Overview
Goal: The goal of this tutorial is to provide an introduction to data mining with a focus on recent developments in the area of fuzzy set and rough set hybridisation. Also, it will provide a demonstration of how such techniques can be employed for various data mining tasks such as feature selection, and classification using the Weka data mining suite.
The areas of fuzzy sets and rough sets have become topics of great research interest, particularly in the last 20 or so years. The integration or hybridisation of such techniques has also attracted much attention, due mainly to the fact that these distinct approaches to data and knowledge modelling are complementary when attempting to deal with uncertainty and noise. A large body of the work on fuzzy-rough set hybridisation, however, has tended to focus on formal aspects of the theory and thus has been framed in that context. This tutorial provides a platform and a unique opportunity to explore the foundations of fuzzy-rough sets and demonstrate the advantages offered for data mining tasks using the Weka environment
This tutorial will cover the background to the main fuzzy-rough data mining techniques as well as the techniques themselves, and also a demonstration of the Weka environment and the fuzzy-rough implementations using example data.
Materials
Slides and other resources will appear here soon...
- Tutorial slides: Talk, demo
- Weka program with fuzzy-rough methods included
- Example dataset: Heart
- Optional walkthrough
References
There are many papers in these areas; this is a selection of papers that are relevant to this tutorial. Most of the papers can be accessed freely in the accompanying links.
Feature Selection
(2014) Finding rough and fuzzy-rough set reducts with SAT. Information Sciences 255 pp. 100-120. download
(2013) Unsupervised fuzzy-rough set-based dimensionality reduction. Information Sciences 229 pp. 106-121. 10.1016/j.ins.2012.12.001
(2010) Attribute Selection with Fuzzy Decision Reducts. Information Sciences 180 (2) pp. 209-224. 10.1016/j.ins.2009.09.008 download
(2010) A Distance Measure Approach to Exploring the Rough Set Boundary Region for Attribute Reduction. IEEE Transactions on Knowledge and Data Engineering 22 (3) pp. 306-317. 10.1109/TKDE.2009.119 download
(2010) Ordered Weighted Average Based Fuzzy Rough Sets. download Other
(2009) New approaches to fuzzy-rough feature selection. IEEE Transactions on Fuzzy Systems 17 (4) pp. 824-838. 10.1109/TFUZZ.2008.924209 download Other
(2009) Interval-valued Fuzzy-Rough Feature Selection in Datasets with Missing Values. Proceedings of the 18th International Conference on Fuzzy Systems. pp. 610-615. 10.1109/FUZZY.2009.5277289 download
(2008) A Noise-tolerant Approach to Fuzzy-Rough Feature Selection. 17th International Conference on Fuzzy Systems (FUZZ-IEEE'08). download
(2008) Finding Fuzzy-rough Reducts with Fuzzy Entropy. 10.1109/FUZZY.2006.1681746 download
(2007) Feature Selection based on Rough Sets and Particle Swarm Optimization. Pattern Recognition Letters pp. 459-471. 10.1016/j.patrec.2006.09.003 download
(2007) Fuzzy-Rough Sets Assisted Attribute Selection. IEEE Transactions on Fuzzy Systems 15 (1) pp. 73-89. 10.1109/TFUZZ.2006.889761 download
(2006) Performing Feature Selection with ACO. Swarm Intelligence and Data Mining. Springer Verlag pp. 45-73. download Other
(2004) Semantics-Preserving Dimensionality Reduction: Rough and Fuzzy-Rough-Based Approaches. IEEE Transactions on Knowledge and Data Engineering 16 (12) pp. 1457-1471. 10.1109/TKDE.2004.96 download Other
Instance Selection
N. Verbiest (2014) Multi Threshold FRPS: A New Approach to Fuzzy Rough Set Prototype Selection. Rough Sets and Current Trends in Soft Computing, Lecture Notes in Computer Science Volume 8536, pp. 83-91. download
E.C.C. Tsang, Q. Hu, D. Chen (2014) Feature and instance reduction for PNN classifiers based on fuzzy rough sets. International Journal of Machine Learning and Cybernetics, pp. 1-11. download
N. Verbiest, C. Cornelis, F. Herrera (2013) FRPS: a Fuzzy Rough Prototype Selection Method. Pattern Recognition 46(10), pp. 2770-2782. download
J. Derrac, N. Verbiest, S. Garcia, C. Cornelis, F. Herrera (2013) On the Use of Evolutionary Feature Selection for Improving Fuzzy Rough Set Based Prototype Selection. Soft Computing 17(2), pp. 223-238. download
N. Verbiest, C. Cornelis, F. Herrera (2013) OWA-FRPS: A Prototype Selection method based on Ordered Weighted Average Fuzzy Rough Set Theory. Proceedings of the 14th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing (RSFDGrC 2013), LNAI 8170, pp. 180-190. download
N. Verbiest, E. Ramentol, C. Cornelis, F. Herrera (2012) Improving SMOTE with Fuzzy Rough Prototype Selection to Detect Noise in Imbalanced Classification Data. Proceedings of the 13th Ibero-American Conference on Artificial Intelligence (IBERAMIA 2012), LNAI 7637, pp. 169-178. download
(2010) Fuzzy-rough instance selection. download
Classification
(2013) Quality, Frequency and Similarity Based Fuzzy Nearest Neighbor Classification. 2013 IEEE International Conference on Fuzzy Systems (FUZZ). IEEE pp. 1-8. 10.1109/FUZZ-IEEE.2013.6622340
(2012) Fuzzy Rough Positive Region based Nearest Neighbour Classification. 2012 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE). pp. 1961-1967. download
(2011) Fuzzy-Rough Nearest Neighbour Classification and Prediction. Theoretical Computer Science 412 (42) pp. 5871-5884. 10.1016/j.tcs.2011.05.040 download
(2009) Hybrid Fuzzy-Rough Rule Induction and Feature Selection. download
Other topics
R. Jensen, N. Mac Parthalain (2014) Nearest Neighbour-Based Fuzzy-Rough Feature Selection. Lecture Notes in Computer Science Volume 8536, pp. 35-46. download
R. Jensen, N. Mac Parthalain, C. Cornelis (2014) Feature Grouping-Based Fuzzy-Rough Feature Selection. Proceedings of the IEEE International Conference on Fuzzy Systems. (this conference!)
(2013) Simultaneous feature and instance selection using fuzzy-rough bireducts. Proceedings of the 22nd IEEE International Conference on Fuzzy Systems. download
J. Derrac, C. Cornelis, S. García, F. Herrera (2012) Enhancing Evolutionary Instance Selection Algorithms by means of Fuzzy Rough Set based Feature Selection. Information Sciences 186(1), pp. 73-92. download
(2011) Fuzzy-Rough Set based Semi-Supervised Learning. 2011 IEEE International Conference on Fuzzy Systems (FUZZ). pp. 2465-2472. 10.1109/FUZZY.2011.6007483 download
(2008) Computational Intelligence and Feature Selection. Wiley Other