You are on page 1of 6

See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/318959313

A Review of Bio-inspired Algorithm

Conference Paper · January 2017

CITATION READS
1 3,346

3 authors, including:

Waleed A. Hammood Al-Fahim Mubarak-Ali


Universiti Kebangsaan Malaysia Universiti Malaysia Pahang
14 PUBLICATIONS   75 CITATIONS    18 PUBLICATIONS   21 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Generic Code Clone Detection Platform: A platform detecting multi types and multi language code clone View project

A Hybrid Algorithm of Random Forest and Support Vector Machine (RF-SVM) to Select Informative Genes for Higher Classification Accuracy of Cancer Microarray Data View
project

All content following this page was uploaded by Waleed A. Hammood on 24 February 2019.

The user has requested enhancement of the downloaded file.


See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/318959313

A Review of Bio-inspired Algorithm

Conference Paper · January 2017

CITATIONS READS
0 117

3 authors, including:

Waleed A. Hammood Al-Fahim Mubarak-Ali


Universiti Kebangsaan Malaysia Universiti Malaysia Pahang
6 PUBLICATIONS   2 CITATIONS    13 PUBLICATIONS   6 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Generic Code Clone Detection Platform: A platform detecting multi types and multi language code clone View project

A Hybrid Algorithm of Random Forest and Support Vector Machine (RF-SVM) to Select Informative Genes for Higher Classification Accuracy of Cancer Microarray Data View
project

All content following this page was uploaded by Waleed A. Hammood on 07 August 2017.

The user has requested enhancement of the downloaded file.


A Review of Bio-inspired Algorithm

Waleed A.Hammood Kamal Z Zamil AF Mubarak Ali


Faculty of Computer Systems and Faculty of Computer Systems and Faculty of Computer Systems and
Software Engineering Software Engineering Software Engineering
Universiti Malaysia Pahang 26300 Universiti Malaysia Pahang 26300 Universiti Malaysia Pahang 26300
Kuantan, Pahang, Malaysia Kuantan, Pahang, Malaysia Kuantan, Pahang, Malaysia
engwaleed54@yahoo.com kamalz@ump.edu.my fahim@ump.edu.my

Abstract— Nature is, of course, a great and immense source Artificial bee colony described in section 6. Section 7
of the inspiration for solving hard and complex problems in described the bat algorithm. Finally, the last section
computer science since it exhibits extremely diverse, dynamic, concludes the paper.
robust, complex and fascinating phenomenon. It always finds
the optimal solution to solve its problem maintaining perfect
balance among its components. Nature inspired algorithms are II. META- HEURISTICS
meta-heuristics that mimics the nature for solving optimization In bio-inspired algorithms in most popular of these
problems opening a new era in computation. This paper algorithms, Differential Evolution (DE)[2] proposed by
presents a broad overview of biologically inspired optimization
algorithms, grouped by the biological field that inspired each
Storn and Kennedy numeral optimization problems based
and the areas where these algorithms have been most population of algorithm by using evolutionary operators,
successfully applied selection, crossover and mutation. Firefly algorithm (FA)[3]
by Yang based on the communication and flashing behavior
Keywords: Bio-inspired algorithm, Swarm intelligent, of flashes with fireflies. PSO algorithm [4] presented by
Evolution algorithm Eberhart and Kennedy in 1995, based meta-heuristic swarm
I. INTRODUCTION that models the social behavior of fish schooling or bird
flocking. Artificial Bee Colony (ABC) algorithm [5]
In this paper we introduced the existing nature inspired presented and developed by Karaboga 2005 emulation the
algorithms which it meta-heuristics that mimics the nature foraging behavior of honey bees and has been applied to
to resolve optimization problems. Bio-inspired meta- many problems faces in various research areas. Lastly, Bat
heuristic algorithms have shown proficiency of solving a Algorithm (BA) is a bio-inspired algorithm developed by
great many optimization applications[1, 2]. Meta-heuristics Xin-She Yang in 2010 [1] and BA has been found to be
are based on the iterative enhancement of either a very efficient. In this paper, the bio-inspired algorithms are
population of solutions as in (Swarm based algorithms, divided according to Fig. 1
Evolutionary algorithms) or a single solution (e.g. Tabu
Search) and mostly local search and employ randomization
Differential DE
to solve an approaching optimization problem. In Bio- Evolution
inspired, has been proposed in some several fields based on
various natural phenomena such as Differential Evolution FA
Firefly algorithm
(DE)[2], Firefly algorithm (FA)[3], Particle Swarm
Optimization (PSO) algorithm [4], Artificial Bee Colony
Bio-inspired Artificial Bee
(ABC)[5] and Bat Algorithm (BA)[1] Colony ABC

The rest of this paper is organized as follows. In Particle Swarm


PSO
Optimization
Section 2, the meta-heuristic is introduced. The definition
of the differential evolution is discussed in Section 3. In
Section 4 definition of the firefly algorithm is discussed. Bat Algorithm BA
The particle swarm optimization is described in section 5.
Fig. 1.Taxonomy of bio-inspired optimization algorithms
III. DIFFERENTIAL EVOLUTION flocking searching for food. In many fields of engineering
Differential Evolution (DE) is population-based optimization areas, the PSO has been extensively applied
stochastic method for global optimization has been due its unique searching, computational efficiency, simple
introduced to the public in 1995. During the last 20 years concept and easy implementation
research on and with DE has reached an impressive state,
yet there are still new application area are emerging[2, 6]. VI. ARTIFICIAL BEE COLONY
At the beginning of the evolution process, the mutation Presented and developed by Karaboga 2005[5].
operator of DE favours exploration. As evolution Emulation the foraging behaviour of honey bees and has
progresses, the mutation operator favours exploitation. been applied to many problems faces in various research
Hence, DE automatically adapts the mutation increments to areas, these algorithms are classified into two: mating
the best value based on the stage of the evolutionary behaviour and foraging behaviour. ABC as an optimization
process. Mutation in DE is therefore not based on a tool provides a population-based search procedure in which
predefined probability density function. DE It's generally individuals called foods positions are modified by the
considered as a reliable, robust, fast optimization technique artificial bees with time and the bees aim is to discover the
and accurate[7]. places of food source with high nectar amount and finally
the one with the highest nectar. The ABC has high
IV. FIREFLY ALGORITHM flexibility, which allows adjustments and ability to handle
Firefly algorithm proposed by Yang [3] can be the objective cost.
considered as an unconventional swarm-based heuristic
algorithm for constrained optimization tasks inspired by the VII. BAT ALGORITHM
flashing behaviour of fireflies, The algorithm constitutes a is a bio-inspired algorithm developed by Xin-She
population-based iterative procedure with numerous agents Yang in 2010 [1]. It has been built on the assumption that
(perceived as fire flies) concurrently solving a considered able to find its prey complete darkness[8]. Its try to balance
optimization problem. Agents communicate with each other exploitation and exploration by uses the automatic zooming
via bioluminescent glowing which enables them to explore by mimicking the several of pulse emission rates during the
cost function space more effectively than in standard search process when searching for prey by the loudness of
distributed random search, based on Intelligence bats. The standard bat algorithm was based on the
optimization technique its assumption of optimization echolocation or bio-sonar characteristics of microbats.
problem that the solution can be perceived as an agent Among the first set of applications of bat algorithm,
(firefly) which glows proportionally to its quality in a continuous optimization in the context of engineering
considered problem setting. design optimization has been extensively studied, which
demonstrated that BA can deal with highly nonlinear
V. PARTICLE SWARM OPTIMIZATION problem efficiently and can find the optimal solutions
Particle swarm optimization (PSO) is a computational accurately [9-11]. [Table1].
intelligence oriented, stochastic, population-based global
optimization technique proposed by Kennedy and Eberhart
in 1995[4]. It is inspired by the social behaviour of bird

Table1. The details for bio-inspired algorithms


Algorithm Advantages Limitation Parameter Based on Representation Application

FA can deal with when using of i.e., randomized α, Flashing binary, real For solving Travelling
highly non- single method attractiveness β0 and behaviour valued Salesman Problem •
linear, multi- only; this is absorption firefly Digital image
modal because it will be coefficient γ compression and image
optimization overly restrictive processing • Feature
problems for high Selection and fault
naturally and dimensional and detection • Antenna
efficiently, It nonlinear problem design • Structural
does not require a design • Scheduling •
good initial Chemical phase
solution to start equilibrium • Dynamic
its iteration problems
process.
BA Simple, flexible converge very uses parameter Echo real valued Classifications, image
and easy to quickly at the control, which can location processing, feature
implement. * early stage and vary the values of behaviour of selection, scheduling,
Solve a wide then convergence parameters (A and r) micro bat data mining and others.
range of rate slow down, as the iterations
problems and accuracy may be proceed. This
highly nonlinear limited if the provides a way to
problems number of automatically switch
efficiently function from exploration to
evaluations is not exploitation when
high the optimal solution
is approaching
DE Easy to difference Population size, Sensitive to Real-valued unsupervised image
implement between two variable ranges and initial vectors classification ,clustering
requires little vectors yields a number of decision population , digital filter design ,
parameter tuning difference vector optimization of non-
which can be used linear functions , global
with a scaling optimization of non-
factor to traverse linear chemical
the search space engineering processes
and multi-objective
optimization
PSO stability and Dealing with Population size, collective D dimensional multiclass databases,
convergence in a multimodal velocity behaviour of vector for feature selection, web
multidimensional optimization decentralize position ,speed, service composition
complex space, problems d, self- best state course composition,
simple organized dynamic, constrained
implementation systems and combinatorial
optimization problems
ABC Ability to handle Lack of use Swarm size, scouts, foraging D-dimensional scheduling problems,
the objective secondary limit, dimension , behaviour of vector image segmentation,
cost, ability to information, employee bees (50% honey bees ( =1,2… ) capacitated vehicle
explore local require new of swarm), onlookers routing problem ,
solution, high fitness test on the (50% of swarm) (WSNs),assembly line
flexibility, which new algorithm balancing problem,
allows parameters, high Solving reliability
adjustments , number of redundancy allocation
broad objective function problem, training neural
applicability, evaluation networks , XOR,
even in complex Decoder–Encoder and
functions 3-Bit Parity benchmark
problems

3. Yang, X.-S., Firefly algorithm, stochastic test


VIII. CONCLUSION functions and design optimisation. International
In this study we review the bio-inspired algorithms. Bio Journal of Bio-Inspired Computation, 2010. 2(2):
inspired algorithms are going to be a new revolution in p. 78-84.
computer science; nature-inspired algorithms are among the 4. Kennedy, J. and R. Eberhart. Particle swarm
most powerful algorithms for optimization which is going to optimization (PSO). in Proc. IEEE International
have a wide impact on future generation computing. Finally, Conference on Neural Networks, Perth, Australia.
we explained the details for each algorithm. 1995.
5. Karaboga, D., An idea based on honey bee swarm
IX. REFERENCES
for numerical optimization. 2005, Technical report-
1. Yang, X.-S. and X. He, Bat algorithm: literature tr06, Erciyes university, engineering faculty,
review and applications. International Journal of computer engineering department.
Bio-Inspired Computation, 2013. 5(3): p. 141-149. 6. Chakraborty, U., Advances in differential
2. Das, S. and P.N. Suganthan, Differential evolution: evolution. Vol. 143. 2008: Springer.
a survey of the state-of-the-art. IEEE transactions 7. Hegerty, B., C.-C. Hung, and K. Kasprak. A
on evolutionary computation, 2011. 15(1): p. 4-31. comparative study on differential evolution and
genetic algorithms for some combinatorial
problems. in Proceedings of 8th Mexican
International Conference on Artificial Intelligence.
2009.
8. Das, G., Bat algorithm based soft computing
approach to perceive hairline bone fracture in
medical x-ray images. International Journal of
Computer Science & Engineering Technology
(IJCSET), 2013. 4(04).
9. Yang, X.-S. and A. Hossein Gandomi, Bat
algorithm: a novel approach for global
engineering optimization. Engineering
Computations, 2012. 29(5): p. 464-483.
10. Kumari, A.C. and K. Srinivas, Hyper-heuristic
approach for multi-objective software module
clustering. Journal of Systems and Software, 2016.
117: p. 384-401.
11. Alsariera, Y.A., A. Nasser, and K.Z. Zamli,
Benchmarking of Bat-inspired interaction testing
strategy. International Journal of Computer
Science and Information Engineering (IJCSIE),
2016. 7: p. 71-79.

View publication stats

You might also like