regression technique
3.Presents the neural network based prediction of software faults in integrated navigation system including the prediction of number of faults by a single layer of network only to reduce training time, and a new static reliability model suitable for prediction of quality and quality fit depending upon complexity of software, and the comparison with the traditional regression technique which shows that the prediction with a single hidden layer neural network achieves better quality than that with the traditional statistic model, and concludes that the neural network technique has better quality fit and prediction capability when it is applied to the data for a large-scale integrated navigation system and it provides a good managemant tool for software engineering.
4.A lot of data of elevation in different places of the shallow water of N antong were obtained by fish-exploring machine and GPS determining and tide cor recting.An image which reflects landforms of Nantong was obtained by selecting f rom the many NOAA images on different channels and in different phases.Based on the image,grey scales corresponding to different places were obtained.By using c la ssifying liner regression technique,liner regression equations were established between the elevation and grey scale,and the threshold values of grey scales of the different elevations were determined.According to the threshold values,the a reas of the tidal zone above different elevations of the shallow water of Nanton g were estimated.
5.A technique is proposed to improve the properties of ESN solution,which performs ridge regression in the reservoir state space instead of the previous linear regression.
6.Li (1989, 1991) and Duan and Li (1991) proposed a new technique for analyzing the multivariate date: sliced inverse regression.
7.Support vector machine is a learning technique based on the structural risk minimization principle as well as a new regression method with good generalization ability.
8.Based on the data of gas consuming quantum in zinc refining process and some new forecasting technique, a combined forecasting model of index regression and grey theory was established.
9.Support vector machine (SVM) is a novel learning technique based on the principles of structure risk minimization and very good application potentialities has been shown in classification and regression.
10.Two methods are used to calculate the organic carbon content: ①Overlay technique for acoustic slowness curves and resistivity curves; ②The regression formula of organic carbon content and log responses obtained from experiments.
