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

Tackling the anomaly detection challenge in large-scale wireless sensor networks

10.11591/ijece.v15i2.pp2479-2490
Tamara Zhukabayeva , Aigul Adamova , Lazzat Zholshiyeva , Yerik Mardenov , Nurdaulet Karabayev , Dilaram Baumuratova
One of the areas of ensuring the security of a wireless sensor network (WSN) is anomaly detection, which identifies deviations from normal behavior. In our paper, we investigate the optimal anomaly detection algorithms in a WSN. We highlight the problems in anomaly detection, and we also propose a new methodology using machine learning. The effectiveness of the k-nearest neighbor (kNN) and Z Score methods is evaluated on the data obtained from WSN devices in real time. According to the experimental study, the Z Score methodology showed a 98.9% level of accuracy, which was much superior to the kNN 43.7% method. In order to ensure accurate anomaly detection, it is crucial to have access to high-quality data when conducting a study. Our research enhances the field of WSN security by offering a novel approach for detecting anomalies. We compare the performance of two methods and provide evidence of the superior effectiveness of the Z Score method. Our future research will focus on exploring and comparing several approaches to identify the most effective anomaly detection method, with the ultimate goal of enhancing the security of WSN.
Volume: 15
Issue: 2
Page: 2479-2490
Publish at: 2025-04-01

Maximum expansion with contiguity constraints scheduling algorithm: enhancing uplink transmission in long-term evolution vehicular environments

10.11591/ijece.v15i2.pp1709-1719
Shafinaz Ismail , Shajahan Maidin , Darmawaty Mohd Ali , Mohd Kamarulnizam Abdul Rahim
Uplink scheduling has become increasingly important due to increased activities like uploading videos, photos, and file sharing. Many users share or stream live videos and engage with social networks, significantly increasing uplink data traffic volume. Single carrier frequency division multiple access (SC-FDMA) is favored for its power efficiency and high data rates, benefiting user equipment (UE) battery life. However, maintaining the contiguity of resource blocks (RBs) poses challenges in uplink scheduling. The maximum expansion with contiguity constraints (MECC) algorithm has been introduced to address this challenge. MECC prioritizes contiguity, fairness, and throughput for users at the cell edge. The algorithm operates in two phases: initially allocating RBs proportionally and assigning RBs with the highest metrics while ensuring contiguity. Performance evaluation of MECC, conducted under conditions simulating vehicular movement at 30 km/h, demonstrates its superiority over other algorithms. MECC provides high fairness and throughput for both real-time (RT) and non-real-time (NRT) traffic, making it the preferred scheduler for ensuring quality of service (QoS) for both traffic types. Its focus on contiguity, fairness, throughput, and spectral efficiency establishes MECC as a valuable tool for optimizing uplink transmission in mobile networks, addressing the evolving needs of users in today's digital landscape.
Volume: 15
Issue: 2
Page: 1709-1719
Publish at: 2025-04-01

Improved convolutional neural network-based bearing fault diagnosis using multi-phase motor current signals

10.11591/ijece.v15i2.pp1656-1669
Hai Dang Huu , Ngoc-My Bui , Van-Phuc Hoang , Thang Bui Quy , Yen Hoang Thi
Diagnosing bearing faults of the induction motor is crucial for the maintenance of rotating electrical machines. Numerous methods have been developed and published for monitoring and classifying these faults using sensor data such as vibration, audio, and current signals. Ideally, the current phases are balanced; however, faults disrupt this symmetry, causing each phase to reveal unique diagnostic details. Consequently, studies that rely on a single phase of the current signal may not capture all fault-related characteristics. Research on motor bearing fault diagnosis using two current phases typically extracts features from each phase separately, applying machine learning to classify the faults. Currently, no approach has been proposed to extract features from both phases simultaneously. Furthermore, the proposed solutions have only been published with noise-free data. To address these challenges, this paper introduces an enhanced solution that improves the accuracy of motor bearing fault classification based on an improved convolutional neural network that processes current signals from two phases simultaneously. Experimental results demonstrate that the proposed method significantly outperforms traditional approaches, particularly in scenarios where the sample signals are noise-adding signals. Fault classification accuracy of the proposed improved convolutional neural network (MI-CNN) about 95.12% with noise-adding signals at the signal-to- noise ratio of 20 dB.
Volume: 15
Issue: 2
Page: 1656-1669
Publish at: 2025-04-01

Enhancing credit card security using RSA encryption and tokenization: a multi-module approach

10.11591/ijict.v14i1.pp132-140
Mainak Saha , M. Trinath Basu , Arpita Gupta , K. Ashrith , Chevella Vamshi Vardhan Reddy , Shashanth Reddy , Rohith Reddy
The security of credit card information remains a critical challenge, with existing methods often falling short in safeguarding data integrity, confidentiality, and privacy. Traditional approaches frequently transmit sensitive information in unencrypted formats, exposing it to significant risks of unauthorized access and breaches. This study introduces a robust security framework that leverages Rivest-Shamir-Adleman (RSA) encryption and tokenization to protect credit card information during transactions. The proposed solution is structured into three key modules: merchant, tokenization, and token vault. The merchant module works in tandem with the tokenization module to generate transaction validation tokens and securely transmit credit card data. The token vault, maintained on a secure cloud storage platform, acts as a restricted-access database, ensuring that sensitive information is encrypted and inaccessible to unauthorized entities. Through this multi-layered approach, the study demonstrates a significant enhancement in the security of credit card transactions, effectively mitigating the risks of data breaches and unauthorized disclosures. The findings indicate that the proposed method not only addresses existing security vulnerabilities but also offers a scalable and efficient solution for protecting financial transactions.
Volume: 14
Issue: 1
Page: 132-140
Publish at: 2025-04-01

The advances in natural language processing technology and its impact on modern society

10.11591/ijece.v15i2.pp2325-2333
Nadezhda Borisova , Elena Karashtranova , Irena Atanasova
A wide range of information, such as books, news, reports, and other content, is constantly being produced, much of which is available online. Machine translation, spam detection, natural language interfaces, and question-answering applications have become increasingly popular. Natural language processing (NLP) is at the core of the automatic retrieval of information stored on computers. This article discusses NLP and its applications in daily activities. It covers the main stages of NLP and provides examples of its advances in various higher-level tasks. The objective is to highlight the significance of NLP in processing online content and in efficient interactions between humans and computers across various applications. As an essential element of artificial intelligence, NLP provides solutions for real-world problems and has the potential to transform the way companies operate.
Volume: 15
Issue: 2
Page: 2325-2333
Publish at: 2025-04-01

Enhancing predictive modelling and interpretability in heart failure prediction: a SHAP-based analysis

10.11591/ijict.v14i1.pp11-19
Niaz Ashraf Khan , Md. Ferdous Bin Hafiz , Md. Aktaruzzaman Pramanik
Predictive modelling plays a crucial role in healthcare, particularly in forecasting mortality due to heart failure. This study focuses on enhancing predictive modelling and interpretability in heart failure prediction through advanced boosting algorithms, ensemble methods, and SHapley Additive exPlanations (SHAP) analysis. Leveraging a dataset of patients diagnosed with cardiovascular diseases (CVD), we employed techniques such as synthetic minority over-sampling technique (SMOTE) and bootstrapping to address class imbalance. Our results demonstrated exceptional predictive performance, with the gradient boosting (GBoost) model achieving the highest accuracy of 91.39%. Ensemble techniques further enhanced performance, with the voting classifier (VC), stacking classifier (SC), and Blending achieving accuracies of 91.00%. SHAP analysis uncovered key features such as time, Serum_creatinine, and Ejection_fraction, significantly impacting mortality prediction. These findings highlight the importance of transparent and interpretable machine learning models in healthcare decision-making processes, facilitating informed interventions and personalized treatment strategies for heart failure patients.
Volume: 14
Issue: 1
Page: 11-19
Publish at: 2025-04-01

Factors influencing teacher performance in Shanghai high schools in COVID-19 pandemic

10.11591/ijere.v14i2.31992
Yuan Jiang , Mat Rahimi Yusof , Muhamad Dzahir Kasa
The performance of teachers in schools has become a questionable phenomenon during COVID-19 due to changing landscape of teaching. Since the performance of teachers is linked to performance of students, it is imperative to investigate the influencing factors for teachers’ performance. This study is conducted to examine the relationships between instructional leadership (IL), teaching autonomy (TA), school resources (SR), teacher self-efficacy (TSE), teacher performance (TP) and teaching workload (TW). A sample of 321 responses was collected using a Likert scale questionnaire. Partial least square–structural equation modeling (PLS-SEM) was used to analyze the data using Smart PLS 3. The findings of the study confirmed that TA, IL, and SR are significant antecedents of TSE. The study reports that TSE is a significant predictor of TP. The study reports that TSE is a significant mediator and TW is a significant moderator. The study suggests that TP can be improved with TSE which is improved by IL, TA, and SR. The school education administration in China is required to develop policies in line with this research to contribute to knowledge. The study recommends that the policymakers and practitioners should focus on school’s resources, IL and TA which significantly will improve the performance of teachers in China.
Volume: 14
Issue: 2
Page: 898-909
Publish at: 2025-04-01

Evaluating tumor heterogeneity in oncology with genomic-imaging and cloud-based genomic algorithms

10.11591/ijece.v15i2.pp2427-2435
Gurumoorthi Gurulakshmanan , Raveendra N. Amarnath , Sivaprasad Lebaka , Munnangi Koti Reddy , Nagarajan Mohankumar , Surulivelu Muthumarilakshmi , Chelliah Srinivasan
The goal of this initiative is to rethink how oncology is traditionally practiced by integrating novel approaches to genomic imaging with cloud-based genomic algorithms. The research intends to give a thorough knowledge of cancer biology by focusing on the decoding of tumor heterogeneity as its primary objective. It is possible to get a more nuanced understanding of the intricacy of tumors via the integration of high-resolution imaging tools and sophisticated genetic analysis. It is a pioneering use of cloud computing, which enables the quick analysis of large genomic information. The major goal is to decipher the complex genetic variants that are present inside tumors in order to direct the creation of individualized treatment strategies. This discovery marks a significant step forward, since it successfully bridges the gap between genetics and imaging. Diagnostic accuracy and treatment effectiveness have both been improved. This innovative technique permits real-time analysis, which in turn enables treatment tactics to be adjusted in a timely manner. It makes a significant contribution to the continuous development of oncological research as well as its translation into better clinical outcomes for cancer patients.
Volume: 15
Issue: 2
Page: 2427-2435
Publish at: 2025-04-01

Markov processes in Bayesian network computation

10.11591/ijece.v15i2.pp2181-2191
Assem Shayakhmetova , Nurbolat Tasbolatuly , Ardak Akhmetova , Assel Abdildayeva , Marat Shurenov , Anar Sultangaziyeva
The article examines the influence of Markov processes on computations in Bayesian networks (BN), an important area of research within probabilistic graphical models. The concept of Bayesian Markov networks (BMN) is introduced, an extension of traditional Bayesian networks with the addition of a Markov constraint, according to which the probability in a node can only depend on the state of neighboring nodes. This constraint makes the model more realistic for many practical tasks, as most graphical models that reflect real-world processes possess the Markov property. The article also discusses that Bayesian networks, in the absence of evidence, actually exhibit the Markov property. However, when evidence (additional information) is introduced into the model, challenges arise that require more complex computational methods. In response, the article proposes algorithms adapted for working with Bayesian Markov networks in the presence of evidence. These algorithms are aimed at optimizing computations and reducing computational complexity. Additionally, a comparative analysis of calculations in Bayesian networks without Markov constraints and with them is conducted, highlighting the advantages and disadvantages of each approach. Special attention is paid to the practical applications of the proposed methods and their effectiveness in various scenarios.
Volume: 15
Issue: 2
Page: 2181-2191
Publish at: 2025-04-01

An model for structured the NoSQL databases based on machine learning classifiers

10.11591/ijict.v14i1.pp229-239
Amine Benmakhlouf
Today, the majority of data generated and processed in organizations is unstructured. NoSQL database management systems perform the management of this data. The problem is that these unstructured databases cannot be analyzed by traditional OLAP analytical treatments. The latter are mainly used in structured relational databases. In order to apply OLAP analyses on NoSQL data, the structuring of this data is essential. In this paper, we propose a model for structuring the data of a document-oriented NoSQL database using machine learning (ML). This method is broken down into three steps, first the vectorization of documents, then the learning via different ML algorithms and finally the classification, which guarantees that documents with the same structure will belong to the same collection. Therefore, the modeling of a data warehouse can be carried out in order to create OLAP cubes. Since the models found by learning allow the parallel computation of the classifier, our approach represents an advantage in terms of speed since we will avoid doubly iterative algorithms, which rely on textual comparisons (TC). A comparative study of the performances is carried out in this work in order to detect the most efficient methods to perform this type of classification.
Volume: 14
Issue: 1
Page: 229-239
Publish at: 2025-04-01

The influence of virtual laboratories on students’ interest in STEM fields: a longitudinal study in secondary education

10.11591/ijere.v14i2.30505
Batesh Karimova , Bibigul Zhumabekova , Sholpan Hamzina
The objective of this article is to investigate the impact of virtual laboratories (biology, chemistry, physics, and mathematics) on students’ interest in science, technology, engineering, and mathematics (STEM) fields over six months of study. The study involved 317 participants from Alkey Margulan Pavlodar Pedagogical University (Pavlodar Region, Kazakhstan), who were divided into experimental and control groups. An experimental approach was employed, wherein participants underwent training using virtual laboratories for six months. Statistical methods, specifically t-tests for paired and independent samples, were employed to analyze the results. The experiment revealed a statistically significant positive influence of virtual laboratories on students’ interest in STEM fields. Participants in the experimental group exhibited an increased interest in biology, chemistry, physics, and mathematics compared to the control group. The research findings hold important practical implications for enhancing STEM education. The implementation of virtual laboratories may contribute to an increase in students’ interest in studying STEM disciplines, which is crucial for shaping the future generation of specialists in these fields. Future considerations should involve exploring various types of virtual laboratories, taking into account sociocultural context, and addressing individual differences among students. Additionally, it is essential to investigate the longer-term effects of using digital technologies in STEM education.
Volume: 14
Issue: 2
Page: 1023-1033
Publish at: 2025-04-01

A novel one-dimensional chaotic map with improved sine map dynamics

10.11591/ijece.v15i2.pp2128-2137
Mohamed Htiti , Ismail Akharraz , Abdelaziz Ahaitouf
These days, keeping information safe from people who should not have access to it is very important. Chaos maps are a critical component of encryption and security systems. The classical one-dimensional maps, such as logistic, sine, and tent, have many weaknesses. For example, these classical maps may exhibit chaotic behavior within the narrow range of the rate variable between 0 and 1and the small interval's rate variable. In recent years, several researchers have tried to overcome these problems. In this paper, we propose a new one-dimensional chaotic map that improves the sine map. We introduce an additional parameter and modify the mathematical structure to enhance the chaotic behavior and expand the interval's rate variable. We evaluate the effectiveness of our map using specific tests, including fixed points and stability analysis, Lyapunov exponent analysis, diagram bifurcation, sensitivity to initial conditions, the cobweb diagram, sample entropy and the 0-1 test.
Volume: 15
Issue: 2
Page: 2128-2137
Publish at: 2025-04-01

High speed space division multiplexing based integrated fiber transmission system and its impact on atmospheric conditions

10.11591/ijece.v15i2.pp1745-1753
Kakarla Phaneendra Kumar , T. Sreenivasulu Reddy
With several advantages over traditional wireless and fiber optic cables, free space optical communication is becoming more and more popular because of its high speed and bandwidth applications. In particular, the high transmission capacity of free space optics (FSO) communication systems makes them preferred, which enables them to handle the growing amount of internet traffic. Because FSO has no regulatory limitations, operates over large distances with high levels of security, and transmits data faster than radio frequency communication technologies are widely utilized. However, given different atmospheric conditions, the availability and capacity of FSO optical bands represent a major concern. For next-generation information transmission networks to satisfy end users high-capacity demands, the transmission technology known as space-division multiplexing (SDM) has become essential. Hence in this work, High speed space division multiplexing based integrated fiber/FSO transmission system and its impact on atmospheric conditions is presented. The SDM transmission system developed in this study is based on an integrated multimode fiber (MMF)/ FSO link with linear polarized (LP) spatial modes. This approach takes into consideration extreme climate conditions like snow and turbulence while evaluating performance. Utilizing bit error rate (BER) and received optical power (ROP) are the performance of FSO is evaluated in different weather conditions.
Volume: 15
Issue: 2
Page: 1745-1753
Publish at: 2025-04-01

Readiness of Indonesian physics teachers to implement augmented reality-based learning

10.11591/ijere.v14i2.28769
Zeni Haryanto , Shelly Efwinda , Muhammad Sholeh , Bening Anggraeni , Dian Rachel Pasaribu
In the 21st century, technological development has entered all aspects of life, including education. With its global potential, technology digitizes education, requiring teachers to use technology through media such as augmented reality (AR). This study aims to determine the readiness of physics teachers in Indonesia to implement AR-based learning. More specifically, this research explores the extent to which physics teachers are prepared based on aspects of alignment, capability, and engagement (ACE) in implementing AR-based learning. This exploratory research is conducted by distributing questionnaires with ACE aspects. This study involved several junior and senior high school physics teachers. Data analysis techniques use KH coder and quantitative descriptive. The results show that teachers already know the definition, features, and benefits of AR in learning (alignment aspect). Still, only a minority of teachers have implemented AR-based learning (capability aspect). In the engagement aspect, it is known that teachers want to learn more about how to create AR and implement AR effectively. The implications of this research are recommendations to stakeholders to encourage and facilitate teachers, especially physics teachers.
Volume: 14
Issue: 2
Page: 1398-1407
Publish at: 2025-04-01

Understanding the challenges faced by Orang Asli students in solving mathematics problems

10.11591/ijere.v14i2.29206
Abdul Hakim Abd Jalil , Abdul Halim Abdullah
The educational attainment of Orang Asli students, a minority group in Malaysia, particularly in mathematics, has been a persistent concern. Despite this, research on Orang Asli mathematics education, especially in the southern region of Peninsular Malaysia, remains scarce. This study scrutinized the academic performance of Orang Asli students in whole numbers and operations at level 2 of primary school, focusing on their challenges in solving word problems in mathematics. A total of 22 Orang Asli students from year 4 and 5 in two Orang Asli primary schools participated, undertaking a mathematics test comprising five-word problems. The study identified five prevalent errors among Orang Asli students: i) failure to comprehend the question; ii) misconceptions; iii) inability to grasp specific terms in the question; iv) carelessness; and v) poor reading skills. The findings are thoroughly discussed, and strategies to enhance Orang Asli students’ mathematical problem-solving abilities are proposed.
Volume: 14
Issue: 2
Page: 938-946
Publish at: 2025-04-01
1 2 3
...
2097 2098
Show 319 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