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

28,451 Article Results

Enhanced pre-broadcast video codec validation using hybrid CNN-LSTM with attention and autoencoder-based anomaly detection

10.11591/ijai.v14.i4.pp2864-2875
Khalid El Fayq , Said Tkatek , Lahcen Idouglid
This study presents a machine learning-based approach for proactive video codec error detection, ensuring uninterrupted television broadcasting for TV Laayoune, part of Morocco’s SNRT network. Building upon previous approaches, our method introduces autoencoders for improved anomaly detection and integrates data augmentation to enhance model resilience to rare codec configurations. By combining convolutional neural networks (CNNs) and long short-term memory (LSTM) networks with an attention mechanism, the system effectively captures spatial and temporal video features. This architecture emphasizes critical metadata attributes that influence video playback quality. Embedded within the broadcasting pipeline, the model enables real-time error detection and alerts, minimizing manual intervention and reducing transmission disruptions. Experimental results demonstrate a 97% accuracy in detecting codec errors, outperforming traditional machine learning models. This study highlights the transformative role of machine learning in broadcasting, enabling scalable deployment across diverse television networks.
Volume: 14
Issue: 4
Page: 2864-2875
Publish at: 2025-08-01

Optimizing traffic lights at unbalanced intersections using deep reinforcement learning

10.11591/ijai.v14.i4.pp2991-3002
Duman Care Khrisne , Made Sudarma , Ida Ayu Dwi Giriantari , Dewa Made Wiharta
Unbalanced intersectional traffic flow increases vehicle delays, fuel consumption, and pollution. This study investigates the application of deep reinforcement learning (DRL) to optimize traffic signal timing at the Pamelisan intersection in Denpasar, Indonesia. Real-world traffic data were incorporated into a SUMO microsimulation environment to train DRL agents using the deep Q-network (DQN) algorithm. Experimental results show that DRL-based optimization reduced the average vehicle waiting time from 594.49 seconds (static control) to 169.44 seconds and 173.10 seconds for agents trained without and with noise, respectively. The average vehicle speed remained stable at 5.6–5.97 m/s across all scenarios, indicating enhanced traffic efficiency without adverse effects. The findings underscore the effectiveness and adaptability of DRL in addressing traffic inefficiencies, optimizing them, and offering a robust solution for dynamic traffic management at unbalanced traffic intersections in urban areas.
Volume: 14
Issue: 4
Page: 2991-3002
Publish at: 2025-08-01

Machine learning application for particle accelerator optimization-a review

10.11591/ijai.v14.i4.pp3014-3021
Isti Dian Rachmawati , Nazrul Effendy , Taufik Taufik
Particle accelerators receive significant attention from researchers. This machine consists of various interdependent elements, so it is complex. Efficient system tuning and diagnostics are essential for utilizing accelerator technology. In addition, machine learning (ML) has been applied in several applications. ML methods such as artificial neural networks, random forest, reinforcement learning, genetic algorithm, and Bayesian optimization have been used for accelerator optimization. The optimization of particle accelerators covers their performance and efficiency. This paper reviews the application of ML techniques in optimizing particle accelerators, highlighting their importance in addressing the complexity inherent in accelerator systems and advancing accelerator science and technology.
Volume: 14
Issue: 4
Page: 3014-3021
Publish at: 2025-08-01

Bolstering image encryption techniques with blockchain technology - a systematic review

10.11591/ijict.v14i2.pp594-604
Narmadha Annadurai , Agusthiyar Ramu
Multimedia data plays a momentous role in present world. With the advancements in various fields of research like internet of things (IoT), industrial IoT (IIoT), cloud computing, medical image processing, and many more technologies, the digital images have already encroached the multimedia eon. The major challenge lies in providing a tamper proof image with higher level of security and confidentiality while being transmitted through a public network. Image encryption techniques are considered to be the predominant method to anticipate security from any unauthorized user access. This has indeed provoked the researchers to create new diverse and hybrid algorithms for encrypting the images. At present blockchain has been the most prevalently discussed method for security and the next level of security can be foreseen using the blockchain encryption techniques. This paper identifies the literature which mainly focuses on assorted image encryption techniques with blockchain technology applied on digital images from heterogeneous sources. An overview has been proposed to discuss on these techniques.
Volume: 14
Issue: 2
Page: 594-604
Publish at: 2025-08-01

Improving the transfer learning for batik besurek textile motif classification

10.11591/ijai.v14.i4.pp3172-3181
Marissa Utami , Ermatita Ermatita , Abdiansah Abdiansah
This proposed research discussion is a new combination model for classifying batik besurek fabric from the implementation transfer learning with mixed contrast enhancement, activation function, and optimizer method. The size of the batik besurek fabric motif image as an input image is 250×250 with three channels consisting of red, green, and blue totaling five classes, namely kaligrafi, rafflesia, burung kuau, relung paku and rembulan. All images in the dataset will be divided into train data (1540 images), validate data (380 images), and test data (480 images) that are taken directly from the batik store in Bengkulu. The division method used is stratified random sampling to take all the data, shuffles it, and divides the data sets for each class. Based on the experiment results, ResNet50 obtained the best performance compared to MobileNetV2, InceptionV3, and VGG16, with a training accuracy of 99.60%, a validation accuracy of 97.44%, and a testing accuracy of 98.12%. In the improvement experiment phase, the ResNet50 model with Adam optimizer, rectified linear unit (ReLU) activation function and contrast limited adaptive histogram equalization (CLAHE) as the contrast enhancement method obtained the highest test accuracy (98.75%), showing that CLAHE was very effective in improving performance on batik besurek data.
Volume: 14
Issue: 4
Page: 3172-3181
Publish at: 2025-08-01

Interpretable machine learning for academic risk analysis in university students

10.11591/ijai.v14.i4.pp3089-3098
Mukti Ratna Dewi , Mochammad Reza Habibi , Bassam Babgei , Lovinki Fitra Ananda , Brodjol Sutijo Suprih Ulama
Higher education institutions often grapple with issues related to academic risk among their students. These academic risks encompass low academic performance, study delays, and dropouts. One approach to address these challenges is to predict students’ academic performance as accurately as possible by leveraging advanced computational techniques and utilizing academic and non-academic student data. This research aims to develop a model that accurately identifies students with high potential for academic risk while explaining the contributing factors to this phenomenon in the Faculty of Vocational Studies, Institut Teknologi Sepuluh Nopember (ITS). The prediction model is constructed using the light gradient boosting machine (LightGBM) method and is subsequently interpreted using the Shapley additive explanations (SHAP) value. Additionally, an oversampling method, based on synthetic minority oversampling technique (SMOTE), is implemented to address imbalances in the dataset. The proposed approach achieves 96% and 97% accuracy and specificity rates, respectively. Analysis based on SHAP values reveals that extracurricular activities, choice of major, smoking habit, gender, and friendship circle are among the top five factors impacting students’ academic risk.
Volume: 14
Issue: 4
Page: 3089-3098
Publish at: 2025-08-01

Optimizing long short-term memory hyperparameter for cryptocurrency sentiment analysis with swarm intelligence algorithms

10.11591/ijai.v14.i4.pp2753-2764
Kristian Ekachandra , Dinar Ajeng Kristiyanti
This study investigates the application of swarm intelligence algorithms, specifically particle swarm optimization (PSO), ant colony optimization (ACO), and cat swarm optimization (CSO), to optimize long short-term memory (LSTM) networks for sentiment analysis in the context of cryptocurrency. By leveraging these optimization techniques, we aimed to enhance both the accuracy and computational efficiency of LSTM models by fine-tuning critical hyperparameters, notably the number of LSTM units. The study involved a comparative analysis of LSTM models optimized with each algorithm, evaluating performance metrics such as accuracy, loss, and execution time. Results indicate that the PSO-LSTM model achieved the highest accuracy at 86.08% and the lowest loss at 0.57, with a reduced execution time of 58.43 seconds, outperforming both ACO-LSTM and CSO-LSTM configurations. These findings underscore the effectiveness of PSO in tuning LSTM parameters and emphasize the potential of swarm intelligence for enhancing neural network performance in real-time sentiment analysis applications. This research contributes to advancing optimized deep learning techniques in high dimensional data environments, with implications for improving cryptocurrency sentiment predictions.
Volume: 14
Issue: 4
Page: 2753-2764
Publish at: 2025-08-01

Continuous professional development for madrasa teacher professionalism: engaging motivation for engagement

10.11591/ijere.v14i4.33501
Syahraini Tambak , Desi Sukenti , Ahmad Zabidi Abdul Razak , Agustina Agustina , Khalilullah Amin Ahmad , Firdaus Firdaus , Miftah Syarif
Much research has been done on continuous professional development (CPD) madrasa (Islamic school) teachers, but incorporating motivation of engagement in future professions into them needs to be addressed. This study aims to determine CPD madrasa teachers based on the motivation to engage future professionals in teaching. This research used a phenomenological design involving 16 madrasa Aliyah teachers as informants. Data was collected by interviews with madrasa teachers and analyzed using a systematic design. This research shows that CPD madrasa teachers are related to organizing teaching and learning activities to improve teachers' abilities and competencies in carrying out professional duties and performing as educators. CPD should include skills using digital technology, ethics, and professional values, applying sharia principles, makarim sharia, and integrity in educating students. Madrasa teachers’ view of motivation for engagement in a future profession in CPD refers to the drive that teachers professionals have to continue to be committed to their profession and develop with the changes and demands of the times. The motivation for madrasa teachers’ future professional involvement and sustainable professional development is mutually reinforcing. Motivation becomes a driving force for madrasa teachers to engage in CPD, while CPD renews and strengthens madrasa teachers’ motivation by providing the skills and knowledge necessary to adapt to future challenges. In this way, motivation and CPD together support better quality education, increase job satisfaction for madrasa teachers, and ensure that teachers remain relevant and competent in facing developments in the world of education.
Volume: 14
Issue: 4
Page: 3171-3182
Publish at: 2025-08-01

Design and assessment of effective multimedia-based courseware for student quantitative data analysis

10.11591/ijere.v14i4.32055
Abdulnassir Yassin , Ashadi Bashir , Herman Dwi Surjono , Zul Afdal , Victor Novianto
The rapidly evolving technological trends are transforming higher education. This study focused on designing and evaluating the effectiveness of multimedia-based courseware in improving students’ data analysis at Islamic University in Uganda. The objectives were: i) to create interactive multimedia courseware (IMC) to enhance students’ quantitative data analysis skills; ii) to evaluate the suitability of IMC’s content, interactivity, user interface, and design; and iii) to profile students’ perceived benefits of using the IMC to learn quantitative data analysis. A descriptive survey involving 160 education undergraduate finalists, selected through random and consensus sampling, was conducted. Data was collected through a self-report survey instrument with high validity (content validity index=0.886) and reliability (Cronbach alpha=0.878). The IMC development followed the analysis, design, development, implementation, and evaluation (ADDIE) model and Gagne’s learning events. Results indicated that the IMC content (mean=3.90, SD=0.94), interactivity (mean=4.10, SD=0.79), user interface (mean=4.04, SD=0.82), and screen design (mean=4.05, SD=0.87) were highly appropriate. Students perceived IMC as effective in enhancing their data analysis skills (mean=3.86, SD=0.92). The findings suggest that IMC can significantly improve students’ quantitative analysis abilities. However, recommending further studies on the impact of IMC on students’ quantitative data analysis skills comprehensively in a multidisciplinary manner, to potentially revolutionize learning.
Volume: 14
Issue: 4
Page: 3103-3115
Publish at: 2025-08-01

Comparing bidirectional encoder representations from transformers and sentence-BERT for automated resume screening

10.11591/ijai.v14.i4.pp3404-3411
Asmita Deshmukh , Anjali Raut Dahake
In today’s digital age, organizations face the daunting challenge of efficiently screening an overwhelming number of resumes for job openings. This study investigates the potential of two state-of-the-art natural language processing models, bidirectional encoder representations from transformers (BERT) and sentence-BERT (S-BERT), to automate and optimize the resume screening process. The research addresses the need for accurate, efficient, and unbiased candidate evaluation by leveraging the power of these transformer-based language models. A comprehensive comparison between BERT and S-BERT is performed, evaluating their performance across multiple metrics, including accuracy, screening time, correlation with job descriptions, and ranking quality. The findings reveal that S-BERT outperforms BERT, achieving higher accuracy (90% vs. 86%), faster screening time (0.061 seconds vs. 1 second per resume), and stronger correlation with job descriptions (0.383855 vs. 0.1249). S-BERT though has a smaller vector size of 384 enables capturing richer semantic information compared to BERT’s vector size of 768, contributing to its superior performance. The study provides insights into the strengths and limitations of each model, offering valuable guidance for organizations seeking to streamline their talent acquisition processes and enhance candidate selection through automated systems.
Volume: 14
Issue: 4
Page: 3404-3411
Publish at: 2025-08-01

Improving firewall performance using hybrid of optimization algorithms and decision trees classifier

10.11591/ijai.v14.i4.pp2839-2848
Mosleh M. Abualhaj , Ahmad Adel Abu-Shareha , Sumaya Nabil Al-Khatib , Adeeb M. Alsaaidah , Mohammed Anbar
One of the primary concerns of governments, corporations, and even individual users is their level of online protection. This is because a large number of attacks target their primary assets. A firewall is a critical tool that almost every organization uses to protect its assets. However, firewalls become less reliable when they deal with large amounts of data. One method for reducing the amount of data and enhancing firewall performance is feature selection. The main aim of this study is to enhance the firewall's performance by proposing a new feature selection method. The proposed feature selection method combines the strengths of Harris Hawks optimization (HHO) and whale optimization algorithm (WOA). Experiments were performed utilizing the NSL-KDD dataset to measure the effectiveness of the proposed method. The experiments employed the decision trees (DTs) as a machine classifier. The experimental results show that the achieved accuracy is 98.46% when using HHO/WOA for feature selection and DT for classification, outperforming the HHO and WOA when used separately for feature selection. The study's findings offer insightful information for researchers and practitioners looking to improve firewall effectiveness and efficiency in defending internet connections against changing threats.
Volume: 14
Issue: 4
Page: 2839-2848
Publish at: 2025-08-01

Enhancing touchless smart locker systems through advanced facial recognition technology: a convolutional neural network model approach

10.11591/ijai.v14.i4.pp3262-3273
Abdul Haris Rangkuti , Evawaty Tanuar , Febriant Yapson , Felix Octavio Sijoatmodjo , Varyl Hasbi Athala
As the world recovers from COVID-19, demand for contactless systems is increasing, promising safety and convenience. Touchless technology, particularly public locker security systems that use facial recognition and hand detection, is advancing rapidly. The system minimizes physical contact, increasing user safety. It uses advanced models such as multi-task cascaded convolutional networks (MTCNN) and RetinaFace, FaceNet512, ArcFace, and visual geometry group (VGG)-Face for face detection and recognition, with a combination of RetinaFace, ArcFace, and L2 norm Euclidean or cosine as the most effective distance metric method, where the accuracy reaches 96 and 90%. 'Yourvault', an application demonstrating this efficient security feature, provides notifications for mask detection, facial authenticity and locker status, offering a solution to the problem of convenience and security of public spaces. Future research could investigate the impact of photo age on facial recognition accuracy, potentially making touchless systems more efficient. In general, the application of this technology is an important step towards a safer and more comfortable world after the pandemic. This model approach can be followed up with more optimal facial recognition.
Volume: 14
Issue: 4
Page: 3262-3273
Publish at: 2025-08-01

Urban incident detection based on hybrid convolutional neural networks and bidirectional long short-term memory

10.11591/ijai.v14.i4.pp3153-3159
Meryem Ayou , Jaouad Boumhidi
Real-time incident detection is a major challenge in urban roads. This paper proposes an innovative hybrid method for incident detection, combining convolutional neural networks (CNN) and bidirectional-long short-term memory (Bi-LSTM). CNN extracts complex spatial features from raw data, while Bi-LSTMs are used for incident detection by capturing long-term temporal dependencies present in data. The proposed algorithm is evaluated using simulated data from the open-source software simulation of urban mobility (SUMO). This combination improves incident detection's accuracy and robustness by exploiting spatial and temporal information. Experimental results show that our hybrid approach outperforms the support vector machine (SVM), random forest (RF), and Bi-LSTM algorithms, with a substantial decrease in false positives and the speed of detecting urgent situations.
Volume: 14
Issue: 4
Page: 3153-3159
Publish at: 2025-08-01

An optimal pheromone-based route discovery stage for 5G communication process in wireless sensor networks

10.11591/ijai.v14.i4.pp2788-2796
Sinduja Mysore Siddaramu , Kanathur Ramaswamy Rekha
The rapid advancement of 5G communication underscores the need for heightened efficiency within wireless sensor networks (WSNs), where challenges such as data loss, inefficiency, and jitter are exacerbated by complex operations. This paper presents the optimal pheromone-based route discovery stage (OpRDS) algorithm, inspired by the natural foraging behaviors of ants, as a novel solution designed to optimize routing processes in the dynamic and demanding 5G environments. The study conducts a comparative analysis of OpRDS against traditional routing protocols, including the ad hoc on-demand distance vector (AODV), destination-sequenced distance-vector (DSDV), dynamic source routing (DSR), and zone routing protocol (ZRP), focusing on key performance metrics such as packet delivery ratio (PDR), latency, throughput, routing overhead (RO), energy consumption (EC), network lifespan, route discovery speed, and scalability. Our results reveal that OpRDS significantly outperforms the conventional protocols, evidencing a 2% increase in PDR, a 5.5% decrease in latency, a 6.7% rise in throughput, an 8.3% reduction in RO, an 11.1% decrease in EC (resulting in an 11% extension of network lifespan), a 10% improvement in route discovery speed, and a 6.7% enhancement in scalability. These findings highlight the algorithm's superior efficiency and adaptability in addressing the robust demands of 5G networks.
Volume: 14
Issue: 4
Page: 2788-2796
Publish at: 2025-08-01

An automatic social engagement measurement during human-robot interaction

10.11591/ijai.v14.i4.pp2805-2814
Wael Hasan Ali Almohammed , Sinan Adnan Muhisn , Zahraa AbedAljasim Muhisn
Social engagement refers the expressions of existing interpersonal relationships during the interaction which represents the actual interesting of human in the interaction. However, social engagement measurement is a significant concern in social human-robot interaction (HRI) because of its role in understanding the interaction’s trend and adapt robot’s behavior accordingly. Hence, we achieved the two main objectives of this study. Firstly, enrichment the theoretical literature and related concepts. Secondly, proposed a robust neural network model which is multilayer perceptron (MLP) classifier to measure social engagement state during interaction. PInSoRo dataset was used for training and testing purpose. In particular, the parameters of MLP model were meticulously crafted to recognize the social engagement accurately. We evaluated the model’s performance by several metrics and the result showed an interesting accuracy reached 94.85%. Given that, it supports the robot to has adaptive and responsive behavior in real time applications which is improving HRI eventually.
Volume: 14
Issue: 4
Page: 2805-2814
Publish at: 2025-08-01
1 2 3
...
1896 1897
Show 48 of 1897

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