ANALYSIS OF DATA MINING AND SOFT COMPUTING TECHNIQUES IN PROSPECTING DIABETES DISORDER IN HUMAN BEINGS: A REVIEW

Diabetes is one of the deadliest and non-contagious diseases that can adversely affect several parts of human body. Early prognosis of diabetes can inkling the grievous complications and help to save human life. Several researchers have used different data mining (Iterative Dichotomiser 3, Random Forest, Support Vector Machine, k-Nearest Neighbour, C4.5) and soft computing (Genetic Algorithm, Ant Colony Optimization, Particle Swarm optimization, Artificial Bee Colony) techniques to prospect diabetes in human beings. In last 10 years, C4.5 was the most preferred choice for mining diabetic patients. Likewise, in soft computing, maximum number of researchers have used genetic algorithm. Furthermore, the usage of pre-processing techniques is significantly increasing in diabetes diagnosis. It is also observed that rate of accuracy achieved in diagnosing diabetes using traditional data mining lies in 68.5% - 95.3%. Likewise, the range for soft computing and their hybridized use lies in 74% - 100%. In addition, rate of accuracy achieved using GA based hybridized approach is better than the accuracy obtained using PSO as well as ABC. Most of the researchers have used textual and numeric data for diabetes diagnosis. Few researchers have used images for the same. However, no significant research is found where diabetes has been diagnosed using audio or sound. Moreover, the diagnostic results obtained using image based data are not as good as obtained using textual or discrete data. Therefore, an attention is still obligatory to develop smart diabetes diagnostic system that can effectively work on different types of data like text, images as well as sound.