Biswajit Sahoo
Biswajit Sahoo

Machine Learning Engineer

Biography

Professional with 7+ years of experience in data-driven fault diagnosis and prognosis of rotating machinery. I got introduced to these fields during my PhD research at IIT Kharagpur, where I was advised by Prof. A. R. Mohanty. I am a trained Mechanical Engineer with proficiency in machine learning and programming. Always eager to leverage my domain knowledge and machine learning experience to tackle emerging problems in condition-based maintenance and Industry 4.0. An open source contributor aiming to demystify technical jargons through expository writing and code that would contribute towards understanding of digital transformation happening in mechanical/manufacturing industry. My open source contributions can be found here and my blogs can be found here. Beyond research, I like literature and music.

Interests
  • Machine Learning
  • 3D Printing
  • Anomaly Detection
  • Time Series Analysis
  • Natural Language Processing
  • Signal Processing
  • Condition-Based Maintenance
  • Industrial Internet of Things
Education
  • Ph.D. in Mechanical Engineering

    Indian Institute of Technology, Kharagpur, India

  • MTech in Mechanical Engineering

    National Institute of Technology, Rourkela, India

  • BTech in Mechanical Engineering

    Odisha University of Technology and Research (Formerly College of Engineering and Technology), Bhubaneswar, India

Experience

  1. Machine Learning Engineer

    HP Inc. R&D
  2. Machine Learning Engineer

    TEKsystems (HP Inc. R&D)
  3. Project Manager (Condition-Based Maintenance)

    MachineSense (Prophecy Sensorlytics Pvt. Ltd.)
  4. Senior Data Science Consultant

    MachineSense (Prophecy Sensorlytics Pvt. Ltd.)
Recent Posts
Projects
Publications
(2022). Multiclass bearing fault classification using features learned by a deep neural network. In International Congress and Workshop on Industrial AI 2021.
(2021). Machine Learning, Regression, and Optimization. In Data Science and SDGs.
(2020). Feature Subset Selection Using Sparse Principal Component Analysis and Multiclass Fault Classification Using Selected Features. In Advances in Asset Management and Condition Monitoring. Smart Innovation, Systems and Technologies.