Virginia Tech Transportation Institute
Machine Learning Research Assistant
(Dec 2020 – Present)
- Designed, trained, and fine-tuned ML algorithms for scene classification achieving an F score of 95.1%
- Constructed AI and decision support systems for crash preventability, scene perception and driver behavior
- Built pipelines to develop, scale, and evaluate ML based computer vision algorithms using Docker, PyTorch & Apache Spark
- Developed scene perception algorithms to track vehicle and pedestrian movement around autonomous vehicles using OpenCV, SciPy, Pandas & NumPy
- Engineered an automation pipeline to perform vehicle crash preventability analysis for 10K+ cases using Selenium, SQL, OCR, Seaborn & Pandas thereby increasing throughput by 90%.
Bradley Department of Electrical and Computer Engineering, Virginia Tech.
Teaching Assistant
(Aug 2020 – Dec 2020)
- Advised 45 students for the course Cyber-Security and IoT & hosted office hours to assist graduates
Computer Vision Lab, Virginia Tech.
Machine Learning Research Assistant
(May-2020 – Dec 2020)
- Developed a new hybrid ML algorithm by fusing CNN & LBP Micro-Texture features to detect spoof attack with face masks
- Achieved the least false acceptance rate of 0.23% on mask attacks with hybrid model compared to state-of-the-art face anti spoofing algorithms (FAS) on Replay-Attack dataset
- Determined vulnerabilities in open-source FAS algorithms by attacking them with various 3D occlusions and achieving a 20% increase in the classification error rate (APCER) in CNN based FAS models
Virginia Tech.
M.Eng in Computer Science, Software & Machine Intelligence, GPA: 3.6/4.0
(Aug 2021)
Ajay Kumar Garg Engineering College
B.Tech in Electronics and Communications, Honors
(May 2018)
TECHNICAL SKILLS & LANGUAGES
- Relevant Coursework Data Structures & Algorithms, Machine Learning, Deep Learning, Computer Vision, Natural Language Processing, Object-Oriented Programming (OOP), Web Application Development, Computer Networks, Computer Security, Linear Algebra, Engineering Mathematics I/II. Microprocessors, Digital Signal Processing
- Languages: Python (NumPy, Pandas, SciPy, Scikit-Learn, Selenium, OpenCV), C++, Java, JavaScript, HTML/CSS, SQL
- Machine Learning: Neural Network, Recurrent Neural Network, Deep Learning, SVM, Linear Regression, Logistic Regression, Decision Trees, Recommender System, LSTM, Transformers, GAN, Autoencoders, Supervised Learning
- Frameworks/Libraries: Docker, Kubernetes, Git, AWS, Apache Spark, PyTorch, TensorFlow, Keras, MXNet, XGBoost, MLlib
- Data Engineering: Data Structures & Algorithms, Databases
- Visualization: Matplotlib, Seaborn, Tableau, Power BI
