Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

30,096 Article Results

MNetNCR: MobileNet model for efficient traditional Nusantara script character recognition

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

Explainable social media disaster image classification using a lightweight attention-based deep learning approach

10.11591/ijai.v15.i2.pp1464-1472
Rashmi Kangokar Taranath , Geeta Chidanandappa Mara
In recent years, the rapid dissemination of social media content during natural and man-made disasters has created a need for automated and accurate disaster image classification systems. This paper proposes lightweight explainable attention-based disaster network (LEAD-Net), a deep learning (DL) model designed for classifying disaster-related images with high accuracy and interpretability. The system integrates an EfficientNet-B0 backbone enhanced with squeeze-and-excitation (SE) attention modules and a lightweight neural architecture search (NAS-lite) strategy for tuning the classifier head and training hyperparameters. The model was evaluated on two benchmark datasets comprehensive disaster dataset (CDD) and damage multimodal dataset (DMD) achieving 96% and 87% accuracy, respectively, outperforming several established convolutional neural network (CNN) baselines. To ensure transparency, gradient-weighted class activation mapping (Grad-CAM) was employed to generate visual explanations of the model’s decisions, confirming its focus on semantically relevant image regions.
Volume: 15
Issue: 2
Page: 1464-1472
Publish at: 2026-04-01

The effects of data imbalance on fraud detection model accuracy

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

Drone-assisted deep learning weed detection for sustainable agriculture and environmental resilience

10.11591/ijai.v15.i2.pp1428-1440
Agustan Latif , Handaru Jati , Herman Dwi Surjono , Mani Yusuf
Effective weed detection plays a crucial role in sustainable agriculture, boosting crop productivity and supporting environmental conservation. This study compares three deep learning models—YOLOv5, YOLO-NAS, and mask region-based convolutional neural network (Mask R-CNN)-against traditional methods in terms of accuracy, processing speed, and adaptability in tropical agricultural conditions, with Merauke, Indonesia, as the case study. The results show that YOLO-NAS delivers the highest accuracy at 96% with a processing time of 25 ms per image, making it suitable for high precision applications. YOLOv5 balances strong accuracy (94%) with faster processing at 12 ms per image, establishing it as the most effective for real time scenarios. Mask R-CNN also achieves 94% accuracy and provides advanced segmentation capabilities, but its slower processing speed of 31 ms limits large-scale implementation. Traditional methods perform poorly in comparison, with only 85% accuracy and processing time above 50 ms per image. These findings highlight the transformative potential of artificial intelligence (AI)-based weed detection for precision agriculture, particularly in tropical regions like Merauke. Adoption of models such as YOLOv5 reduces manual labor dependence while advancing efficient, eco-friendly weed management. Future research should expand datasets and explore newer models like YOLOv8, YOLO-NAS, vision transformers (ViTs), and hybrid approaches.
Volume: 15
Issue: 2
Page: 1428-1440
Publish at: 2026-04-01

An intelligent and explainable IoT-Edge-Cloud architecture for real-time water quality monitoring

10.11591/ijai.v15.i2.pp1109-1120
Sara Bouziane , Badraddine Aghoutane , Aniss Moumen , Anas El Ouali , Ali Essahlaoui , Abdellah El Hmaidi
Continuous and reliable monitoring of water quality is critical for early detection of environmental deterioration, yet conventional monitoring approaches are often slow and lack timely data availability. This study proposes an intelligent and explainable internet of things (IoT)–Edge–Cloud architecture to monitor water quality in real time, using IoT sensing, edge based artificial intelligence (Edge AI), cloud-stream processing, and explainable artificial intelligence (XAI). The system calculates the water quality index (WQI) directly at the edge and predicts its evolution using a stacking ensemble model trained on physicochemical measurements taken from the Moulouya River Basin in Morocco. An explainability module based on Shapley additive explanations (SHAP) values gives a clearer image of the contribution of various parameters to WQI predictions, providing transparency of the features, which builds trust in the model’s output. The proposed architecture was implemented as an end-to-end prototype and validated using a simulation-based experimental that mimicked realistic sensor dynamics and connectivity interruptions. The experimental results show strong predictive performance (R² =0.945), stable system operations, and reliable interpretability highlighting the potential of the proposed approach for scalable, intelligent, and transparent environmental monitoring.
Volume: 15
Issue: 2
Page: 1109-1120
Publish at: 2026-04-01

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

Deep learning for early detection of cardiovascular diseases via auscultation sound classification

10.11591/ijai.v15.i2.pp1746-1761
Shreyas Kasture , Sudhanshu Maurya , Amit Kumar Sharma , Santhosh Chitraju Gopal Varma , Kashish Mirza , Firdous Sadaf Mohammad Ismail
Heart diseases are one of the most prominent causes of death globally, which requires immediate and accurate diagnosis. The auscultation methods used in conventional medical practice, where the doctor listens to the sounds produced by the body without intervention is very ineffective because of the limitations in the actual skills and perception of the doctor. The main goal of this project will be designing a mobile-based system for the early detection of cardiovascular disease (CVD) by utilizing deep learning for auscultation sound classification. The approach involves the use of deep learning structures to classify cardiac sounds into normal and abnormal patterns on its own. Wavelet transformations, time-frequency representations, and Mel frequency cepstral coefficients (MFCC) have been used in feature extraction. The ResNet152V2 model showed high classification performance with area under the receiver operating characteristic curve (AUROC) of 0.9797 and 0.9636 on two datasets. Contrary to that, data augmentation, hyperparameter optimization, attention mechanisms, as well as input-output residual connections, led to better functionality and interpretability. This research seeks to overcome the limitations of traditional stethoscope use through the incorporation of sophisticated algorithms and the availability of mobile technology that could result in early diagnosis and prevention of CVDs, especially in underprivileged areas.
Volume: 15
Issue: 2
Page: 1746-1761
Publish at: 2026-04-01

Adaptive control of ball and beam system using SNA-PID combined with recurrent fuzzy neural network identifier

10.11591/ijai.v15.i2.pp1202-1210
Minh-Thanh Le , Chi-Ngon Nguyen
The ball and beam system is a nonlinear and inherently unstable single input, multiple-output (SIMO) system, which poses significant challenges for control design. Intelligent control algorithms are often applied to autonomously control complex systems when there are changes in parameters or the control environment. Therefore, in this paper, we research and develop two methods: proportional integral derivative (PID) and single neuron adaptive (SNA)-PID-recurrent fuzzy neural network identifier (RFNNI) to control the ball and beam system. Simulation results on MATLAB/Simulink show that the SNA-PID-RFNNI controller provides a more stable output signal than the traditional PID controller, with minimal overshoot and a settling time of about 15 seconds. Next, we will conduct real-time experiments on the object using the proposed algorithm through the MEGA2560 control board with an ultrasonic positioning mechanism.
Volume: 15
Issue: 2
Page: 1202-1210
Publish at: 2026-04-01

Exponential long short-term memory with Levy flight optimization for lung nodule classification

10.11591/ijai.v15.i2.pp1451-1463
Kaliba Gowthami , Kamalakannan Jayaseelan
Lung cancer, which commonly appears as lung nodules is a deadly type of cancer that develops in a lung. Early detection of lung cancer is critical and challenging task due to presence of overlapping structures, which make it challenging to differentiate the benign and malignant regions. This research proposes long short-term memory (LSTM) with exponential linear unit (ELU) method for the classification of different classes of lung nodules. The hyperparameters of the LSTM network are optimized using the developed dynamic Levy flight – Archimedes optimization algorithm (DLF-AOA), which effectively identifies the optimal parameters for classification. The ResNet-18 method is used for the extraction of high-level features to differentiate various classes of lung nodules. Furthermore, Bayesian active contour (BAC) is employed for the segmentation of images as containing cancerous and non-cancerous regions of lung nodules. The LSTM with ELU method achieves 98.56% accuracy, 97.54% sensitivity, 98.22% specificity, 96.93% precision, 96.33% F1-score, and 1.44 error rate in IQ-OTH/NCCD lung cancer dataset.
Volume: 15
Issue: 2
Page: 1451-1463
Publish at: 2026-04-01

Usability analysis of the individual creativity assessment tool using the adjusted system usability scale

10.11591/ijai.v15.i2.pp1955-1962
Mohamad Rahimi Mohamad Rosman , Noor Arina Md Arifin , Siti Aishah Mokhtar , Nur Ainatul Mardiah Mat Nawi , Huda Hamidon , Salliza Md Radzi
Creativity is a critical element in the learning environment, which leads to innovation and research advancement in higher education. However, assessing creativity is challenging due to its diverse nature and the lack of standardized tools. The existing assessment tools often overlook the critical role of organizational culture in shaping individual creativity within academic settings. To address this gap, the individual creativity assessment tool (i-CAT) was developed based on the framework of organizational culture to assess its contribution to creativity among Malaysian academicians. This study aimed to i) assess the usability of i-CAT and ii) determine the significant effect of demographic factors on its usability assessment. A quantitative methodology, utilizing expert sampling and the system usability scale (SUS), was employed as the primary evaluation method. 20 experts with relevant professional and academic experience were selected for the validation. The results showed excellent usability, with 95% of experts rating the information system as functionally acceptable. A one way analysis of variance (ANOVA) found no significant difference in usability based on profession or education levels, but a significant difference was observed for experience levels. These findings confirm that i-CAT is a functional, user-friendly, and culturally relevant tool for creativity assessment within Malaysia’s higher education institutions.
Volume: 15
Issue: 2
Page: 1955-1962
Publish at: 2026-04-01

AI-induced fatigue among students in higher education: a latent profile analysis

10.11591/ijai.v15.i2.pp1963-1971
Dynah D. Soriano , Jordan L. Salenga , John Paul P. Miranda , Juvy C. Grume , Emerson Q. Fernando , Jr., Amado B. Martinez , Raymond A. Cabrera , Jaymark A. Yambao
The integration of artificial intelligence (AI) tools in education offers significant benefits but also introduces challenges, including AI-induced fatigue among students. This study aimed to classify students’ experiences with AI tools using latent profile analysis (LPA). A quantitative cross sectional design and referral approach were used to collect survey data from 388 college students who actively used AI tools for academic purposes from November to December 2024. The survey measured AI usage intensity, AI literacy, self-efficacy, perceived usefulness, cognitive load, technostress, sleep quality, general fatigue levels, and attitude toward AI. Descriptive results indicated moderate levels of AI usage intensity, AI literacy, perceived usefulness, cognitive load, sleep quality, and general fatigue, with technostress and attitude toward AI also at moderate levels. Model selection considered Akaike information criterion (AIC), Bayesian information criterion (BIC), entropy, and profile size adequacy, and expert review supported the retained six-profile structure. The LPA identified six interpretable user groups: competent but sleep-deprived users, overwhelmed and high-strain users, stable moderate users, strained moderate users, high intensity strained users, and low-strain selective users. The findings show differences in patterns of competence, strain, fatigue, and sleep outcomes associated with AI tool use, which supports the development of profile specific strategies to manage technostress, cognitive load, fatigue, and sleep disruption among higher education students.
Volume: 15
Issue: 2
Page: 1963-1971
Publish at: 2026-04-01

Real-time detection of rider fatigue: a comparative study of black-box and glass-box artificial intelligence approaches

10.11591/ijai.v15.i2.pp1409-1417
Cynthia Hayat , Iwan Aang Soenandi , Budi Harsono
Rider fatigue poses a critical safety challenge in two-wheeled vehicle operation due to limited physical protection, increased balance demands, and prolonged exposure to environmental stressors. Effective real-time fatigue detection is essential to mitigate accident risks, particularly in high-traffic regions such as Indonesia. This study presents a comparative analysis of black-box and glass-box artificial intelligence (AI) models for real-time detection of rider fatigue, evaluated through a human factor’s lens emphasizing interpretability, intrusiveness, and cognitive compatibility. Multimodal data comprising physiological signals, behavioral indicators, and environmental context were collected using wearable sensors and rider telemetry to train and assess the models. Experimental results reveal that black-box models, including convolutional neural network (CNN) + long short-term memory (LSTM), random forest (RF), and support vector machine (SVM), achieve superior predictive accuracy (94.3%, 91.5%, and 88.2%, respectively) but lack inherent transparency. Conversely, glass-box models such as decision tree (DT) and logistic regression (LR) offer greater interpretability, a critical factor in safety-sensitive applications, though with reduced accuracy (approximately 83–85%). These findings underscore the trade-off between predictive performance and explainability, highlighting the need to tailor model choice to specific operational requirements. This research advances the design of intelligent, human-centered rider support systems that balance accuracy, transparency, and user trust, fostering safer two-wheeled transportation.
Volume: 15
Issue: 2
Page: 1409-1417
Publish at: 2026-04-01

Breast cancer detection using residual DenseNets in deep learning

10.11591/ijai.v15.i2.pp1632-1645
Naganandini Gururajarao , Vishwanath R. Hulipalled
Breast cancer, the leading cause of cancer-related deaths among women globally, requires a prompt and precise diagnosis in order to increase survival rates via therapy. There is a possibility of bias and inconsistency in the results of traditional diagnostic procedures like mammography, ultrasound, and histological testing since they rely on the expertise of radiologists and pathologists. There are exciting new opportunities for breast cancer diagnostics to be enhanced by artificial intelligence (AI) and deep learning. The purpose of this research is to examine the feasibility of using convolutional neural networks (CNNs) and residual dense networks (ResDenseNets) used for breast cancer automated detection in medical images. Because of their superior capacity to learn hierarchical features from raw image data, CNNs are ideal for medical image interpretation. By including residual connections, which allow for the training of considerably deeper models, ResDenseNets—an extension of CNNs—mitigate the problem of vanishing gradient in deep networks. ResDenseNet and CNNs considerably enhance the accuracy of breast cancer diagnosis in comparison to conventional approaches, according to the findings. Notably, ResDenseNets outperform other types of networks because they are able to learn intricate and nuanced properties directly from the data.
Volume: 15
Issue: 2
Page: 1632-1645
Publish at: 2026-04-01

Double-hop of reconfigurable intelligent surfaces-aided for wireless optical link under log-normal fading channels

10.11591/ijai.v15.i2.pp1174-1180
Duong Huu Ai , Van Loi Nguyen , Khanh Ty Luong
In optical wireless communication (OWC), the reconfigurable intelligent surfaces (RIS) are used to manipulate optical signals by controlling the phase shifts or amplitude of reflected beams, which helps improve signal quality. RIS units can be tailored to increase the strength and reliability of the communication link, especially in challenging fading conditions. The double-hop scenario involves two RIS-assisted segments, such as transmitter to RIS-1 and RIS-1 to RIS-2 or a receiver. Each hop encounters log-normal fading, which impacts the overall link performance. Log-normal fading models the irradiance fluctuation caused by turbulence, which is significant in free-space optical (FSO) systems, this fading model assumes that the received optical signal’s amplitude varies with a log-normal distribution, making it more suited for weak to moderate turbulence. Numerical results are obtained under different of link distance, subcarrier quadrature amplitude modulation (QAM) is displayed quantitatively illustrate the average symbol error rate in the absence of RIS and with double-hop of RIS.
Volume: 15
Issue: 2
Page: 1174-1180
Publish at: 2026-04-01

A deep learning-based approach for hearing loss detection

10.11591/ijai.v15.i2.pp1701-1708
Deepa Deepa , Manjula Gururaj Rao
Millions of people across the world are affected by hearing loss and early detection is very important for effective intervention. The traditional hearing screening methods are effective but they often rely on specialized equipment and clinical resources, making them less accessible to common people. Hearing loss is a state that affects the ability to communicate, socially interact and overall quality of life. The advancements in recent years have aimed to enhance the accessibility and efficiency of hearing tests, mainly in remote areas. The accurate classification of hearing loss is essential for effective detection and treatment in audiology. This study presents a deep learning (DL)-based approach based on a feedforward neural network (FNN). This paper focuses on common causes like cerumen impaction, otitis media, and otosclerosis. The study tries to explore ways to improve the diagnosis of hearing loss. The goal is to develop solutions that make hearing screenings more accessible and cost-effective for populations with limited access to healthcare resources. The results show the advantages of DL models in supporting automated accurate classification of hearing loss for intelligent diagnostic systems in audiological healthcare.
Volume: 15
Issue: 2
Page: 1701-1708
Publish at: 2026-04-01
1 2 3
...
2006 2007
Show 22 of 2007

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