Article
Engineering, Electrical & Electronic
Hong Zhong, Yang Ding, Yahui Qian, Liangmo Wang, Baogang Wen
Summary: This paper proposes a novel nonlinear underdetermined blind source separation (UBSS) solution for bearing fault diagnosis. It utilizes source number estimation and improved sparse component analysis (SCA) to deal with the problem of nonlinear mixture of vibration signals. The proposed approach includes ensemble empirical mode decomposition (EEMD), correlation coefficient (CC), and adaptive threshold singular value decomposition (ATSVD) for source number estimation, and short-time Fourier transform (STFT) for transforming observed signals into the time-frequency domain. The results from simulations and experiments demonstrate that the proposed UBSS solution can accurately estimate the source number and effectively separate the signals.
Article
Computer Science, Artificial Intelligence
Yuan Xie, Kan Xie, Shengli Xie
Summary: In this paper, a novel framework is proposed to solve the underdetermined blind source separation of speech mixtures problem using a compressed sensing model. The method includes noise reduction pretreatment, blind identification for accurate mixing matrix estimation, and simultaneous updating of codewords and coefficients for dictionary selection. The approach reduces computational complexity and demonstrates superiority in experimental results.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2021)
Article
Computer Science, Information Systems
Jindong Wang, Xin Chen, Haiyang Zhao, Yanyang Li, Delong Yu
Summary: This paper proposes an approach for estimating mixing matrix in underdetermined blind source separation, which uses a two-stage clustering algorithm to enhance accuracy and achieves significant improvement in experiments.
Article
Chemistry, Analytical
Norsalina Hassan, Dzati Athiar Ramli
Summary: Blind source separation (BSS) is a method to recover source signals without knowing the mixing process or source signals. Sparse component analysis (SCA) is a commonly used solution for underdetermined BSS, which includes mixing matrix estimation and source recovery estimation. Adaptive time-frequency thresholding (ATFT) is introduced to improve the accuracy of the mixing matrix estimation, while least squares methods are used for source recovery estimation.
Article
Engineering, Electrical & Electronic
Qingyi Wang, Yiqiong Zhang, Yuduo Wang, Genping Wu
Summary: This paper addresses the problem of estimating the mixing matrix and determining the number of source signals in underdetermined blind source separation. The proposed method uses sparse subspace clustering to find low-dimensional data structures in observed data. The algorithm accurately estimates the mixing matrix and is robust and adaptable to a wide range of mixing circumstances.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Ziheng Li, Zhanxuan Hu, Feiping Nie, Rong Wang, Xuelong Li
Summary: This study proposes a method to learn a relaxed consistent spectral embedding to address the impact of different qualities and structures of multiple graphs on clustering results. The proposed method introduces an adaptively weighted system and utilizes the Relaxed MM approach for solving, improving the robustness of the algorithm and reducing computation complexity.
Review
Engineering, Electrical & Electronic
Wei Cui, Shuxu Guo, Lin Ren, Ying Yu
Summary: A new blind separation strategy is proposed to solve the problem of blind separation in non-cooperative communication under general underdetermined conditions. The strategy involves fuzzy mean clustering algorithm and singular value membership matching algorithm to achieve accurate separation and reconstruction of mixed signals.
PHYSICAL COMMUNICATION
(2021)
Article
Engineering, Electrical & Electronic
Baoze Ma, Guojun Li, Chen Yi
Summary: This brief proposes a tensor-based underdetermined blind identification method for instantaneous mixture, which explores effective statistical information of observed signals and reduces computational complexity to speed up convergence.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Computer Science, Information Systems
Mengdie Niu, Ye Zhang
Summary: In this paper, a novel autoencoder network architecture with clustering mechanism is proposed for underdetermined blind speech source separation. Experimental results demonstrate that the proposed method outperforms baseline algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
S. Akhavan, H. Soltanian-Zadeh
Summary: This study explores blind source separation (BSS) when sources are sparse signals with nonlinear combinations. It approximates the nonlinear mixtures with polynomial functions, estimates the sources and polynomial coefficients alternately, and discusses identifiability issues. Experimental results demonstrate the effectiveness of the proposed method.
DIGITAL SIGNAL PROCESSING
(2021)
Article
Chemistry, Analytical
Wensong Xie, Jun Zhou, Tao Liu
Summary: A composite fault-diagnosis blind extraction method based on SMF, DPC, and OMP is proposed to effectively separate and extract bearing composite faults, reducing the time cost.
Article
Automation & Control Systems
Minjie Wang, Genevera Allen
Summary: The study introduces a method for integrating multiple feature sets using a convex formalization which achieves strong empirical performance and effectively addresses the clustering issues in multi-view data sets. An adaptive feature selection method is proposed as well. Experimental results and real data examples show superior empirical performance of the approach in high-dimensional mixed multi-view data sets.
JOURNAL OF MACHINE LEARNING RESEARCH
(2021)
Article
Computer Science, Information Systems
Weihong Fu, Xiaowei Bai, Fan Shi, Chunhua Zhou, Yongyuan Liu
Summary: The paper introduces an original algorithm for underdetermined mixing matrix estimation, which effectively estimates the mixing matrix and source signal number, improving sparsity and accuracy. By utilizing methods such as transform matrix and element sorting, successful source point detection and signal number estimation have been achieved.
Article
Engineering, Electrical & Electronic
Yitong Guo, Bingo Wing-Kuen Ling
Summary: This paper introduces a spherical coordinate-based kernel principal component analysis method, which reduces the dimension of vectors by transforming them into spherical coordinate system, adjusting parameters, and then transforming them back into Cartesian coordinate system. The computational power required for the conversion is low, and the mean square reconstruction error is lower compared to conventional PCA methods.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Article
Computer Science, Information Systems
Mahbanou Zohrevandi, Saeed Setayeshi, Azam Rabiee, Midia Reshadi
Summary: This paper proposes a method for separating underdetermined convolutive blind speech in a multi-speaker environment based on mask prediction in the time-frequency domain. Clustering with a weighting function is used to consider parts of masks with potentially only one active source, and sparse filters are utilized in the time-domain to improve signal quality. Performance evaluation shows that the proposed method is more accurate than conventional algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)