Work place: Chandigarh Group of Colleges, Gharuan, Punjab, India

E-mail: bssohi@yahoo.com


Research Interests: Computational Engineering, Engineering


Balwinder S. Sohi is currently working as Campus Director at CGC – a group of colleges in Engineering & Technology. He has a long administrative experience as Director, University Institute of Engineering & Technology – a premier engineering institute of Panjab University at Chandigarh, India. He has served at various faculty positions as Professor, Assistant Professor and Lecturer, during his long professional carrier of 38½ years (including 4 years in research organizations). Graduated from Panjab Engineering College, Chandigarh, he has attained his masters and PhD degrees from Panjab University, Chandigarh.

He has guided the research works at masters and PhD levels and has more than 70 national and international research papers to his credit. He has been responsible in setting up various facilities in the field of Electronics & Communication, through sponsored projects from agencies like MHRD, AICTE, DIT etc. He has been Dean of Engineering & Technology at Panjab University, Chandigarh. He has contributed to technical education in various capacities at different fora like AICTE etc. He has been honored twice by Institute of Engineers, Kolkata, India, for best research work.

Author Articles
Internet Traffic Classification for Educational Institutions Using Machine Learning

By Jaspreet Kaur Sunil Agrawal B.S.Sohi

DOI: https://doi.org/10.5815/ijisa.2012.08.05, Pub. Date: 8 Jul. 2012

In recent times machine learning algorithms are used for internet traffic classification. The infinite number of websites in the internet world can be classified into different categories in different ways. In educational institutions, these websites can be classified into two categories, educational websites and non-educational websites. Educational websites are used to acquire knowledge, to explore educational topics while the non-educational websites are used for entertainment and to keep in touch with people. In case of blocking these non-educational websites students use proxy websites to unblock them. Therefore, in educational institutes for the optimum use of network resources the use of non-educational and proxy websites should be banned. In this paper, we use five ML classifiers Naïve Bayes, RBF, C4.5, MLP and Bayes Net to classify the educational and non-educational websites. Results show that Bayes Net gives best performance in both full feature and reduced feature data sets for intended classification of internet traffic in terms of classification accuracy, recall and precision values as compared to other classifiers.

[...] Read more.
Other Articles