soft computing

• Genetic Algorithm


  Search and optimization procedures motivated by the principles of natural genetics and natural selection
• Genetic Algorithms


  • Borrow some fundamental ideas of genetics and use them artificially to construct search algorithms that are robust and require minimal problem information
  • Their working principle is very different from that of most of the classical optimization techniques
• All living creatures are descendants of older species
• Variation


  Any variation occurs due to natural selection, where some individuals have greater chance of reproduction due to some heritable differences and are said to have higher "fitness"
• Fitness


  Measures the success of an organism
• Chromosome


  Strands (twisted together) of DNA that consist of genes (smallest hereditary unit)
• Genome


  The set of all chromosomes
• In humans, genes vary in size from a few hundred DNA bases to more than 2 million bases
• Gene


  A sequence of DNA or RNA that codes for a molecule that has a function
• Evolution


  • The theory that all living things have changed in response to environmental conditions by the natural selection of randomly occurring mutations
• Requirements for evolution to take place


  • Fitness
  • Variation
  • Crossover
  • Mutation
• Fitness


  It measures the ability of an individual to survive and reproduce. The difference between the values of one organism to another is the higher number of offspring of one with the higher fitness value
• Variation


  It is essential for evolution to take place. This is the series of changes occurring in species
• Types of Variation


  • Inherited variation
  • Environmental variation
• Inherited Variation


  It is a genetically inherited character. Offsprings inherit half of their characters from each of their parents
• Environmental Variation


  Factors like climate and culture affect organisms
• Solving a cylindrical can design problem


  1. Represent the parameter values in binary strings

  2. Evaluate the solution using the objective function and constraint functions

  3. Apply genetic operators like selection, crossover, and mutation
• Phenotypic representation


  The can itself is the phenotypic representation of an artificial chromosome of 10 genes
• Each bit position or combination of two or more bit positions can have some feature of the can, but some are interesting and important whereas some are not that important
• Fitness assignment


  GAs work with strings representing design operators instead of parameters themselves. Once a string is created by a genetic operator, it is necessary to evaluate the solution under the context of the objective function and constraint functions
• Genetic Operators


  1. Selection Operator

  2. Crossover Operator

  3. Mutation Operator
• Selection Operator


  Its primary objective is to emphasize good solutions and eliminate bad solutions in a population, while keeping the population size constant
• Selection Operator Methods


  • Tournament selection
  • Proportionate selection
  • Ranking selection
  • Binary tournament selection
• Binary Tournament Selection


  Played between two solutions, the better solution is chosen and placed in a population slot. Two other solutions are picked again, and another population slot is filled up with the better solution. If done systematically, each solution can be made to participate in exactly two tournaments. The best solution in a population will win both times, thereby making two copies of it in the new population. The worst solution will lose in both tournaments and will be eliminated from the population.
• Crossover Operator


  Selection operator cannot generate new solutions, it only makes more copies of good solutions at the expense of not-so-good solutions. Creation of new solutions is performed in crossover and mutation operators. There exist a number of crossover operators like single point crossover, two-point crossover, multipoint crossover, and uniform crossover. In almost all crossover operators, two strings are picked from the mating pool at random and some portions of the strings are exchanged between the strings.
• Crossover Operators


  • Single point crossover
  • Two-point crossover