Vikas Kumar

Motivated Computer Science and Engineering graduate (B.Tech, 2023) currently pursuing M.Tech with a specialization in Computer Science and Engineering. Completed IIT Roorkee’s PG Certification in AI and Machine Learning through Simplilearn, gaining strong conceptual and practical knowledge in Python, SQL, Machine Learning, Deep Learning, and Natural Language Processing (NLP). Demonstrates excellent analytical, problem-solving, and research skills with a strong interest in data-driven technologies. Passionate about exploring AI-based solutions and advancing expertise in Machine Learning, Deep Learning, and Data Science to contribute effectively to innovative academic or industry projects.

• Professional Certificate Program in Generative AI and Machine Learning
• Python for Data Science

• OpenCV attendance project

Developed a Python-based face recognition attendance system using OpenCV to automatically mark attendance through a webcam. Stored attendance records with timestamps in a structured dataset for efficient management.

• Education AI ChatBot

Developed a Python-based educational chatbot that helps students learn topics chapter-wise through interactive conversations. The chatbot also conducts quizzes after each chapter and provides instant feedback to assess learning progress.

• Smart Parking System Optimisation Using Enhanced Multi-Objective Greedy Approach

Developed a Smart Parking System using Enhanced Multi-Objective Greedy Algorithm(EMGA) to optimise parking space allocation through adaptive priority-based task scheduling in a
cloud/fog environment. Improved system performance by reducing response time, execution cost, task failure, and resource load imbalance while enhancing overall Qos.

• Machine Learning-Driven Dynamic Multi-Objective Greedy Scheduling in Fog–Edge–Cloud

Machine learning-driven Dynamic EMGA for adaptive task scheduling in fog-edge-cloud computing environments using ML-derived performance weights.

• Optimized Algorithm Development for Smart Vehicle Parking System

Developed a Fog–Edge–Cloud based Smart Parking System using an Enhanced Multi-Objective Greedy Algorithm (EMGA) to optimize task scheduling. Improved response time, execution cost, and load balancing through efficient resource allocation and machine learning-based dynamic optimization.