Nairit Barkataki
Assistant Professor
Department of Instrumentation & USIC
ABOUT
Nairit Barkataki has been working on analysis and interpretation of GPR data using artificial intelligence since 2016. He and his team has developed various neural network models for detection of buried objects and the estimation of their sizes, shapes and materials. He is also working on the estimation of different soil properties as soil moisture and soil type in real time from GPR data. His team is also developing a prototype GPR system for research purposes. It’s purpose is to generate and transmit custom waveforms, use a variety of antennas across various frequencies, and process the GPR data on an FPGA platform in real time using AI models developed in-house.

Research Areas

Ground Penetrating Radar
Signal Processing and Hardware Design

Electromagnetics
EM Characterisation and Antenna Design

Artificial Intelligence
Deep Learning on FPGAs and GPUs
Latest Articles
Size estimation of underground targets from GPR frequency spectra: A deep learning approach
Abstract . GPR (Ground Penetrating Radar) is a robust and...
Read MoreEstimation of soil moisture from GPR data using Artificial Neural Networks
Soil moisture estimation is essential for understanding the water cycle...
Read MoreA CNN model for predicting size of buried objects from GPR B-Scans
Abstract . A convolutional neural networks (CNN) model for predicting...
Read MoreClassification of Soil Types from GPR B-Scans using Deep Learning Techniques
Abstract . Traditional methods for classification of soil types are...
Read More