An hybrid approach of active learning using SVM and N-gramtechnique

Authors

  • Kirti Sharma Assistant Professor, Department of Computer Science & Engineering, Bhopal Institute of Technology, Bhopal (M.P) India
  • Himanshi Department of Computer Science & Engineering, Bhopal Institute of Technology, Bhopal (M.P) India
  • Nita Department of Computer Science & Engineering, Bhopal Institute of Technology, Bhopal (M.P) India

Abstract

Active learning is an important subject in data mining and machine learning, which has been studied extensively and has a wide range of applications. Learning based on association rules, also called rule based learning, is a technique that uses association rules learning and taking proper decision. Heterogeneous DTC employs a novel data structure, association rule, to compactly store and efficiently retrieve a large number of rules for learning. We consider an active learning scenario in which the supervisor (trainer) can make decisions regarding the possibility to choose new examples for learning. In the classical forms of supervised learning, the training set is chosen according to some known or random given distribution. The supervisor is a passive agent in the sense that he is not able to interact with the training set in order to improve the performances of the learning process. In this paper hybrid approach that use N-gram with SVM has been proposed. Hybrid approach lead formal manner to learn “difficult learning” and “easy learning” related to the training data set.

Keywords:

Machine Learning, Active Learning, N-gram, SVM, Classification

Published

2024-04-11
Statistics
Abstract Display: 0
PDF Downloads: 0

Issue

Section

Articles

How to Cite

An hybrid approach of active learning using SVM and N-gramtechnique. (2024). Scienxt Journal of Computer Science & Information Technology, 2(1). https://journals.scienxt.com/index.php/sjcsit/article/view/336