Sudhir Kumar Singh - NAMTECH Faculty
Sudhir Singh

Sudhir Kumar Singh

Accomplished in advanced data analytics and machine learning, adept at leading complex engineering research projects with significant improvements in prediction accuracy and process efficiency. Combines a rich academic background with practical industry experience, excelling in applying theoretical insights to real-world challenges. Passionate about innovative research in engineering, specializing in the application of novel technologies for advanced infrastructure monitoring and analysis.

2019 – 2024 PhD Machine Learning

  1. Indian Institute of Technology Kharagpur, India

2013 – 2017 BTech Mining Engineering

  1. Indian Institute of Technology Kharagpur, India

2017 – 2018 Management Trainee

  1. Coal India Limited Jharkhand, India

2019 – 2024 Senior Research Fellow

  1. Indian Institute of Technology Kharagpur Kharagpur, India
  1. S.K. Singh, D. Chakravarty, Assessment of Slope Stability using Classification and Regression Algorithms Subjected to In-ternal and External Factors. Archives of Mining Sciences. 68 (1), 87–102 (2023). SCIE. DOI: 10.24425/ams.2023.144319
  2. S.K. Singh, D. Chakravarty, Efficient and Reliable Prediction of Dump Slope Stability in Mines using Machine Learning: An in-depth Feature Importance Analysis. Archives of Mining Sciences. (2023) SCIE. DOI: 10.24425/ams.2023.148157
  3. S.K. Singh, D. Chakravarty (2023). Interpretable Predictions: Machine Learning Approaches to Understand Slope Stability in the Presence of Joint Networks. In: Sinha, A., Sarkar, B.C., Mandal, P.K. (eds) Proceedings of the 10th Asian Mining Congress 2023. AMC 2023. Springer Proceedings in Earth and Environmental Sciences. Springer, Cham. DOI: https://doi.org/10.1007/978-3-031-46966-4_16
  1. Crafted intelligent machine learning models for pit slope stability prediction under non-homogeneous and diverse external conditions, achieving a 99% accuracy improvement and leading to a publication in a reputed SCI-indexed journal. Developed tailored machine learning architectures for dump slope stability estimation, reaching 98.5% accuracy while implementing SMOTE, with the work accepted for publication in another reputable SCI-indexed journal. Integrated Convolutional and Variational Autoencoders to revolutionize displacement predictions in slope stability assessments, this ongoing work shows promising early results, potentially simplifying, streamlining, and enhancing the reliability of the process, marking a significant advancement in the field.

Councils & Boards