ABSTRACT
High dimensional and multidimensional data is found in different applications for object classification, face image recognition, processing of electrocardiography signals, medical images classification of disease, telecommunication, process and program monitoring. This chapter discusses a variety of dimension reduction techniques and identifies key features, strengths and limitations of these techniques. A common goal of dimension reduction is to prepare data for machine learning algorithms and models to make classification and predictions precise. Another objective is to examine the data in situations where classification is unknown and can occur in the future, with the goal of predicting what will be classified and how it can be classified. Dimension Reduction Techniques create a new representation of the original data by transforming it to lower dimensions with the aim of preserving the original structure of the data. These techniques help to identify sets of redundant and irrelevant features for subsequent analysis.
