1State Key Laboratory of Coal Resources and Safe Mining,Beijing 100083,China;2College of Geoscience and Surveying Engineering,China University of Mining and Technology,Beijing 100083,China
In order to improve the picking accuracy of the weak signal in low signal to noise ratio，a pickup method based on STransform and deep belief neural network（DBN）was proposedThe network model training was divided into two stepsFirst，the original data processed by STransformation was subjected to unsupervised pretraining by using a restricted Boltzmann machine（RBM），and the initial values of the network model parameters were obtainedNetwork parameters adjusted by error backpropagation were used to build the final DBN modelThen，the trained network was used to pick up the dataCompared with pickup results of the STA/LTA method，the method we used has higher antinoise performance
DownLoad: