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 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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Elsevier BV
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/20.500.11937/38754 |
| _version_ | 1848755405449068544 |
|---|---|
| author | Lam, H.K. Ekong, U. Xiao, B. Ouyang, G. Liu, H. Chan, Kit Yan Ling, S. |
| author_facet | Lam, H.K. Ekong, U. Xiao, B. Ouyang, G. Liu, H. Chan, Kit Yan Ling, S. |
| author_sort | Lam, H.K. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | This paper presents a novel neural network having variable weights, which is able to improve its learning and generalization 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 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 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 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 datais contaminated by noise. |
| first_indexed | 2025-11-14T08:55:47Z |
| format | Journal Article |
| id | curtin-20.500.11937-38754 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T08:55:47Z |
| publishDate | 2015 |
| publisher | Elsevier BV |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-387542017-09-13T14:16:25Z Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications Lam, H.K. Ekong, U. Xiao, B. Ouyang, G. Liu, H. Chan, Kit Yan Ling, S. Bayesian decision Neural networks Variable-weight neural networks Material recognition KNN Epilepsy signals This paper presents a novel neural network having variable weights, which is able to improve its learning and generalization 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 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 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 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 datais contaminated by noise. 2015 Journal Article http://hdl.handle.net/20.500.11937/38754 10.1016/j.neucom.2014.09.011 Elsevier BV fulltext |
| spellingShingle | Bayesian decision Neural networks Variable-weight neural networks Material recognition KNN Epilepsy signals Lam, H.K. Ekong, U. Xiao, B. Ouyang, G. Liu, H. Chan, Kit Yan Ling, S. Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title | Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title_full | Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title_fullStr | Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title_full_unstemmed | Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title_short | Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| title_sort | variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications |
| topic | Bayesian decision Neural networks Variable-weight neural networks Material recognition KNN Epilepsy signals |
| url | http://hdl.handle.net/20.500.11937/38754 |