A SURVEY ON SIMILARITY MEASURES AND MACHINE LEARNING ALGORITHMS FOR CLASSIFICATION AND PREDICTION

Abstract

An important observation which figures out when we look into several applications which are the result of applying data science, machine learning, and deep learning techniques is that most of these techniques are based on the concept of measuring similarity between any two vectors. These vectors may act as representatives for objects being considered. Similarity measurement thus gains a great importance in the design of machine learning or deep learning algorithms and techniques. In similar lines, when we are required to carry a supervised or unsupervised learning task, an algorithm is required to carry the task efficiently. Thus, in this paper, our objective is to outline various similarity measures that have been considered for carrying supervised or unsupervised learning tasks and also to throw light on different machine learning algorithms employed for supervised and unsupervised learning tasks from disease classification and prediction point of view and also interdisciplinary domains such as time series analysis, temporal data mining, medical data mining, and anomaly or intrusion detection.