Hybrid Computational Intelligent Attribute Reduction System, Based on Fuzzy Entropy and Ant Colony Optimization
Attribute reduction plays a crucial role in reducing the computational complexity and therefore the resource consumptions in the area of artificial intelligence, machine learning and computing applications. Rough sets are a very promising technique in att
- PDF / 505,433 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 89 Downloads / 216 Views
Abstract Attribute reduction plays a crucial role in reducing the computational complexity and therefore the resource consumptions in the area of artificial intelligence, machine learning and computing applications. Rough sets are a very promising technique in attribute reduction or feature selection. Fuzzy and rough set hybrids have been proven to be more effective in selecting important features from the available data, particularly in the case of real-time data. There is a need for global searching strategies to find the best possible, minimal combination of features, and at the same time to maintain the originality of information. This paper proposes a hybrid computational intelligent attribute reduction system based on fuzzy entropy, fuzzy rough sets, and ant colony optimization, which do not depend on fuzzy dependency degree. Experimentation conducted on several UCI universal benchmark data sets proves this method to be feasible in obtaining minimal feature set with undisturbed or improved classification accuracy when compared to fuzzy entropy and dependency degree-based fuzzy rough quick reduct.
Keywords Rough sets Fuzzy rough sets Fuzzy entropy Ant colony optimization ACO Feature selection Attribute reduction
P. Ravi Kiran Varma (&) MVGR College of Engineering, Vizianagaram, AP, India e-mail: [email protected] V. Valli Kumari Andhra University College of Engineering, Visakhapatnam, AP, India e-mail: [email protected] S. Srinivas Kumar University College of Engineering Kakinada, JNTU Kakinada, Kakinada, AP, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 M.S. Reddy et al. (eds.), International Proceedings on Advances in Soft Computing, Intelligent Systems and Applications, Advances in Intelligent Systems and Computing 628, https://doi.org/10.1007/978-981-10-5272-9_30
307
308
P. Ravi Kiran Varma et al.
1 Introduction Computational intelligent systems often require a preprocessing stage called feature selection or attribute reduction. Feature reduction will help to optimize the computational complexity of the knowledge processing task; sometimes it also comes with additional benefit of improved accuracy, and also the volume of data features to be collected reduces. There is a continuous research in the area of feature selection [1] or attribute reduction; the main goal of which is to optimize the features at the same time retain the quality and originality of data objects. Rough sets [2, 3] are introduced by Pawlak and became very popular as a tool which mathematically deals with vagueness, lack of preciseness, and uncertainness in the knowledge extraction, and analysis of data. The advantage of rough sets is that it does not depend on any external inputs and also do not transform the existing data. It is best suitable for dimensionality reduction. Other applications of rough sets include rule generation and prediction [4]. Traditional rough sets [5] can be applied directly for discrete data, where there is a need for additional step of discretizati
Data Loading...
