IJMECS Vol. 14, No. 6, Dec. 2022
Cover page and Table of Contents: PDF (size: 603KB)
The use of machine learning algorithms for higher education performance assessment is an emerging area of research and several works have focused on student performance and related problems. The preliminary goal of this work is to determine and quantify the role of prerequisites in academic success by using machine learning algorithms with the Weka environment. The main objective is the development of a tool based on machine learning algorithms for the prediction of future results for a training program based solely on the previous academic profiles of the students. The interest is to link whether success in previous courses is associated with success in subsequent target courses. This will help to improve the planning of course sequences in a training program on the one hand and the overall academic students’ success on the other. The proposed methodology is applied for the analysis of the role of the prerequisites influencing courses success of a training course in Mathematical and Computer Sciences in a Moroccan university. For this purpose, we use several classification algorithms such as Random Forest, J48, and Multilayer Perceptron.
Preliminary results show that the correlation between the prerequisite reliability rates of the courses studied and the accuracy with which the learning algorithms predict the success outcomes of these courses is confirmed.
Also, these results show that the best accuracy and the best Receiver Operator Characteristic ROC area are obtained by using Random Forest algorithm and have reached 86% for the accuracy and 75.6% for the ROC area.
Almost all educational institutions have shifted their academic activities to digital platforms due to the recent COVID-19 epidemic. Because of this, it is very important to assess how well teachers are performing with this new way of online teaching. Educational Data Mining (EDM) is a new field that emerged from using data mining techniques to analyze educational data and making decision based on findings. EDM can be utilized to gain better understanding about students and their learning processes, assist teachers do their academic tasks, and make judgments about how to manage educational system. The primary objective of this study is to uncover the key factors that influence the quality of teaching in a virtual classroom environment. Data is gathered from the students’ evaluation of teaching from computer science students of three online semesters at X University. In total, 27622 students participated in these survey. Weka, sentimental analysis, and word cloud generator are applied in the process of carrying out the research. The decision tree classifies the factors affecting the performance of the teachers, and we find that student-faculty relation is the most prominent factor for improving the teaching quality. The sentimental analysis reveals that around 78% of opinions are positive and “good” is the most frequently used word in the opinions. If the education system is moved online in the future, this research will help figure out what needs to be changed to improve teachers’ overall performance and the quality of their teaching.[...] Read more.
Pedagogical scientists often need to process the results of a pedagogical experiment. However, not every scientist (especially in humanitarianism) has appropriate mathematical training, so statistical data processing is a problem for him. Scientists-pedagogues in Ukraine use various statistical methods to process the results of a pedagogical experiment and face the problem of cumbersome calculations and the accuracy of assessments. Therefore, we developed a method that is based on the correct mathematical apparatus, simplifies the processing of empirical data, and allows us to draw qualitative conclusions without the explicit use of mathematical apparatus. To simplify the statistical analysis of the results of the pedagogical experiment and the interpretation of the obtained data, the authors suggest using a spreadsheet and analyzing the data according to Student's and Fisher's criteria (comparing the average sample and its variance) and controlling intermediate indicators of the results of the pedagogical experiment. The method developed by the authors has an advantage compared to other methods: it is enough to analyze the pair "mean and variance" for the sample to conclude the significance of the differences in the control and experimental groups. The method has a simple implementation since almost every researcher has a spreadsheet processor on his computer. The method does not require a thorough knowledge of the statistics course. The method guarantees more reasonable conclusions (two criteria are used at once), which is important when conducting a pedagogical experiment.[...] Read more.
Clustering diabetic patients with comorbidity patterns are necessary to learn relationships between diabetes patients’ clinical profiles and as an essential pre-processing stage for analysis tasks, like classification and categorization. Nevertheless, the heterogeneity of these data makes traditional clustering methods more difficult to apply, necessitating the development of novel clustering algorithms. In this paper, we recommend an effective and scalable clustering technique suitable for datasets made up of attributes which are atomic and set-valued. In these datasets, each record corresponds to a different diagnosis detail of a diabetic patient based on his or her hospital visit, where diagnosis details in each record are represented using the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes. Our proposed technique involves three main stages. In the first stage, we selected the top-k diabetes-specific comorbidities patterns. In the second stage, we ensured that the co-occurring conditions in the selected top-k diabetes-specific comorbidities patterns really co-occur together or not using topic modeling and in the last stage, we constructed high quality clusters efficiently using average linkage agglomerative clustering with cosine similarity. Also, based on silhouette analysis, we assessed the efficiency and effectiveness of our proposed technique using a large, freely available MIMIC dataset (MIMIC-III and MIMIC-IV), comprised of over 14,222 and 68,118 distinct records, respectively. Our findings reveal that our technique finds clusters that: (i) preserve interrelations between demographics (age, gender) and diagnosis codes (ICD-9-CM codes), and (ii) are well-separated and compact. Finally, the founded clusters are beneficial for numerous investigative tasks like query answering, visualization, anonymization, classification etc.[...] Read more.
State-of-the-art architectures of convolutional neural networks (CNN) are widely used by authors for facial expression recognition (FER). There are many variants of these models with positive results in studies for FER and successful applications, some well-known models are VGG, ResNet, Xception, EfficientNet, DenseNet. However, these models have considerable complexity for some real-world applications with limitations of computational resources. This paper proposes a lightweight CNN model based on a modern architecture of dense-connectivity with moderate complexity but still ensures quality and efficiency for facial expression recognition. Then, it is designed to be integrated into learning management systems (LMS) for recording and evaluation of online learning activities. The proposed model is to run experiments on some popular datasets for testing and evaluation, the results show that the model is effective and can be used in practice.[...] Read more.
The pandemic situation due to covid-19 has disrupted routine activities such as attending classes physically in educational institutions, which insisted on moving towards online education with the help of advent and increased uses of new telecommunication services. Service quality is the prerequisite for customer satisfaction. Service quality assessment is crucial to ensure increased customer satisfaction in any service. Typically, it is not easy to evaluate service quality because of opacity in the information, and incompleteness characteristics of problems. With the collected data through an online survey, this study aims to analyze the facts that influence the students’ perception regarding the impact of telecommunication service quality on online education during the pandemic situation. Initially, some relevant criteria are derived from literature reviews. The proposed model is exerted to evaluate the quality of the online education and telecommunication service in Bangladesh during the covid-19 pandemic with the participation of 350 students answering 39 questions. The collected data is analyzed to assess the current state of service quality by evaluating the students’ satisfaction using the entropy technique. The findings of the study suggest that the online education system in Bangladesh is not interactive enough, and the telecommunication service quality here is not sufficient for this purpose. Telecommunication challenges such as poor network quality, overpricing structure of telecommunication services and slow connection speed must be resolved to ensure satisfactory quality of online education.[...] Read more.