Pavinder Yadav

Pavinder Yadav

Assistant Professor

Profile Summary

Pavinder Yadav has submitted his Ph.D. thesis in Mathematics and Scientific Computing at the National Institute of Technology, Hamirpur, specializing in deep learning for real-time weapon detection. His research focuses on developing efficient deep learning models, particularly YOLO-based architectures, for security applications. With expertise in machine learning, optimization, and computer vision, he applies his knowledge to surveillance, medical imaging, and intelligent automation. His work emphasizes computational efficiency, ensuring real-time deployment on edge devices for large-scale systems.   

Work Experience

Pavinder Yadav is currently an Assistant Professor in School of Computer Science (SoCS) at UPES, Dehradun. Previously, he worked as a Visiting Assistant Professor at Deenbandhu Chhotu Ram University of Science and Technology, Haryana, where he taught advanced mathematics. He also served as a Block Resource Person in Mathematics, conducting teacher training programs to enhance modern teaching methodologies. 

Research Interests

His research spans deep learning, machine learning, and mathematical optimization, with applications in real-time threat detection, image processing, and adaptive learning frameworks. His future work aims to enhance AI-driven surveillance, autonomous systems, and intelligent computing for security and healthcare.

Teaching Philosophy

Pavinder Yadav believes in a hands-on, application-driven teaching approach that bridges theory with real-world implementation. He integrates Python, MATLAB, and Jupyter Notebooks into coursework, emphasizing practical problem-solving and interdisciplinary learning. His goal is to equip students with both theoretical knowledge and industry-relevant skills, fostering innovation and critical thinking. 

Courses Taught

Pavinder Yadav has taught a variety of courses, including:

  • Machine Learning: Fundamentals of supervised and unsupervised learning, deep learning architectures, and real-world applications using Python (scikit-learn, TensorFlow, PyTorch).
  • Deep Learning & Computer Vision: Object detection, segmentation, and tracking using CNNs and YOLO-based models for real-time applications.
  • Mathematics for Computing: Linear algebra, calculus, and optimization techniques with applications in data science and AI.
  • Programming & Computational Tools: Teaching Python, MATLAB, and LaTeX for scientific computing and algorithmic problem-solving.
  • Data Analysis & Visualization: Techniques for processing and interpreting large datasets using Python, Pandas, and visualization tools like Matplotlib and Tableau.

Awards and Grants

  • Junior Research Fellowship (JRF) awarded by the University Grants Commission (UGC), India (2020).
  • Senior Research Fellowship (SRF) awarded by the University Grants Commission (UGC), India (2022).
  • Qualified CSIR NET/JRF (Mathematics) in December 2017 and June 2018.
  • Qualified GATE (Mathematics) in 2019.

Scholarly Activities

  • Published impactful research in reputed journals like Expert Systems with Applications and Digital Signal Processing, focusing on deep learning and weapon detection.
  • Presented research findings at international conferences, including Springer Nature Conferences on deep learning-based security applications.
  • Developed open-source tools for real-time weapon detection and image enhancement, accessible on GitHub.
  • Mentored postgraduate students on research projects in machine learning, deep learning, and computer vision applications.
  • Contributed to interdisciplinary projects involving X-ray threat detection, medical imaging, and AI-based automation.
  • Served as a peer reviewer for scientific journals in AI and image processing, ensuring research quality and innovation.
  • Conducted workshops on deep learning, AI, and hyperparameter tuning, engaging both academic and industry participants.