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

25,002 Article Results

Enhancing accuracy in greenhouse microclimate forecasting through a hybrid long short-term memory light gradient boosting machine ensemble approach

10.11591/ijece.v15i2.pp2392-2403
Mokeddem Kamal Abdelmadjid , Seddiki Noureddine , Bourouis Amina , Benahmed Khelifa
Greenhouse cultivation is one of the main methods for improving agricultural yield and quality. With the world needing more and more production, improving greenhouses using innovative technology becomes a must. These high-tech, aka, smart greenhouses depend much on the accuracy and availability of sensor data to perform at their best. In challenging situations such as sensor malfunctions or data gaps, utilizing historical data to predict microclimate parameters within the greenhouse is essential for maintaining optimal growing conditions and effective sustainable resource management control. In this work, and by employing a synthesis technique across various time series models, we forecast internal temperature and humidity, the two main parameters for a greenhouse, by incorporating diverse characteristics as input into a customized forecasting model. The selected architecture integrates deep learning and nonlinear learning models, specifically long short-term memory (LSTM) and light gradient boosting machine (LightGBM) as an ensemble approach, providing a comprehensive framework for time-series prediction, evaluated through mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R²) metrics. With a focus on improving accuracy in anticipating environmental changes, we have achieved high precision in predicting temperature (98.45%) and humidity (99.61%).
Volume: 15
Issue: 2
Page: 2392-2403
Publish at: 2025-04-01

A secure and cloud-based patient management system using attribute-based encryption algorithm

10.11591/ijece.v15i2.pp2445-2454
Senthilkumar Kalarani , Mahalingam Shobana , Edamakanti Uma Shankari , Bolly Joshi Praveena , Subramaniam Shanthi , Rathinasabapathy Ramadevi , Rajendar Sandiri
Using attribute-based encryption (ABE), cloud-based patient management systems may be made more secure and efficient. The goal is to provide a scalable encryption infrastructure with dynamic attribute handling and context-aware access control for safe data access. Encryption procedures should directly comply with regulatory criteria to secure healthcare data and ensure data privacy and integrity. Secure attribute issuance and revocation are achieved using advanced key management and real-time auditing and monitoring to identify and react to unauthorised access. To help healthcare providers handle data, user-centric security measures including extensive training and adaptive security procedures are used. The encryption system is implemented and maintained using cost-effective cloud and open-source methodologies to ensure seamless integration and operational effectiveness in healthcare contexts. First, secure patient management system dataset results reveal ABE algorithm encryption. The encrypted values are 8F5D6A..., 7C4A3B..., 6E3B2C..., 9D8A7B..., 5E4D3C.... in the second instance, derived from role-based access control of ABE. The patients are 25-60 years old, have medical codes 101-105, 201-205, and 301-305. For roles from different fields, attribute code is 401-406, level code is 501-505.
Volume: 15
Issue: 2
Page: 2445-2454
Publish at: 2025-04-01

Novel technique to deblurring and blur detection techniques for enhanced visual clarity of ancient images

10.11591/ijece.v15i2.pp2314-2324
Poonam Pawar , Bharati Ainapure
Digital image quality often degrades due to various factors such as noise and blur. Many images are affected by these issues, reducing their clarity and accuracy. This degradation is especially problematic for ancient images, significantly hampers the ability to analyze historical documents and artworks. This paper presents a novel approach to both blur detection and deblur ancient images, enhancing their clarity and readability. This research introduces a technique that combines wavelet transform and convolutional neural networks (CNNs) for effective blur identification and deblurring, specifically aimed at restoring blurred ancient images, regardless of the type of blur degradation. This novel approach demonstrated an average accuracy of 98.3% in blur detection on ancient image datasets. The performance of deblurring algorithms is typically evaluated using metrics such as peak signal-to-noise ratio (PSNR), mean squared error (MSE), and structural similarity index (SSIM) which quantify fidelity and quality of the deblurred images. In the deblurring, this approach produced PSNR values of 55.5 to 68.3 dB, MSE values of 2.99 to 11.1, and an SSIM of 0.9 across different types of blurs. These results show significant promise for the restoration of ancient images, providing researchers, historians, and archaeologists with valuable tool for conservation cultural heritage.
Volume: 15
Issue: 2
Page: 2314-2324
Publish at: 2025-04-01

Design and experimental validation of a single phase grid tied inverter for residential low power applications

10.11591/ijece.v15i2.pp1372-1384
Ali Mousmi , Ambroise Schellmanns , Salem Elghadhi , Quentin Desouches
This paper presents the design and control of a single phase grid tied inverter intended for low power applications in residential sector as part of smart grid environments or solar photovoltaic source integration. The total cost of the converters used in such applications involving low power rates, generally lower than 1 kW, cannot afford expensive components or complex techniques, so, the optimization of the power circuits as well as the simplification of the control algorithms are necessary to meet the specifications. In this purpose, this work presents the design steps of a single phase grid tied inverter including the structure choice, a synchronization algorithm based on the grid voltage zero crossing method, and the algorithm to control the injected power. Different experimental tests have been carried out and show the good performance of the converter which meets the requirements in terms of total harmonic distortion and efficiency.
Volume: 15
Issue: 2
Page: 1372-1384
Publish at: 2025-04-01

Intrusion detection based on generative adversarial network with random forest for cloud networks

10.11591/ijece.v15i2.pp2491-2498
Gnanam Jeba Rosline , Pushpa Rani
The development of cloud computing enables individuals and organizations to access a wide range of online programs and services. Because of its nature, numerous users can access and distribute cloud infrastructure. In cloud computing several security threats change the data and operations. A network's ability to detect malicious activity and possible threats is greatly aided by intrusion detection. To solve these issues, intrusion detection based on generative adversarial network with random forest (GAN-RF) for cloud networks is introduced. The function of the generative adversarial networks (GANs) based network abnormality recognition system is evaluated. It uses the CICIDS2018 dataset to detect intrusion. GAN is utilized to improve network anomaly detection in conjunction with an ensemble random forest (RF) classifier. The GAN-RF model achieved 95.01% of accuracy for intrusion detection and obtain better recall and F1-score. Extensive assessments and valuations illustrate the efficiency of the GAN-RF approach in accurately identifying network issues.
Volume: 15
Issue: 2
Page: 2491-2498
Publish at: 2025-04-01

Advancing network security: a comparative research of machine learning techniques for intrusion detection

10.11591/ijece.v15i2.pp2271-2281
Shynggys Rysbekov , Abylay Aitbanov , Zukhra Abdiakhmetova , Amandyk Kartbayev
In the current digital era, the advancement of network-based technologies has brought a surge in security vulnerabilities, necessitating complex and dynamic defense mechanisms. This paper explores the integration of machine learning techniques within intrusion detection systems (IDS) to tackle the intricacies of modern network threats. A detailed comparative analysis of various algorithms, including k-nearest neighbors (KNN), logistic regression, and perceptron neural networks, is conducted to evaluate their efficiency in detecting and classifying different types of network intrusions such as denial of service (DoS), probe, user to root (U2R), and remote to local (R2L). Utilizing the national software laboratory knowledge discovery and data mining (NSL-KDD) dataset, a standard in the field, the study examines the algorithms’ ability to identify complex patterns and anomalies indicative of security breaches. Principal component analysis is utilized to streamline the dataset into 20 principal components for data processing efficiency. Results indicate that the neural network model is particularly effective, demonstrating exceptional performance metrics across accuracy, precision, and recall in both training and testing phases, affirming its reliability and utility in IDS. The potential for hybrid models combining different machine learning (ML) strategies is also discussed, highlighting a path towards more robust and adaptable IDS solutions.
Volume: 15
Issue: 2
Page: 2271-2281
Publish at: 2025-04-01

The impact of revenue structure on the financial performance of general colleges and universities in China

10.11591/ijere.v14i2.30543
Hou Yuyan , Hazianti Abdul Halim , Mohd Faizal Basri
Despite the continuous increase in total funding for general colleges and universities in China, these institutions face challenges related to insufficient educational funds and inefficient fund utilization, leading to suboptimal financial performance. Therefore, the main purpose of this study is analyzing their revenue structures, which comprise the proportion of financial subsidy revenue, career revenue and other revenue and to examine the impact of revenue structures on their financial performance (measured by talent cultivation, scientific research, and social services). This study builds linear regression models and combines panel data of general colleges and universities from 2010 to 2021 to study the impact of revenue structure on their financial performance. The findings indicate that the revenue of general colleges and universities in China is based mainly on financial subsidy revenue, with the proportion of such revenue increasing annually. The financial performance of these institutions also predicates an increasing trend. Most importantly, regression analysis shows that financial subsidy revenue has a positive impact on financial performance, whereas career revenue and other revenue negatively impact financial performance. Thus, Chinese general colleges and universities should prioritize increasing financial subsidy revenue while carefully managing career and other revenue to enhance financial performance.
Volume: 14
Issue: 2
Page: 1114-1123
Publish at: 2025-04-01

Enhancing mathematics learning in phase E: assessing Wordwall effectiveness

10.11591/ijere.v14i2.30051
Sri Rezeki , Sindi Amelia
The use of technology, classroom atmosphere, facilities, and learning resources can support quality learning outcomes in students. Wordwall, as a gamification tool, has been proven to be effective for elementary and junior high school students in mathematics. However, the effectiveness of Wordwall in enhancing senior high school students’ cognitive abilities in mathematics learning has not been investigated. Previous studies have only shown its effectiveness in improving affective abilities. Therefore, this study endeavors to evaluate the effects of using Wordwall on the mathematics learning outcomes of senior high school students in phase E. Through quasi-experimental research with pre- and post-test group design, 38 experimental class students and 37 control class students were selected as samples in this study. The study found a statistically significant difference (sig. 0.000<0.05) in the mean learning outcomes of students who used Wordwall compared to those who did not. Descriptively, the experimental group displayed superior average mathematics learning outcomes compared to the control group, demonstrating a moderate level of effectiveness (ES=0.57). The strong effect of Wordwall can be realized if it is used not only as an exercise tool within the classroom but also as an instrument for knowledge transformation, incorporating consideration of students’ learning styles.
Volume: 14
Issue: 2
Page: 1246-1252
Publish at: 2025-04-01

Principal instructional leadership practice and its relationship with teacher job performance

10.11591/ijere.v14i2.31127
Xiang Yuanyuan , Bity Salwana Alias
Excellent principal leadership actions will be guidance for teachers’ high-quality teaching performance. However, the role of instructional principal is not fully utilized, and principals lack the highly effective leadership qualities necessary to promote teachers in improving teacher job performance. This study was conducted in Shenzhen, China to investigate the effect of principal instructional leadership practices on teachers’ job performance. This study employed a quantitative approach. The sample of the study was all private secondary school teachers in Shenzhen China, consisting of 297 teachers selected from 1,300 populations. To figure out the research questions, SPSS software was used with the help of descriptive and inferential analysis. The findings of this study show that both principal instructional leadership practice and teachers’ job performance are at a high level. Moreover, there was a very strong positive relationship between two variables (r=0.974). In conclusion, the findings underscore the significance of principals’ instructional leadership attributes on teacher job performance and provide implications for the government and the school principals regarding the implementation of principal training system or the improvement of educational management policy in private schools throughout Shenzhen, China.
Volume: 14
Issue: 2
Page: 1097-1104
Publish at: 2025-04-01

Digital media’s role in overcoming anxiety, enhancing linguistic elements and fostering motivation for developing speaking skills

10.11591/ijere.v14i2.31931
Syamsudin Syamsudin , Langgeng Budianto , Kususanto Ditto Prihadi , Djoko Susanto , Abdul Rohman , Ahmad Kholil , Muhammad Anwar Firdousi
The qualitative study investigated the digital media impact on language learning, focusing on overcoming anxiety, enhancing linguistic elements, and fostering motivation for developing speaking skills among four English as foreign language (EFL) learners at an Islamic University in Malang, Indonesia. Through the use of observations and in-depth interviews, the study found that learners utilized various digital media such as storytelling, movies, variety shows, and song videos to aid their speaking learning process. The findings indicated that digital media played a significant role in helping learners overcome language anxiety by providing a platform for practice without direct peer interaction, thereby reducing feelings of fear and shyness. Additionally, digital media usage contributed to linguistic element enhancement, including vocabulary, pronunciation, grammar, and speaking fluency. Moreover, learners’ motivation for developing speaking skills was positively influenced by the enjoyment derived from using digital media which increased their willingness to practice speaking. The study underscores the importance of integrating digital media into EFL speaking instruction due to its potential to address language anxiety, improve linguistic elements, and foster motivation for speaking ability development. By leveraging digital media tools effectively, educators can create engaging and supportive learning milieus that provide to the diverse needs of language learners, eventually enhancing learners’ speaking skills.
Volume: 14
Issue: 2
Page: 1379-1388
Publish at: 2025-04-01

Accounting education from 1960 to 2023: a bibliometric review

10.11591/ijere.v14i2.30486
Guojing Hu , Haslinah Muhamad , Hasri Mustafa , Mushtaq Yousif Alhasnawi
Since 1960, publications in accounting education have demonstrated a high level of productivity and influence. However, few studies have attempted to use bibliometric methods to map and visualize accounting education research. This study aimed to identify global issues in accounting education through bibliometric analysis, covering the period from 1960 to 2023, by exploring publication trends, top topics, and major contributors in the field. Tools such as Microsoft Excel, VOSviewer, the bibliometric R-package, and WordSift were utilized to comprehensively analyze 717 Scopus-indexed documents. The findings underscore a continuous and recently accelerated historical evolution of accounting education publications, with primary research areas clustering around “business, management, and accounting.” Noteworthy trends include a geographic concentration in the United States, the United Kingdom, and Australia, with RMIT University emerging as a key contributor. Hassell, from the United States, is recognized as the most influential author, and “accounting education” from Taylor & Francis stands out as the most productive journal. Works by Bui and Porter in 2020 emerge as the most frequently cited documents. The research results indicate that future research directions should focus on students, higher education, and the profession, emphasizing themes such as curriculum, learning, and skills.
Volume: 14
Issue: 2
Page: 849-861
Publish at: 2025-04-01

Attention, relevance, confidence, and satisfaction motivation model in mathematics education: a systematic literature review

10.11591/ijere.v14i2.31597
He Mengyao , Zaleha Ismail , Norulhuda Ismail , He Xueting
With the aims to find out how the attention, relevance, confidence, and satisfaction (ARCS) motivation model was applied into mathematics education; what research methods were used; and what outcomes were reported in these empirical studies, this paper systematically reviewed the empirical studies applied the ARCS motivation model into mathematics education trends on 2013-2023. Among 26 articles identified, the findings of this review indicated that the data from several contexts support the applicability of the ARCS model in diverse environments for mathematics learning, across different stages students, and in various nations. Three dimensions of the role of the ARCS model in mathematics education studies are identified: instructional design; theoretical framework; and measurement tool. Quantitative method was used most, and experimental studies and quasi-experimental studies were the main methods. Three types of outcomes were mainly focused on the past empirical studies: affective outcomes, cognitive outcomes, social outcomes. The findings highlighted the prospective paths that this area of research should pursue.
Volume: 14
Issue: 2
Page: 1506-1517
Publish at: 2025-04-01

Multiple intelligence based tasks for enhancing reading motivation of university students in Ethiopia

10.11591/ijere.v14i2.30195
Teshale Alemu Gebremeskel , Mebratu Mulatu Bachore , Elias Woemego Bushisso
The purpose of the study was to investigate the effectiveness of multiple intelligence-based tasks in enhancing students’ motivation towards reading. It employed a quasi-experimental design. A total of 60 communicative English class university students, who were selected purposefully participated as treatment and comparison groups. The research process was carried out with reading tasks that were designed based on a model for teaching using multiple intelligence-driven tasks for the treatment group while the comparison group followed the conventional approach for 12 weeks. English-reading motivation questionnaires and focused group discussions were used to gather data. Data normality check was carried out using Shapiro-Wilk tests, and a p value of 0.05 was used to determine the level of significance. T-tests were used to compare the scores between the two groups. It was found that multiple intelligence-based reading tasks (MIBRT) brought a significant difference in the students’ motivation, with the effect size value ranging from low (for importance), moderate (for efficacy and for extrinsic), and strong (for intrinsic). It was suggested that university teachers should use multiple intelligence-driven reading tasks as an alternative scaffolding tools to raise the motivational levels of struggling readers in the context of the study.
Volume: 14
Issue: 2
Page: 1548-1556
Publish at: 2025-04-01

The effect of convenience and self-efficacy on the satisfaction of learning management system usage

10.11591/ijere.v14i2.32065
Zulherman Zulherman , Abu Bakar Ahmad Mansor , Christoph Kulgemeyer
Universities widely use the learning management system (LMS) technology due to its flexibility and ease of use for lecturers when managing online learning with the LMS. The primary determinant of success is the admittance of students utilizing this technology based on the LMS. However, institutions have challenges when utilizing LMS systems. The study aims to evaluate the factors that impact student satisfaction (SS) when using the LMS. The study methodology employs the Delone McLean model technique, incorporating the elements of convenience (Co) and self-efficacy (SE) into the survey. Data was gathered from a sample of 178 undergraduate students. The data analysis conducted using structural equation modeling (SEM) partial least squares (PLS) entailed the testing of six hypotheses. The results found that only three hypotheses were supported: information quality (IQ) and system quality (SQ) had a positive impact on SS. Student satisfaction also harmed the use of LMS (LU). This research contributes to the knowledge that internal and external factors of the LMS system also play an important role in the satisfaction of LMS usage.
Volume: 14
Issue: 2
Page: 910-917
Publish at: 2025-04-01

Exploring the development of front office instructional module from the experts’ opinions

10.11591/ijere.v14i2.30124
Wei Boon Quah , Tajularipin Sulaiman , Fazilah Razali
In the world of hospitality, the front office plays a crucial role as it is the first point of contact for guests entering a hotel. This makes front office operation (FOO) a vital subject in hospitality education programs, especially at community colleges. While there is a growing body of research on FOO, there's a lack of instructional modules designed specifically for community college students. To address this gap, a study was conducted to understand the need for developing a FOO module based on expert opinions. Using the analyze, design, develop, implement, and evaluate (ADDIE) framework, data from three experts were analyzed. Educators cited issues such as limited practice time, communication skill hesitancy, and struggles with term comprehension and pronunciation. Meanwhile, students encountered obstacles like inadequate practical equipment, unsupportive learning environments, and overwhelming syllabi. Nonetheless, educators acknowledged the potential of a FOO instructional module to enhance student learning experiences. This study emphasizes the significance of crafting a tailored module for community college students, paving the way for advancements in hospitality education.
Volume: 14
Issue: 2
Page: 1172-1182
Publish at: 2025-04-01
1 2 3
...
1666 1667
Show 22 of 1667

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