ABSTRACT

Discriminant analysis is the statistical technique that is most commonly used to solve complex problems. Its use is appropriate when you can classify data into two or more groups, and when you want to find one or more functions of quantitative measurements that can help you discriminate among the known groups. The objective of the analysis is to provide a method for predicting which group a new case is most likely to fall into, or to obtain a small number of useful predictor variables. In this work, the purpose is to classify cotton bales into well define groups or categories based on a training set of similar samples for grading cotton blends. A new algorithm has been implemented using discriminant analysis and its advantages in quality design of cotton blends are demonstrated.