On Several Predictive Methods Based on Artificial Neural Network for Ocean Exploration Signal Processing
Wu Chen Xia Zuxun (Dept.of Computer Science and Eng., East China Shipbuilding Institute,Zhenjiang,Jiangsu, 212003)Presented at the First New Zealand International Two Stream Conference on Artificial Neural Networks and Expert Systems,Dunedin,New Zealand,November 24～26,1993
Discusses and compares the following predictive methods for ocean exploration signal processing:Linear predictive method based on data statistics,traditional BP neural network method,improved BP neural network method with additional linear links and ARMA (Autoregressive Moving Average) model with BP neural network learning algorithms.The later two methods are theoretically analysed and inferred by authors.It is found that the speeds of the later two methods are faster than that of the traditional BP methods and the ratioes of the data compression of the later two are also higher.
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.