The wavelet-artificial neural network is used for speaker identification, which unites the localization characteristic of wavelet transform and unique study ability on artificial neural network.

According to the characteristics of multi variable,nonlinear and large time lag of prediction of 28ds cement compressive strength,a new prediction method which combining artificial neural networks with the special decimal system coding genetic algorithms was proposed.

The quantum-chemical descriptors were used on the study of structures of benzoic acid derivatives and their pK_a values, and the algorithms of multiple linear regression(MLR) and artificial neural network(ANN) were applied for 2D-QSPR.

Artificial neural network (ANN) and multiple linear regression(MLR) were used for the simulation of C-13 NMR chemical shifts of 118 central carbon atoms in 18 pyridines and quinolines.

The input variables of artificial neural network are reduced, learning samples are extracted, stochastic events are roughly classified, a probable rule set about the relation between stochastic event classes and system states are draw out by means of rough set methods.

In this paper, a face detection algorithm for color images based on skin color and template, which is composed of skin color segmentation, template matching, and neural network verifying is presented.