Swarm intelligence

(Particle swarm optimisation)

Ahmed Mouelhi, M. Saad Qureshi, and Suneetha Cherukuwada

Information Technology, Heilbronn University
Max-Planck-Str. 27, Heilbronn, Germany
amouelhi, mqureshi, scheruku @stud.hs-heilbronn.de

I. INTRODUCTION
Swarm in nature is a collection of homogenous particles to
achieve the same objective where there is no centralized
control. Examples of these species are ants, birds and bees.
Even though that each member of the swarm is unintelligent,
the whole group manages to cooperatively reach an upper
level of intelligence. These behaviors have fascinated
scientists and researchers and have been a source of
inspiration to solve multiple complex problems and creating a
whole new branch in Artificial Intelligence called Swarm
intelligence(SI). Initially this term was introduced by Gerardo
Beni and Jing Wang in 1989. This collective behavior gives a
new way to design intelligent systems by replacing
centralization, preprogramming and control with distributed
functioning, emergence and autonomy. This paper will
describe In section 2, The various application fields that use
swarm intelligence and in section 3, A brief description about
different swarm intelligence algorithms that are inspired by a
kind of animals. In section 4, The description about our
subarea of Swarm Intelligence i.e., Particle Swarm
optimization. The social behavior of PSO particles, and brief
description of algorithms. In section 5,

Swarm Intelligence is widely used in the field of Robotics.

For example, to push large obstacles, exploring an unknown
planet, space research, surveillance and other military
applications.
SI has already been used in movies for Crowd simulation.
Ex: Batman returns (Simulation of bats), Lord of the rings
(massive technology).
It seems that swarm intelligence and knowledge extraction
does not have common attributes but they can give good results
if they are used together. Recently methods of swarm
intelligence have been used for image processing and pattern
recognition [6]. Researchers formed a clustering method based
on SI and applied it on the problems of unsupervised
classifications and image segmentation. This method was
designed with a goal to reduce intra-clusters distance and the
quantization error, and increase inter-clusters distance.
III. SWARM INTELLIGENCE AGORITHMS
Until now we have presented briefly swarm intelligence
and mentioned some of the fields where it has been applied.
In this part, we introduce some of different algorithms that
belong to the swarm intelligence family.

II. SI APPLICATIONS
SI algorithms have successfully solved several optimization
and data analysis problems in different fields such as
combinatorial optimization problems, structural optimization,
function optimization, finding optimal routes, scheduling,
image analysis, data mining, machine learning, medical
informatics, dynamical systems, bioinformatics, industrial
problems, operations research.
SI has been found useful in the Cloud computing domain to
use the heuristic to minimize the total cost of execution of
application workflows on Cloud computing environments
The future of SI is quite promising with many other
domains still to be explored for example bioinformatics. Lately
SI has attracted the attention of bioinformatics researchers
which found SI to be useful and efficient with several
bioinformatics related tasks like the 2D and 3D hydrophobic
polar protein folding and DNA sequencing by hybridization.
Researchers of medical informatics are trying to use SI
based control of nanorobots to fight Cancer.

Fig. 1: Hirarical representation of swarm intelligence algorithms.

a) Artificial Bee Colony algorithm

Honey Bees are social insects. They are very

efficient in finding the best food source both in terms of
quality and distance. They are the most standard example of
organized team work, labor division, coordination,
simultaneous task performance and well-knit communication.
The typical bee colony has three types of bees.
1) The queen Bee
2) Many male drone bees and
3) Thousands of worker bees.
The queen bee is responsible for laying eggs and drone
bees are responsible for mating with the queen bee and the
worker bees also called as scout bees are responsible for
searching for food and collecting the food. These Scout bees
communicate among themselves through Waggle dance to
inform about the best food source. Figure 2 shows the waggle
dance performed by honey bee.

Fig. 2: Waggle dance performed by a bee

While performing, this waggle dance the scouts tells

the foragers about direction of food with respect to the sun
and the intensity of waggle indicates how far is the food
source from the nest. By doing this dance the scout bee will
volunteer the other bees. This will be done until they found
the best food source. Fig. 3 shows the typical behavior of bee
foraging

.
Fig 3: behavior f bee foraging

This technique of artificial bee colony has introduced by

Karabora in 2005. This technique has been successfully
applied for finding the global minimum of test functions like
classic optimization problem, sphere function that is
continuous, convex and unimodal function.
b) Cat swarm intelligence
Cat swarm optimization is a recent metaheuristic
technique developed by Chu and Tsai (2007). It is inspired
from the behavior of cats in order to solve optimization
problems. Cats have two distinct characteristics. The first is
their strong curiosity when they spot a moving object and the
second one is their great hunting skills and from these two
characteristics two modes are introduced in this metaheuristic
algorithm: The seeking mode and the tracing mode. The first
one manifests the curiosity characteristic of cats and the
second one describes their hunting skills while tracing a target.
The two modes are combined by mixture ratio (MR).
approach, cats are represented using the velocity and the
position vectors in a d-dimensional space and each cat has a
flag which describes its mode.
c) Ant colony optimization
This algorithm belongs the Ant colony algorithms
family which are algorithms that come from the behavior of
ants, forming a great organization. In 1983, researchers
discovered that ants are always able to find the shortest path
between their colonies and food sources found. Knowing that
most ants are almost blind, which is quite surprising.
Furthermore, ants are also able to respond to changes in the
environment. Thus, when the path is blocked by an obstacle,
the ants find another way, always shorter than all the other
possible. The researchers explain this phenomenon by the
pheromone.
This chemical substance secreted, as a mean of
communication between these insects. Each ant deposits along
its path of pheromone. All members of the colony perceive
this substance and preferentially orient their march towards
the most odorous regions. The volatility of the pheromone
ensures the disappearance of solutions that are not anymore
suitable as shown in Fig1.

Fig.1: Ants stigmergic behavior in finding the shortest route between food and
nest.

The ant colony algorithm was originally mainly used to

produce near-optimal solutions to the traveling salesman
problem in 1990.The general concept is to simulate the
behavior of several agents working in the search for a better

solution using a simple mean of communication: the

pheromone. As part of the ant colony optimization, agents are
artificial ants. Thus, an artificial ant:
Has a memory allowing it to retain the solution it
built.
Is not totally blind and can therefore see a little
beyond its immediate circle
Manages the amount of pheromone deposited
depending on the quality of the solution.
d) Artificial fish swarm algorithm
Artificial fish swarm algorithm was presented by Li Xiao
Lie Artificial in 2002[7]. It is stochastic population-based
algorithm influenced by group movement of fish and their
social interactions. Fish tries to retain their colony and show
intelligent behavior during migration, search for food and
managing a threat. They lack knowledge about their
surrounding and whole group. They move in environment by
interchanging their data with nearby companions.
The main concept of artificial fish swarm algorithm is to
simulate behaviors of fish like swarming, preying and reaching
global optimum by local search done by single fish. Artificial
fish lives in a habitat which is made of solution space and other
fishes states. Its next interaction is based on its present state
and local surrounding state. An AF influences its environment
through its actions and by its other group fishes activities.
There are multiple benefits of this algorithm like flexibility,
high accuracy, high speed of convergence and fault tolerance.
e) Particle swarm optimization
Particle swarm optimization is one of the popular
algorithm of Swarm intelligence which is inspired from bird
flocking or fish schooling. Generally, we observe birds flying
in large groups without making any collisions and travel for
long distances. To achieve this, they follow some simple rules.
In this paper, we describe the behavior of these particles and
how does it inspire researches to solve the real-time problems,
and applications that use this technique.
IV. PARTICLE SWARM OPTIMISATION MODEL
As mentioned above Particle Swarm Optimisation is one of
the most popular and successful subarea of Swarm Intelligence.
PSO was introduced by an electrical engineer Russel Elbert
and a social psycologist James Kennedy in 1995. Since then
researchers have developed new applications and derived new
versions of PSO. This section describes the sociological
flocking behavior of birds, A brief description about various
applications of PSO.
A. Socialogical flocking behavior of Birds or Fishes
The flocking behavior of birds or fishes is to achieve a
common objective like foraging food or long distance
migration. These animals have efficient interaction which
leads to capable of
Travelling together without making any
collisions and changing directions suddenly.

Whenever there is an external threat they scatter

and quickly regroup.
These animals change their physical movement to
o Optimize environmental parameters such as
temperature.
o Avoid predators
o Seek food and mates.
1) To achieve the goal of long distance migration they
follow the nearest animal direction and it tries to
match the velocity of its nearest neighbor.
2) To find the food they follow the animal that is
nearest to the food.
B. PSO Algorithm
Particle Swarm Optimization technique was introduced by
Dr. Kennedy and Dr. Herbert in 1995 which is a stochastic
optimization technique. In recent times, many researches
are showing more interest in this new algorithm.

Authors and Affiliations

The template is designed so that author affiliations are not
repeated each time for multiple authors of the same affiliation.
Please keep your affiliations as succinct as possible (for
example, do not differentiate among departments of the same
organization). This template was designed for two affiliations.
1) For author/s of only one affiliation (Heading 3): To
change the default, adjust the template as follows.
a) Selection (Heading 4): Highlight all author and
affiliation lines.
b) Change number of columns: Select the Columns icon
from the MS Word Standard toolbar and then select 1
Column from the selection palette.
c) Deletion: Delete the author and affiliation lines for
the second affiliation.
2) For author/s of more than two affiliations: To change
the default, adjust the template as follows.
a) Selection: Highlight all author and affiliation lines.
b) Change number of columns: Select the Columns
icon from the MS Word Standard toolbar and then select 1
Column from the selection palette.
c) Highlight author and affiliation lines of affiliation 1
and copy this selection.
d) Formatting: Insert one hard return immediately after
the last character of the last affiliation line. Then paste down
the copy of affiliation 1. Repeat as necessary for each
additional affiliation.
e) Reassign number of columns: Place your cursor to
the right of the last character of the last affiliation line of an
even numbered affiliation (e.g., if there are five affiliations,
place your cursor at end of fourth affiliation). Drag the cursor
up to highlight all of the above author and affiliation lines. Go

to Column icon and select 2 Columns. If you have an odd

number of affiliations, the final affiliation will be centered on
the page; all previous will be in two columns.
C. Identify the Headings
Headings, or heads, are organizational devices that guide
the reader through your paper. There are two types: component
heads and text heads.
Component heads identify the different components of your
paper and are not topically subordinate to each other. Examples
include ACKNOWLEDGMENTS and REFERENCES, and for
these, the correct style to use is Heading 5. Use figure
caption for your Figure captions, and table head for your
table title. Run-in heads, such as Abstract, will require you to
apply a style (in this case, italic) in addition to the style
provided by the drop down menu to differentiate the head from
the text.
Text heads organize the topics on a relational, hierarchical
basis. For example, the paper title is the primary text head
because all subsequent material relates and elaborates on this
one topic. If there are two or more sub-topics, the next level
head (uppercase Roman numerals) should be used and,
conversely, if there are not at least two sub-topics, then no
subheads should be introduced. Styles named Heading 1,
Heading 2, Heading 3, and Heading 4 are prescribed.
D. Figures and Tables
1) Positioning Figures and Tables: Place figures and
tables at the top and bottom of columns. Avoid placing them in
the middle of columns. Large figures and tables may span
across both columns. Figure captions should be below the
figures; table heads should appear above the tables. Insert
figures and tables after they are cited in the text. Use the
abbreviation Fig. 1, even at the beginning of a sentence.
TABLE I.
Table
Head
copy

Table Column Head

Subhead

ACKNOWLEDGMENT (Heading 5)
The preferred spelling of the word acknowledgment in
America is without an e after the g. Avoid the stilted
expression one of us (R. B. G.) thanks .... Instead, try R. B.
G. thanks.... Put sponsor acknowledgments in the unnumbered
footnote on the first page.

REFERENCES
The template will number citations consecutively within
brackets [1]. The sentence punctuation follows the bracket [2].
Refer simply to the reference number, as in [3]do not use
Ref. [3] or reference [3] except at the beginning of a
sentence: Reference [3] was the first ...
Number footnotes separately in superscripts. Place the
actual footnote at the bottom of the column in which it was
cited. Do not put footnotes in the reference list. Use letters for
table footnotes.
Unless there are six authors or more give all authors
names; do not use et al.. Papers that have not been published,
even if they have been submitted for publication, should be
cited as unpublished [4]. Papers that have been accepted for
publication should be cited as in press [5]. Capitalize only
the first word in a paper title, except for proper nouns and
element symbols.
For papers published in translation journals, please give the
English citation first, followed by the original foreign-language
citation [6].

TABLE STYLES

Table column subhead

writing Figure axis labels to avoid confusing the reader. As an

example, write the quantity Magnetization, or
Magnetization, M, not just M. If including units in the
label, present them within parentheses. Do not label axes only
with units. In the example, write Magnetization (A/m) or
Magnetization (A ( m(1), not just A/m. Do not label axes
with a ratio of quantities and units. For example, write
Temperature (K), not Temperature/K.

Subhead

[1]

More table copya

a.

Sample of a Table footnote. (Table footnote)

We suggest that you use a text box to insert a graphic

(which is ideally a 300 dpi resolution TIFF or EPS file with
all fonts embedded) because this method is somewhat more
stable than directly inserting a picture.

[2]

To have non-visible rules on your frame, use the

MSWord Format pull-down menu, select Text Box >
Colors and Lines to choose No Fill and No Line.

[4]
[5]

b.

[3]

[6]

Fig. 1. Example of a figure caption. (figure caption)

Figure Labels: Use 8 point Times New Roman for Figure

labels. Use words rather than symbols or abbreviations when

[7]

G. Eason, B. Noble, and I.N. Sneddon, On certain integrals of

Lipschitz-Hankel type involving products of Bessel functions, Phil.
Trans. Roy. Soc. London, vol. A247, pp. 529-551, April 1955.
(references)
J. Clerk Maxwell, A Treatise on Electricity and Magnetism, 3rd ed., vol.
2. Oxford: Clarendon, 1892, pp.68-73.
I.S. Jacobs and C.P. Bean, Fine particles, thin films and exchange
anisotropy, in Magnetism, vol. III, G.T. Rado and H. Suhl, Eds. New
York: Academic, 1963, pp. 271-350.
K. Elissa, Title of paper if known, unpublished.
R. Nicole, Title of paper with only first word capitalized, J. Name
Stand. Abbrev., in press.
Y. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, Electron spectroscopy
studies on magneto-optical media and plastic substrate interface, IEEE
Transl. J. Magn. Japan, vol. 2, pp. 740-741, August 1987 [Digests 9th
Annual Conf. Magnetics Japan, p. 301, 1982].
M. Young, The Technical Writers Handbook. Mill Valley, CA:
University Science, 1989.