Empirical Analysis of Bio-Inspired Algorithms for Medical Disease Detection: A Statistical Perspective

Abstract

Medical disease detection is a vast field of image, signal and video processing that involves a large number of complex operations, which include but are not limited to data acquisition, pre-processing, segmentation, feature extraction, feature selection, classification and post-processing. The efficiency of signal classification is directly proportional to the efficiency with which these internal blocks are designed. In order to improve the efficiency of these blocks, several bio-inspired optimization algorithms are proposed by researchers. These include but are not limited to, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Neural Networks (NN), etc. Each of these algorithms can be applied to optimize individual signal processing blocks, thereby improving overall system performance. Due to a large variety of available bio-inspired algorithms, it is ambiguous for system designers to select the best possible algorithmic combination for their medical disease classification design. In order to reduce this ambiguity, the underlying text evaluates performance of some of the most efficient bio-inspired algorithms, and statistically compares them on basis of their application. These applications vary w.r.t. identified disease, type of signal being processed, etc. This comparison will assist researchers and system designers to develop highly efficient medical disease classification systems for clinical use.