Developed an independent research proposal focused on energy-efficient pipeline leak detection using neuromorphic computing and Spiking Neural Networks (SNNs). The project integrates multi-modal sensing, including acoustic, pressure, vibration, and temperature signals, with advanced signal processing and feature engineering techniques. Designed a Time-to-First-Spike (TTFS) encoding framework to transform sensor data into spike-based representations, enabling low-power real-time inference on resource-constrained edge devices. The proposed system combines multi-sensor data fusion, temporal neural computation, and embedded AI to achieve robust leak classification while significantly reducing computational and energy costs for industrial monitoring applications. (Ongoing)

Project carried out under the guidance of Dr. Yashwant Singh Patel.