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

TY - JOUR

T1 - Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications

AU - Lam, H. K.

AU - Ekong, Udeme

AU - Xiao, Bo

AU - Ouyang, Gaoxiang

AU - Liu, Hongbin

AU - Chan, K. Y.

AU - Ho Ling, Sai

PY - 2015/2/3

Y1 - 2015/2/3

N2 - This paper presents a novel neural network having variable weights, which is able to improve its learning and generalisation capabilities, 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 can adapt to different characteristics of input data resulting in better performance compared with ordinary neural networks with fixed weights. The effectiveness of the VWNN is 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 neighbours 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 the input data is contaminated with noise.

AB - This paper presents a novel neural network having variable weights, which is able to improve its learning and generalisation capabilities, 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 can adapt to different characteristics of input data resulting in better performance compared with ordinary neural networks with fixed weights. The effectiveness of the VWNN is 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 neighbours 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 the input data is contaminated with noise.

KW - Bayesian decision

KW - Epilepsy signals

KW - KNN

KW - Material recognition

KW - Neural networks

KW - Variable-weight neural networks

UR - http://www.scopus.com/inward/record.url?scp=84912521727&partnerID=8YFLogxK

U2 - 10.1016/j.neucom.2014.09.011

DO - 10.1016/j.neucom.2014.09.011

M3 - Article

AN - SCOPUS:84912521727

SN - 0925-2312

VL - 149

SP - 1177

EP - 1187

JO - NEUROCOMPUTING

JF - NEUROCOMPUTING

IS - Part C

ER -