Deep‐learning‐based line enhancer for passive sonar systems

Abstract

Detection of acoustic tonals from surfaces and underwater vehicles is important for passive sonar systems. Enhancements of the tonals are usually necessary in passive sonar prior to detections. Conventionally, passive sonars employ adaptive line enhancers (ALE) in order to realise enhancements of the tonals. However, ALEs have requirements on their input signalto-noise ratios (SNR). When the SNR inputs are too low, the ALEs cannot perform well. Therefore, for the purpose of overcoming the limitations of the SNR inputs to ALEs, this study proposes to enhance tonals using unsupervised deep-learning techniques. The proposed deep-learning-based line enhancer (DLE) is based on an autoencoder neural network. The simulation results show that when the input SNR is −28 dB, the proposed DLE still achieves an SNR gain of 15 dB. However, the reference ALE fails. The experimental results also demonstrate the superiority of the proposed DLE.

Simulation‐data‐driven load disaggregation based on multi‐channel neural network for industrial and commercial users

“…Scenario 2 (Noise‐like signals interference): As is often the case, aggregate data in bulk supply systems may contain numerous noise signals in data measurement and transmission. In order to validate model robustness under strong noise interference, Gaussian white noise in a normal distribution is added to the original aggregate load data, and the strength of noise signals is measured by SNR (signal‐to‐noise ratio) [42] as Equation (9). $$$$\begin{equation}SNR = 10\lg \frac{{\sum_1^T {{P}_{{\rm{Agg}},{\rm{t}}}^2} }}{{\sum_1^T {{e}_t^2} }}.\end{equation}$$$$where SNR stands for the signal power intensity ratio of the original signal P Agg,t to that of noise signal e t , a higher SNR means lower noise proportion in test signal P Aggtest,t .…”

“…Scenario 2 (Noise-like signals interference): As is often the case, aggregate data in bulk supply systems may contain numerous noise signals in data measurement and transmission. In order to validate model robustness under strong noise interference, Gaussian white noise in a normal distribution is added to the original aggregate load data, and the strength of noise signals is measured by SNR (signal-to-noise ratio) [42] as Equation (9).…”

A multi‐step method for passive broadband source localisation using a single vector sensor

“…Li et al [7] presented a joint-source range and depth estimation method using a bottom-deployed scalar VLA. In recent years, the method of machine learning has aroused great heat [8,9]. Wang et al [10] proposed a method of the target ranging in the deep ocean by using deep transfer learning.…”

“…[7] presented a joint‐source range and depth estimation method using a bottom‐deployed scalar VLA. In recent years, the method of machine learning has aroused great heat [8, 9]. Wang et al.…”