Bat algorithm: Difference between revisions

Revision as of 17:03, 2 July 2016

Revision as of 17:04, 2 July 2016

Line 4:

The idealization of the [[Animal echolocation|echolocation]] of microbats can be summarized as follows: Each virtual bat flies randomly with a velocity <math>v_i</math> at position (solution) <math>x_i</math> with a varying frequency or wavelength and loudness <math>A_i</math>. As it searches and finds its prey, it changes frequency, loudness and pulse emission rate <math>r</math>. Search is intensified by a local [[random walk]]. Selection of the best continues until certain stop criteria are met. This essentially uses a frequency-tuning technique to control the dynamic behaviour of a swarm of bats, and the balance between exploration and exploitation can be controlled by tuning algorithm-dependent parameters in bat algorithm.

A detailed introduction of metaheuristic algorithms including the bat algorithm is given by Yang <ref>Yang, X. S., Nature-Inspired Metaheuristic Algorithms, 2nd Edition, Luniver Press, (2010).</ref> where a demo program in Matlab/Octave is available, while a comprehensive review is carried out by Parpinelli and Lopes.<ref>{{cite journal | last1 = Parpinelli | first1 = R. S. | last2 = Lopes | first2 = H. S. | year = 2011 | title = New inspirations in swarm intelligence: a survey,Int | url = | journal = J. Bio-Inspired Computation | volume = 3 | issue = | pages = 1–16 | doi=10.1504/ijbic.2011.038700}}</ref> A further improvement is the development of an evolving bat algorithm (EBA) with better efficiency.<ref>{{cite journal | last1 = Tsai | first1 = P. W. | last2 = Pan | first2 = J. S. | last3 = Liao | first3 = B. Y. | last4 = Tsai | first4 = M. J. | last5 = Istanda | first5 = V. | year = 2012 | title = Bat algorithm inspired algorithm for solving numerical optimization problems | url = | journal = Applied Mechanics and Materials | volume = 148-149 | issue = | pages = 134–137 | doi=10.4028/www.scientific.net/amm.148-149.134}}</ref>

A Matlab demo is available at the Matlab exchange<ref>here http://www.mathworks.com/matlabcentral/fileexchange/37582</ref>

Line 13:

== Multi-objective Bat Algorithm (MOBA) ==

Using a simple weighted sum with random weights, a very effective but yet simple multiobjective bat algorithm (MOBA) has been developed to solve multiobjective engineering design tasks.<ref>X. S. Yang, bat algorithm for multi-objective optimisation, ''Int. J. Bio-Inspired Computation'', Vol. 3, 267-274 (2011).</ref> Another multiobjective bat algorithm by combining bat algorithm with

NSGA-II produces very competitive results with good efficiency.<ref>{{cite journal | last1 = Bora | first1 = T. C. | last2 = Coelho | first2 = L. S. | last3 = Lebensztajn | first3 = L. | year = 2012 | title = Bat-inspired optimization approach for the brushless DC wheel motor problems | url = | journal = IEEE Trans. Magnetics | volume = 48 | issue = 2| pages = 947–950 | doi=10.1109/tmag.2011.2176108}}</ref>

== Bat Algorithm Embedded with FLANN (BAT-FLANN) ==

BAT-FLANN model was proposed by Sashikala et al. in 2012.<ref>{{cite journal | last1 = Mishra | first1 = S. | last2 = Shaw | first2 = K. | last3 = Mishra | first3 = D. | year = 2012 | title = A new metaheuristic classification approach for micro array data | url = | journal = Procedia Technology | volume = 4 | issue = | pages = 802–806 | doi=10.1016/j.protcy.2012.05.131}}</ref> to solve classification of gene expression data. Using simple bat frequency,loudness and pulse updation logic and random weight, a very effective algorithm is designed that give promising result.

The same model has been used for designing a Meta-heuristic Framework for Secondary Protein Structure Prediction where BAT has been used to optimize FLANN network.<ref>{{cite journal | last1 = Shaw | first1 = K. | last2 = Mishra | first2 = D. | year = 2015 | title = A Meta-heuristic Framework for Secondary Protein Structure Prediction using BAT-FLANN Optimization Algorithm | url = | journal = Indian Journal of Science and Technology | volume = 8 | issue = 16| pages = 951–960 | doi=10.17485/ijst/2015/v8i16/63605}}</ref>

== Directed Artificial Bat Algorithm (DABA) ==

Line 30:

== Applications ==

Bat algorithm has been used for engineering design,<ref>{{cite journal | last1 = Yang | first1 = X. S. | last2 = Gandomi | first2 = A. H. | year = 2012 | title = Bat algorithm: a novel approach for global engineering optimization | url = | journal = Engineering Computations | volume = 29 | issue = 5| pages = 464–483 | doi=10.1108/02644401211235834}}</ref> classifications of gene expression data is done by BAT-FLANN model by Sashikala Mishra,kailash shaw and Debahuti Mishra.,<ref>{{cite journal | last1 = Mishra | first1 = S. | last2 = Shaw | first2 = K. | last3 = Mishra | first3 = D. | year = 2012 | title = A new metaheuristic classification approach for microarray data | url = | journal = Procedia Technology | volume = 4 | issue = | pages = 802–806 | doi=10.1016/j.protcy.2012.05.131}}</ref> It also helps in the field of Protein Secondary Structure Prediction by means of optimizing classifier [11].A fuzzy bat clustering method has been developed to solve ergonomic workplace problems<ref>Khan, K., Nikov, A., Sahai A., A Fuzzy Bat Clustering Method for Ergonomic Screening of Office Workplaces,S3T 2011,

Advances in Intelligent and Soft Computing, 2011, Volume 101/2011, 59-66 (2011).</ref>

An interesting approach using fuzzy systems and bat algorithm has shown

a reliable match between prediction and actual data for exergy modelling.<ref>T. A. Lemma, Use of fuzzy systems and bat algorithm for exergy modelling in a gas turbine generator, IEEE Colloquium on Humanities, Science and Engineering (CHUSER'2011), pp. 305-310 (2011).</ref>

A detailed comparison of bat algorithm (BA) with genetic algorithm (GA), PSO and other methods for training feed forward neural networks concluded clearly that BA has advantages over other algorithms.<ref>{{cite journal | last1 = Khan | first1 = K. | last2 = Sahai | first2 = A. | year = 2012 | title = A comparison of BA, GA, PSO, BP and LM for training feed forward neural networks in e-learning context | url = | journal = Int. J. Intelligent Systems and Applications | volume = 4 | issue = 7| pages = 23–29 | doi=10.5815/ijisa.2012.07.03}}</ref>

==Notes==