Novel mixing matrix estimation approach in underdetermined blind source separation

Sun, Junhua; Li, Yuxia; Wen, Jia; Yan, Shengnan

doi:10.1016/j.neucom.2015.08.008

Cited by 53 publications

(37 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In different SNR cases, the additive white Gaussian noise is used to demonstrate the performance of the proposed method and other mainstream methods, which also ensures the availability of all methods. We selected V.G.’s Hierarchical Clustering algorithm , the DBSCAN‐Hough algorithm , Yibing's algorithm , and the modified similarity‐based robust clustering method (MSCM) to make comparison, and all parameters in the selected methods are based on their reference.…”

Section: Results and Analysismentioning

confidence: 99%

“…Considering the scope of application of the proposed method, the white Gaussian noise is added to explore. Because the minimum of 2 is given by (23), it also indicates the proposed method's tolerance to noise, which depends on the specific mixing matrix. The mixing matrix A is the same as Section 3.2.12.5; it is and the ratio of the coefficients is so the minimum difference among a 1t /a 2t is 0.3612.…”

Section: Scope Of Application Of the Proposed Methodsmentioning

confidence: 99%

“…The mixing matrix A is the same as Section 3.2.12.5; it is and the ratio of the coefficients is so the minimum difference among a 1t /a 2t is 0.3612. According to (23), for the validity of the proposed method, there should be < 0.1806. Here, is set as 0.15 after the normalization on the input hybrid signals, and other parameters are set as the same as Table 3.…”

Section: Scope Of Application Of the Proposed Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Mixing matrix estimation method for dual‐channel time‐frequency overlapped signals based on interval probability

Liu¹,

Li²,

Zheng

2019

ETRI Journal

View full text Add to dashboard Cite

For dual‐channel time‐frequency (TF) overlapped signals with low sparsity in underdetermined blind source separation (UBSS), this paper proposes an effective method based on interval probability to estimate and expand the types of mixing matrices. First, the detection of TF single‐source points (TF‐SSP) is used to improve the TF sparsity of each source. For more distinguishability, as the ratios of the coefficients from different columns of the mixing matrix are close, a local peak‐detection mechanism based on interval probability (LPIP) is proposed. LPIP utilizes uniform subintervals to optimize and classify the TF coefficient ratios of the detected TF‐SSP effectively in the case of a high level of TF overlap among sources and reduces the TF interference points and redundant signal features greatly to enhance the estimation accuracy. The simulation results show that under both noiseless and noisy cases, the proposed method performs better than the selected mainstream traditional methods, has good robustness, and has low algorithm complexity.

show abstract

Section: Results and Analysismentioning

confidence: 99%

Section: Scope Of Application Of the Proposed Methodsmentioning

confidence: 99%

Section: Scope Of Application Of the Proposed Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Mixing matrix estimation method for dual‐channel time‐frequency overlapped signals based on interval probability

Liu¹,

Li²,

Zheng

2019

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…As a branch of BSS, underdetermined BSS (UBSS) has become a critical research problem in the recent years, wherein the number of sensors is less than the number of sources . Sparse component analysis (SCA) is the main method for handling the problems facing UBSS . Most existing SCA algorithms are composed of two steps: estimating the mixing matrix and then restoring the sources.…”

Section: Introductionmentioning

confidence: 99%

“…These SSPs present a good directional clustering property that corresponds to columns of the mixing matrix; therefore, we can detect all the SSPs to complete the mixing matrix estimation by clustering algorithms. On this basis, algorithms for detecting the SSPs appear to further relax the assumption of sparsity . These algorithms make use of the directional clustering property by comparing the absolute directions of the real and imaginary parts of the TF coefficient vectors of the mixed signals to complete the estimation of the mixing matrix.…”

Section: Introductionmentioning

confidence: 99%

Novel underdetermined blind source separation algorithm based on compressed sensing and K‐SVD

Ruan

Guo

Gao

2018

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In this paper, a novel two‐stage underdetermined blind source separation (UBSS) algorithm based on eigenvalue decomposition and compressed sensing (CS) is proposed. UBSS techniques can separate the complex mixed signals into multiple single signal components, which are widely applied in the field of electronic surveillance, spectrum management, radar applications, etc. Our major contributions are summarized as follows: (1) deriving a single source points detection algorithm based on eigenvalue decomposition; (2) proposing a novel hierarchical coupling dictionary training method based on K‐means singular value decomposition; and (3) using the two‐stage method to realize the separation of radar signals under the condition of unknown prior information. In the first stage, we present a single source point detection method involving eigenvalue decomposition to estimate the unknown mixing matrix. In this method, the eigenvector corresponding to the maximum eigenvalue is estimated and clustered as a vector of mixing matrix. The second stage is the recovery of sources from the observed signals utilizing the mixing matrix estimated by the first step. In the second stage, we first build the unified model of UBSS and CS, thus the reconstruction algorithm in the CS field can be applied to UBSS. Then, a hierarchical coupling dictionary training method based on K‐means singular value decomposition is proposed. The dictionary training method obtains the prior training signals by pre‐separation and employs the hierarchical coupling idea to train the dictionary efficiently. Simulations illustrate the validity of the method and show that the proposed method outperforms the traditional methods in source separation, especially in real‐world noncooperative cases without prior knowledge.

show abstract

Compound Faults Separation Based on Intrinsic Characteristic-Scale Decomposition and Sparse Component Analysis

Hao

Wang

Song

et al. 2020

Advances in Asset Management and Condition Monitoring

View full text Add to dashboard Cite

Novel mixing matrix estimation approach in underdetermined blind source separation

Cited by 53 publications

References 22 publications

Mixing matrix estimation method for dual‐channel time‐frequency overlapped signals based on interval probability

Mixing matrix estimation method for dual‐channel time‐frequency overlapped signals based on interval probability

Novel underdetermined blind source separation algorithm based on compressed sensing and K‐SVD

Compound Faults Separation Based on Intrinsic Characteristic-Scale Decomposition and Sparse Component Analysis

Contact Info

Product

Resources

About