24
Internet of Things (IoT)
called an organism. Typically, an organism is a single genome represented as a vector
of length n:
c c i n
i
(
)
=
≤ ≤ ,
(2.2)
where c i is called a gene.
An abstract view of a generational genetic algorithm (GA) is given in Figure 2.1. A group
of organisms is called a population. Successive populations are called generations. A generational GA starts from initial generation G(0), and for each generation G(t), generates a new
generation G(t + 1) using genetic operators such as mutation and crossover. The mutation
operator creates new genomes by changing values of one or more genes at random. The crossover operator joins segments of two or more genomes to generate a new genome. The process
is repeated until a specified stopping criterion has been met, as described in Figure 2.1.
2.4.4 Genetic Algorithms for Rough K-Medoid Clustering
This section describes a variation of the evolutionary rough K-means approach proposed
by Lingras [7]. The proposal replaces K-means with K-medoids. A medoid is the most centrally located object in a given cluster. For k clusters, we will have K-medoids. A genetic
algorithm can be used to search for the most appropriate K-medoids. The genome will
contain k genes, each corresponding to a medoid. This reduces the size of a genome from
km by a factor of m to k. The smaller genomes will reduce the space requirements and
facilitate faster convergence. The genes in the rough K-means algorithm were continuous
real variables with no restriction on their values. The values of genes for the medoids will
be discrete and limited to the number of objects in the dataset. If we number the objects
from 1,…,n, then each gene can take an integer value in the range 1,…,n. This restriction on the values of genes will further reduce the search space allowing for even faster
convergence.
The next step in the development of a rough K-medoid algorithm is to assign an object
to lower and/or upper bound of one of the clusters. The process is similar to the rough
Initialize
population
Select individuals
for mating
Mate individuals
to produce offspring
Mutate offspring
Insert offspring
into population
Are stopping
criteria satisfied?
Finish
FIGURE 2.1
Flowchart of a generational genetic algorithm [33].
Internet of Things (IoT)
called an organism. Typically, an organism is a single genome represented as a vector
of length n:
c c i n
i
(
)
=
≤ ≤ ,
(2.2)
where c i is called a gene.
An abstract view of a generational genetic algorithm (GA) is given in Figure 2.1. A group
of organisms is called a population. Successive populations are called generations. A generational GA starts from initial generation G(0), and for each generation G(t), generates a new
generation G(t + 1) using genetic operators such as mutation and crossover. The mutation
operator creates new genomes by changing values of one or more genes at random. The crossover operator joins segments of two or more genomes to generate a new genome. The process
is repeated until a specified stopping criterion has been met, as described in Figure 2.1.
2.4.4 Genetic Algorithms for Rough K-Medoid Clustering
This section describes a variation of the evolutionary rough K-means approach proposed
by Lingras [7]. The proposal replaces K-means with K-medoids. A medoid is the most centrally located object in a given cluster. For k clusters, we will have K-medoids. A genetic
algorithm can be used to search for the most appropriate K-medoids. The genome will
contain k genes, each corresponding to a medoid. This reduces the size of a genome from
km by a factor of m to k. The smaller genomes will reduce the space requirements and
facilitate faster convergence. The genes in the rough K-means algorithm were continuous
real variables with no restriction on their values. The values of genes for the medoids will
be discrete and limited to the number of objects in the dataset. If we number the objects
from 1,…,n, then each gene can take an integer value in the range 1,…,n. This restriction on the values of genes will further reduce the search space allowing for even faster
convergence.
The next step in the development of a rough K-medoid algorithm is to assign an object
to lower and/or upper bound of one of the clusters. The process is similar to the rough
Initialize
population
Select individuals
for mating
Mate individuals
to produce offspring
Mutate offspring
Insert offspring
into population
Are stopping
criteria satisfied?
Finish
FIGURE 2.1
Flowchart of a generational genetic algorithm [33].