Prediction of High Energy Shower Primary Energy and Core Location using Multi Classifier System

Cosmic showers generate secondary particles called Extensive Air Shower (EAS) while they enter the atmosphere of the earth. Several constraints are associated with the analysis of these EASs resulting in inaccuracies in measurements for which there exist a necessity to develop a readily available system based on soft-computational approaches. This is due to the fact that soft computational tools like the Artificial Neural Network (ANN)s can be trained as classifiers to adapt and learn the surrounding variations. But single classifiers fail to reach optimality of decision making for which Multiple Classifier System (MCS) are preferred. This work describes the formation of an MCS using Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN) and Probabilistic Neural Network (PNN) for EAS primary energy prediction and location determination. The results show that the set-up can be adopted for real time practical applications involving EAS from density values captured using detectors in a circular grid.