International Journal of Modern Education and Computer Science (IJMECS)

IJMECS Vol. 17, No. 4, Aug. 2025

Cover page and Table of Contents: PDF (size: 726KB)

Table Of Contents

REGULAR PAPERS

Utilizing Machine Learning-Based Decision-Making to Align Higher Education Curriculum with Industry Requirements

By Muhammad Faisal Titik Khawa Abd Rahman Darniati Zainal Husni Mubarak Fadly Shabir Nizirwan Anwar Imam Asrowardi

DOI: https://doi.org/10.5815/ijmecs.2025.04.01, Pub. Date: 8 Aug. 2025

The accelerating pace of industrial transformation necessitates a strategic reconfiguration of higher education curricula to ensure alignment with dynamic labor market demands. This study introduces a hybrid decision-making framework that integrates Machine Learning with Multi-Criteria Decision Making techniques to evaluate and classify the readiness and relevance of academic programs. The methodological core includes the Step-wise Weight Assessment Ratio Analysis, Linguistic q-Rung Orthopair Fuzzy Numbers, and the Multi-Attributive Border Approximation Area Comparison method for criteria weighting, coupled with a classification model based on Support Vector Machine optimized using the Salp Swarm Optimization algorithm. The results demonstrate the framework's efficacy in identifying curricular gaps and recommending adaptive enhancements, especially for programs categorized as “Needs Improvement.” Beyond classification, the system facilitates strategic curriculum planning, fosters pedagogical innovation, and promotes industry-responsive learning pathways. This study highlights the transformative potential of  
machine learning in higher education, equipping students with the skills required to navigate an increasingly dynamic professional landscape, while offering actionable insights into instructional redesign, competency-based delivery, and industry-informed pedagogy. Future research will explore longitudinal impact assessment and broader stakeholder integration to enhance the framework’s scalability and contextual adaptability.

[...] Read more.
Fuzzy Intelligent System for Student Software Project Evaluation

By Anna Ogorodova Pakizar Shamoi Aron Karatayev

DOI: https://doi.org/10.5815/ijmecs.2025.04.02, Pub. Date: 8 Aug. 2025

Developing software projects allows students to put knowledge into practice and gain teamwork skills. However, assessing student performance in project-oriented courses poses significant challenges, particularly as class sizes increase. This paper introduces a fuzzy intelligent system designed to evaluate academic software projects using an object-oriented programming and design course as an example. Our methodology involved conducting a survey of student project teams (n=31) and faculty (n=3) to identify key evaluation parameters and their applicable ranges. The critical criteria—clean code, use of inheritance, and functionality—were represented as fuzzy variables with corresponding fuzzy sets. We collaborated with three experts, including one professor and two course instructors, to define a set of fuzzy rules for a fuzzy inference system. This system processes the input criteria to produce a quantifiable measure of project success. Our fuzzy intelligent system demonstrated promising results in automating project evaluation, standardizing assessments, and reducing subjective bias in manual grading. The key findings show that the system effectively manages the increasing instructor workload, provides consistent and transparent evaluations, and offers timely and accurate feedback to students.

[...] Read more.
Fostering EFL Pre-Service Teachers‟ TPACK through Inquiry-Based, Technology-Saturated, and Flipped Instructional Model

By Maulana Mualim Margana Agus Widyantoro Luluil Maknun

DOI: https://doi.org/10.5815/ijmecs.2025.04.03, Pub. Date: 8 Aug. 2025

As the English language and information and communication technology (ICT) enhance global interconnection, demands on educating the young generation with English language skills and technological competence increase exponentially. As the successor of education, pre-service English teachers need to be trained with technological pedagogical content knowledge (TPACK). This study aims to develop an instructional model oriented to pre-service English teachers' (PST) TPACK. This is design-based research carried out in three stages: informed exploration, enactment, and evaluation. This study employed a multiphase mixed method. A qualitative design was done in the informed exploration stage, and an explanatory sequential mixed design was used for the evaluation stage. Nine PSTs, three lecturers, and 4 experts were invited as the participants of this study. The qualitative data were analyzed thematically on NVIVO software while the quantitative data were analyzed using descriptive statistic calculation. The results showed that the PSTs need an instructional model that facilitates student agency, learning agency, self-reliance, innovation, and cooperation. An instructional model called Inquiry-based, technology-saturated, and flipped instructional model (INSTALL) was developed. The expert validation result showed that the products of this development study were in the “Very Good” category. The results of the expert judgment indicated that INSTALL could be utilized to enhance the PSTs’ TPACK by blending inquiry-based learning and technology-saturated flipped instruction. 

[...] Read more.
Optimizing Heritage Design Education in Morocco Using English and AI

By Hicham Diouane Abdessamad Binaoui Mohammed Moubtassime

DOI: https://doi.org/10.5815/ijmecs.2025.04.04, Pub. Date: 8 Aug. 2025

The Specialized Institute of Applied Technology (ISTA) in Fes provides a vocational training course focused on heritage design to protect and promote the richness and diversity of Moroccan heritage. Currently, this course is taught in French. However, English-language resources, including CAD software, AI tools and online courses predominantly influence the design and new technologies fields. This study investigates the attitudes and preferences of ISTA trainees regarding the language of instruction for heritage design training, how they perceive integrating AI tools into their work, and the relationship between AI and language preference in this field. The study employed a mixed-methods approach, combining quantitative data from surveys with qualitative insights from in-depth interviews. The institution's trainees revealed that approximately 50% do not perceive the current language of instruction (French) as a significant barrier. Nonetheless, 70% expressed a preference for English-language instruction. The Chi-Square as well as Fisher's Exact tests revealed no significant association between language preference and the use of artificial intelligence in heritage-related work in the context of the current sample. Interestingly, the actual use of AI software among participants is low suggesting that while the theoretical value of AI is acknowledged, practical adoption is limited, possibly due to barriers such as lack of access to AI tools or insufficient training. 

[...] Read more.
Developing Audio-to-Text Converters with Natural Language Processing for Smart Assistants

By Mareeswari V. Vijayan Ramaraj Pratistha Tulsyan Suji R.

DOI: https://doi.org/10.5815/ijmecs.2025.04.05, Pub. Date: 8 Aug. 2025

In recent years, smart assistants have transformed human interaction with technology, offering voice-controlled interactions like music playback and information retrieval. However, existing systems often struggle with accurately interpreting natural language input. To address it, this proposed work aims to develop an audio-to-text converter integrated with natural language processing (NLP) capabilities to enhance interactions of smart assistants. Additionally, the system will incorporate intent recognition to discern user intentions and generate relevant responses. The proposed work commenced with a literature survey to gather insights into existing smart assistant systems. Based on the findings, a comprehensive architecture was designed, integrating NLP techniques like tokenization and lemmatization. The implementation phase involved developing and training a Feedforward Neural Network (FNN) model tailored for NLP tasks, leveraging Python and libraries like TensorFlow and NLTK. Testing evaluated the system's performance using standard evaluation metrics, including Word Error Rate (WER) and Character Error Rate (CER), across various audio input conditions. The system exhibited higher WER and CER with accented speech (15.3% and 7.9% respectively) while the clean audio dataset produced WER and CER of 4.7% and 2.55% respectively. The proposed work also involved training the FNN model while monitoring training loss and accuracy to ensure model performance. Ultimately, the model achieved an accuracy of 97.62% with training loss reduced to 1.45%. Insights from the training phase inform further optimization efforts to improve system performance. It practices the Google WebSpeech API and compares it with other Speech-to-text models. In conclusion, our proposed work represents a significant step towards realizing seamless voice-controlled interactions with smart assistants and enhancing user experiences and productivity. Future work includes refining the system architecture, optimizing model performance, and expanding the capabilities of the smart assistant for broader application domains.

[...] Read more.
A Novel CatML Stacking Classifier Based Intelligent System for Predicting Postgraduate Admission Chances: A Study on Bangladesh

By Abu Kowshir Bitto Md. Hasan Imam Bijoy Aka Das Jannatul Ferdousi Afsana Begum Imran Mahmud

DOI: https://doi.org/10.5815/ijmecs.2025.04.06, Pub. Date: 8 Aug. 2025

This paper introduces an intelligent tool with a novel CatML stacking classifier designed to enhance predictive analytics for postgraduate university admission chances. The proposed classifier uses the CatBoost algorithm as a core component of the stacking ensemble method, which integrates CatBoost and Multi-Layer Perceptron (MLP) learners to improve predictive performance. The dataset comprises 13 questionnaire-based surveys, including academic records, standardized test scores (i.e., GRE, IELTS/TOEFL), publication status, extracurricular activities, recommendation letters, and personal statements from Bangladeshi students who applied to various U.S. postgraduate programs. Experimental results demonstrate that the CatML stacking classifier outperforms conventional models, achieving superior accuracy (88.14%) and robustness in predicting admission outcomes. The enhanced performance is attributed to the model’s ability to capture complex, non-linear relationships within the data, facilitated by the CatBoost algorithm's handling of categorical features and prevention of overfitting. Finally, this model deploys in a web system developed with HTML, CSS, JavaScript and Flask. This research underscores the efficacy of advanced ensemble techniques in educational data mining and provides a valuable intelligent tool for students aiming to navigate the complexities of U.S. postgraduate admissions. The CatML stacking classifier offers significant improvements in predictive analytics, thereby assisting students in making informed application decisions.

[...] Read more.
Fuzzy Clustering of Educational Data with Automated Selection of Processing Parameters in System Analysis of Quality Education

By Zhengbing Hu Oleksandr Derevyanchuk Serhiy Balovsyak Yuriy Ushenko Hanna Kravchenko Iryna Sapsai

DOI: https://doi.org/10.5815/ijmecs.2025.04.07, Pub. Date: 8 Aug. 2025

Clustering of educational data was performed in the space of two parameters using the K-Means method. Students who are characterized by grades in certain types of activities were used as objects of clustering. Software for fuzzy data clustering is implemented in the Python language in the Google Colab cloud service. The obtained clusters are described by fuzzy Gaussian membership functions, which allowed to reliably determine the membership of each object to a certain cluster, even if the clusters do not have clear boundaries. Due to clustering, the most important characteristics of the educational process for a certain task are obtained, that is, this is how Data Manning tasks are solved. Fuzzy membership functions implemented using the scikit-fuzzy library. The developed program can also be used for educational purposes, as it allows a better understanding of the principles of cluster analysis and fuzzy logic. The correctness of the work of the developed program was confirmed during the processing of test educational data. The determination of the number of clusters was performed by software, taking into account the intra-cluster and inter-cluster distances, as well as the shape of the clusters. Automated selection of the number of clusters and cluster boundaries allows to reduce data processing time. The developed clustering tools are designed to increase the efficiency of system analysis of quality education.

[...] Read more.