Dr. Barnali Barman

Dr. Barnali Barman

Assistant Professor

  • Faculty of Engineering

About

Name: Specialization:
Dr. Barnali Barman Data mining, Hyperspectral image, Rough set

Qualification

B. E.(IT), MTech (IT), PhD (CSE)

Working Experience

      1. Worked as a project fellow in a project entitled “Development of Pronunciation Lexicon – Bodo”
         sponsored by MCIT, Govt. of India from July 2013 to August 2014.

       2.Worked as teaching assistant in Tezpur University from January 2016 to June 2020.

       3. Worked as Junior Consultant IT under Xeam Ventures Pvt. Ltd. (Client located at ORGI & CCI
           Guwahati Assam) from November 2020 till August 2021.

       4. Worked as Assistant Professor in Tetso College from August 2021 – December 2021

       5. Working as Assistant Professor in Assam Down Town University (iNurture) from December 2021  
          till now.

Research

  1. Barman, B., Patra, S.: Empirical study of neighbourhood rough sets based band selection techniques for classification of hyperspectral images. IET Image Processing 13(8), 1266 - 1279 (2019) (SCI journal, Impact factor: 2)
  2.  Barman, B., Patra, S.: A novel technique to detect a suboptimal threshold of neighborhood rough sets for hyperspectral band selection. Soft Computing 23, 13709–13719 (2019) (SCI journal, Impact factor: 3.6)
  3.  Barman, B., Patra, S.: Variable precision rough set based unsupervised band selection technique for hyperspectral image classification. Knowledge-Based Systems 193, 105414 (2020) (SCI journal, Impact factor: 8)
  4. Patra, S. and Barman, B.: A novel dependency definition exploiting boundary samples in rough set theory for hyperspectral band selection. Applied Soft Computing, 99, pp. 106944, (2021)( (SCI journal, Impact factor: 6.7))
  5. Barman, B., and  Patra S.: Hyperspectral image analysis using neighborhood rough set and mathematical morphology (International Conference on Accessibility To Digital World IEEE) pp 75-80 (2016)
  6. Barman, B., and  Patra S.: Hyperspectral Band Selection based on Variants of Rough Set Theory (International Conference on Electronic Systems and Intelligent Computing Springer) pp. 909-917 (2020)