Dr. Vipin Kumar
Ph.D (JNU) & M.Tech(JNU), B.Tech(NIT Allahabad)
Embedded Files
Post: Assistant Professor
Post: Assistant Professor
CURRENTLY WORKING AT:
CURRENTLY WORKING AT:
Department of Computer Science and IT, Mahatma Gandhi Central University, Zilla School Campus, Motihari, Bihar-845401
Email ID:
Email ID:
Research Interests:
Research Interests:
Machine learning, Big Data Analytics, Data Mining & Text-Mining.
Teaching Experience:
Teaching Experience:
1). Department of Computer Science, University of Delhi, Delhi, India.
01 Year, 04 Months
2). Department of Computer Science and Information Technology, Mahatma Gandhi Central University, Bihar India.
Since Nov, 2016 to till now
Education:
Education:
Ph.D.(Computer Science): JNU, New Delhi
Ph.D.(Computer Science): JNU, New Delhi
[2012-2015]:
School of Computer and Systems Sciences (CS&SS), Jawaharlal Nehru University (JNU), New Delhi, INDIA. Thesis Title: "Multi-view Ensemble Learning for High Dimensional Data Classification" , under the supervision of Prof. (Dr) Sonajharia Minz
M.Tech.(CS&T): JNU, New Delhi
M.Tech.(CS&T): JNU, New Delhi
[2010-2013]:
School of Computer and Systems Sciences (CS&SS), Jawaharlal Nehru University (JNU), New Delhi, INDIA. Thesis Title: "Mood Classification of Lyrics using SentiWordNet", under the supervisor: Prof. (Dr) Sonajharia Minz.
B.Tech. (CSE): NIT Allahabad
B.Tech. (CSE): NIT Allahabad
[2005-2009]:
Computer Science and Engineering, Motilal Nehru National Institute of Technology, Allahabad (MNNIT- Allahabad), Uttar Pradesh, India.
Honors and Awards:
Honors and Awards:
- CSIR Senior Research fellowship (CSIR-SRF) in Computer Science 2015
- UGC-NET in Computer Science and Applications. 2012
A Brief Description of Ph.D. Work:
A Brief Description of Ph.D. Work:
During my Ph.D., I worked on Multi-view Ensemble Learning(MEL) for high dimensional data classification. We have proposed three methods as Optimal feature set partitioning method (OFSP),feature set partitioning using C-PSO, Multi-objective Multi-view ensemble learning using PSO(MEL-MOPSO), which perform better than the classical classification methods in terms of classification accuracies, time complexity, disagreement among the views.
Google Sites
Report abuse