Ravindra Eklarker

Work place: Geenthanjali College of Engineering and Technology, Hyderabad, India

E-mail: raviprabha2817@gmail.com

Website: https://orcid.org/0000-0002-8178-3048

Research Interests:

Biography

Ravindra Eklarker received his Ph D degree from VTU Belagavi Karnataka in 2014. He is currently working as Professor in CSE, Dean Industry Institute Interaction Cell (IIIC) and HOD (CSE) in Geethanjali College of Engineering Hyderabad India. He has 28 years of teaching experience and 11 years of research and 12 years of Administrative experience. He has published more than 30 research papers in various reputed journals, conferences, published Book chapters, patents and authored Book. His research interest includes Wireless Mobile Ad Hoc Networks, Mobile Computing, Sensor Networks.

Author Articles
Enhancing Student Performance Insights Through Multi Parametric STBO Based Analysis in Engineering Education

By Santhosh Kumar Medishetti Ravindra Eklarker Kommuri Venkatrao Maheswari Bandi Rameshwaraiah Kurupati

DOI: https://doi.org/10.5815/ijmecs.2025.05.05, Pub. Date: 8 Oct. 2025

This research presents a novel approach to evaluating student academic performance at Nalla Narasimha Reddy Group of Institutions (NNRG) by implementing a Student Training Based Optimization (STBO) algorithm. The proposed method draws inspiration from the structured training and adaptive learning behavior of students, simulating their progression through knowledge acquisition, skill refinement, and performance enhancement phases. The STBO algorithm is applied to optimize academic performance assessment by identifying key parameters such as attendance, internal assessments, learning pace, participation, and project outcomes. By modelling student development as a dynamic optimization process, the algorithm effectively predicts academic outcomes and recommends personalized strategies for improvement. Experimental evaluation on real academic datasets from NNRG CSE, CSE (Data Science), and CSE (AIML) Students demonstrates that the STBO algorithm achieves higher prediction accuracy and adaptive feedback generation when compared to traditional statistical and machine learning techniques. This approach also facilitates early identification of at-risk students and promotes data-driven decision-making for faculty and administration. Overall, the STBO-based framework not only enhances performance assessment but also contributes to academic excellence by aligning learning strategies with individual student needs.

[...] Read more.
Other Articles