Search

Surface material classification has attracted a lot of attention from the academic and industrial communities. The surface material classification methods are for static object material data. However, in real industrial production, data cannot be generated overnight. It is generated continuously. In this work, we propose an algorithm named Multi-Scale Local Receptive Field Based Online Sequential Extreme Learning Machine (MSLRF-OSELM) for material classification, which not only can make dynamic training of networks by using data that are generated online of material images, but also can extract highly representative features from complex texture by multi-scale local receptive field. We conduct experiments on the public texture ALOT dataset and MNIST dataset. Experimental results verify the effectiveness of our algorithm and has good generalization performance.

Multipath is the dominant error source for high-accuracy positioning systems. It is significant for eliminating the multipath error and improving the positioning accuracy to estimate multipath parameters. The existing multipath estimation algorithms are usually designed for Gaussian noise, and their performances degrade dramatically in non-Gaussian noise. To solve the problem, a multipath estimation algorithm based on kernel minimum error entropy filter (KMEEF) is proposed. In KMEEF, the minimum error entropy (MEE) criterion instead of mean square error (MSE) criterion is applied, which is not limited to the assumption of Gaussian and linearity. According to the stochastic information gradient (SIG) method, an optimal filer gain matrix is obtained by minimizing the error entropy. Furthermore, the learning rate is suggested by a convergence analysis. The simulation results show the effectivity of the proposed algorithm for multipath estimation.