# What is Soft Computing : Techniques and Differences

Computation is a process of converting the input of one form to some other desired output form using certain control actions. According to the concept of computation, the input is called an antecedent and the output is called the consequent. A mapping function converts the input of one form to another form of desired output using certain control actions. The computing concept is mainly applicable to computer science engineering. There are two types of computing, hard computing, and soft computing. Hard computing is a process in which we program the computer to solve certain problems using mathematical algorithms that already exist, which provides a precise output value. One of the fundamental examples of hard computing is a numerical problem.

## What is Soft Computing?

Soft computing is an approach where we compute solutions to the existing complex problems, where output results are imprecise or fuzzy in nature, one of the most important features of soft computing is it should be adaptive so that any change in environment does not affect the present process. The following are the characteristics of soft computing.

• It does not require any mathematical modeling for solving any given problem
• It gives different solutions when we solve a problem of one input from time to time
• Uses some biologically inspired methodologies such as genetics, evolution, particles swarming, the human nervous system, etc.

There are three types of soft computing techniques which include the following.

### Artificial Neural Network

It is a connectionist modeling and parallel distributed network. There are of two types ANN (Artificial Neural Network) and BNN (Biological Neural Network). A neural network that processes a single element is known as a unit. The components of the unit are, input, weight, processing element, output. It is similar to our human neural system. The main advantage is that they solve the problems in parallel, artificial neural networks use electrical signals to communicate. But the main disadvantage is that they are not fault-tolerant that is if anyone of artificial neurons gets damaged it will not function anymore.

An example of a handwritten character, where a character is written in Hindi by many people, they may write the same character but in a different form. As shown below, whichever way they write we can understand the character, because one already knows how the character looks like. This concept can be compared to our neural network system.

### Fuzzy Logic

The fuzzy logic algorithm is used to solve the models which are based on logical reasoning like imprecise and vague. It was introduced by Latzi A. Zadeh in 1965. Fuzzy logic provides stipulated truth value with the closed interval [0,1]. Where 0 = false value, 1= true value.

An example of a robot that wants to move from one place to another within a short time where there are many obstacles on the way. Now the question arises is that how the robot can calculate its movement to reach the destination point, without colliding to any obstacle. These types of problems have uncertainty problem which can be solved using fuzzy logic.

### Genetic Algorithm in Soft Computing

The genetic algorithm was introduced by Prof. John Holland in 1965. It is used to solve problems based on principles of natural selection, that come under evolutionary algorithm. They are usually used for optimization problems like maximization and minimization of objective functions, which are of two types of an ant colony and swarm particle. It follows biological processes like genetics and evolution.

### Functions of the Genetic Algorithm

The genetic algorithm can solve the problems which cannot be solved in real-time also known as the NP-Hard problem. The complicated problems which cannot be solved mathematically can be easily solved by applying the genetic algorithm. It is a heuristic search or randomized search method, which provides an initial set of solutions and generate a solution to the problem efficiently and effectively.

A simple way of understanding this algorithm is by considering the following example of a person who wants to invest some money in the bank, we know there are different banks available with different schemes and policies. Its individual interest how much amount to be invested in the bank, so that he can get maximum profit. There are certain criteria for the person that is, how he can invest and how can he get profited by investing in the bank. These criteria can be overcome by the “Evolutional Computing” algorithm like genetic computing.

### Difference Between Hard Computing and Soft Computing

The difference between hard computing and soft computing are as follows

 Hard Computing Soft Computing The analytical model required by hard computing must be precisely represented It is based on uncertainty, partial truth tolerant of imprecision and approximation. Computation time is more Computation time is less It depends on binary logic, numerical systems, crisp software. Based on approximation and dispositional. Sequential computation Parallel computation Gives exact output Gives appropriate output Examples: Traditional methods of computing using our personal computer. Example: Neural networks like Adaline, Madaline, ART networks, etc.

The benefits of soft computing are

• The simple mathematical calculation is performed
• Good efficiency
• Applicable in real-time
• Based on human reasoning.

The disadvantages of soft computing are

• It gives an approximate output value
• If a small error occurs the entire system stops working, to overcome its entire system must be corrected from the beginning, which is time taking process.

### Applications

The following are the applications of soft computing

• Controls motors like induction motor, DC servo motor automatically
• Power plants can be controlled using an intelligent control system
• In image processing, the given input can be of any form, either image or video which be manipulated using soft computing to get an exact duplicate of the original image or video.
• In biomedical applications where it is closely related to biology and medicine, soft computing techniques can be used to solve biomedical problems like diagnosis, monitoring, treatment, and therapy.
• Smart instrumentation is trendy nowadays, where intelligent devices automatically communicate with other devices using a certain set of communication protocols to perform certain tasks, but the problem here is there is no proper standard protocol to communicate. This can be overcome by using soft computing techniques, where the smart devices are communicated over multiple protocols, with high privacy and robustness.

Computing is a technique used to convert particular input using control action to the desired output. There are two types of computing techniques hard computing and soft computing. Here in our article, we are mainly focusing on soft computing, its techniques like fuzzy logic, artificial neural network, genetic algorithm, comparison between hard computing and soft computing, soft computing techniques, applications, and advantages. Here is the question “How are soft computing is applicable in the medical field?”