Classification of Agarwood using ANN

• Main Authors: M. S., Najib, N. A., Mohd Ali, M. N., Mat Arip, M., Abd Jalil, M. N., Taib
• Format: Article
• Language: English
• Published: 2012
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://umpir.ump.edu.my/id/eprint/6889/1/Classification_of_Agarwood_using_ANN.pdf; http://umpir.ump.edu.my/id/eprint/6889/
• Institution: Universiti Malaysia Pahang

An artifical neural network (ANN) has been modeled for the classification of Agarwood region. The target regions were from Melaka, Pagoh, Super Pagoh, Ulu Tembeling and Indonesia. The data analysis using Principal Component Analysis (PCA) was done to find significant input selection from 32 sensors of the E-nose and to recognize pattern variations from different number of Agarwood samples as inputs to ANN training. The network developed based on three layers feed forward network and the back propagation learning algorithm was used in executing the network training. Five input neurons, two hidden layer sizes and one output neurons were found to be the optimized combination for the network. The experimental results reveal that the proposed method is effective and significant to the classification of Agarwood region.