Learn More
A spectral feature selection scheme is proposed for multi-class automated rock recognition from real world drilling data using Gaussian Process classification. This work is part of a larger project aimed at surface mine automation. The motivation for this research is to investigate which combination of drilling data measurements is most relevant for rock(More)
Aiming at defect points in CL points gernerated by CAM, fast CL points pre-processing algorithm was proposed. The defect poinnts were divided into different types including flaw point, S shape and back traverse, the uneven length of the adjacent distance, and each case was identified and corrected by the proposed algorithm. The efficiency and effectiveness(More)
Mid- and long term hydrologic forecasting of drainage area is a difficult issue in engineering design and hydrological process simulation. Combined with wavelet neural network (WNN) to calculate and forecast the weight of model, fuzzy recognition model (FRM) is used to fit and predict mid- and long term hydrological phenomena, and the regression equation(More)
and Applied Analysis 3 (1) An objective set P = {p 1 , p 2 , . . . , p m } for comparing the importance and build a binary importance sequence matrix E according to the degree of importance of the target elements. (2) Arrange the sum ofEmatrix lines from large to small, and obtain the importance sequence of the objective set. (3) According to the matrix E,(More)
In this paper, a computationally efficient version of the widely used Takagi-Sugeno (T-S) fuzzy reasoning method is proposed, and applied to river flood forecasting. It is well known that the number of fuzzy rules of traditional fuzzy reasoning methods exponentially increases as the number of input parameters increases, often causing prohibitive(More)