Pooja Kamat

Papers

Total Citations

H-Index

About

Pooja Kamat is a researcher at the intersection of machine learning, computer vision, and industrial diagnostics. Her work focuses on developing intelligent systems for both predictive maintenance and visual recognition. In her highly cited 2021 study, "Bearing Fault Detection Using Comparative Analysis of Random Forest, ANN, and Autoencoder Methods," she systematically evaluated three distinct machine learning architectures for identifying mechanical faults, providing a critical benchmark for condition monitoring in rotating machinery—a paper that has already garnered 20 citations for its practical, comparative insights. More recently, Kamat has advanced the field of computer vision with her 2024 paper, "Color-Driven Object Recognition: A Novel Approach Combining Color Detection and Machine Learning Techniques." This work introduces a hybrid framework that leverages color cues to enhance object recognition accuracy, addressing a key challenge in robotics and autonomous systems. By integrating traditional color detection with modern ML classifiers, her approach offers a computationally efficient pathway for real-time visual tasks. With a growing citation record and a clear trajectory from fault diagnosis to perception, Kamat is establishing herself as a versatile contributor to applied AI, bridging the gap between robust engineering diagnostics and intelligent visual systems.