Rice Leaf Disease Identification using Novel Nature Inspired Attribute Selection Algorithms

Abstract

In communication with the world, one of the important goals forhuman beings is to recognize objects around them. Researchers and scientists,in the area of machine intelligence, aims to design solution to real lifeproblems in a manner analogous to human beings. Pattern recognition is anintegral part of most machine intelligent systems, built for decision making. newlineMost of the information that surrounds mankind manifests itself inthe form of patterns. Pattern recognition, naturally, is based on patterns. Apattern can be as basic as a set of measurements and attributes are anyextractable measurements from it. Thus, pattern recognition aims to classifypatterns based on a set of attributes obtained from measurement space.Generally, a corpus of attributes is extracted to better characterize apattern recognition problem. It is also important that the extracted attributesyield high predictive performance pertinent to the pattern recognition problemin hand. Attribute selection is a pre-processing tool to classification. It newlinereduces the dimensionality of attribute spaceby selecting highly predictiveattributes from the problem space. newline newline newline newline