Genetic Algorithms (GA) and its applications

What is Genetic Algorithms (GA)?

A global search heuristics technique to find true or approximate solutions to optimization problems. GA is a particular class of evolutionary algorithms that use techniques inspired by evolutionary biology such as inheritance, mutation, selection, and crossover (recombination). The evolution usually starts from a population of randomly generated individuals and happens in generations.

In each generation, the fitness of every individual in the population is evaluated, multiple individuals are selected from the current population (based on their fitness), and modified to form a new population. The new population is used in the next iteration of the algorithm. The algorithm terminates when either a maximum number of generations has been produced, or a satisfactory fitness level has been reached for the population. See below figure for a complete flowchart of a simple GA.

GA Flowchart

The real-world problems applicable to GA are wide and numerous. Below is a list of just some of them.

GA ApplicationsThe main idea of working with GA is the Formulation of the Problem, which Albert Einstein quoted as below, and a very good documentation of basics of GA is attached here.Albert_Einstein

An application which I am keen to look into is using GA for Data Mining practical application. This article gives a good explanation on how GA can be used for Data Mining applications. Genetic Algorithm could also be applied in the prediction of Time Series data.

A patent has been filed on Automated Predictive Data Mining Model Selection using GA.

A more useful version of GA is the Multi-Objectives Genetic Algorithms. The purpose is to search for Pareto optimal solutions (i.e. non-dominated solutions) of multi-objectives optimization problems using the famous Nondominated Sorting Genetic Algorithm II (NSGA-II) from Professor Deb. A very good example is from Airbus which uses multi-objective optimization to process 9 objective functions, about dozen degrees of freedom and more than 30 constraints.

Multi-Objective Optimization can be applicable to Production Planning and Control in the manufacturing environment too.

A list of Multi-Criteria Optimization test problems using nsga2R package is shown here.

See also Invited Software Demonstration at Third International Conference on Evolutionary Multi-Ceriterion Optimization (EMO2005).


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s