Blind Source Separation Method Based on Neural Network with Bias Term and Maximum Likelihood Estimation Criterion

Abstract

Convergence speed and steady-state source separation performance are crucial for enable engineering applications of blind source separation methods. The modification of the loss function of the blind source separation algorithm and optimization of the algorithm to improve its performance from the perspective of neural networks (NNs) is a novel concept. In this paper, a blind source separation method, combining the maximum likelihood estimation criterion and an NN with a bias term, is proposed. The method adds L2 regularization terms for weights and biases to the loss function to improve the steady-state performance and designs a novel optimization algorithm with a dual acceleration strategy to improve the convergence speed of the algorithm. The dual acceleration strategy of the proposed optimization algorithm smooths and speeds up the originally steep, slow gradient descent in the parameter space. Compared with competing algorithms, this strategy improves the convergence speed of the algorithm by four times and the steady-state performance index by 96%. In addition, to verify the source separation performance of the algorithm more comprehensively, the simulation data with prior knowledge and the measured data without prior knowledge are used to verify the separation performance. Both simulation results and validation results based on measured data indicate that the new algorithm not only has better convergence and steady-state performance than conventional algorithms, but it is also more suitable for engineering applications.

A MLE-based blind signal separation method for time–frequency overlapped signal using neural network

“…• To the best of our knowledge, we are the first to explicitly explore the applicability of using neural network to accomplish time-frequency overlapped digital signals separation based on maximum likelihood estimation. In contrast, the prior work [41] employed a fixed function to express the original signals' probability density based on signal type-super-Gaussian distribution or sub-Gaussian distribution or Gaussian distribution; however, we use kernel density estimation method to estimate the probability density of the original digital communication signal, and then, the estimation results will be regarded as a term of cost function. • We provide the cost function based on MLE-the detail will be introduced in Sect.…”

“…The MLE-based cost function of our method is composed by log-likelihood function and a bias term ( b ) [41]. However, the bias term ( b ) in our method is much different from that of reference [41].…”

“…Pang et al [40] proposed a novel BSS method for single-input multi-output (SIMO) system based on the periodicity of original signal, which can separate time-frequency overlapped multi-component signal effectively. Recently, a BSS method, combining the maximum likelihood estimation (MLE) criterion and a neural network (NN) with a bias term, is proposed in reference [41]. Based on this architecture, we employ neural network to implicate time-frequency signal communication signal separation based on MLE, the main difference to reference [41] is the application field, and the main innovation is that-for our application area time-frequency overlapped digital communication signal separation-we use the kernel density estimation method to estimate the probability density of the digital communication signal instead that in paper [41] using fixed function expression based on the type of the source signals.…”

Monitoring of Industrial Machine Using a Novel Blind Feature Extraction Approach

“…This is also proven to be a promising technique to solve the BSS problem. Liu et al [8] have proposed a NN with bias term and maximum likelihood estimation criterion technique to improve the convergence speed of source separation performance that most BSS algorithms suffer from. It is validated with actual data recorded in a real ship's engine room to separate the key component frequencies and the result proves its effectiveness in practical engineering applications.…”

Blind Source Separation Based on Quantum Slime Mould Algorithm in Impulse Noise

“…BSS is a signal processing method that extracts or restores each component of the source signal only through the received observation signals without any prior knowledge of the source signals and the transmission channels. BSS has gradually become a research hotspot and has been successfully applied in various fields, such as image and voice signal processing, biomedical signal analysis and processing, or antenna array signal processing [1][2][3]. However, the current BSS methods still have many shortcomings.…”