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

31,458 Article Results

Enhanced accuracy estimation model energy import in on-grid rooftop solar photovoltaic

10.11591/ijece.v14i5.pp5970-5983
Alfin Sahrin , Imam Abadi , Ali Musyafa
Installing rooftop solar photovoltaic (PV) with an on-grid system benefits consumers because it can reduce imports of electrical energy from the grid. This study aims to model the estimation of energy imports generated from on-grid rooftop solar PV systems. This estimation model was carried out in 20 provincial capitals in Indonesia. The parameters used are weather conditions, orientation angle, and energy generated from the on-grid rooftop solar PV system. The value of imported energy is divided into three combinations based on the azimuth angle direction, which describes the type and shape of the roof of the building (one-direction, two-directions, and three-directions). Modeling was done using machine learning with neural network (NN), linear regression, and support vector machine. A comparison of the machine learning algorithm results is NN produces the smallest root mean square error (RMSE) value of the three. Model enhancement uses a grid search cross-validation (GSCV) to become the GSCV-NN model. The RMSE results were enhanced from 53.184 to 44.389 in the one-direction combination, 145.562 to 141.286 in the two-direction combination, and 81.442 to 76.313 in the three-direction combination. The imported energy estimation model on the on-grid rooftop solar PV system with GSCV-NN produces a more optimal and accurate model.
Volume: 14
Issue: 5
Page: 5970-5983
Publish at: 2024-10-01

A novel comprehensive investigation for enhancing cluster analysis accuracy through ensemble learning methods

10.11591/ijece.v14i5.pp5802-5812
H. N. Lakshmi , Thaduri Venkata Ramana , LNC Prakash K , L. Kiran Kumar Reddy , Kachapuram Basava Raju
Ensemble learning stands out as a widely embraced technique in machine learning. This research explores the application of ensemble learning, including ensemble clustering, to enhance the precision of cluster analysis for datasets with multiple attributes and unclear correlations. Employing a majority voting-based ensemble clustering approach, specific techniques such as k-means clustering, affinity propagation, mean shift, BIRCH clustering, and others are applied to defined datasets, leading to improved clustering results. The study involves a comprehensive comparative analysis, contrasting ensemble clustering outcomes with those of individual techniques. The process of improving cluster identification accuracy encompasses data collection, pre-processing to exclude irrelevant elements, and the application of standard clustering algorithms. The task includes defining the optimal number of groups before comparing clustering models. Additionally, a combined model is constructed by merging BIRCH clustering and mean shift clustering, leveraging their advantages to enhance overall clustering strength and accuracy. This research contributes to advancing ensemble learning and ensemble clustering methodologies, offering improved accuracy, and uncovering hidden patterns in complex datasets.
Volume: 14
Issue: 5
Page: 5802-5812
Publish at: 2024-10-01

Scientific landscape on opportunities and challenges of large language models and natural language processing

10.11591/ijeecs.v36.i1.pp252-263
Rachel Edita O. Roxas , Reginald Neil C. Recario
This paper conducted a systematic review of Scopus-indexed publications on large language models (LLMs) and natural language processing (NLP) extracted in October 2023 to address the dearth of literature on their opportunities and challenges. Through bibliometric analysis, from the 1,600 relevant documents, the study explored research productivity, revealing both opportunities and challenges spanning research and real-world applications in education, medicine, and health care, citations, and keyword co-occurrence networks. Results highlighted distribution patterns and dominant players like Google LLC and Stanford University. Opportunities such as technological development in generative artificial intelligence (AI), were contrasted with challenges such as biases and ethical concerns. The intellectual structure analysis revealed prominent application areas in health and education and also emphasized issues such as AI divide and human-AI partnership. Improvement on the technology performance of LLM and NLP remains to be a challenge. Recommendations include further exploration of open research problems and bibliometric studies using other research databases given the research bias towards Scopus-indexed English publications.
Volume: 36
Issue: 1
Page: 252-263
Publish at: 2024-10-01

Effectiveness of digital learning on students’ higher order thinking skills

10.11591/ijere.v13i5.29449
Hamidah Mat , Siti Salina Mustakim , Fazilah Razali , Norliza Ghazali , Asnul Dahar Minghat
In the realm of education, learning and instructional activities play a crucial role in cultivating lasting and meaningful comprehension among science students. This research aims to evaluate the effectiveness of the i-Genius module in enhancing students’ performance in science. The i-Genius module’s development adhered to the ADDIE model, and two specific research questions were formulated: i) is there a statistically significant difference in mean scores between the experimental and control groups? and ii) to what extent can i-Genius contribute to students’ conceptual evolution compared to traditional methods? To address these questions, a sequential mixed-method approach involving interviews, pre-tests, and post-tests was implemented in two distinct schools in the Seremban District. The experimental group comprised 35 participants, and the control group also included 35 students with similar characteristics. Student performance, assessed through pre-test and post-test mean scores, revealed that students exposed to i-Genius achieved significantly higher scores than those exposed to traditional methods in the post-test (t(68)=8.37, p<0.05). This study’s implications lie in its practical application within the school context, offering an alternative instructional tool for teaching science and presenting an instructional model to guide teachers in formulating strategies that encourage problem-posing within the science curriculum.
Volume: 13
Issue: 5
Page: 2817-2824
Publish at: 2024-10-01

Phase structures-based hybrid approaches for defect detection in vials

10.11591/ijece.v14i5.pp5185-5199
C. R. Vishwanatha , V. Asha
Quality control and assurance in pharmaceutical vial manufacturing are paramount to ensure drug safety and efficacy. Defects such as cracks, bubbles, black spots, and wrinkles can compromise product quality and patient safety. This study proposes a novel methodology that integrates fast non-local means (FNLM) filtering with hybrid image processing techniques to detect these defects. Previous approaches have often struggled with subtle anomalies in texture and surface features. The proposed solution leverages phase structure analysis, utilizing phase stretch transform (PST) to effectively highlight subtle anomalies by extracting features sensitive to phase variations. These features are further refined using Gaussian filtering, with Otsu thresholding applied for precise segmentation and defect boundary identification. Morphological dilation enhances detection speed and accuracy, while region of interest (ROI) identification aids in localizing defects and facilitating decision-making. The system demonstrates significant improvements in quality control, achieving high performance metrics: precision (98.85%), recall (98.57%), accuracy (98.36%), specificity (98.0%), and F1-score (98.71%). It also achieves impressive AUC-ROC (98.18%) and AUC-PR (99.08%) values, demonstrating its robustness and suitability for defect detection in pharmaceutical vials.
Volume: 14
Issue: 5
Page: 5185-5199
Publish at: 2024-10-01

Mathematics education in the curricula of the preservice teacher in early childhood education in Spain

10.11591/ijere.v13i5.28892
María de los Ángeles Hidalgo-Méndez , Carmen León-Mantero , José Carlos Casas-Rosal , Miguel Ernesto Villarraga-Rico
The objective of this research is to describe the situation of mathematical training in the early childhood education degree curricula in Spain through the analysis of the teaching guides of the subjects with mathematical content offered in the different Spanish universities. The aim is to identify the typology of subjects, the number of subjects offered, and the recommended bibliography. The methodology used is descriptive, exploratory, ex post facto, and census. For this purpose, the registry of universities, centers, and degrees was first consulted during the 2019-2020 academic year to obtain a list of all the Spanish universities that offer degrees in early childhood education and, therefore, to be able to download the corresponding teaching guides. Of the 91 universities in Spain, the early childhood education degree is taught in 66. Likewise, 101 subjects with mathematical content have been identified, although only 99 are available for analysis. Most are compulsory, have a study load of six European credit transfer system (ECTS) credits, and are taught in the third year of the degree. The recommended bibliography mainly concentrates on publications from 2001-2010 and mostly on book references.
Volume: 13
Issue: 5
Page: 3474-3484
Publish at: 2024-10-01

Experimental study of a medical data analysis model based on comparative performance of classification algorithms

10.11591/ijeecs.v36.i1.pp672-684
Aigerim Ismukhamedova , Indira Uvaliyeva , Zhenisgul Rakhmetullina
This article centers around the development and analysis of machine learning (ML) and deep learning models aimed at enhancing diabetes diagnosis. In the swiftly evolving landscape of data technologies, it becomes crucial to explore the applications of these methods for accurate predictions and improved medical decision-making. Our research encompasses diverse datasets, leveraging state-of-the-art algorithms and technologies for model training and testing. The primary emphasis lies in evaluating the accuracy, sensitivity, and specificity of models within the realm of diabetes diagnosis. The study results reveal significant advancements in disease prediction, underscoring the potential of ML and deep learning in medical applications. This work introduces fresh perspectives on the utilization of computational methods in healthcare and serves as a foundation for prospective research in this domain.
Volume: 36
Issue: 1
Page: 672-684
Publish at: 2024-10-01

Improved deep learning architecture for skin cancer classification

10.11591/ijeecs.v36.i1.pp501-508
Hamza Abu Owida , Nawaf Alshdaifat , Ahmed Almaghthawi , Suhaila Abuowaida , Ahmad Aburomman , Adai Al-Momani , Mohammad Arabiat , Huah Yong Chan
A leading cause of mortality globally, skin cancer is deadly. Early skin cancer diagnosis reduces mortality. Visual inspection is the main skin cancer diagnosis tool; however, it is imprecise. Researchers propose deep-learning techniques to assist physicians identify skin tumors fast and correctly. Deep convolutional neural networks (CNNs) can identify distinct objects in complex tasks. We train a CNN on photos with merely pixels and illness labels to classify skin lesions. We train on HAM-10000 using a CNN. On the HAM10000 dataset, the suggested model scored 95.23% efficiency, 95.30% sensitivity, and 95.91% specificity.
Volume: 36
Issue: 1
Page: 501-508
Publish at: 2024-10-01

Estimation of kernel density function using Kapur entropy

10.11591/ijece.v14i5.pp6016-6022
Leena Chawla , Vijay Kumar , Arti Saxena
Information-theoretic measures play a vital role in training learning systems. Many researchers proposed non-parametric entropy estimators that have applications in adaptive systems. In this work, a kernel density estimator using Kapur entropy of order α and type β has been proposed and discussed with the help of theorems and properties. From the results, it has been observed that the proposed density measure is consistent, minimum, and smooth for the probability density function (PDF) underlying given conditions and validated with the help of theorems and properties. The objective of the paper is to understand the theoretical viewpoint behind the underlying concept.
Volume: 14
Issue: 5
Page: 6016-6022
Publish at: 2024-10-01

Indonesian vocational college students’ attitudes towards project-based learning in English courses

10.11591/ijere.v13i5.28406
Ira Mutiaraningrum , Sri Wuli Fitriati , Issy Yuliasri , Mursid Saleh
Following the mandatory adoption of project-based learning (PjBL) in Indonesian vocational education, there has been a revival in popularity as a prevalent instructional approach in higher education. However, no research on students' attitudes toward mandatory PjBL in Indonesia has raised concerns about its acceptance. This article describes Indonesian vocational college students’ attitudes toward PjBL in English language courses. The study specifically focuses on cognitive, affective, and behavioral attitudes and how students perceive the advantages of PjBL for their English skills and career aspirations. This quantitative study included 336 Indonesian vocational students from twelve state and private colleges in Indonesia. The results of this study revealed that students had a positive attitude toward PjBL in their English courses. Students’ cognitive, affective, and behavioral attitudes indirectly influenced their career aspirations, with English skill benefits acting as mediators. This study proves that how students feel, think, and behave affects their future career goals by shaping how they perceive improvement in their English language skills.
Volume: 13
Issue: 5
Page: 3177-3184
Publish at: 2024-10-01

Tech driven wellness: centralized integrated health management system in UAE

10.11591/ijeecs.v36.i1.pp583-591
Mohamad Fadi Dakwar , Norseen Fadi Dakwar , Halah Yaseen Ali , Yomna O. Shaker
With the ever-more increasing usage of technology in our day-to-day life, an incursion into healthcare has been warranted. Especially in today’s age, where you have digital trackers all around, confusing terms of service, and just in general difficult management of healthcare. HealthPulse seeks to revolutionize that and simplify the concept of healthcare to the simple person. This will be accomplished by integrating the application with the Emirates ID, in the United Arab Emirates, and granting access to various insurance and past records. Additionally, it features a section for early diagnoses and standard measurements, in addition to extensions and plugins to be provided by third parties. Using biometrics will apply in the implementation for the creation of a secure digital national ID and enhancing the merger of public. Machine learning framework, which is trained on a dataset of images of certain diseases will be able to differentiate between a healthy and inflicted cases.
Volume: 36
Issue: 1
Page: 583-591
Publish at: 2024-10-01

Digitalization of educational plays for quality education

10.11591/ijece.v14i5.pp5443-5457
Younes Alaoui Soulimani , Lotfi Elaachak , Mohammed Bouhorma
Repetitive tests on a learning material help schoolchildren to memorize and to learn this material. Psychologists call this phenomenon the testing effect. Skilled teachers use learning plays to embed routine tests in an engaging way. To widespread this practice, we propose a framework to digitize learning plays embedding routine tests into educational videogames. We have identified the smallest set of game design elements required to build an educational videogame out of a learning play. We have used the self-determination theory to group game design elements, and to define a breakdown structure for engagement engineering. This structure helps select the appropriate design elements for an engagement driver. We have applied the framework to digitize a learning play. We have tested the digital play with 238 schoolchildren who considered it as a video game. The video game tested a proposed pattern to create challenges allowing an engaging flow experience. The pattern increased responses (9%) and created time distortion (24%). Delivering rewards following variable schedules reduced errors (49%) and increased time distortion (16%). This research explores how to digitize learning plays into engaging educational video games and how to design engaging video games to remediate missed learning.
Volume: 14
Issue: 5
Page: 5443-5457
Publish at: 2024-10-01

Schema theory’s immediate impact on college students’ Chinese reading comprehension

10.11591/ijere.v13i5.28898
Tsui-Feng Huang , Sheng-Chieh Chou , Anna Liao
Studies show that there is an increase of college students who prefer reading short summaries rather than long complex texts containing knowledge or theory. Thus, this study focuses on improving first-year students’ reading comprehension in Chinese courses by observing the effectiveness of teaching reading lessons in Chinese courses with the curriculum designed based on “schema theory”. The selected reading materials are extensive texts with certain knowledge or theories. For evaluation purposes, the reading test questions uses the same measure of reading proficiency levels of program for international student assessment (PISA) to assess learners’ reading comprehension, contextual reasoning, integration, and analysis abilities more accurately. By comparing the results and discrepancies of the pre- and post-assessment, the preliminary research found that the teaching practice and curriculum designed based on schema theory effectively improves learners' reading scores and instill habits to increase their tendency to reach a deeper understanding of the reading material. This finding demonstrates the effectiveness of applying schema theory to reading lessons; resulting in potential of immediate and enhanced levels of comprehension.
Volume: 13
Issue: 5
Page: 3535-3543
Publish at: 2024-10-01

Research productivity on science learning: a bibliometric study international from 2013 to 2023

10.11591/ijere.v13i5.29103
Widayanti Widayanti , Edi Istiyono , Haryanto Haryanto , Heri Retnawati , Arini Rosa Sinensis , Dian Andesta Bujuri
This research focuses on evaluating research productivity in the realm of science learning using various bibliometric indicators. A total of 4,942 scientific publications were taken from the Scopus database from the period 2013–2023, applying related keyword searches. The result is presented in graphical form. Studies also use VOSviewer and Biblioshiny tools through R to evaluate network visualizations and find the most prolific authors, number of publications and citations, country representatives, organizational and university contributions, publishers, and frequently appearing words. The results reveal a growing trend in total publications in the past 10 years of research. Out of a total of 4,942 scientific publications, NA NA is one of the most prolific authors. The USA and China are the most productive countries when it comes to publishing research in the field. The University of California, National Taiwan Normal University, and Purdue University are reported to be the top three productive organizations in the field of science learning. The study also looked at collaboration and cooperation between authors, countries, and organizations in visualization analysis. The results of the word that often appears are reported to be that science, education, learning, and effects have maximum link strength.
Volume: 13
Issue: 5
Page: 3220-3230
Publish at: 2024-10-01

Proposed model to predict preeclampsia using machine learning approach

10.11591/ijeecs.v36.i1.pp694-702
Raden Topan Aditya Rahman , Muhammad Modi Lakulu , Ismail Yusuf Panessai , Esti Yuandari , Ika Mardiatul Ulfa , Fitriani Ningsih , Lensi Natalia Tambunan
Pregnancy complications, which are the biggest cause of death in productive women, are more common in developing countries with low incomes. One of the contributors to death in pregnant women is preeclampsia which contributes 2-8% every day. Based on research results, more than 70% of the use of technology can be a solution for early prevention in detecting cases of pregnancy. The aim of this research is to build a model for early detection of preeclampsia using a machine learning approach. Sample using retrospective data with sample size 1.473. Based on the result, decision tree (DT) is the best model with accuracy 92.2% (area under curve (AUC): 0.91; Spec: 92.3; and Sens: 83.6), according to weigh correlation we can show 3 (three) highest features causes preeclampsia is history of hypertension, history of diabetes mellitus, and history of preeclampsia. The health of pregnant women is essential in the development of the fetus, so it needs optimal monitoring. Monitoring during pregnancy can now be done through technology-based examinations for assist health workers in making decisions during pregnancy.
Volume: 36
Issue: 1
Page: 694-702
Publish at: 2024-10-01
1 2 3
...
2097 2098
Show 435 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