Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications

This paper presents a novel neural network having variable weights, which is able to improve its learning and generalization capability, to deal with classification problems. The variable weight neural network (VWNN) allows its weights to be changed in operation according to the characteristic of the network inputs so that it demonstrates the ability to adapt to different characteristics of input data resulting in better performance compared with ordinary neural networks with fixed weights. The effectiveness of the VWNN are tested with the consideration of two real-life applications. The first application is on the classification of materials using the data collected by a robot finger with tactile sensors sliding along the surface of a given material. The second application considers the classification of seizure phases of epilepsy (seizure-free, pre-seizure and seizure phases) using real clinical data. Comparisons are performed with some traditional classification methods including neural network, k-nearest neighbors and naive Bayes classification techniques. It is shown that the VWNN classifier outperforms the traditional methods in terms of classification accuracy and robustness property when input data is contaminated by noise. This work was partially supported by King’s College London and partially supported by Fundação para a Ciência e Tecnologia (grant number SFHR/BD/44162/2008) and European Social Fund in the POPH framework. H.K. Lam, Udeme Ekong, Bo Xiao and Hongbin Liu are with the Department of Informatics, King’s College London, Strand, London, WC2R 2LC, United Kingdom. e-mail: {hak-keung.lam, udeme.ekong, bo.xiao, hongbin.liu}@kcl.ac.uk. Gaoxiang Ouyang is with state Key Laboratory of Cognitive Neuroscience and Learning, School of Brain and Cognitive Sciences, Beijing Normal University, No.19, XinJieKoWai St., HaiDian District, Beijing, 100875, P. R.China. email: [email protected] Kit Yan Chan is with the Department of Electrical and Computer Engineering, Curtin University, Perth, Australia. e-mail: [email protected]. Sai Ho Ling is with the Centre for Health Technologies, Faculty of Engineering and Information Technology, Sydney, NSW, Australia. e-mail: [email protected]. Manuscript received 2014. JOURNAL OF LATEX CLASS FILES 2