The effect of data preprocessing on the performance of artificial neural networks techniques for classification problems

• Main Author: Atomi, Walid Hasen
• Format: Thesis
• Language: English; English
• Published: 2012
• Subjects: QA Mathematics; QA71-90 Instruments and machines
• Online Access: http://eprints.uthm.edu.my/2156/1/24p%20WALID%20HASEN%20ATOMI.pdf; http://eprints.uthm.edu.my/2156/2/WALID%20HASEN%20ATOMI%20WATERMARK.pdf; http://eprints.uthm.edu.my/2156/

The artificial neural network (ANN) has recently been applied in many areas, such as medical, biology, financial, economy, engineering and so on. It is known as an excellent classifier of nonlinear input and output numerical data. Improving training efficiency of ANN based algorithm is an active area of research and numerous papers have been reviewed in the literature. The performance of Multi-layer Perceptron (MLP) trained with back-propagation artificial neural network (BP-ANN) method is highly influenced by the size of the data-sets and the data-preprocessing techniques used. This work analyzes the advantages of using pre-processing datasets using different techniques in order to improve the ANN convergence. Specifically Min-Max, Z-Score and Decimal Scaling Normalization preprocessing techniques were evaluated. The simulation results showed that the computational efficiency of ANN training process is highly enhanced when coupled with different preprocessing techniques.