Genetic algorithms are used to find optimal solutions by the method of development-induced discovery and adaptation; Generally used in problems where finding linear / brute-force is not feasible in the context of time, such as – Traveling salesmen problem, timetable fixation, neural network load, Sudoku, tree (data-structure) etc. to set. The first requirement is an encoding scheme that is suitable for representing individuals, the second requirement is an evaluation function to represent a person’s fitness.
Genetic Algorithm in Artificial Intelligence:-
Genetic algorithm plays the same role as Artificial Intelligence. But sometimes the genetic algorithm is considered stronger than AI. This is because unlike conventional AI systems, GA will adjust on the changing input and will also be able to handle noise or fuzzy input. In addition, GE is capable of handling complex problems better.
Phases in Genetic Algorithm:-
1.Initial Population: The process begins with a set of individuals called the population. Everyone is the solution to the problem that you want to solve. A person is characterized by a set of parameters known as genes. To make chromosome, the gene is added to a wire.
2.Fitness Function:The fitness function determines how to fit a person is (the ability to compete with someone else’s person). It gives each person a fitness score The possibility that a person is selected for reproduction is based on his fitness score.
3.Selection:The idea of the election phase is to select the most suitable individuals and allow them to pass their genes to the next generation. Two pairs of parents (parents) are selected on the basis of their fitness score. People with high fitness are more likely to be selected for reproduction.
4.Crossover: Crossover is playing a vital role in genetic algorithms. For each pair of parents, a crossover point is selected from within the genes on random.
5. Mutation: In some newborns formed, some of their genes can be subjected to mutation with less random chance. This means that some bits may be flipped in the bit string.
6. Termination: The algorithm expires if the population has changed (does not produce a line which is quite different from the previous generation). Then it is said that the genetic algorithm has given a solution to our problem.
Genetic Algorithm Examples and its Applications:-
Artificial Creativity
Audio watermark detection
Automatic Design = Computer-Automatic Design
Automatic design of a mechatronic system using Bond graph and Genetic Programming (NSF) Automatic design of industrial equipment using exemplary lever pattern catalogs
Automatic design of sophisticated business systems in the financial sector Design of water Distribution system Distributed computer network topology
Electronic Circuit Design, Known As evolvable hardware.
Game theory balance resolution
Genetic Algorithm for Rule-Set Production
Economics
Plant floor layout.
Pop Music Record Manufacturer.
Power Electronics Design
Protein folding and protein/ligand docking.
Quality control Air flight scheduling planning
Optimize the MRT train schedule.
Problems with Traveling Salesmen
Plant floor layout.
Engineering Wanted – Antenna Design
Bioinformatics: Multiple Sequence Alignment
Genetic Algorithm in Soft Computing:-
We know how PSO (Particle sworm optimization) has been inspired by a group of social insects for food. In the same way, we can define biogeographic based adaptation, which is inspired by genetic development.
Genetic algorithms are based on the above principles. Whereas we had a herd in PSO, here we have a ‘population’. All particles in the PSO survive till the end. In genetic algorithms, this cannot be necessarily true, because the weaker population dies over time.
Consider 2 particles that reproduce their own 2 more particles, which are called descent.
Eventually, these 4 particles, 2 parents and 2 children, weaker 2 will die, while stronger 2 will be saved. It can be done very well in comparison to Darwin’s theory of evolution: More than many generations, those who help in reproduction and reproduction in succession, become more powerful in the population, while others who are harmful and They have undesirable traits, they are forced to fall into oblivion.
Genetic algorithms are used to find optimal solutions by the method of development-induced discovery and adaptation; Generally used in problems where finding linear / brute-force is not feasible in the context of time, such as – Traveling salesmen problem, timetable fixation, neural network load, Sudoku, tree (data-structure) etc. to set. The first requirement is an encoding scheme that is suitable for representing individuals, the second requirement is an evaluation function to represent a person’s fitness.
