Article Preview
Top1. Introduction
The optimization is the part of the living things and used by every living object in this world based on their structure, behaviour, shape size and weight etc.
Ant, bird, bee, firefly, BAT and cuckoo optimize their path base on knowledge structure, behaviour, shape size and weight and human being above all used their nature to solve the problem of their own based on the techniques used by ant, bird, bee, firefly, bat and cuckoo. The question arises as to whether such optimal behaviour of BAT can be used to be built up by assembling elementary units of behaviour. This paper has made effort echolocation behaviour of bats to solve the optimization problems.
1.1. Objective
The main objective of the paper is to develop an integrated system that is capable of extracting precise information (knowledge) based on some stored information using the techniques of data mining and soft computing. It has been further observed that the frequency selection (Discussed in Methodology) in the Bat algorithm plays a vital role to select the optimal solution in result.
For the purpose of extracting precise information based on some stored information, it has been further observed that the research work related to the area of knowledge discovery based on certain information with the help of a data mining or soft computing model has been done but the performance based on the particular soft computing or data mining model has not been reviewed as compared to the other models. The comparison of performance of various models in the area of soft computing domain or statistical domain or data mining area have been remained unattended with limitation of survey. This absence leads to the necessity and carrying out research work for effective knowledge discovery based on a particular set of information on utilizing the versatile and potential view generation tools like AI (Artificial Intelligence), ANN (Artificial Neural Network), GA (Genetic Algorithm), ACO (Ant Colony Optimization), PSO (Particle Swarm Optimization), ABC (Artificial Bee Colony Optimization), HS (Harmony Search), DEA (Differential Evolution Algorithm), TS (Tabu Search) and SA (Simulating Annealing).
1.2. Problem Definition and its Importance
For the extraction of knowledge, five sets of data have been chosen from UCI machine learning repository. These are Iris flower data set (2013), Wine data set (“Wine Quality”.), Boston city data set (“Welcome to”), Wisconsin breast cancer data set (“Breast Cancer”) and Concrete slump test (“Concrete Slump”) Initially Iris data set have been used for gathering of knowledge. Thereafter Wine data set, Boston city data set, Wisconsin breast cancer data set and Concrete slump test have been used for further mining of information.