Unit-V

Introduction to Swarm Intelligence,

Swarm Intelligence Techniques: Ant
Colony Optimization, Particle
Swarm Optimization, Bee Colony
Optimization etc. Applications of
Computational Intelligence
 Introduction to Swarm Intelligence
• Swarm Intelligence (S.I.) was introduced by Gerardo Beni and Jing
Wang in the year 1989. S.I. simply means using the knowledge of
collective objects (people, insects, etc.) together and then reaching the
optimized solution for a given problem. “Swarm” means a group of
objects (people, insects, etc.). In other words, let’s say we give a problem
statement to a single person and tell him or her to go through this problem
and then give the solution, then this means that we will consider the
solution of that particular person only, but the problem is that the solution
given by that person may not be the best solution or maybe, that solution is
not good for others. So to avoid that, what we do is we give that problem to
a certain amount of people together (swarm) and ask them to reach the best
solution possible for that problem, and then computing all the responses
together to reach the best solution possible, so here we are using the
knowledge of the group as a whole to reach to the best solution or
optimized solution for that problem and that solution will be good for all of
them individually too, so that is the idea behind swarm intelligence.
• Note: In swarm intelligence, each individual (object) in the
group is independent of others, each individual is responsible
for their own contribution to solve that problem regardless of
what others are doing.
• Example
• Let’s say we have a jar containing 500 marbles in that. The question is
without touching the jar a person needs to predict how many marbles are in
that jar. Suppose we take only one response from a person and it predicts
that according to him the jar contains 400 marbles. So by this result, we can
conclude that this estimation of that person is not very bad since
the difference (error) is of 100 only, but this might not be the best solution,
we can optimize this even more. So now what we will do is instead of
taking response from only one person we will be taking response from 10
people let’s say. Let ‘P’ denote a person therefore the responses are as
follows:
• So after collecting the responses from 10 different individuals
we can take the average of their responses.
• Average:
• (400 + 450 + 550 + 600 + 480 + 390 + 520 + 490 + 510 + 450) / 10
• Average = 4840 / 10
• = 484 (marbles in the jar)
• Now from this, we can say that from the collective predictions
from 10 different persons we have reached a more optimal
answer that is 484 marbles in the jar. We are very close to the
actual result of 500 marbles in the jar, here in this case
the difference (error) reduces to only 16 marbles as
compared to the previous error which was 100. So that is the
main idea behind swarm intelligence, that is to use the
collective knowledge of objects.
 Why Swarm Intelligence?
• The answer to this is simple now and we proved this in our
previous marble example, which is collecting the answers
(responses) from different objects individually and then
computing all responses as a whole to a solution that best fits
our given problem. So here, with this approach, we are having
a more optimized solution for a given problem and that is the
reason why swarm intelligence came into the picture, because
of this reason we can use it in different scenarios of life e.g.
Forecasting, Which policy is good for the business, etc. So
simply we are using the ‘Brain of Brains’ to reach the
solution for a given problem. If we will observe in our
surroundings (nature) then we will be able to find many
examples of swarm intelligence like ‘ant colony’, ‘swarm of
bees’, ’flock of birds’ etc. and in reality, also the idea of
swarm intelligence was taken from nature only. Some are
explained below:
 • Ant Colony
• If we will observe closely then the ants also follow
the principle of swarm intelligence, for example, to
build the home they collect mud particles from the
surroundings and individually have a responsibility to
build their home. They communicate through signals
and pheromones (ants use this for tracing other ants)
and regardless of what other ants are doing, an
individual ant is responsible for only its own
contribution to build the home. Similarly when they
search for food then at first they search individually
for food leaving the pheromones behind and once
they find the food source then that ant communicates
with other ants and then other ants can trace it and
follow that path to reach the source of food instead of
just randomly searching food in different locations
every time.
 • Swarm of Bees
• Bees also use the same principle for their survival that is when they
search for the place like where they can build their hive, then the
task of each bee is to consider several parameters that the hive which
will be built should be on good height to avoid predators, should be
near water resource, should be near pollens (flowers to collect
nectar), etc. then they use their collective research and finally a
place is decided that where the hive would be built considering all
those parameters and they reach the best solution for that problem.
• Artificial Swarm Intelligence (ASI)
• It is also known as Human Swarm. Here also the idea is same that
we randomly make some of the persons participating in a real-time
system and tell them to find the solution for that particular problem
individually, the final solution is then computed after taking
responses from each participant and the final solution is presented
which is more optimized as compared to the solution taking from
only one participant.
• Applications of Swarm Intelligence
• Used in military services.
• NASA is generating the idea to use swarm
intelligence for planetary mapping.
• Used in Data Mining.
• M. Anthony Lewis and George A. Bekey
presented the idea that with the help of
swarm intelligence we can control nanobots in
our body to kill cancer tumors.
• Used in business to reach better financial
decisions etc.
 Swarm Intelligence
Swarms

• Natural phenomena as inspiration

• A flock of birds sweeps across the Sky.
• How do ants collectively forage for food?
• How does a school of fish swims, turns
together?
• They are so ordered.
 What made them to be so
ordered?
• There is no centralized controller
• But they exhibit complex global behavior.
• Individuals follow simple rules to interact
with neighbors .
• Rules followed by birds
– collision avoidance
– velocity matching
– Flock Centering
 Swarm Intelligence-Definition

• “Swarm intelligence (SI) is artificial

intelligence based on the collective behavior
of decentralized, self-organized systems”
 Characteristics of Swarms

• Composed of many individuals

• Individuals are homogeneous
• Local interaction based on simple rules
• Self-organization
 Overview

• Ant colony optimization

• TSP
• Bees Algorithms
• Comparison between bees and ants
• Conclusions
 Ant Colony Optimization

• The way ants find their food in shortest path

is interesting.
• Ants secrete pheromones to remember their
path.
• These pheromones evaporate with time.
 Ant Colony Optimization..

• Whenever an ant finds food , it marks its

return journey with pheromones.
• Pheromones evaporate faster on longer
paths.
• Shorter paths serve as the way to food for
most of the other ants.
 Ant Colony Optimization

• The shorter path will be reinforced by the

pheromones further.
• Finally , the ants arrive at the shortest path.
 Optimizations of SI

• Swarms have the ability to solve problems

• Ant Colony Optimization (ACO) , a meta-
heuristic
• ACO can be used to solve hard problems like
TSP, Quadratic Assignment Problem(QAP)
• We discuss ACO meta-heuristic for TSP
 ACO-TSP

• Given a graph with n nodes, should give the

shortest Hamiltonian cycle
• m ants traverse the graph
• Each ant starts at a random node
 Transitions

• Ants leave pheromone trails when they

make a transition
• Trails are used in prioritizing transition
 Transitions

• Suppose ant k is at u.
• Nk(u) be the nodes not visited by k
• Tuv be the pheromone trail of edge (u,v)
• k jumps from u to a node v in Nk(u) with
probability
puv(k) = Tuv ( 1/ d(u,v))
 Iteration of AOC-TSP

• m ants are started at random nodes

• They traverse the graph prioritized on trails
and edge-weights
• An iteration ends when all the ants visit all
nodes
• After each iteration, pheromone trails are
updated.
 Updating Pheromone trails

• New trail should have two components

– Old trail left after evaporation and
– Trails added by ants traversing the edge during
the iteration
• T'uv = (1-p) Tuv + ChangeIn(Tuv)
• Solution gets better and better as the
number of iterations increase
 Performance of TSP with ACO heuristic

• Performs better than state-of-the-art TSP

algorithms for small (50-100) of nodes
• The main point to appreciate is that Swarms
give us new algorithms for optimization
Bee Algorithm
 Bees Foraging
• Recruitment Behaviour :
– Waggle Dancing
– series of alternating left and right loops
– Direction of dancing
– Duration of dancing
• Navigation Behaviour :
– Path vector represents knowledge
representation of path by inspect
– Construction of PI.
 Algorithm

• It has two steps :

– ManageBeesActivity()
– CalculateVectors()
• ManageBeesActivity: It handles agents
activities based on their internal state. That is it
decides action it has to take depending on the
knowledge it has.
• CalculateVectors : It is used for administrative
purposes and calculates PI vectors for the
agents.
 Uses of Bee Algorithm

• Training neural networks for pattern

recognition
• Forming manufacturing cells.
• Scheduling jobs for a production machine.
• Data clustering
 Comparisons
• Ants use pheromones for back tracking
route to food source.
• Bees instead use Path Integration. Bees are
able to compute their present location from
past trajectory continuously.
• So bees can return to home through direct
route instead of back tracking their original
route.
• Does path emerge faster in this algorithm.
 Results

• Experiments with different test cases on

these algorithms show that.
– Bees algorithm is more efficient when finding
and collecting food, that is it takes less number
of steps.
– Bees algorithm is more scalable it requires less
computation time to complete task.
– Bees algorithm is less adaptive than ACO.
 Applications of Swarm Intelligence

• In Movies : Graphics in movies like Lord of

the Rings trilogy, Troy.
• Unmanned underwater vehicles(UUV):
– Groups of UUVs used as security units
– Only local maps at each UUV
– Joint detection of and attack over enemy vessels
by co-ordinating within the group of UUVs
 More Applications

• Swarmcasting:
– For fast downloads in a peer-to-peer file-sharing
network
– Fragments of a file are downloaded from
different hosts in the network, parallelly.
• AntNet : a routing algorithm developed on
the framework of Ant Colony Optimization
• BeeHive : another routing algorithm
modelled on the communicative behaviour
of honey bees
 A Philosophical issue

• Individual agents in the group seem to have

no intelligence but the group as a whole
displays some intelligence
• In terms of intelligence, whole is not equal
to sum of parts?
• Where does the intelligence of the group
come from ?
• Answer : Rules followed by individual agents
 Conclusion

• SI provides heuristics to solve difficult

optimization problems.
• Has wide variety of applications.
• Basic philosophy of Swarm Intelligence :
Observe the behaviour of social animals and
try to mimic those animals on computer
systems.
• Basic theme of Natural Computing: Observe
nature, mimic nature.