International Journal of Education and Management Engineering @ijeme
Journal articles - International Journal of Education and Management Engineering
All articles: 685
Interactive Web-interface for Competency-based Classroom Assessment
Scientific article
In this study, four phases of competency-based learning model, namely, i) unconscious incompetence, ii) conscious incompetence, iii) conscious competence and iv) unconscious competence is deployed in classroom teaching methodology. Competency-based learning model helps to understand a student's competence level on a particular topic that is already delivered in the classroom. The current work introduces a web-based competency-based learning model which is focused towards meeting learning objectives. Using the model, post lecture classroom online quiz will help to categorize the weaker student and also will also help to know the emotional state of the learners.
Free
Introducing Arabic-SQuADv2.0 for Effective Arabic Machine Reading Comprehension
Scientific article
Machine Reading Comprehension (MRC), known as the ability of computers to read and understand unstructured text and then answer questions, is still an open research field. MRC is considered one of the most research-demanding sub-tasks in Natural Language Processing (NLP) and Natural Language Understanding (NLU). MRC introduces multiple research challenges. One of these challenges is that the models should be trained to answer all questions and abstain from answering when the answer is not covered in the given context. Another challenge lies in dataset availability. These challenges are amplified for non-Latin-based languages; Arabic as an example. Currently, available Arabic MCR datasets are either small-sized high-quality collections or large-sized low-quality datasets. Additionally, they do not include unanswerable questions. This lack of resources depicts the model as incapable of real-world deployments. To tackle these challenges, this paper proposes a novel large-size high-quality Arabic MRC dataset that includes unanswerable questions, named “Arabic-SQuAD v2.0'”. The dataset consists of 96051 triplets {question, context, answer} in an attempt to help enrich the field of Arabic-MRC. Furthermore, a Machine Learning (ML)-based model is introduced that is capable of effectively solving Arabic MRC-with-unanswerable questions. The results of the proposed model are satisfactory and comparable with Latin-based language models. Furthermore, the results show a significant improvement of the current state-of-the-art Arabic MRC. To be exact, the model scores 71.49 F1-score and 65.12 Exact Match (EM). This proposed dataset and implementation pave the way to further Arabic MRC; aiming to reach a state when MRC models could mimic human text reasoning.
Free
Investigation and Study on the Status of the College Students with Left-Behind Experience in China
Scientific article
College students with left-behind experience are a special group and have different characteristics compared to students without left-behind experience. Based on investigation, college students with left-behind experience and interview some students around at them, this paper analyzed the basic situations of the college students with left-behind experience, as well as the key factors leading to these situations. Finally, the corresponding suggestions and expectations to improve the situations are put forward.
Free
Investigation of Student Dropout Problem by Using Data Mining Technique
Scientific article
Throughout the past twenty years, we've seen a huge increase in the number of school universities. Given the intense competition among major universities and schools, this attracts students to apply for admission to these institutions. Early school dropout prediction is a critical problem for learners, and it is hard to tackle. And a wide number of factors can impact student retention. In order to attain the best accuracy, the conclusion of the program, the standard classification approach that was used to solve this problem frequently needs to be applied the majority of organizations and courses launched by universities operate on either an auto model, therefore they always prefer course enrollment over student caliber. As a result, many students stop taking the course after the first year. In order to manage student dropout rates, this research provides a data mining application. The predictive model may provide an effective predictive list of students who typically require the greatest help from the student dropout program given updated data on new students. The results indicate that the object classification algorithm Random Forest data mining technique can create a reliable prediction model using existing student academic data. Future research on student dropout rates will continue to be vital for informing policy decisions, identifying at-risk populations, evaluating interventions, enhancing support services, predicting trends, understanding long-term consequences, and promoting global learning and collaboration in education.
Free
K-Nearest Neighbors Bayesian Approach to False News Detection from Text on Social Media
Scientific article
Social media usage has increased due to the rate at which technologies are emerging and it is less likely to detect false news/information manually as it aims to capture the human mind. The spread of false news can cause havoc; therefore, detection of false news becomes paramount where almost everyone has access to social media. Our proposed system optimizes the false news detection process. The system combines advantages of two textual feature extraction methods and two machine learning algorithms for text classification. Basic pre-processing methods were employed. Feature extraction was carried out using Term Frequency-Inverse Document Frequency with Word2Vector. K-Nearest Neighbour (KNN) and Naïve Bayes (NB) algorithms are combined to give KNN Bayesian. The most available systems made use of a single feature extraction method but in our system, two feature extraction methods are combined. The evaluation metrics used were accuracy, precision, recall, f1score and KNN Bayesian performed better than KNN. To further evaluate our model, the Area under the Curve-Receiver Operator Characteristics (AUC-ROC) revealed that AUC of KNN Bayesian ROC curve is higher than that of KNN.
Free
Key term extraction using a sentence based weighted TF-IDF algorithm
Scientific article
Keyword ranking with similarity identification is an approach to find the significant Keywords in a corpus using a Variant Term Frequency Inverse Document Frequency (VTF-IDF) algorithm. Some of these may have same similarity and they get reduced to a single term when WordNet is used. The proposed approach that does not require any test or training set, assigns sentence based Weightage to the keywords(terms) and it is found to be effective. Its suitability is analyzed with several data sets using precision and recall as metrics.
Free
Keyphrase extraction of news web pages
Scientific article
Keyphrase extraction from news web pages is an important task for news documents retrieval and summarization. Keyphrases are like index terms that enclose the important information about document content. Keyphrases actually offer concise and precise description of document content. Key phrases are considered as a single word or a combination of more than one word that represent the important concepts in a text documents. The aim of this paper is to develop and evaluate an automatic keyphrases extraction approach for news web pages. Our approach identifies the candidate keyphrases from documents and chooses those candidate keyphrase having highest weight score. Weight formula combines the feature set that includes TF*IDF, phrase disatnce in documents and lexical chain that is based on WordNet to represent semantic relations between words. The experimental results show that the performance of our approach is better than the contemporary approaches today.
Free
Scientific article
The purpose of this study was to describe Academic Cyber Loafing in Management Departement Soegijapranata Chatolic University students in online learning because of the covid 19 pandemic. The instrument in this study was developed from previous research by adding two indicators, namely physical activity, and enrichment of knowledge as a novelty in this study. Methods of data collection using a questionnaire. The data were analyzed descriptively quantitatively and categorized into minor, serious, or not doing Academic Cyberloafing, and the causes were identified. The results of the study show that the level of Academic Cyberloafing is in a low category and the level of Academic Cyberloafing is in the high seriousness in the aspect of enrichment to knowledge, which means that students independently access the internet to enrich knowledge even by ignoring ongoing online learning. The research results found something different from the results in previous research, where this research found a positive impact of Academic Cyberloafing, namely enriching knowledge, while in previous research it was more towards a negative impact. Another thing is that physical activities are the cause of Academic Cyberloafing, which was not the case in previous research. This study found that students were “forced” to engage in Academic Cyber Loafing because of the sudden increase in demands for personal needs as a result of online learning, and changes in family income because parents were laid off or their businesses suffered setbacks as a result of the “COVID-19” pandemic.
Free
LMS analysis using IPA Matrix for Web Applications
Scientific article
The use of learning websites in the field of education has now become a necessity. One of them is using a Learning Management System that supports the learning process. The Learning Management System is a system that tertiary institutions widely use to help the teaching and learning process run smoothly. Apart from providing benefits to tertiary institutions, this system must also be well received by the primary users, namely students. To assess the performance of a Learning Management System, tools that can be used include the Analysis using the Index – Performance Matrix. This matrix was initially developed to assess consumer satisfaction with the marketing of goods or services. Still, it can be developed to assess user satisfaction with the services of an LMS website. This study tries to assess one LMS using indicators to assess website user satisfaction, using the Importance – Performance Analysis Matrix, which is modified according to website assessment standards. The results of this Analysis obtained data on the gap between the performance expected by the user and the user's preferences regarding the level of importance of each indicator. Based on the data spread over the four quadrants, it can be determined which factors should be prioritized for improvement or improvement. These variables are variables 2, 3, 4 and 6, namely the Application features , application reliability, replication suitability and also ease of repair, we found several variables that need to be fixed immediately and which factors are not yet urgent. This research was conducted at a university in South Tangerang.
Free
Landscape Pattern Evolvement in Mining Area: a Case of Liyuan Town in China
Scientific article
Landscape pattern in mining area is both the result of long-term action of multi driving forces and the base of regional coordination and development. This paper takes Liyuan Town, where Jinggezhuang locates, in Tangshan as an example and analyzes land use changes in the year 1997 and 2003 using GIS. The results showed that in mining area in urban-rural fringe of plain area, the number and the fragmentation of the patches increased and the patch density as the whole was in a rising trend. And the patch number of each type of landscape distributed unevenly. The landscape pattern characteristics and evolvement in Liyuan Town indicates that under the double functions of mining development and urbanization, it is necessary adequately to obey the evolvement regularity of special landscape in region to promote the evolvement of landscape destruction, restoration, reconstruction and function, in order to realize the regional coordination development.
Free
Scientific article
The human capital hypothesis and the screening hypothesis were commonly used to explain the positive effect of education level on individual incomes in the field of education economics. Using graduates of the newly-upgraded universities of China as the sample, this paper tested the two contending hypothesis. The results were in favor of the human capital hypothesis, which indicated higher education was rather a production means than merely a signal of productivity for graduates of these universities.
Free
Learning Computer Network by Writing Your Own Protocol Analyzer
Scientific article
Computer network is one of the fundamental courses for college students majoring in CS, CSE and EECS. The objective of this course is to explain the basic principles and architecture of network based on TCP/IP. However, many students find the course quite abstract and difficult to understand. Inspired by the idea of "learning by doing", we propose a learning approach by asking the students to design and to implement their own protocol analyzer during the course. This task not only synthesizes the knowledge of all the important protocols ranging from data link layer to application layer, but also bridges the gap between theory and practical aspect. Promising feedbacks from students demonstrate that this method is very helpful for student to study computer network.
Free
Learning Preferences to Physiology of Undergraduate Students in a Chinese Medical School
Scientific article
Students learning may be classified according to the sensory modalities using VARK instrument, which categorizes learning modes as visual (V), auditory (A), reading-writing (R), or kinesthetic (K). We administered the VARK questionnaire to our second-year medical students, and 98 of 133 students (74%) returned the completed questionnaire. Only 14.3% of the students preferred a single mode of information presentation. In contrast, most students (85.7%) preferred multiple modes of information presentation. Knowing the students preferred modes and using web-based learning system may help the instructors to tailor to the student's individual preference in the teaching of medical science.
Free
Scientific article
This research was conducted to explain that long before the Covid 19 outbreak hit. There has been a deadly plague that has long affected human life at large. Anticipatory actions of the Dutch Colonial government were carried out intensively to inhibit the rate of spread of plagues at that time such as cholera, malaria, and smallpox. The influenza and bubonic plague epidemics of 1918 and 1911 threatened successively and smallpox emerged at the same time, hampering the pace of life in all fields. Moving on from this time, the Covid 19 outbreak has affected all fields including education. So far, when face-to-face began to be done again after a long time online, here a polemic emerged. Vaccination for children aged 6-11 years at primary school age. In field research, there are several obstacles experienced. Based on the results of interviews conducted in this study, most respondents were afraid of vaccines when administered to their elementary school-age children. Fear of risks such as hoaxes circulating on social media. Based on the results of the research conducted, in general, the people of Padang City are not entirely aware of the Covid-19 vaccination policy for elementary school-age children (6-11 years) because for them this is very risky because not all children in their bodies can receive vaccines. The research implementation procedure. This research uses the historical method (heuristics, criticism, interpretation, historiography). The purpose of the historical method is used starting with the collection of sources: first, literature and document studies, and field studies through in-depth interviews with several parents of students, teachers, such as elementary school residents in Padang City. Second, criticizing the sources obtained, Third, analyzing the relationship between the facts found, and finally the fourth is writing the findings. The purpose of this research to be achieved is to be able to explain the implications that the covid 19 outbreak has a lot of impact when it is required to vaccinate as a condition for face-to-face learning to be carried out again.
Free
Literature Survey on Educational Dropout Prediction
Scientific article
Educational Data Mining (EDM) is one of the crucial application areas of data mining which helps in predicting educational dropout and hence provides timely help to students. In Indian context, predicting educational dropouts is a major problem. By implementing EDM, we can predict the learning habits of the student. At present EDM has not been introduced at higher education level. Due to this we cannot recognize the genuine problems of students during their education. The objective of this analysis is to find the existing gaps in predicting educational dropout and find the missing attributes if any, which my further contribute for better prediction. After that we try to find the best attributes and DM techniques which are frequently used for dropout prediction. Based on the combination of missing attribute and best attribute of student data thus far, a new algorithm can be tested which may overcome the shortcomings of previous work done.
Free
Literature Survey on Student’s Performance Prediction in Education using Data Mining Techniques
Scientific article
One of the most challenging tasks in the education sector in India is to predict student's academic performance due to a huge volume of student data. In the Indian context, we don't have any existing system by which analyzing and monitoring can be done to check the progress and performance of the student mostly in Higher education system. Every institution has their own criteria for analyzing the performance of the students. The reason for this happing is due to the lack of study on existing prediction techniques and hence to find the best prediction methodology for predicting the student academics progress and performance. Another important reason is the lack in investigating the suitable factors which affect the academic performance and achievement of the student in particular course. So to deeply understand the problem, a detail literature survey on predicting student’s performance using data mining techniques is proposed. The main objective of this article is to provide a great knowledge and understanding of different data mining techniques which have been used to predict the student progress and performance and hence how these prediction techniques help to find the most important student attribute for prediction. Actually, we want to improve the performance of the student in academic by using best data mining techniques. At last, it could also provide some benefits for faculties, students, educators and management of the institution.
Free
Machine Learning Algorithms for Iron Deficiency Anemia Detection in Children Using Palm Images
Scientific article
Anemia is a common condition among adults, particularly in children and pregnant women. Anemia is defined as a lack of healthy red blood cells or hemoglobin. Early identification of anemia is critical for excellent health and well-being, which contributes to the sustainable development goals (SDGs), notably SDG 3. The intrusive way to detecting anemia has several hurdles, including anxiety and cost, which impedes health development. With the advent of technology, it is critical to create non-invasive techniques to diagnose anemia that can minimize costs while also improving detection efficacy. A distinct non-invasive technique is developed in this study employing machine learning (ML) models. This study's dataset contains 4260 observations of non-anemic (0) and anemic (1) children. To train the dataset, six (6) different ML models were employed: k-Nearest Neighbor (KNN), decision tree (DT), logistic regression (LR), nave bayes (NB), random forest (RF), and kernel-support vector machine (KSVM). The DT and RF models obtained the highest accuracy of 99.92%, followed by the KNN at 98.98%. The ML models used in this study produced substantial results. The models also received high marks on performance evaluation metrics such as accuracy, recall, F1-score, and Area Under the Curve-Receiver Operating Characteristics (AUC-ROC). When compared to the other ML models, the DT and RF had the best precision (1.000), recall (0.9987), F1-score (0.9994), and AUC-ROC (0.9994) ratings. According to the findings, ML models are crucial in the detection of anemia using a non-invasive technique, which is critical for health facilities to boost efficiency and quality healthcare. Various machine learning models were used in this study to detect anemia in children using palm images. Finally, the findings confirm earlier studies on the effectiveness of ML algorithms as a non-invasive means of detecting iron deficiency anemia.
Free
Machine Learning Applications in Algorithmic Trading: A Comprehensive Systematic Review
Scientific article
This paper reviews recent advancements in machine learning (ML) driven automated trading systems (ATS). ATS has progressed from simple rule-based systems to sophisticated ML models like deep reinforcement learning, deep learning, and Q-learning that can adapt to evolving markets. These techniques have been successfully applied across various financial instruments to optimize trading strategies, forecast prices, and enhance profits. The literature indicates that ML improves ATS performance over conventional methods by identifying intricate patterns and relationships in data. However, risks like overfitting, instability, and low interpretability exist. Techniques to mitigate these limitations include cross-validation, careful model management, and utilizing more transparent algorithms. Although challenges remain, ML creates valuable opportunities for ATS via alternative data sources, advanced feature engineering, optimized adaptive strategies, and holistic market modelling. While research shows ML improves market quality through increased liquidity and efficiency, heightened volatility needs further analysis. Promising future research directions include leveraging innovations in deep learning, reinforcement learning, sentiment analysis, and hybrid systems. More work is also needed on evaluating different techniques systematically. Overall, the progress in ML-driven ATS contributes significantly to the field, but judicious application and balanced regulations are required to address risks. Further advancements in ML will enable more capable, nuanced, and profitable algorithmic trading.
Free
Scientific article
The disease burden of Gastroesophageal Reflux Disease (GERD) varies across the globe and have a significant impact on the overall health of the communities. A number of complications and diseases stem from chronic GERD. In order to provide improved healthcare measures and to effectively monitor and control GERD, it is important to identify rate of incidence of the disease and the associated risk factors along with symptoms. Therefore, this study was conducted by retrieving the relevant data through machine learning. Principles of Artificial Neural Networks were applied to sort the data and the results were obtained in the form of a network by using VOSviewer software. These artificial intelligence and machine learning based results reveal that the Asian population is increasingly becoming prone to GERD and sporadic reports from Pakistan have surmounted to disclose that GERD is constantly present across different districts and cities of Pakistan. The major risk factors identified among the Pakistani population in different research articles include consumption of oily foods, the habit of having late dinners, sedentary lifestyles and a lack of understanding about disease diagnosis, and GERD management and treatment. Our results suggest that acid reflux and inflammation of esophageal cavity are some of the main symptoms of the disease. On the basis of the results obtained, it is speculated that this study will provide a ground to improve the symptomatic diagnosis of GERD by closely observing and analyzing the risk factors and the rate of incidence with symptoms. It would enable the healthcare facilities to effectively monitor the GERD cases so that the disease burden due to GERD and related illnesses could be reduced. Moreover, the identification of regional differences and a comparative data would help us in identifying the disease hotspots where more efforts would be needed to manage and control the disease.
Free
Malay language mobile learning system (MLMLS) using NFC technology
Scientific article
This paper proposes a portable learning framework that uses cell phones and Near Field Communication (NFC) innovation in which this application permits understudies to connect with genuine questions and get data from the labels that are put on the item by filtering the tag put on the article. These gimmicks empower the learning procedure at all over the place (pervasive learning) and enhance the viability of the learning methodology. In this paper, Mobile Application Development Lifecycle (MADLC) model was utilized to safeguard effective M-Lang framework conveyance. M-lang framework clients are required to utilize cell phones to advance the involvement in Malay Language learning.
Free
