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

Exploring patient-patient interactions graphs by network analysis

10.11591/ijai.v14.i3.pp1752-1762
Zaher Salah , Esraa Abu Elsoud , Kamal Salah
Understanding how patient demographics and shared experiences impact interactions is essential for strengthening pa/tient support networks and optimizing health outcomes as personalized healthcare becomes more and more important. To this end, this study explores the patient-patient interactions (PPIs) graph as a network and applies selected network analysis approaches to examine the PPIs network of accutane drug. Two main research questions are addressed by gaining deeper insight at the hidden patterns of reactivity and connectivity among interchanging nodes. There was a negative response to the first research question, which asked if patients react to others that have similar gender and/or age profiles in a consistent way. Patients tended to interact with people of different genders and ages, indicating a high degree of heterogeneity in the network. Negative responses were likewise given to the second research question, which asked if communities inside the network could identify patients based on gender or age profile. Network analysis approaches for community detection failed to distinguish between groups with similar demographic characteristics. Rather, groups seemed to emerge based on other factors, like similarity in patient opinions. The results imply that gender and age do not have a major influence on community membership. Future research will concentrate on applying more sophisticated graph mining techniques to expand these approaches to cover more and larger PPIs networks.
Volume: 14
Issue: 3
Page: 1752-1762
Publish at: 2025-06-01

Novel artificial intelligence-based ensemble learning for optimized software quality

10.11591/ijai.v14.i3.pp1820-1828
Sangeetha Govinda , Agnes Nalini Vincent , Merwa Ramesh Babu
Artificial intelligence (AI) contributes towards improving software engineering quality; however, existing AI models are witnessed to deploy learning-based approaches without addressing various complexities associated with datasets. A literature review showcases an unequilbrium between addressing the accuracy and computational burden. Therefore, the proposed manuscript presents a novel AI-based ensemble learning model that is capable of performing an effective prediction of software quality. The presented scheme adopts correlation-based and multicollinearity-based attributes to select essential feature selection. At the same time, the scheme also introduces a hybrid learning approach integrated with a bio-inspired algorithm for constructing the ensemble learning scheme. The quantified outcome of the proposed study showcases 65% minimized defect density, 94% minimized mean time to failure, 62% minimized processing time of the algorithm, and 43% enhanced predictive accuracy.
Volume: 14
Issue: 3
Page: 1820-1828
Publish at: 2025-06-01

Camera-based advanced driver assistance with integrated YOLOv4for real-time detection

10.11591/ijai.v14.i3.pp2236-2245
Keerthi Jayan , Balakrishnan Muruganantham
Testing object detection in adverse weather conditions poses significant chal lenges. This paper presents a framework for a camera-based advanced driver assistance system (ADAS) using the YOLOv4 model, supported by an electronic control unit (ECU). The ADAS-based ECU identifies object classes from real-time video, with detection efficiency validated against the YOLOv4 model. Performance is analysed using three testing methods: projection, video injection, and real vehicle testing. Each method is evaluated for accuracy in object detection, synchronization rate, correlated outcomes, and computational complexity. Results show that the projection method achieves highest accuracy with minimal frame deviation (1-2 frames) and up to 90% correlated outcomes, at approximately 30% computational complexity. The video injection method shows moderate accuracy and complexity, with frame deviation of 3-4 frames and 75%correlated outcomes. The real vehicle testing method, though demand ing higher computational resources and showing a lower synchronization rate (> 5 frames deviation), provides critical insights under realistic weather condi tions despite higher misclassification rates. The study highlights the importance of choosing appropriate method based on testing conditions and objectives, bal ancing computational efficiency, synchronization accuracy, and robustness in various weather scenarios. This research significantly advances autonomous ve hicle technology, particularly in enhancing ADAS object detection capabilities in diverse environmental conditions.
Volume: 14
Issue: 3
Page: 2236-2245
Publish at: 2025-06-01

Deep learning for the identification of autism traits in children through facial expressions: a systematic review

10.11591/ijece.v15i3.pp3279-3290
Daniella Romani Palomino , Christian Ovalle , Heli Cordova-Berona
This study employs a bibliometric analysis to examine research on the application of artificial intelligence, specifically deep learning, in the detection of autism traits through facial expressions. Using quantitative methodologies. The analysis revealed a notable growth in scientific output from 2019, with an emphasis on techniques such as convolutional neural networks and systems based on the facial action coding system (FACS- CNN). The results highlight improvements in diagnostic accuracy thanks to the use of deep learning, although challenges related to data quality and availability remain. This study underscores the importance of international collaboration and technological innovation to advance the diagnosis and treatment of autism, offering a comprehensive perspective on current and future trends in this interdisciplinary field.
Volume: 15
Issue: 3
Page: 3279-3290
Publish at: 2025-06-01

A hybrid convolutional neural network-recurrent neural network approach for breast cancer detection through Mask R-CNN and ARI-TFMOA optimization

10.11591/ijece.v15i3.pp3084-3094
Keshetti Sreekala , Srilatha Yalamati , Annemneedi Lakshmanarao , Gubbala Kumari , Tanapaneni Muni Kumari , Venkata Subbaiah Desanamukula
This paper presents a novel hybrid deep learning-based approach for breast cancer detection, addressing critical challenges such as overfitting and performance degradation in varying data conditions. Unlike traditional methods that struggle with detection accuracy, this work integrates a unique combination of advanced segmentation and classification techniques. The segmentation phase leverages Mask region-based convolutional neural network (R-CNN), enhanced by the adaptive random increment-based tomtit flock metaheuristic optimization algorithm (ARI-TFMOA), a novel algorithm inspired by natural flocking behavior. ARI-TFMOA fine-tunes Mask R-CNN parameters, achieving improved feature extraction and segmentation precision while ensuring adaptability to diverse datasets. For classification, a hybrid convolutional neural network-recurrent neural network (CNN-RNN) model is introduced, combining spatial feature extraction by CNNs with temporal pattern recognition by RNNs, resulting in a more nuanced and comprehensive analysis of breast cancer images. The proposed framework achieved significant advancements over existing methods, demonstrating improved performance. This hybrid integration of ARI-TFMOA and Hybrid CNN-RNN models represents a unique contribution, enabling robust, accurate, and efficient breast cancer detection.
Volume: 15
Issue: 3
Page: 3084-3094
Publish at: 2025-06-01

Ensemble model-based arrhythmia classification with local interpretable model-agnostic explanations

10.11591/ijai.v14.i3.pp2012-2025
Md. Rabiul Islam , Tapan Kumar Godder , Ahsan Ul-Ambia , Ferdib Al-Islam , Anindya Nag , Bulbul Ahamed , Nujhut Tanzim , Md. Estiak Ahmed
Arrhythmia can lead to heart failure, stroke, and sudden cardiac arrest. Prompt diagnosis of arrhythmia is crucial for appropriate treatment. This analysis utilized four databases. We utilized seven machine learning (ML) algorithms in our work. These algorithms include logistic regression (LR), decision tree (DT), extreme gradient boosting (XGB), K-nearest neighbors (KNN), naïve Bayes (NB), multilayer perceptron (MLP), AdaBoost, and a bagging ensemble of these approaches. In addition, we conducted an analysis on a stacking ensemble consisting of XGB and bagging XGB. This study examines various arrhythmia detection techniques using both a single base dataset and a composite dataset. The objective is to identify the optimal model for the combined dataset. This study aims to evaluate the efficacy of these models in accurately categorizing normal (N) and abnormal (A) heartbeats as binary classes. The empirical findings demonstrated that the stacking ensemble approach exhibited superior accuracy when used with the combined dataset. Arrhythmia classification models rely on this as a crucial component. The binary classification achieved an accuracy of 98.61%, a recall of 97.66%, and a precision of 97.77%. Subsequently, the local interpretable model-agnostic explanations (LIME) technique is employed to assess the prediction capability of the model.
Volume: 14
Issue: 3
Page: 2012-2025
Publish at: 2025-06-01

Exploring the effectiveness of hybrid artificial bee PyCaret classifier in delay tolerant network against intrusions

10.11591/ijece.v15i3.pp3149-3161
Rajashri Chaudhari , Manoj Deshpande
In challenging environments with intermittent connectivity and the absence of end-to-end paths, delay tolerant networks (DTNs) require robust security measures to safeguard against potential threats. This study addresses these issues by implementing an intrusion detection system (IDS) enhanced with machine learning techniques. Common threats such as distributed denial-of-service (DDoS) and flood attacks are tackled using datasets like network intrusion detection (NID) and flood attack datasets. Multiple machines learning methods, including k-nearest neighbors (K-NN), decision trees (DT), logistic regression (LR), and others, are utilized to improve detection accuracy. A PyCaret-based approach is developed to increase efficiency while preserving attack detection accuracy in DTNs. Comparative research demonstrates that PyCaret outperforms Scikit-learn models, and the artificial bee PyCaret classifier (ABPC) optimizes hyperparameters to improve model performance. NS2 simulation shows the system's ability to thwart attacks, offering useful insights into DTN security and improving communication reliability in various situations.
Volume: 15
Issue: 3
Page: 3149-3161
Publish at: 2025-06-01

Evaluating the feasibility of a photovoltaic-wind-diesel-battery hybrid microgrid for sustainable off-grid electrification in Dakhla, Morocco

10.11591/ijece.v15i3.pp2655-2668
Sara Fennane , Houda Kacimi , Hamza Mabchour , Fatehi ALtalqi , Adil Echchelh
Hybrid renewable energy systems (HRES) present a promising solution for improving energy reliability and reducing costs in remote, off-grid areas. This study explores the feasibility of implementing an HRES in Dakhla, Morocco, where conventional electrical infrastructure is lacking. By integrating photovoltaic (PV) panels, wind turbines, diesel generators, and battery storage, this study aims to optimize energy resource management while balancing technical performance and economic viability. Using real- world data on energy consumption, climatic conditions, and installation constraints, advanced simulation tools such as HOMER were employed to evaluate both technical and economic parameters. The objective was to minimize the cost of energy (COE) while ensuring reliability, availability, and a high renewable fraction. The results, compared with optimization algorithms like genetic algorithm (GA), particle swarm optimization (PSO), and simulated annealing (SA), revealed the PV-wind-diesel-battery configuration as the most cost-effective solution. This configuration resulted in a net present cost (NPC) of $829,380, a COE of $0.160/kWh, and minimal CO2 emissions of 54.9 kg/year. The findings highlight the viability of this hybrid microgrid as a sustainable off-grid electrification solution and emphasize the role of renewable energy in addressing global energy challenges.
Volume: 15
Issue: 3
Page: 2655-2668
Publish at: 2025-06-01

Rooftops detection with YOLOv8 from aerial imagery and a brief review on rooftop photovoltaic potential assessment

10.11591/ijai.v14.i3.pp2282-2290
Md. Sabbir Ahmed , Md. Shohel Arman , Nusrat Tasnim , Md Hafizul Imran , Musabbir Smmak , Touhid Bhuiyan
Recent years have seen significant advancements in the switch from fossil fuel-based energy systems to renewable energy. Decentralized solar photovoltaic (PV) is one of the most promising energy sources since there is a lot of rooftop space, it is easy to install, and the cost of the PV panels is low. The determination of rooftop locations for PV installation is crucial for energy planning. With this context, this study aimed to detect the suitable rooftops of different shapes. The dataset of 5,076 building roofs used in this study was gathered by us utilizing a drone. This study identified ten distinct roof shapes accurately, including triangle, square, penta, hexa, hepta, octa, nona, deca, gabled roof, and hipped roof, using the most recent version of you only live once (YOLO), known as YOLOv8. Recent research revealed, YOLOv8 is more accurate than earlier YOLO models which is the reason of utilizing YOLOv8. Accuracy of this work of rooftops detection is 93.6%. Also, the precision, recall, and F1-score confidence curve showed good performances too. Finally, a brief review of the most recent studies on the evaluation of rooftop PV potential was conducted to provide insight into the use of solar energy.
Volume: 14
Issue: 3
Page: 2282-2290
Publish at: 2025-06-01

Optimizing real-time data preprocessing in IoT-based fog computing using machine learning algorithms

10.11591/ijai.v14.i3.pp1900-1909
Nandini Gowda Puttaswamy , Anitha Narasimha Murthy
In the era of the internet of things (IoT), managing the massive influx of data with minimal latency is crucial, particularly within fog computing environments that process data close to its origin. Traditional methods have been inadequate, struggling with the high variability and volume of IoT data, which often leads to processing inefficiencies and poor resource allocation. To address these challenges, this paper introduces a novel machine learning-driven approach named real-time data preprocessing in IoT-based fog computing using machine learning algorithms (IoT-FCML). This method dynamically adapts to the changing characteristics of data and system demands. The implementation of IoT-FCML has led to significant performance enhancements: it reduces latency by approximately 0.26%, increases throughput by up to 0.3%, improves resource efficiency by 0.20%, and decreases data privacy overhead by 0.64%. These improvements are achieved through the integration of smart algorithms that prioritize data privacy and efficient resource use, allowing the IoT-FCML method to surpass traditional preprocessing techniques. Collectively, the enhancements in processing speed, adaptability, and data security represent a substantial advancement in developing more responsive and efficient IoT-based fog computing infrastructures, marking a pivotal progression in the field.
Volume: 14
Issue: 3
Page: 1900-1909
Publish at: 2025-06-01

Leukemia detection using SegNet and faster region-based convolutional neural network

10.11591/ijece.v15i3.pp3028-3038
Della Reasa Valiaveetil , T. Kanimozhi
Prevention of cancer is mostly attained by surveillance of the transformation zones. White blood cells (WBCs) are established in the bone marrow and intemperate growth of WBC leads to leukemia. Hematologists examine the microscopic images in manual method for predicting leukemia, but it is very complex process and without any guaranteed for accurate. In this proposed study, deep learning techniques involved to segment and classify the three types of leukemia like acute lymphocytic leukemia (ALL), acute myeloid leukemia (AML) and chronic lymphocytic leukemia (CLL) using the BioGps dataset. The purpose of deep learning in medical science enhances the accuracy and precision of determining leukemia in early stages. In this study, introducing a sigmoid stretching (SS) in pixel enhancement for preprocessing; SegNet (St) is comfort to extract the structural features of the leukocytes and to segment the normal and blast cells for a clear classification; faster region-based convolutional neural network (faster R- CNN) carried under the process of classification and optimization done by dragon fly algorithm. The result of this work achieves best accuracy related to the existing techniques of convolutional neural network (CNN) such as support vector machine (SVM), k-nearest neighbors (kNN) and Bayesian model. This study achieves the accuracy rate of 97%, precision rate of 94% and sensitivity rate of 90% respectively with low complexity.
Volume: 15
Issue: 3
Page: 3028-3038
Publish at: 2025-06-01

Addressing the challenges of harmonizing law and artificial intelligence technology in modern society

10.11591/ijai.v14.i3.pp2471-2478
Lamprini Seremeti , Sofia Anastasiadou , Andreas Masouras , Stylianos Papalexandris
The invasion of artificial intelligence (AI) in all forms of human activity causes the sudden change of social cohesion into a new hybrid reality, where the static rule of law maybe is overthrown by the instant violations of fundamental human rights, including the general rights of personhood, in its image, honor, and privacy, as well as, of general principles of law, including the principle of the “abuse of rights”, the principle of contractual autonomy, principles of tort liability, and general principles of intellectual property law. In that sense, AI disrupts the acquis due to the poor regulatory quality indicators covering unforeseen occurrences. We call this instantiation AI legal “coup d’état”. This paper constitutes a philosophical thesis statement which is in accordance with the global efforts to legally embed AI into societal systems. As part of an ongoing research on AI and law synergy, this paper focuses on proposing a theoretical framework utilizing category theory to align AI functionalities with traditional legal principles.
Volume: 14
Issue: 3
Page: 2471-2478
Publish at: 2025-06-01

Electroencephalography and heart rate variability prognostics in mental health therapies for Malaysian workers

10.11591/ijphs.v14i2.25224
Nurnadiah Zamri , Samhani Ismail , Azimah Ismail , Norsuhaily Abu Bakar , Siti Nurani Hassan , Tuan Sharipah Tuan Hadi , Amir Zulhilmi Yahaya , Chong Siew Koon , Nor Azmi Abu Bakar
Globally, over a million individuals succumb to suicide annually, with depression contributing to 6.7% of these tragic deaths. Such crises often stem from life-induced pressures, escalating into severe mental health issues. Recognizing these early signs is pivotal, but insufficient without effective therapeutic measures. This study endeavors to address these challenges by exploring patient responses to therapy using electroencephalogram (EEG) and heart rate variability (HRV) data. Conducted in Kuala Terengganu, Malaysia, the research involves workers and employs aromatherapy, deep breathing exercises, and ruqyah alongside a control group. EEG and HRV signals monitor brain wave patterns and heart rhythm coherence, aiding in identifying depression, stress, and anxiety indicators. Integrating questionnaire data including the depression-anxiety-stress-scale (DASS), beck depression inventory (BDI), beck anxiety inventory (BAI), and statistical analysis, the study aims to evaluate therapeutic efficacy in enhancing relaxation and mental well-being. Metrics like HRV coherence ratio and EEG delta wave activity offer insights into therapy optimization. Results suggest deep breathing exercises and aromatherapy as most effective in inducing calmness, followed by ruqyah. By tailoring therapy to individual needs, especially among workers, the study endeavors to foster mental health resilience in communities, paving the path towards a mentally healthier populace.
Volume: 14
Issue: 2
Page: 760-772
Publish at: 2025-06-01

Genetic algorithm-adapted activation function optimization of deep learning framework for breast mass cancer classification in mammogram images

10.11591/ijece.v15i3.pp2820-2833
Noor Fadzilah Razali , Iza Sazanita Isa , Siti Noraini Sulaiman , Muhammad Khusairi Osman , Noor Khairiah A. Karim , Dayang Suhaida Awang Damit
The convolutional neural network (CNN) has been explored for mammogram cancer classification to aid radiologists. CNNs require multiple convolution and non-linearity repetitions to learn data sparsity, but deeper networks often face the vanishing gradient effect, which hinders effective learning. The rectified linear unit (ReLU) activation function activates neurons only when the output exceeds zero, limiting activation and potentially lowering performance. This study proposes an adaptive ReLU based on a genetic algorithm (GA) to determine the optimal threshold for neuron activation, thus improving the restrictive nature of the original ReLU. We compared performances on the INbreast and IPPT-mammo mammogram datasets using ReLU and leakyReLU activation functions. Results show accuracy improvements from 95.0% to 97.01% for INbreast and 84.9% to 87.4% for IPPT-mammo with ReLU and from 93.03% to 99.0% for INbreast and 84.03% to 91.06% for IPPT-mammo with leakyReLU. Significant accuracy improvements were observed for breast cancer classification in mammograms, demonstrating its potential to aid radiologists with more robust and reliable diagnostic tools.
Volume: 15
Issue: 3
Page: 2820-2833
Publish at: 2025-06-01

Techniques of Quran reciters recognition: a review

10.11591/ijai.v14.i3.pp1683-1695
Ibrahim Alomari , Asma Alshargabi , Mohammed Hadwan
The Quran is the holy book of the Islam. Reading and listening to the Quran is an important part of the daily life of Muslims. Muslims are keen to listen to recitations of Quran by skilled reciters to learn the correct recitation for the purpose of understanding and contemplating. Therefore, there are large variety of audio recitations for many skilled reciters. With the availability of this huge amount of recitations and also with the great progress in voice recognition technologies, many research efforts have been devoted to contribute making recitation better using artificial intelligence. One useful application in this area is identifying the reciters of the Quran. There are various solutions introduced by researchers; however, these solutions vary significantly in terms of accuracy, and efficiency. This research seeks to provide a review of these solutions. It also reviews available datasets using different criteria. Finally, some open issues and challenges were addressed.
Volume: 14
Issue: 3
Page: 1683-1695
Publish at: 2025-06-01
1 2 3
...
2097 2098
Show 277 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