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

29,922 Article Results

Quality of service optimization for 4G LTE upload and download throughput

10.11591/ijict.v14i3.pp1024-1033
Afrizal Yuhanef , Siska Aulia , Lefenia Indriani
Demand for mobile data services and people’s dependence on 4G LTE networks continue to increase. However, the quality of service (QoS) of this network still requires improvement, especially regarding the effect of QoS on throughput at specific frequencies. The research gap lies in the lack of indepth analysis of the impact of QoS parameters on network performance at frequencies of 2,100 MHz and 2,300 MHz. This study evaluates the effect of QoS parameters, such as delay, jitter, and packet loss, on throughput in 4G LTE networks at both frequencies. The research methodology uses an experimental approach with throughput, delay, jitter, and packet loss measurements in various network conditions. The results showed that delay (17.2174 ms to 37.0322 ms), jitter, and packet loss significantly influence throughput, ranging from 624.5 Kbps to 1,322.4 Kbps. The 2,100 MHz frequency tends to show better performance than 2,300 MHz. This study concludes that optimizing QoS parameters, especially delay and jitter, can significantly improve 4G LTE network performance. These findings provide practical contributions for mobile operators in improving network quality and customer satisfaction and open opportunities for further research on other frequencies or newer network technologies.
Volume: 14
Issue: 3
Page: 1024-1033
Publish at: 2025-12-01

Real-time posture monitoring prediction for mitigating sedentary health risks using deep learning techniques

10.11591/ijict.v14i3.pp1126-1135
D. B. Shanmugam , J. Dhilipan
Sedentary behavior has become a pressing global public health issue. This study introduces an innovative method for monitoring and addressing posture changes during inactivity, offering real-time feedback to individuals. Unlike our prior research, which focused on post-analysis, this approach emphasizes real-time monitoring of upper body posture, including hands, shoulders, and head positioning. Image capture techniques document sedentary postures, followed by preprocessing with bandpass filters and morphological operations such as dilation, erosion, and opening to enhance image quality. Texture feature extraction is employed for comprehensive analysis, and deep neural networks (DNN) are used for precise predictions. A key innovation is a feedback system that alerts individuals through an alarm, enabling immediate posture adjustments. Implemented in MATLAB, the method achieved accuracy, sensitivity, and specificity rates of 98.2%, 90.7%, and 99.2%, respectively. Comparative analysis with established methods, including support vector machine (SVM), random forest, and K-nearest neighbors (KNN), demonstrate the superiority of our approach in accuracy and performance metrics. This real-time intervention strategy has the potential to mitigate the adverse effects of sedentary behavior, reducing risks associated with cardiovascular and musculoskeletal diseases. By providing immediate corrective feedback, the proposed system addresses a critical gap in sedentary behavior research and offers a practical solution for improving public health outcomes.
Volume: 14
Issue: 3
Page: 1126-1135
Publish at: 2025-12-01

Novel multilevel local binary texture descriptor for oral cancer detection

10.11591/ijict.v14i3.pp837-844
Vijaya Yaduvanshi , Raman Murugan
Categorizing texture medical images is an extensive job in most of the fields of computer vision, pattern recognition and biomedical imaging. For the past few years, the texture analysis system model, especially for biological images, has been brought to attention because of its ever-growing requirements and characteristics. This research shows its novelty by using a multilevel local binary texture descriptor (MLBTD) algorithm with support vector machine (SVM), k-nearest neighbor (KNN), and CT Classifiers to investigate the texture features of the oral cancer samples. The simulation work is done in MATLAB2021a environment by employing the MLBTD algorithm. A Mendeley dataset, containing 89 oral cavity histopathological images and 439 OSCC images in 100x magnification, is used. A statistical comparative study of local binary pattern (LBP) and MLBTD with linear SVM, KNN, CT classifier is performed in which results show the better performance of MLBTD and linear SVM with 89.94% of accuracy and by applying MLBTD algorithm over 90.57% accuracy is obtained whereas LBP algorithm only provides 86.16% of accuracy.
Volume: 14
Issue: 3
Page: 837-844
Publish at: 2025-12-01

State space controller of SLCC and design analysis with MPPT approaches

10.11591/ijict.v14i3.pp791-801
Jeyaprakash Natarajan , Nivethitha Devi Manoharan , Mohanasanthosh Murugan , Karnati Venkata Lokeshwar Reddy , Thirumalaivasal Devanathan Sudhakar
Power systems with standalone properties like remote unit telecommunication network requires high negative DC supply voltage. In such remote places, solar photovoltaic (PV) are used to generate power. Maximum power point tracking techniques (MPPT) gives unregulated voltage from solar panel. This unregulated voltage is converted into regulated voltage by providing proper pulse width modulation (PWM) signal to self-lift cuk converter (SLCC). In comparison with classic cuk converter, SLCC reduces load voltage and load current ripples. This paper focuses on state space controller design and implementation of SLCC used in MPPT based PV system. The switching pulse of SLCC can be generated by perturb and observe (P&O), incremental conductance (IC) and also using fuzzy control. The simulation of SLCC has been performed using MATLAB/Simulink and its specifications in time domain has been compared.
Volume: 14
Issue: 3
Page: 791-801
Publish at: 2025-12-01

Legal challenges of artificial intelligence in the European Union’s digital economy

10.11591/ijict.v14i3.pp960-971
Volodymyr I. Kudin , Tamara Kortukova , Maryna Dei , Andrii Onyshchenko , Petro Kravchuk
This article critically examines the legal and regulatory challenges posed by artificial intelligence (AI) within the European Union’s (EU) digital economy, focusing on the recently adopted EU Ai Act (Regulation 2024/1689). While previous studies have addressed AI's ethical and theoretical dimensions, this research fills a gap by analyzing the Act’s practical application across its temporal, personal, material, and territorial scopes. The study adopts a qualitative legal methodology, integrating doctrinal interpretation, comparative analysis, and systemic review of EU and international legal instruments. Key findings reveal that the EU AI Act establishes a pioneering risk-based regulatory framework, distinguishing itself through strong safeguards for fundamental rights, transparency, and human oversight. However, critical limitations remain, including ambiguous high-risk classifications, reliance on provider self-assessment, and exemptions for national security that may undermine human rights protections. The article compares the EU approach with those of the United States and China, illustrating divergent models of AI regulation and their global implications. It argues that while the EU AI Act sets an ambitious precedent, its success depends on effective enforcement, stakeholder compliance, and international regulatory convergence. By addressing these challenges, the EU can shape a globally influential framework for ethical and responsible AI deployment. This study contributes to the evolving academic and policy debate on AI governance by offering practical insights and recommendations for future research and legal development.
Volume: 14
Issue: 3
Page: 960-971
Publish at: 2025-12-01

Does empathy and awareness of bullying affect the performance of Moroccan students in PISA?

10.11591/ijict.v14i3.pp860-867
Ilyas Tammouch , Abdelamine Elouafi , Soumaya Nouna
Socioemotional skills, such as empathy and bullying awareness, play a pivotal role in shaping students' personal and academic development. These skills are increasingly recognized as critical factors influencing educational outcomes, particularly in addressing challenges like bullying that can hinder learning. This study examines the impact of empathy and bullying awareness on the academic performance of Moroccan students, using data from the 2018 Programme for International Student Assessment (PISA). To ensure robust causal inference in high-dimensional data, the double/debiased machine learning (DML) technique is employed. The findings reveal that higher levels of empathy and awareness of bullying significantly enhance performance across reading, mathematics, and science, with the most notable improvements observed in reading. These results remain consistent across various demographic and socioeconomic groups, highlighting their robustness. The study underscores the importance of integrating socioemotional learning into educational practices to foster academic success and create supportive school environments. By contributing to the growing evidence on non-cognitive skills in education, this research offers valuable insights for educators and policymakers seeking to improve student outcomes.
Volume: 14
Issue: 3
Page: 860-867
Publish at: 2025-12-01

Enhancing biodegradable waste management in Mauritius through real-time computer vision-based sorting

10.11591/ijict.v14i3.pp1119-1125
Geerish Suddul , Avitah Babajee , Nundjeet Rambarun , Sandhya Armoogum
Mauritius faces a significant waste management challenge due to the indiscriminate mixing of biodegradable and non-biodegradable waste. This practice hinders proper recycling and composting efforts, contributing to environmental pollution and resource depletion. This research proposes a computer vision-based system for real-time classification of waste into biodegradable and non-biodegradable categories. Transfer learning approach based on deep learning models, specifically DenseNet121, MobileNet, InceptionV3, VGG16 and VGG19 were evaluated with two different classifiers, the K-nearest neighbors (KNN) and support vector machine (SVM). Our experiments demonstrate that the MobileNet paired with SVM achieves a classification accuracy of 97% for detection in realtime. Compared to other studies, our results demonstrate better performance and realtime classification capabilities through the implementation of a prototype, facilitating automatic sorting of waste.
Volume: 14
Issue: 3
Page: 1119-1125
Publish at: 2025-12-01

AI-based federated learning for heart disease prediction: a collaborative and privacy-preserving approach

10.11591/ijict.v14i3.pp751-759
Stuti Bhatt , Surender Reddy Salkuti , Seong-Cheol Kim
People with symptoms like diabetes, high BP, and high cholesterol are at an increased risk for heart disease and stroke as they get older. To mitigate this threat, predictive fashions leveraging machine learning (ML) and artificial intelligence (AI) have emerged as a precious gear; however, heart disease prediction is a complicated task, and diagnosis outcomes are hardly ever accurate. Currently, the existing ML tech says it is necessary to have data in certain centralized locations to detect heart disease, as data can be found centrally and is easily accessible. This review introduces federated learning (FL) to answer data privacy challenges in heart disease prediction. FL, a collaborative technique pioneered by Google, trains algorithms across independent sessions using local datasets. This paper investigates recent ML methods and databases for predicting cardiovascular disease (heart attack). Previous research explores algorithms like region-based convolutional neural network (RCNN), convolutional neural network (CNN), and federated logistic regressions (FLRs) for heart and other disease prediction. FL allows the training of a collaborative model while keeping patient info spread out among various sites, ensuring privacy and security. This paper explores the efficacy of FL, a collaborative technique, in enhancing the accuracy of cardiovascular disease (CVD) prediction models while preserving data privacy across distributed datasets.
Volume: 14
Issue: 3
Page: 751-759
Publish at: 2025-12-01

Predictive insights into student online learning adaptability: elevating e-learning landscape

10.11591/ijict.v14i3.pp892-902
Mohamed El Ghali , Issam Atouf , Kamal El Guemmat , Mohamed Talea
In Morocco’s rapidly transforming educational landscape, this study delves into students’ adaptability to online learning environments by integrating sophisticated artificial intelligence (AI) algorithms and hyperparameter optimization techniques. This research uses the comprehensive “online learning adaptivity” dataset to identify pivotal factors influencing student flexibility and effectiveness in e-learning platforms. We applied various AI models, with a particular emphasis on the CatBoost classifier, which exhibited exceptional predictive performance, achieving an accuracy rate near 98%. This high precision in predicting student adaptiveness offers essential insights into tailoring digital education systems. The results underscore the significant potential of machine learning technologies to enhance educational methodologies by catering to the diverse needs of students. Such capabilities are instrumental for educators and policymakers dedicated to refining e-learning strategies that effectively accommodate individual learning styles, ultimately improving the broader educational outcomes in Moroccan tertiary education. These findings advocate for a more nuanced understanding of the interplay between student behavior and technological solutions, providing a roadmap for developing more responsive and effective educational platforms.
Volume: 14
Issue: 3
Page: 892-902
Publish at: 2025-12-01

Optimized ultra-low power and reduced delay GNR Ternary SRAM using a 7-transistor architecture

10.11591/ijict.v14i3.pp1044-1055
Ravikishore Gaddikoppula , Nandhitha Nathakattuvalasu Muthu
Greater need and evolution in electronics require a memory device that can go with a decreased power delay, SRAM plays an important role as a storage element in digital circuit design. Power and delay are vital problems faced by today’s RAM technology. It is necessary to lessen the power and increase the speed. There is a need to reduce power utilization and time delay. The proposed method is seen in the Electronics technical tool H-Spice technology. The technique proposed on DRG 7T- transistors SRAM consumes less power and delay. After the analysis and enhancement of the circuit, this approach gives the power delay product of the graphene nanoribbon (GNR) 7T SRAM as 80% at 0.7 V, 59% at 0.8 V, 34 % at 0.9 V, which is much less when compared to conventional SRAM power delay product.
Volume: 14
Issue: 3
Page: 1044-1055
Publish at: 2025-12-01

Shellcode classification analysis with binary classification-based machine learning

10.11591/ijict.v14i3.pp923-932
Jaka Naufal Semendawai , Deris Stiawan , Iwan Pahendra Anto Saputra , Mohamed Shenify , Rahmat Budiarto
The internet enables people to connect through their devices. While it offers numerous benefits, it also has adverse effects. A prime example is malware, which can damage or even destroy a device or harm its users, highlighting the importance of cyber security. Various methods can be employed to prevent or detect malware, including machine learning techniques. The experiments are based on training and testing data from the UNSW_NB15 dataset. K-nearest neighbor (KNN), decision tree, and Naïve Bayes classifiers determine whether a record in the test data represents a Shellcode attack or a non-Shellcode attack. The KNN, decision tree, and Naïve Bayes classifiers reached accuracy rates of 96.26%, 97.19%, and 57.57%, respectively. This study's findings aim to offer valuable insights into the application of machine learning to detect or classify malware and other forms of cyberattacks.
Volume: 14
Issue: 3
Page: 923-932
Publish at: 2025-12-01

Revolutionizing human activity recognition with prophet algorithm and deep learning

10.11591/ijict.v14i3.pp1108-1118
Jaykumar S. Dhage , Avinash K. Gulve
Various industries, such as healthcare and surveillance, depend heavily on the ability to recognize human activity. The “human activity recognition (HAR) using smartphones data set” can be found in the UCI online repository and includes accelerometer and gyroscope readings recorded during a variety of human activities. The accelerometer and gyroscope signals are also subjected to a band-pass filter to eliminate unwanted frequencies and background noise. This method effectively decreases the dimensionality of the feature space while improving the model's accuracy and efficiency. “Convolutional neural networks (CNNs)” and “long shortterm memory (LSTM)” networks are combined to create pyramidal dilated convolutional memory network (PDCMN), which is the final proposal. Results from experiments demonstrate the effectiveness and reliability of the suggested method, demonstrating its potential for precise and effective HAR in actuality schemes.
Volume: 14
Issue: 3
Page: 1108-1118
Publish at: 2025-12-01

Quantifying the severity of cyber attack patterns using complex networks

10.11591/ijict.v14i3.pp1179-1188
Ahmed Salih Hasan , Yasir F. Mohammed , Basim Mahmood
This work quantifies the severity and likelihood of cyberattacks using complex network modelling. A dataset from common attack pattern enumerations and classifications (CAPEC) is collected and formalized as nodes and edges aiming at creating a network model. In this model, each attack pattern is represented as a node, and an edge is created between two nodes when there is a relation between them. The dataset includes 559 attack patterns and 1921 relations among them. Network metrics are used to perform the analysis on the network level and node level. Moreover, a rank of the CAPECs based on a complex network perspective is generated. This rank is compared with the CAPEC ranking system and deeply discussed based on cybersecurity perspective. The findings show interesting facts about the likelihood and severity of attacks. It is found that the network perspective should be given attention by the CAPEC ranking system. Finally, the results of this work can be of high interest to security architects.
Volume: 14
Issue: 3
Page: 1179-1188
Publish at: 2025-12-01

Leveraging IoT with LoRa and AI for predictive healthcare analytics

10.11591/ijict.v14i3.pp1156-1162
Pillalamarri Lavanya , Selvakumar Venkatachalam , Immareddy Venkata Subba Reddy
Progress in mobile technology, the internet, cloud computing, digital platforms, and social media has substantially facilitated interpersonal connections following the COVID-19 pandemic. As individuals increasingly prioritise health, there is an escalating desire for novel methods to assess health and well-being. This study presents an internet of things (IoT)-based system for remote monitoring utilizing a long range (LoRa), a low-cost and LoRa wireless network for the early identification of health issues in home healthcare environments. The project has three primary components: transmitter, receiver, and alarm systems. The transmission segment captures data via sensors and transmits it to the reception segment, which then uploads it to the cloud. Additionally, machine learning (ML) methods, including convolutional neural networks (CNN), artificial neural networks (ANN), Naïve Bayes (NB), and long short-term memory (LSTM), were utilized on the acquired data to forecast heart rate, blood oxygen levels, body temperature patterns. The forecasting models are trained and evaluated using data from various health parameters from five diverse persons to ascertain the architecture that exhibits optimal performance in modeling and predicting dynamics of different medical parameters. The models' accuracy was assessed using mean absolute error (MAE) and root mean square error (RMSE) measures. Although the models performed similarly, the ANN model outperformed them in all conditions.
Volume: 14
Issue: 3
Page: 1156-1162
Publish at: 2025-12-01

Electric load forecasting using ARIMA model for time series data

10.11591/ijict.v14i3.pp830-836
Balasubramanian Belshanth , Haran Prasad , Thirumalaivasal Devanathan Sudhakar
Any country's economic progress is heavily reliant on its power infrastructure, network, and availability, as energy has become an essential component of daily living in today's globe. Electricity's distinctive quality is that it cannot be stored in huge quantities, which explains why global demand for home and commercial electricity has grown at an astonishing rate. On the other hand, electricity costs have varied in recent years, and there is insufficient electricity output to meet global and local demand. The solution is a series of case studies designed to forecast future residential and commercial electricity demand so that power producers, transformers, distributors, and suppliers may efficiently plan and encourage energy savings for consumers. However, load prognosticasting has been one of the most difficult issues confronting the energy business since the inception of electricity. This study covers a new one–dimensional approach algorithm that is essential for the creation of a short–term load prognosticasting module for distribution system design and operation. It has numerous operations, including energy purchase, generation, and infrastructure construction. We have numerous time series forecasting methods of which autoregressive integrated moving average (ARIMA) outperforms the others. The auto–regressive integrated moving average model, or ARIMA, outperforms all other techniques for load forecasting.
Volume: 14
Issue: 3
Page: 830-836
Publish at: 2025-12-01
1 2 3
...
1994 1995
Show 78 of 1995

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