Neural Network based Classification of Material Type and its Surface Properties

Abstract

Classification of material type and its surface roughness by means of a plunger probe and optical mouse is presented in this paper. An experimental prototype was developed which involves bouncing or hopping of the plunger based impact probe freely on the plain surface of an object under test. The time and features of bouncing signal are related to the material type and its surface properties, and each material has a unique set of such properties. During the bouncing of the probe, a time varying signal is generated from optical mouse that is recorded in a data file on PC. Some dominant unique features are then extracted using Digital Signal Processing tools to optimize neural network based classifier used in the existing system. The classifier is developed on the basis of application of supervised structures of Neural Networks. For this, an optimum Multilayer Perceptron Neural Network (MLP NN) model is designed to maximize accuracy under the constraints of minimum network dimension.

Indexing terms:

• Classification
• Multi-layer perceptron neural network
• Signal processing

Additional information

Notes on contributors

Nadir N Charniya

Nadir N Charniya was born on 30th September 1966. He received ME (Electronics) degree from Victoria jubilee Technical Institute, Mumbai. He is pursuing PhD work in the field of Intelligent Sensors using Neural Networks. He has about 17 years of teaching expenence. Presently, he is working as Asst. Professor in the Department of Electronics and Telecomm Engineering at B N College of Engineering, Pusad, Maharashtra (India). He has papers published in refereed journals and conference proceedings. Project guided by him received First prize and “Maharashtra State Engineering Design Award” by Indian Society for Technical Education. He has been invited to work as a reviewer for many papers submitted to the Elsevier International Journal of Applied Soft Computing. He has delivered expert talk on Signal processing techniques and their applications at various engineering colleges. His areas of interest are Intelligent Sensors and Systems, and Soft Computing. He is member of International Neural Network Society, USA and member of IETE.

Sanjay V Dudul

Sanjay V Dudul was born on 28th of August 1964. He received his Ph.D in Electronics Engineering from SGB Amravati University, Amravati in 2003. Presently, he is working as Professor and Head of the Department of Applied Electronics, SGB Amravati University. He has many papers published in refereed journals and conference proceedings. He has been invited to work as a reviewer for several papers submitted to the Elsevier International Journal of Applied Soft Computing. He has conducted numerous comprehensive workshops on Soft Computing techniques and their applications at various engineering colleges. He has chaired International as well as National conferences. His fields of interest are engineering applications of soft computing techniques, Machine learning. System identification and Signal processing. He is member of IEEE Computational Intelligence Society, ISTE, CSI, ISA and ISCA. He is chartered engineer of IE (India). He is also Fellow of IE (India) and IETE.