Single channel blind source separation method

Abstract

The invention discloses a single channel blind source separation method, and belongs to the technical field of electronic information. The single channel blind source separation method is characterized by adopting an extreme point symmetric prolongation method, carrying out processing of removing an end effect to ensemble empirical mode decomposition, transforming one-way mixed signals to intrinsic mode functions (IMFs) by using the ensemble empirical mode decomposition, restraining noise, carrying out dimension reduction processing to multi-channel IMFs by utilizing principal component analysis, removing invalid components in the IMFs, and carrying out independent component analysis to multi-channel signals after dimensionality reduction to achieve blind source separation. Implementation steps comprise carrying out linear adding to the multi-channel signals and mixing the multi-channel signals to single-channel signals to transmit, recovering source signals simply, fast and effectively under the condition of not influencing later stage pattern recognition effect, and achieving the outputting of multi-channel outputs. The single channel blind source separation method has the advantages of being capable of separating the multi-channel frequency-spectrum-overlapped signals mixed to one channel under the condition of not influencing the later stage recognition effect.

Description

technical field [0001] The invention belongs to the technical field of electronic information, and in particular relates to a single-channel blind source separation method. Background technique [0002] Blind Source Separation (BSS) began to rise in the 1980s, especially with the popularity of neural networks, it has been studied by more and more people, and it has become one of the research hotspots in the field of signal processing. It has been widely used in many fields, including image, communication, vibration engineering, biomedical engineering, array signal processing, remote sensing and telemetry, especially in sonar, communication, radar, voice, image processing, etc. It plays a vital role in the development of military and national defense science and technology. [0003] The most classic application example of blind source separation is the so-called "cocktail party problem". This problem is based on such a scenario: in a cocktail party attended by many people, e...

AI Technical Summary

Problems solved by technology

[0005] At present, there are three main types of single-channel blind source separation methods: ①Single-channel ICA analysis, when the frequency spectrum of the signal is relatively close, such as the mixed signal of mother and infant heartbeat, this method cannot be used for separation; ②For the singular value of the signal ICA processing is performed after decomposition, and ICA processing is performed after singular spectrum analysis. When the signal spectrum overlaps, the two methods have poor separation effect and aliasing; ③ ICA processing is performed after wavelet decomposition, that is, W_ICA, and empirical model After modal decomposition, carry out ICA processing, that is, EMD_ICA. These two methods can still separate the signals when the spectrum overlaps. When using wavelet decomposition, it is necessary to select wavelets for different signals, and empirical modal decomposition is based on the characteristics of the signal. The Intrinsic Model Function (IMF) is extracted, which has strong adaptability; because some of the collected signal spectrums will overlap under certain circumstances, the actual comparison of W_ICA, EMD_ICA and EEMD_ICA shows that EMD_ICA is separated The effect waveform is smooth and closer to the original signal, but the processing speed of this method is slow, and the process requires people to select signals based on experience, and the intelligence is not high. EEMD_ICA is better than EMD_ICA in suppressing noise, but there are endpoints like EMD_ICA problem of effect

In the "screening" process of the intrinsic mode function, the cubic spline function that constitutes the upper and lower envelopes will diverge at both ends of the data sequence, and the result of this divergence will continue with the "screening" process. Gradually "contaminate" the entire data sequence inwards, which seriously distorts the obtained results

Images