Eguavoen, Victor Osasu
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

A Hybrid FCM-PSO-ANFIS Model for Predicting Student Academic Performance Eguavoen, Victor Osasu; Nwelih, Emmanuel
Jurnal Sarjana Teknik Informatika Vol. 12 No. 3 (2024): Oktober
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v12i3.29519

Abstract

This study introduces a novel hybrid soft-computing model integrating Fuzzy C-Means (FCM) clustering, Particle Swarm Optimization (PSO), and Adaptive Neuro-Fuzzy Inference System (ANFIS) to enhance student academic performance prediction in higher education. We developed a hybrid FCM-PSO-ANFIS model using a comprehensive dataset encompassing pre-admission data, academic constraints, and student performance records. The model's performance was evaluated against standard ANFIS and Genetic Algorithm-optimized ANFIS using multiple error metrics. The proposed PSO-optimized ANFIS model demonstrated superior performance, achieving the lowest error metrics in both training (MSE: 0.16667, RMSE: 0.40826) and testing (MSE: 0.19748, RMSE: 0.44439) phases. Comparative analysis showed that our model outperformed standard ANFIS and GA-optimized ANFIS in terms of prediction accuracy and generalization capability. The hybrid FCM-PSO-ANFIS model offers a robust, adaptive tool for early identification of at-risk students, enabling timely interventions and personalized learning approaches. This research contributes to improving educational outcomes and retention rates in higher education institutions by providing more accurate and reliable predictions of student performance. Future work should focus on enhancing model interpretability, addressing computational complexity, and exploring applications in diverse educational contexts.
Predictive Modelling for Mental Health Disorders using Machine Learning Techniques Eguavoen, Victor Osasu; Nwelih, Emmanuel
Jurnal Sarjana Teknik Informatika Vol. 13 No. 1 (2025): Februari
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v13i1.29536

Abstract

This study evaluates the application of machine learning techniques in improving the prediction and diagnosis of mental health disorders. Traditional diagnostic methods are subjective and time-consuming, necessitating more accurate and efficient alternatives. Using a dataset from the Open-Sourcing Mental Illness survey, this study compares five machine learning algorithms-logistic regression, decision trees, random forests, k-nearest neighbours, and naïve bayes-on mental health prediction tasks. The findings indicate that Naïve Bayes achieves the highest accuracy (82.54%), suggesting its potential for more accurate mental health diagnostics. These results underscore the value of machine learning techniques in enhancing early detection and management of mental health conditions, paving the way for future research into more diverse datasets and ensemble approaches to refine predictive models for clinical application.
Soft Computing Hybrid System for Student Performance Evaluation Eguavoen, Victor Osasu; E, Nwelih
Jurnal Sarjana Teknik Informatika Vol. 11 No. 2 (2023): Juni
Publisher : Program Studi Informatika, Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jstie.v11i2.26134

Abstract

Education Institutions have deployed technology accelerated learning systems and innovations for effective learning outcomes. Evaluating student’s performance in these systems must align with the cognitive, affective, and psychomotor learning domains. In this research, a Hybrid soft computing system comprising of the Clustering Algorithm, Machine learning technique, and Optimization algorithm were hybridized and implemented to evaluate student academic performance using academic, social, and economic data of students. The quality of Categorizing information first utilizing Fuzzy C-Means and preparing ANFIS utilizing Particle Swarm Optimization was introduced which formed the Hybrid soft computing system (FCM-PSOANFIS). It demonstrated significantly, a robust predictive capability compared to other hybrid machine learning algorithms such as ANFIS and GANFIS. The results of the proposed Hybrid Soft Computing model (FCM-PSOANFIS) show a higher convergence when compare with ANFIS and GANFIS. The proposed model works better with bigger datasets than with smaller or fewer datasets, and it delivers higher predictive findings under settings that depict student learning capacities while assessing student academic achievement.