantage of our adaptive method is its ability to continuously update its internal model in real-time, allowing it to anticipate and respond to changing road friction and vehicle dynamics more effectively than a static controller. In simulations of a lane change maneuver across speeds of 10-25 m/s and road friction levels from 0.3 (icy) to 1 (dry asphalt), the proposed system demonstrated a substantial performance improvement. The proposed framework demonstrated a 52.8% average reduction in lateral tracking error and enhanced stability by reducing the yaw rate by up to 41.8% on low-friction surfaces, compared to a non-adaptive MPC baseline. These results quantitatively confirm that our framework’s synergistic coordination of steering and braking significantly enhances the safety, precision, and reliability of autonomous lane change maneuvers.
Volume: 24
Issue: 2
Page: 696-706
Publish at: 2026-04-01

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

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

Intelligent artificial neural network-based control for solar electric vehicle charger

10.11591/ijeecs.v41.i3.pp885-893
Rajeshkumar Damodharan , Pradeep Kumar S
The performance of electric vehicle (EV) charging systems in response to sudden changes in solar irradiation and dynamic battery load variations. EV chargers must have effective power conversion and flexibility as the use of renewable energy sources increases. This paper suggests a charging system based on resonant converters that minimizes heat and losses in EV charging stations by enabling high-efficiency, soft-switching power transfer. For modern EV applications, the ability to manage large voltage fluctuations ensures reliable, quick, and portable charging. The artificial neural networks (ANN) controller overcomes the drawbacks of conventional Perturb and Observe (P&O) for solar DC-DC converters and PI control for resonant converter approaches. MATLAB simulation results demonstrate that the proposed system outperforms traditional techniques in terms of an ANN based controller, which enhances maximum power point tracking (MPPT) efficiency to 98.6%, reduces oscillations near the maximum power point by approximately 80%, and increases total EV charging efficiency by 3%. The ANN-based control to EV charging infrastructure greatly enhances overall system dependability and real-time responsiveness, making it a good fit for subsequent smart grid and renewable energy applications.
Volume: 41
Issue: 3
Page: 885-893
Publish at: 2026-03-10

A hybrid approach for measuring semantic similarity in lexically identical but ambiguous sentences

10.11591/ijeecs.v41.i3.pp954-965
Btissam El Janati , Adil Enaanai , Fadoua Ghanimi
This study addresses the critical challenge of semantic similarity and lexical disambiguation in natural language processing, focusing on sentences with structural and lexical ambiguities. We introduce an innovative hybrid approach that synergistically combines symbolic and neural methods to better align with human judgment. Our methodology dynamically integrates fuzzy Jaccard’s lexical precision with SBERT embeddings’ contextual sensitivity, enabling adaptive semantic ambiguity resolution. Experimental evaluation on 33 ambiguous sentences demonstrates that our approach significantly outperforms conventional artificial intelligence (AI) systems, achieving an 11.7% reduction in mean absolute error compared to reference models, with statistical analysis confirming robust results (d = -0.80, p < 0.001). This represents a 65% improvement in human evaluation alignment over existing methods. Our research contributes to advancing the field by showing that architectural intelligence can surpass mere parameter scaling, offering an effective solution for applications requiring both precision and interpretability, with promising directions for multilingual extension and explainable AI integration.
Volume: 41
Issue: 3
Page: 954-965
Publish at: 2026-03-10

A multimodal framework for explainable chest X-ray report generation

10.11591/ijeecs.v41.i3.pp1060-1069
Hamza Chehili , Nourhene Bougourzi , raida malak Makhlouf , hadjer Taib , Mustapha Bensaada
Chest X-ray (CXR) interpretation remains a challenging task due to overlapping anatomical structures, variability in disease presentation, and increasing clinical workload. Existing automated report-generation models provide promising results but often lack explicit interpretability, limited clinical alignment, and insufficient comparative evaluation with established baselines. This study proposes an explainable multimodal framework that combines a dual CNN encoder (ResNet-50 and EfficientNet-B0) with the Gemma-3 1B language model fine-tuned using low-rank adaptation (LoRA). Visual explanations are produced through Gradient-weighted Class Activation Mapping (Grad-CAM) to enhance transparency in the decision process. Unlike prior image-to-text pipelines, our approach follows a findings-guided paradigm and integrates both visual and textual cues during generation. Experiments conducted on public datasets demonstrate consistent improvements over representative vision-language baselines reported in recent literature, with notable gains in BLEU, ROUGE, METEOR, and BERTScore. Generated reports show improved factual completeness and clinically relevant region-level attention. Limitations include the absence of evaluation against emerging foundation models and the need for anatomical- level explainability metrics. Future work will extend benchmarking to models such as M2-Transformer, MedCLIP-GPT, and R2Gen, and will explore clinical validation in real-world workflows.
Volume: 41
Issue: 3
Page: 1060-1069
Publish at: 2026-03-10

Exploring word embeddings and clustering algorithms for user reviews

10.11591/ijeecs.v41.i3.pp1017-1024
Zuleaizal Sidek , Sharifah Sakinah Syed Ahmad
The rapid advancement of information technology has led to a significant surge in the volume of unstructured textual data. This has posed a major problem in terms of analyzing, organizing, and automatically clustering text for research purposes, which is crucial for extracting valuable insights. The process of manually clustering the unstructured data, such as customer reviews on the Internet, which capture the opinions of customers regarding products, services, and social events, requires significant financial resources, manpower, and time. Most of the studies are directed towards the analysis of sentiment in user reviews. In order to address the issues effectively, automated text clustering could assist in categorizing reviews into various themes, thereby simplifying the analysis process. Therefore, in this paper, we present and compare the result of experiment the combination of five text clustering techniques, namely K-means, fuzzy C-mean (FCM), non-negative matrix factorization (NMF), latent dirichlet allocation (LDA), and latent semantic analysis (LSA) with different embedding techniques, namely term frequency–inverse document frequency (TF-IDF), Word2Vec, and global vectors (GloVe). The experiments revealed that LDA is a reliable algorithm as it consistently produces good results across three-word embeddings. The highest Silhouette score recorded in the experiments was 0.66 using LDA and Word2Vec as word embedding. Simultaneously, the application of LSA in conjunction with Word2Vec yields superior outcomes, as evidenced by a Silhouette score of 0.65.
Volume: 41
Issue: 3
Page: 1017-1024
Publish at: 2026-03-10

An innovative deep learning based approach for anomaly detection in intelligent video surveillance

10.11591/ijeecs.v41.i3.pp1105-1116
Megha G. Pallewar , Vijaya R. Pawar
Nowadays, anomaly detection has gained vital importance as security is a major concern everywhere. This work focuses on developing an intelligent video surveillance system capable of detecting anomalous activities in videos, utilizing the UCF Crime dataset as the primary source. The proposed model employed a multistage method uniting the convolutional neural networks (CNN) and long short-term memory (LSTM) networks. In the proposed approach, video frames serve as input to the CNN, which processes them to extract key features. These features are then passed to an LSTM network to capture temporal dependencies and identify anomalous events over time. This CNN-LSTM architecture successfully detects twelve distinct types of anomalous activities: abuse, arrest, arson, assault, burglary, explosion, fight, road accident, robbery, stealing, shoplifting, and vandalism. The dataset is divided into portions for training, testing, and validation, along with cross-validation to ensure model generalization. The system achieves an accuracy of 98.6%, reflecting a significant improvement of 4-5% over existing systems. This demonstrates the robustness of the proposed method in detecting anomalous behavior in video data.
Volume: 41
Issue: 3
Page: 1105-1116
Publish at: 2026-03-10

Satellite-based assisted-offloading for energy-constrained edge networks

10.11591/ijeecs.v41.i3.pp935-945
Thembelihle Dlamini , Mengistu A. Mulatu , Sifiso Vilakati
As the need for global broadband internet connectivity increases, there is a need to consider the use of non-terrestrial networks (NTNs) to extend the network coverage to protected areas (e.g., national parks). Usually, protected areas are prohibited from having power lines thus lacking wireless connectivity. To over come this challenge, energy can be provided through the use of green energy from a solar photovoltaic (PV) system. Then, a green energy-based base station (BS) can be deployed within the area in order to provide mobile connectivity to visitors, as well as also using the NTNs to handle excess traffic or take over the traffic in the event the BS does not have sufficient green energy from stor age. In this paper, a hybrid wireless communication system is proposed to in clude BS sites located in a protected area and satellites in the low earth orbits (LEO), coupled with new offloading strategies, with the main goal of optimizing the trade-off between energy consumption and end-to-end delay for the green energy-based BS sites. For accuracy of our simulations, we consider real data from a solar photovoltaics system, traffic workloads, visitor’s location data, and satellite orbits from Starlink constellations. Our results demonstrate that the co existence of the BS and satellite achieve energy savings from 59% to 34%, with an average system delay of 0.83 seconds and a packet drop rate that ranges from 8.3% to 2.7%, when compared with our benchmark.
Volume: 41
Issue: 3
Page: 935-945
Publish at: 2026-03-10

Synthetic inertia controller of a wind power plant as a means of increasing the stability of electric power systems

10.11591/ijeecs.v41.i3.pp1117-1123
Makhmudov Tokhir Farkhadovich , Ramatov Adxam Nasiriddin o’gli
The article discusses the use of wind power plants as sources of synthetic inertia to enhance power system stability and reduce frequency fluctuations. This research explores the feasibility of implementing a synthetic inertia controller in wind power plants to decrease the magnitude of frequency oscillations during transient operating conditions. The growing integration of wind farms into modern power grids leads to a reduction in the overall kinetic energy, or inertia, available in the system. As a result, the grid may become more vulnerable to disturbances. When the system inertia is too low, frequency stability can be affected, especially when large generating units suddenly fail or disconnect from the grid. In general, a lower level of inertia in the system causes larger frequency deviations following an imbalance in active power. To overcome this issue, a synthetic inertia regulator for wind power plants has been developed, enabling wind turbines to support the grid and reduce the depth of frequency drops during transient events.
Volume: 41
Issue: 3
Page: 1117-1123
Publish at: 2026-03-10

Leveraging CNN to analyze facial expressions for academic engagement monitoring with insights from the multi-source academic affective engagement dataset

10.11591/ijeecs.v41.i3.pp977-999
Noora C. T. , P. Tamil Selvan
The dynamics of student engagement and emotional states significantly influence learning outcomes. Positive emotions, stemming from successful task completion, contrast with negative emotions arising from learning struggles or failures. Effective transitions to engagement occur upon problem resolution, while unresolved issues lead to frustration and subsequent boredom. Facial engagement monitoring is crucial for assessing students’ attention, interest, and emotional responses during learning. Recent advancements in convolutional neural networks (CNNs) show promise in automatically analyzing facial expressions to infer engagement levels. This study proposes a CNN-based approach utilizing the multi-source academic affective engagement dataset (MAAED) to categorize facial expressions into boredom, confusion, frustration, and yawning. By extracting features from facial images, this method offers an efficient and objective means to gauge student engagement. Recognizing and addressing negative affective states, such as confusion and boredom, is fundamental in creating supportive learning environments. Through automated frame extraction and model comparison, this study demonstrates reduced loss values with improving accuracy, showcasing the effectiveness of this method in objectively evaluating student engagement. Facial engagement monitoring with CNNs, using the MAAED dataset, is pivotal in understanding human behavior and enhancing educational experiences. The CNN model, trained on MAAED annotated facial expressions, accurately classifies engagement categories. Experimental results underscore the CNN-based approach’s efficacy in monitoring facial engagement, highlighting its potential to enrich educational environments and personalized learning experiences.
Volume: 41
Issue: 3
Page: 977-999
Publish at: 2026-03-10

Fuzzy logic-based load balancing for voltage symmetry in distribution networks

10.11591/ijeecs.v41.i3.pp873-884
Adeel Saleem , Kholiddinov Ilkhombek Khosiljonovich , Kholiddinova Mashkhurakhon Mutalibjon Qizi , Begmatova Mukhlisakhon Mutalibjon Qizi , Sharobiddinov Mirzokhid
This paper introduces a load balancing approach based on fuzzy logic to enhance the efficiency of power distribution networks. The unbalance of voltages and an unequal load of the phases continue to be the problematic situation of the low-voltage distribution networks, particularly as the percentage of photovoltaic (PV) systems is growing. The results of such conditions include a deviation of voltage, higher losses of power, faster equipment aging, and lower power quality. This paper proposes a fuzzy logic–based phase load balancing approach that explicitly integrates voltage symmetry requirements defined by the GOST 13109-97 power quality standard. Unlike optimization-based and heuristic methods, the proposed fuzzy logic controller (FLC) redistributes phase currents using linguistic rules derived from voltage unbalance coefficients and phase current conditions, without iterative optimization procedures. Simulation results obtained in MATLAB/Simulink demonstrate a reduction of the voltage unbalance factor (VUF) by approximately 25–30% and a decrease in active power losses by 12–15% compared to the initial unbalanced operating state. The proposed method offers low computational complexity, fast response, and high interpret-ability, making it suitable for real-time implementation in smart distribution networks with distributed PV generation.
Volume: 41
Issue: 3
Page: 873-884
Publish at: 2026-03-10
1 2 3
...
1993 1994
Show 17 of 1994

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