Chimp Optimization Algorithm
DR. AHMED FOUAD ALI
FACULTY OF COMPUTERS AND INFORMATICS
SUEZ CANAL UNIVERSITY
Outline
Chimp optimization algorithm (ChOA) (History and main idea)
Social life and inspiration.
Crow search algorithm implementation.
The main four groups (individuals).
The main paraments of the algorithm.
The exploration and the exploitation phase.
The solution updating process.
The sexual motivation process.
The structure of the ChOA.
References.
Chimp optimization algorithm (History and main
idea)
Chimp optimization algorithm (ChOA) is a
nature-inspired algorithm, proposed by
[Link] et al in 2020.
ChOA is a population-based algorithm.
ChOA simulates the chimp's life and
their behavior in the hunting process.
Social life and inspiration
The Chimps are a kind of ape, and they
are considered one of the most
intelligent animal in the world due to
their big brain relative to their body
ratio.
They are living in groups. Each group
tries to discover the environment (search
space) with different strategies.
In a chimp group, each individual has a
different method of hunting.
There are four types of individuals that
are responsible for the hunting in the
group.
Social life and inspiration (Cont.)
The drivers are responsible for pursuing the
prey without catching it.
The barriers are constructing a dam to avoid
the progression of the prey.
The chasers pursue the prey rapidly to catch
up with it.
Finally, the attackers forecast the breakout
route to force the prey to return back to the
position of the chasers.
Social life and inspiration
The other individuals in the group follow
the four leaders (drivers, barriers, chasers,
and attackers) to hunt the prey by
updating their position based on the
leader's position.
The chimps have a distinct social behavior
in the final stage of hunting which is a
sexual motivation by leaving their hunting
duties and trying to search for food
randomly.
The main four groups
.(individuals)
The population in the ChOA is different
than the other swarm intelligence
algorithms.
It contains four groups which are drivers
D , barriers B, chasers C, and attackers A.
The pray represents the optimal solution,
however, it is hard to know its location in
the search space.
During the search, the four leaders are
The main four groups
(individuals) (Cont.)
The main four groups
(individuals) (Cont.)
The main paraments of the
Thealgorithm.
ChOA has three main parameters, these
parameters are the vectors A, C, and M, and they
are calculated as follows.
The vector A is responsible for switching from the
exploration to the exploitation phases.
The vector C is a random vector in the range [0; 2]. It
is applied in the ChoA to increase the diversity of the
algorithm and help it to escape from local optima.
The main paraments of the
Thealgorithm (Cont.) the sexual motivation
vector M represents in
the ChOA and it is computed based on the chaotic
map.
The exploration and the exploitation
Thephase
driver, chaser, and barrier
solutions are responsible for the
exploration phase, while the
exploitation phase is represented by
the attacker solution.
The value of the vector A is in the
range [-1, 1] and the ChOA algorithm
is forced to switch from the
exploration to the exploitation
phases based on the value of the
vector A as shown in Equation 8.
Figure 1
Figure 1 shows the effect of the
The solution updating process
The individuals in the population
update their position based on the
values of the four leaders' individuals
(attacker, driver, chaser, and barriers).
This process can be formulated as
follows.
Where t is the current iteration, the
vectors X1, X2, X3, and X4 are
calculated in Equations 1, 2, 3, and 4.
Figure 2 shows the individuals
Figure 2
updating process in the ChOA.
The sexual motivation process
In the final stage of the In the ChOA, the value of the
hunting process, some parameter is responsible for
chimps release their duties, switching between the normal
and they try to get the food updating position and the
randomly. chaotic updating positions for
all individuals in the
population.
This situation can be
simulated in the ChOA to
accelerate the convergence This process can be formulated
and avoid trapping in local as follows.
optima.
The structure of the ChOA
The overall processes of
the ChOA are presented
in Algorithm 1 as follows.
References
M. Khishe and M. R. Mosavi. Chimp optimization algorithm.
Expert systems with applications, 149, 113338, (2020).