The detection and classification of underwater targets such as fish are one of the major tasks of the underwater acoustic signal processing and are very important for scientific, fisheries and ocean engineering and economic fields. The convolutional neural network (CNN) combined with the discrete wavelet transform (DWT) (namely CNN_DWT) not only reduces the data processing dimension of signals and the computational costs of the signal analysis, but also improves the performance of target detection and classification. This paper proposes a new CNN to classify the images that reflected the underwater acoustic signal in the database that is made up of the scalogram of underwater acoustic signals. Also, in order to attain greater accuracy and comparable efficiency to the spatial domain processing, we convert the data to the wavelet domain. Also, we propose a deep learning method for the classification of underwater acoustic signals using the new CNN combined with DWT. Next, through the simulation experiment, we evaluate our new method for underwater acoustic signal classification using the CNN combined with DWT, by comparing with classical methods. Comparing the proposed method to spatial domain CNN and classical methods, the experimental results reveal a substantial increment in classification accuracy and noise robustness. And the learning curves show that the proposed CNN_DWT does not generate the overfitting problem and its generalization ability is high. The proposed CNN_DWT improves the classification accuracy and convergence of underwater acoustic signals than the classical CNNs. The noise robustness of the proposed CNN_DWT is higher than those of classical CNNs and back-propagation neural networks (BPNNs) for the classification of underwater acoustic signals. Experimental results show that the classification performance of new CNN combined with DWT is higher than those of classical CNNs and BPNNs for the classification of underwater acoustic signals.
For the non-stationary signal denoising, an effective method for dropping ambient noise is based on discrete wavelet transform. Also, in order to minimize the loss of useful signal and get high SNR in the wavelet denoising, it is very important that the thresholding is suitable for the characteristics of signal. In this paper, we propose new thresholding method to reduce an ambient noise and to detect effectively the useful signal. First, we analyze four kinds of previous wavelet threshold functions (Hard, Soft, Garrote and Hyperbola) and propose new wavelet threshold function compromised between Garrote and Hyperbola threshold functions. Next, a threshold value is selected by value to reduce exponentially according to the wavelet decomposition level. We also analyze a continuity and monotonicity, and prove the logic of new threshold function. The results of theoretical analysis show that new threshold function solves the problems of constant error and discontinuity of previous threshold functions, and minimizes the information loss of useful signal. The results of experiment show that SNR of new thresholding method is highest and RMSE and Entropy are smallest. The results of theoretical analysis and experiment show that new thresholding method is more appropriate to wavelet denoising for dropping ambient noise than previous methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.