Novel Neuron-like Procedure of Weak Signal Detection against the Non-Stationary Noise Background with Application to Underwater Sound

Abstract

The well-known method of detecting a useful signal in the presence of noise during underwater remote sensing, based on the matched filtering of the received signal with the test signal, provides the maximum signal-to-noise ratio (SNR) at the receiver output. To do this, a correlation-type criterion function (CF) is constructed for the received and test signals. In the case of large volumes of processed data, this method requires the use of large computing resources. The search for a data processing method with lower computational costs, as well as the effective application of artificial neural networks to array signal processing, motivates the authors to propose an alternative approach to the CF construction based on the McCulloch–Pitts neuron model. Such a neuron-like CF is based on a specific nonlinear transformation of the input and test signals and uses only logical operations, which require much less computational resources. The ratio of the output signal amplitude to the input noise level is indeed the maximum with matched filtering. Studies have shown that it is not this parameter that should be considered, but statistical characteristics, on the basis of which the thresholds for detecting a signal in the presence of noise are determined. Such characteristics include the probability density distributions of correlation and neuron-like CFs in the presence and absence of noise. In this case, the signal detection thresholds will be lower for the neuron-like CF than for the conventional correlation CF. The aim of this research is to increase the accuracy of the selection of a useful signal against the intense noise background when using a processor based on the neuron-like CF and to determine the conditions when the input SNR, at which signal detection is possible, is lower compared to the correlation CF. The comparative results of stochastic modeling show the effectiveness of using a new neuron-like approach to reduce the detection threshold when a chirp signal is received against a background of unsteady Gaussian noise. The advantages of the neuron-like method become significant when the statistical distribution of the additive noise does not change, but its variance increases or decreases. In order to confirm the presence of non-stationarity in real noises, experimental data obtained from the remote sounding of bottom sediments in the Black Sea are presented. The results obtained are considered to be applicable in a wide range of practical situations related to remote sensing in non-stationary environments, long-range sonar and sea bottom exploration.

Deep Learning on Facial Expression Detection : Artificial Neural Network Model Implementation

“…An artificial neural network (ANN) is a specific kind of mathematical model that replicates the functioning of genuine neural networks by employing a neural network architecture that is analogous to that of real neural networks. In 1943, McCulloch and Pitts were the first to suggest the concept of ANN [41], [42] . Because its fundamental concept endows both data sets with a powerful nonlinear mapping capability, ANN is ideally suited for the task of resolving mapping difficulties that exist between them [43], [44] .…”

A Nonlinear Gradient-Coiling Metamaterial for Enhanced Acoustic Signal Sensing

“…Most recently, Xiang et al proposed a robust speech enhancement method based on U-Net and generative adversarial learning to achieve speech enhancement at extremely low SNR conditions using algorithmic post-processing [17]. However, in practical engineering applications, some useful information in acoustic signals is weak, such as harmonic signals caused by structural damage [18][19][20][21]. Conventional cost-effective electrical sensor devices may not be able to sense these weak useful feature signals, and samples doped with strong background noise are difficult to train reliable models using deep learning.…”

Prediction of the Sound Absorption Coefficient of Three-Layer Aluminum Foam by Hybrid Neural Network Optimization Algorithm

“…Testing the absorption coefficient of the three-layer plus cavity open-cell aluminum foam composite structure is complicated and challenging. In this case, an accurate model for sound absorption estimation is necessary [ 15 , 16 , 17 ].…”

“…The transfer matrix method is traditionally used to obtain the absorption coefficients of multilayer acoustic materials [ 17 , 18 ]. The commonly used models are the D-B empirical model [ 19 ], the equivalent fluid model proposed by Johnson-Champoux-Allard [ 20 ], and the Miki model obtained by Miki by modifying the D-B model [ 21 ].…”