Nature Inspired Classifier Based on Binary Neural Network and Fuzzy Ant Colony Optimization Algorithm

Abstract

Since last decade, classification methods are useful in a wide range of applications. Classification is a task to group the sample having similar properties. This capability can be introduced in computer system by designing various types of classifiers. In artificial intelligent there is a technique called neural network which has so many approaches to applying for this problem. Here, Nature Inspired Classifier Based on Binary Neural Network and fuzzy ant colony optimization (NBNNFA) is design and implemented for the application of multi class. Generally data mining model is used to classify unseen data. That's why so many efforts have taken to improve the performance. The multiclass classification performance improvement will be the main goal of this research, which is achieved by using fuzzy ant colony optimization (FACO). FACO able to control the continuous data type, and can remove information uncertainty to perform better than the traditional algorithm. FACO uses a rule-based feature selection concept to minimize the least influent attributes due to which computational time increases. So the preprocessed input binary data first given to FACO than it forms three layered network architecture i.e. Input, Hidden and Output layer. Firstly, it preprocesses data set for the sake of generating binary values. Then, preprocessed data is used for hidden layer as an input, to minimize the training time for all multiple classes the hidden layer training is done in parallel and using the concept of geometrical learning. This approach is tested with various benchmark datasets. The results corresponding to these datasets are generated by varying the learning parameters.