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

Enhancing data security using a multi-layer encryption system

10.11591/ijece.v15i2.pp1961-1967
Osama Abd Qasim , Sajjad Golshannavaz
This study highlights the interesting potential of a new multilayer cryptography scheme for reliable data protection in the field of cybersecurity. To do so, an intensive examination of a multi-layer encryption mechanism is proposed to reinforce the defenses in opposition to online threats to touchy data. The strategy is multilevel, with a superior digital dictionary serving as the foundation for the primary layer. The laborious procedures that went into making this dictionary, including rotation differences, ASCII conversion, and chaotic matrix era, upload to its encoding trouble. A modified model of the advanced encryption standard (AES) algorithm with a brand-new key generation technique, which is based on the chaos idea is furnished through layer 2. A parameter is encrypted using the Rivest-Shamir-Adleman (RSA) method, and further precautions are taken to assure the security of the encryption key. When it comes to encryption time, the first layer significantly outperforms the AES method. In addition to exhibiting instantaneous efficiency in data protection, the first layer outperformed the AES algorithm in terms of encryption time which took more than 3 seconds, and the first layer took less than 0.01 seconds, while both approaches functioned identically in terms of information decryption. In-depth talks are given to customize the suggested method's performance. The results demonstrate the effectiveness of the suggested multi-stage encryption and decryption system and demonstrate its efficacy in protecting text documents.
Volume: 15
Issue: 2
Page: 1961-1967
Publish at: 2025-04-01

Memory management of firewall filtering rules using modified tree rule approach

10.11591/ijict.v14i1.pp141-152
Dhwani Hakani , Palvinder Singh Mann
Firewalls are essential for safety and are used for protecting a great deal of private networks. A firewall’s goal is to examine every incoming and outgoing data before granting access. A notable kind of conventional firewall is the rule-based firewall. However, when it comes to job performance, traditional listed-rule firewalls are limited, and they become useless when utilized with some networks that have extremely big firewall rule sets. This study proposes a model firewall architecture called “TreeRule Firewall,” which has benefits and functions effectively in large-scale networks like “cloud.” In order to improve cloud network security, this study suggests a modified tree rule firewall (MTRF cloud) that eliminates rule discrepancies. For the matching firewall policy, this work creates a tree rule firewall. There are no duplicate rules created by the proposed improved tree rule firewall. Also, memory utilization of different size rules is compared.
Volume: 14
Issue: 1
Page: 141-152
Publish at: 2025-04-01

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

Exploring university students’ engagement and motivation: critical factors

10.11591/ijere.v14i2.30300
Reham Ghanem , Hoda Abdelhameed , Mona Abdulmonem , Rawan Alfrehat , Reem Altaisan , Mona Soliman , Hager Abdel Hameed , Rania Abduljawad , Yousef Alrashed , Nahed Nasr
The study aimed to investigate the critical factors for success students' motivation and their engagement in their learning of Jordan's universities. The quantitative method was employed using a survey questionnaire as the research method to measure students' evaluation of factors. Simple sampling was used to obtain a group of university students. The questionnaire was distributed to 265 university students in Jordan. Data analysis was performed using several analyses such as descriptive analysis, Pearson correlation and regression analysis. The results of the study partially supported several factors influencing students' motivation. The results evidenced that assessment, teaching/learning strategy and students attitudes significantly influenced students learning motivation. The results of this have implications to literature, academicians and decision makers to review and discover the proper methods to invest the necessary tools that can enhance the quality of students learning in the higher education institutions.
Volume: 14
Issue: 2
Page: 1323-1330
Publish at: 2025-04-01

Classification of brain stroke based on susceptibility-weighted imaging using machine learning

10.11591/ijece.v15i2.pp1602-1611
Shaarmila Kandaya , Norhashimah Mohd Saad , Abdul Rahim Abdullah , Ezreen Farina Shair , Ahmad Sobri Muda , Muhammad Izzat Ahmad Sabri
Magnetic resonance imaging (MRI) is used to identify brain disorders, particularly strokes. Rapid treatment, often referred to as "time is brain," is emphasized in recent studies, stressing the significance of early intervention within six hours of stroke onset to save lives and enhance outcomes. The traditional manual diagnosis of brain strokes by neuroradiologists is both subjective and time-intensive. To tackle this challenge, this study introduces an automated method for classify brain stroke from MRI images based on pre- and post-stroke patients. The technique employs machine learning, with a focus on susceptibility weighted imaging (SWI) sequences, and involves four stages: preprocessing, segmentation, feature extraction, classification and performance evaluation. The paper proposes classification and performance evaluation to determine stroke region according to three types of categories, those are poor improvement, moderate improvement and good improvement stroke patients based on pre and post patients. Then, performance evaluation is verified using accuracy, sensitivity and specificity. Results indicate that the hybrid support vector machine and bagged tree (SVMBT) yields the best performance for stroke lesion classification, achieving the highest accuracy which is 99% and showing significant improvement for stroke patients. In conclusion, the proposed stroke classification technique demonstrates promising potential for brain stroke diagnosis, offering an efficient and automated tool to assist medical professionals in timely and accurate assessments.
Volume: 15
Issue: 2
Page: 1602-1611
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

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

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

How teachers’ AI readiness affects AI integration: insights from modeling analysis

10.11591/ijere.v14i2.28242
Nguyen Thi Hong Chuyen , Nguyen The Vinh
This study examined the dynamic relationships among professional development and training, resources and accessibility, attitudes and perceptions, pedagogical knowledge and expertise, teachers’ artificial intelligence (AI) readiness, and the integration of AI in teaching practices. The study employed a non-random purposive approach and utilized the structural equation modeling (SEM) method. Five hypotheses were meticulously formulated and subsequently subjected to empirical scrutiny, involving a cohort of 224 participants. Data were collected via Google Form and subjected to analysis to assess the goodness of fit of the proposed conceptual model. The findings revealed a positive relationship between teachers’ AI readiness and the integration of AI in teaching practices. Additionally, attitudes and perceptions, as well as pedagogical knowledge and expertise, exhibited positive effects on teachers’ AI readiness. However, the associations between teachers’ AI readiness and resources and accessibility, as well as pedagogical knowledge and expertise, were found to be relatively weak and statistically insignificant. The proposed conceptual model accounted for 55.3% of the variance, underscoring the significance of these established relationships for instructors, policymakers, and educators in devising practical intervention strategies to effectively harness the potential of AI.
Volume: 14
Issue: 2
Page: 1496-1505
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

Nonlinear regression analysis to predict mandibular landmarks on panoramic radiographs

10.11591/ijece.v15i2.pp2098-2108
Nur Nafiiyah , Ayu Ismi Hanifah , Edy Susanto , Eha Renwi Astuti , Chastine Fatichah , Ramadhan Hardani Putra , Agus Subhan Akbar
An automatic system for determining mandibular landmark points on panoramic radiography can reduce errors due to differences in expert professionalism and save time. Previous research has shown that the linear regression method is ineffective at predicting condyle and gonion landmark points in panoramic radiography. So, this research proposes an analysis of nonlinear regression methods (support vector machine (SVM) kernel=‘polynomial’, polynomial regression, ensemble regression) for predicting condyle and gonion landmark points. There are four predicted landmark points, namely the right condyle, left condyle, right gonion, and left gonion. The nonlinear regression methods used are SVM, polynomial regression, and ensemble regression. The Dental and Oral Hospital, within the Faculty of Dentistry at Universitas Airlangga, provides the research data. The research encompasses 119 patients between the ages of 19 and 70, dividing 103 into training and 16 into testing. The research results show that the SVM method is only good at predicting the right condyle point with a mean radial error (MRE) of 4,724 pixels. Meanwhile, to predict the left condyle, right gonion, and left gonion points, it is better to use the polynomial regression method and ensemble regression with an order of success detection rate (SDR) of 37.5%, 18.75%, and 12.5%, respectively.
Volume: 15
Issue: 2
Page: 2098-2108
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

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 spatiotemporal weather forecasting accuracy with 3D convolutional kernel through the sequence to sequence model

10.11591/ijece.v15i2.pp2022-2030
Renaldy Fredyan , Karli Eka Setiawan , Kelvin Asclepius Minor
Accurate weather forecasting is important when dealing with various sectors, such as retail, agriculture, and aviation, especially during extreme weather events like heat waves, droughts, and storms to prevent disaster impact. Traditional methods rely on complex, physics-based models to predict the Earth's stochastic systems. However, some technological advancements and the availability of extensive satellite data from beyond Earth have enhanced meteorological predictions and sent them to Earth's antennae. Deep learning models using this historical data show promise in improving forecast accuracy to enhance how models learn the data pattern. This study introduces a novel architecture, convolutional sequence to sequence (ConvSeq2Seq) network, which employs 3D convolutional neural networks (CNN) to address the challenges of spatiotemporal forecasting. Unlike recurrent neural network (RNN)--based models, which are time-consuming due to sequential processing, 3D CNNs capture spatial context more efficiently. ConvSeq2Seq overcomes the limitations of traditional CNN models by ensuring causal constraints and generating flexible length output sequences. Our experimental results demonstrate that ConvSeq2Seq outperforms traditional and modern RNN-based architectures in both prediction accuracy and time efficiency, leveraging historical meteorological data to provide a robust solution for weather forecasting applications. The proposed architecture outperforms the previous method, giving new insight when dealing with spatiotemporal with high density.
Volume: 15
Issue: 2
Page: 2022-2030
Publish at: 2025-04-01

A convex hull based geofencing system to eradicate COVID

10.11591/ijece.v15i2.pp1817-1825
Parul Arora , Suman Deswal
The World Health Organization (WHO) has identified coronavirus disease (COVID-19), as a global pandemic due to its quick global spread to more than 183 countries. Many countries have used movement control orders (MCO) and high alert levels to halt the spread. The primary goal of this research is to provide a geofencing architecture that is specially tailored to the MCO's standard requirement for monitoring an individual's whereabouts during a lockdown. Whenever an individual tests Corona positive, Geofencing uses technology to notify an anticipated network of people who may be affected and to enable traceability for potential patients. Computational techniques such as Delaunay triangulation (inpolygon) and triangle weight characterization (inside polygon) are applied to analyze the geographical boundary in which the patient is isolated. Convex hull, on the other hand, is a better technique than computational algorithms. It is considered the best mathematical technique because it takes the least amount of time (0.014985 sec) to detect the patient within the geofence layer and has the lowest standard deviation when compared with the other computational techniques.
Volume: 15
Issue: 2
Page: 1817-1825
Publish at: 2025-04-01
1 2 3
...
2097 2098
Show 318 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