There are many types of rough sets theory such as fuzzy rough sets, crisp rough sets, tolerance rough sets and so on. If some body can make a comparison between the feature selection capabilities of these extensions?
Article A similarity-based mechanism to control genetic algorithm an...
Dear friend,
Greetings.
Using Rough set theory we can find the relevant feature set from a given set.
I have used this method in one of my paper:
A novel approach for accurate identification of splice junctions based on hybrid algorithms- " Journal of Biomolecular Structure and Dynamics, 2014"
You may have a look at it.I have explained the details of it.
I hope this helps you.
Best regards
Dr.Indrajit Mandal
This is a good question.
A good place to start is
K. Thangavel, Q. Shen, A. Pethalakshmi, Application of clustering for feature selection based on rough set theory approach, AIML journal 6, 2006, no. 1, 19-27:
https://wiki.eecs.yorku.ca/course_archive/2010-11/W/4403/_media/p1120548004.pdf
See Section 1.3, starting on page 20, for an introduction rough set-based feature reduction, which indirectly related to the question for this thread.
Another place to look for an answer is in
R.W. Swiniarksi, A. Skowron, Rough set methods in feature selection and recognition, Pattern Recognition Letters 24, 2003, 833-849:
https://wiki.eecs.yorku.ca/course_archive/2013-14/F/4403/_media/roughsetmethods.pdf
See Section 3, starting on page 837, on defining a feature selection criterion. See Section 3.1, startilng on page 838, on a rough set based approach to feature selection.
Another noteworthy place to consider is
Y. Chen, D. Miao, R. Wang, A rough set approach to feature selection based on ant colony optimization, Pattern Recognition Letters 31, 2010, 226-233:
http://www.tongji.edu.cn/~dqmiao/paper/2010PRL_CYM.pdf
An algorithm that gives detailed steps in the proposed approach is given in Section 4.4, startilng on page 230.
You could see the papers:
Rough sets and evolutionary computation to solve the feature selection problem. In Rough Set Theory: A True Landmark in Data Analysis. En Series: Studies in Computational Intelligence, Volume 174, pp. 235-260, Ajith Abraham, Rafael Falcón, Rafael Bello (Eds.), ISBN: 978-3-540-89920-4. ISSN 1860949V. Alemania. 2009.
Two Step Swarm Intelligence to Solve the Feature Selection Problem. Journal of Universe Computer Science, vol 14, issue 15, pp. 2582-2596. 2008.
Multi-colony ACO and Rough Set Theory to distributed feature selection problem. En Lecture Notes in Computer Science 5518/2009, pp. 458-461, Proceedings (Part II) of Distributed Computing, Artificial Intelligence, Bioinformatics, SoftComputing, and Ambient Assisted Living at 10th International Work-Conference on Artificial Neural Networks IWANN2009, Salamanca, Spain, June 10-12, 2009. Springer Berlin/Heidelberg 2009.
A good review of feature selection (reduct algorithms) using rough set theory is given in,
https://www.igi-global.com/chapter/rough-set-based-feature-selection/28468
In short, classical rough sets is used for feature selection in complete symbolic decision systems, fuzzy rough sets is used for hybrid decision systems and tolerance rough sets is used for Incomplete symbolic decision systems.
- Badges
- Science topic