Application on the Neural Network Information Fusion Technology
- DOI
- 10.2991/asei-15.2015.16How to use a DOI?
- Keywords
- Wavelet Neural Network, model design thought, feature extraction, pattern recognition.
- Abstract
Aims at the characteristics of the chemical agents signals, the pattern recognition method based on the wavelet neural network(WNN) is put forward. Firstly, the model design thought of the WNN pattern recognition technology for chemical agents are analyzed, which shows that the wavelet analysis has good time-frequency features due to its capability of localizing and differentiating the high and low frequencies of a signal and keeping the time domain features of the original signal, as a result, the wavelet transform can effectively extract the feature of the chemical agents signals; Secondly, the model and learning algorithm for the WNN are constructed, which implements that the pattern recognition method for the chemical agents combines with the advantage of the wavelet and NN, the wavelet transform method as a fore processing medium is used to extract the feature which reflects the information of the chemical agents, and the features are fed into the NN as the input patterns for training and classifying, to achieve the intelligence distinguishing; Lastly, the results of the examples and simulated test show that: this method is workable, and of the high identification accuracy, remarkable generalization capability, good stability, and high speed and high reliability.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Sen Zhu AU - Xuelian Bai AU - Hongmin Chen AU - Minghu Zhang PY - 2015/05 DA - 2015/05 TI - Application on the Neural Network Information Fusion Technology BT - Proceedings of the 2015 International conference on Applied Science and Engineering Innovation PB - Atlantis Press SP - 70 EP - 73 SN - 2352-5401 UR - https://doi.org/10.2991/asei-15.2015.16 DO - 10.2991/asei-15.2015.16 ID - Zhu2015/05 ER -