Combined Effect of Soft Computing Methods in Classification
Feature Selection can be done in most of the medical domains to identify the most suitable features that result in the accuracy of classification and to reduce time of computation; as it works on reduced number of features. The nature of the problem domai
- PDF / 132,295 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 43 Downloads / 213 Views
Abstract Feature Selection can be done in most of the medical domains to identify the most suitable features that result in the accuracy of classification and to reduce time of computation; as it works on reduced number of features. The nature of the problem domain and the design issues of soft computing methods used determines the effectiveness of feature selection methods. The study includes the feature selection using Genetic Algorithm (GA), to generate the best feature subset of WBCD breast cancer dataset. The features with the best fitness value are selected for classification. Classification is done using a guided approach called Support Vector Machine (SVM) along with some constraints to specify the performance measures of classification.
⋅
⋅
Keywords Feature selection Classification Soft computing Algorithm Breast cancer Support Vector Machine
⋅
⋅
⋅
Genetic
1 Introduction The aim of Soft Computing is to provide solutions that exploit the tolerance to imprecision and uncertainty to achieve tractability, robustness and low solution cost [1]. Soft Computing techniques are most applicable on human adaptability as they need to be processed soft, without showing effect on the other issues. Soft Computing methods deal with intelligent systems. These methods derive better solutions when applied collaboratively with other techniques. Soft Computing methods are
V.S. Kompalli (✉) Devineni Venkata Ramana & Dr. Hima Sekhar MIC College of Technology, Vijayawada, India e-mail: [email protected] U.R. Kuruba Sri Padmavati Mahila Visvavidyalayam (Women’s University), Tirupati, India e-mail: [email protected] © Springer Science+Business Media Singapore 2017 S.C. Satapathy et al. (eds.), Proceedings of the First International Conference on Computational Intelligence and Informatics, Advances in Intelligent Systems and Computing 507, DOI 10.1007/978-981-10-2471-9_49
501
502
V.S. Kompalli and U.R. Kuruba
chosen to soften the possibility of attaining a better outcome to a problem. The principal components of soft computing are fuzzy logic, neural networks and probability neural networks. Later, few additions like genetic algorithms, Bayesian belief networks, etc., are made to work. Support Vector Machine (SVM) follows guided approach of classification. SVM is widely applied on the techniques like classification, regression and clustering. SVM deals with high-dimensional data of various domains. Nearly, 54 % of the applications are solved using classification methods [2]. Multi-Layer Perceptron [16] is another widely used network that can be compared with SVM. MLP is made to work on training dataset. The decision making limits can be set based on the training set in an indirect manner. In contrast, the training data directly specifies the SVM boundaries. These boundaries can be maximized to form the clear margins of classification in the feature space. The domain parameters are adjusted to derive good results using SVM. Classification using SVM results in better solutions based on working conditions of the d
Data Loading...
