Dedicated and goal-driven academician with over 4 years and 5 months of experience as an Assistant Professor in Computer Science and Engineering. Demonstrated expertise in teaching core computer science subjects, mentoring students, and managing academic and administrative responsibilities at the departmental level. Actively engaged in research, particularly in the domain of data mining and feature selection, with multiple papers published and presented at prestigious IEEE conferences. Participated in various national and international conferences, fostering academic exchange and interdisciplinary collaboration. Recognized for contributing to institutional development through curriculum planning, event coordination, and academic documentation. Passionate about teaching and committed to sharing knowledge and expertise to inspire the next generation of engineers, and instill in them a deep appreciation for the field of computer science.
MTech: A binary krill-herd approach-based feature selection for high-dimensional data
This data mining-based project presents a novel feature selection method aimed at improving classification performance in high-dimensional datasets. Leveraging the bio-inspired Binary Krill-Herd Optimization algorithm, the system intelligently selects a minimal yet highly relevant subset of features, thereby reducing dimensionality and computational complexity. The technique enhances model interpretability and efficiency, making it suitable for large-scale machine learning applications. The entire system was designed and implemented in Java, utilizing its object-oriented features and performance reliability for algorithm development and data processing.
BTech: Adjacent Link Failure Localization with Monitoring Trails in All Mesh Networks
This networking-based project focuses on achieving fast and precise failure localization in mesh networks. It tackles the critical challenge of identifying adjacent link failures promptly—an essential requirement for ensuring network reliability and minimizing downtime. The project employs the innovative concept of M-trail (monitoring trail) as a comprehensive framework to track data paths and accurately pinpoint failure locations. By analyzing network routes and detecting anomalies, the system facilitates swift corrective actions. The entire approach is implemented in Java, leveraging its robust capabilities for network programming and algorithmic problem-solving.