A novel Mamdani fuzzy classifier based on improved chaos immune algorithm is developed, in which bilateral Gaussian membership function parameters are set as constraint conditions and the indexes of fuzzy classification effectiveness and number of correct samples of fuzzy classification as the subgoal of fitness function. Moreover, Iris database is used for classification effectiveness simulation experiment. The results show that Mamdani fuzzy classifier based on improved chaos immune algorithm can effectively improve the prediction accuracy of classification of data sets with noises and outliers.

Orientation data of discontinuities are of paramount importance for rock engineering studies because they affect the rock slope stability and control the path of flow. Most orientation data are collected using linear sampling. However, data acquired by such linear sampling techniques are subject to bias, owing to the orientation of the sampling line. Even if a weighting factor is applied to orientation data to reduce this problem, the bias is not be significantly reduced when certain sampling orientations are involved. If the linear sampling orientation nearly parallels the discontinuity orientation, most of these parallel discontinuities are excluded from the survey results. To correct this bias ,a weighting factor is applied to orientation data first of all and then the orientation data in blindzone is corrected by added date from the different sampling line .The comprehensive pole and contour plots diagram is completed at last, which is consistent of the real situation. This method makes up for the deficiency of linear sampling technique and obtains the comprehensive orientation data in rock.