Identification Method of Small Sample Ship Radiated Noise Based on CNN and DCGAN
A ship target recognition method based on convolutional neural networks(CNN)and Deep Convolutional Generative Adversarial Networks(DCGAN)was established.Based on the collected ship radiated noise data,Mel spectrogram was taken as the input feature of the network,and the DC-Gan network was used to expand the samples after spectrum transformation.The fine-tuned VGG16(visual geometry group)network was used to realize ship target classification,which improved the convergence speed of the network and reduces the training time.The results show that the proposed method can generate high-quality spectrum samples and improve the accuracy of ship radiated noise i-dentification.
万方数据
维普
