Classification of marine noise signals based on DNN (Deep Neural Networks) model

Abstract

In order to solve the problem of different marine noise signals' classification, a multi-layer neuron networks model, which can be used to learn and analyze different marine noise signals, is built based on DNN (Deep Neural Networks) model in this article. Firstly, let's generate the initialized weight value randomly. Secondly, do linear operation that the input values of each layer multiply the weight values and then add the figures together. Thirdly, function value normalization is achieved by implementing nonlinear sigmoid active function, and we can get error function of actual output and desired output. Fourthly, we can get error coefficient of weight value and minimal value by gradient descent algorithm. In the last, we can get classification weight value which can distinguish different marine noise signals by summing this coefficient and weight value to keep weigh value updated. In the article, a four-layer deep neuron networks is built, of which three layers are hidden. Train the matrix data, test it and the result is that there are four errors among 100 test objects with 94%o accuracy. At the same time, the average accuracy of the 10 test results was 91.7%. It proves that this method can achieve the marine noise signals' classification.