What’s New

Dr. Debrup Banerjee

Senior ML Research Scientist, Analytics, JAGSoM

Digital Business and Analytics

Artificial Intelligence, Machine Learning, Statistical Models, Natural Language Processing, Computer Vision, Image Analytics, Deep Learning, Generative AI, Business Analytics

He has published in top-level journals and conferences of repute like Int’l Conf. in Data Mining (ICDM). He has received several awards during his tenure as a doctoral candidate, including several Best Paper Awards at conferences, doctoral fellowship award, Graduate Student Service Award and Shining Star Awards for teaching from Old Dominion University. He has worked for Tata Consultancy Services for clients like British Telecom, UK and Procter & Gamble, USA, before starting his doctoral program. His research interests include Applied Machine Learning, Deep Learning, Speech Emotion Recognition and Generative AI. He also has prior research work in Numerical Simulations of fluid flows in propulsion systems and has published for NASA. He is also a reviewer for several journals. He has conducted more than 150+ corporate trainings in AI/ML/Gen-AI to clients like Oracle, Walmart Tech and others. He also conducts training sessions for participants enrolled in the AI-ML DBA programs at Golden Gate University, San Francisco, USA. He has worked for several organizations in the past.

Educational Qualification
  • Ph.D. (Electrical & Computer Engineering, AI-ML Research Focus), Old Dominion University, Virginia, USA – 2017
  • Master Of Science (MS), Computer Science, Hampton University, Virginia, USA – 2004
  • Bachelor Of Engineering, Mechanical Engineering, Shivaji University, India – 1999
Publications

Publication Date 2019

  • A deep transfer learning approach for improved post-traumatic stress disorder diagnosis (Springer version)

Publication Date 2017

  • A deep transfer learning approach for improved post-traumatic stress disorder diagnosis
  • Deep learning for effective detection of excavated soil related to illegal tunnel activities
  • Speech based machine learning models for emotional state recognition and PTSD detection
  • Speech feature investigation in transfer learning for improved PTSD diagnosis
  • A comparative study of classification schemes in transfer learning for PTSD diagnosis

Publication Date 2013

  • High-dimensional MRI data analysis using a large-scale manifold learning approach

Publication Date 2012

  • Feature selection for RFID tag identification

Publication Date 2011

  • A large-scale manifold learning approach for brain tumor progression prediction
  • Prediction of brain tumor progression using multiple histogram matched MRI scans
  • Histogram analysis of ADC in brain tumor patients

Publication Date 2010

  • Prediction of brain tumours progression using a machine learning technique