Development of intelligent sensor system for classification of material type using neural networks

The present work represents a novel application of the power of neural networks in implementation of the intelligent sensor system for classification of material type. It is found that the sensor system is intelligent due to its ability to classify the material type even with the variation in the sensor parameter (distance between the sensor probe and plain objects). The classifier is developed using Multi-Layer Perceptron Neural Networks (MLP NN). For this, an optimum MLP NN model is designed to maximize accuracy tender the constraints of minimum network dimension. The optimal parameters of MLP NN model based on various performance measures that also includes the area tinder Receiver Operating Characteristics (ROC) and percentage classification accuracy (PCLA) on the testing datasets even after attempting different data partitions are determined.