• Advanced Institute of Engineering and Technology (AVITECH)

  • Research Projects

    Tensor Decomposition Meets Blind Source Separation

    Tensor decomposition plays a crucial role in Blind Source Separation (BSS) by providing a powerful mathematical framework to untangle mixed signals. In the context of BSS, tensors are multi-dimensional arrays that represent the observed mixtures of source signals. Tensor decomposition methods are employed to factorize these high-dimensional tensors into a set of component matrices or core tensors that represent the underlying sources. This enables the extraction of individual source signals even when the mixing process is unknown or complex. Tensor decomposition techniques enhance the ability to model intricate relationships between sources, offering a versatile approach for separating sources in scenarios where traditional methods may face limitations. The application of tensor decomposition in BSS is particularly valuable in fields like audio processing, image analysis, and neuroimaging, where disentangling mixed signals is essential for gaining meaningful insights from complex data.

    In this project, we investigate the problem of blind source separation (BSS) through the lens of tensor decomposition (TD). Two fundamental connections between TD and BSS are established, forming the basis for two novel tensor-based BSS methods, namely TenSOFO and TCBSS. The former is designed for a joint individual differences in scaling (INDSCAL) decomposition, addressing instantaneous (linear) BSS tasks; while the latter efficiently performs a constrained block term decomposition (BTD), aligning with the design of convolutive BSS. Leveraging the benefits of the alternating direction method of multipliers and the strengths of tensor representations, both TenSOFO and TCBSS prove to be effective in BSS. Experimental results demonstrate the robust performance of TCBSS in addressing both BTD and convolutive BSS tasks, particularly when dealing with electromyography (EMG) signal decomposition.


    Collaborators: Prof. Karim Abed-Meraim, Prof. Philippe Ravier, Prof. Olivier Buttelli from University of Orleans, France and Prof. Ales Holobar from University of Maribor, Slovenia.



    Selected Publications: 

    [1]  L.T. Thanh, K. Abed-Meraim, P. Ravier, O. Buttelli, A. Holobar. Tensorial Convolutive Blind Source Separation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.

    [2] L.T. Thanh, K. Abed-Meraim, P. Ravier, O. Buttelli, A. Holobar. Joint INDSCAL Decomposition Meets Blind Source Separation. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024.


    Other information

    Contact: Dr. Le Trung Thanh,  AVITECH


    EEG signal processing from the computer vision perspective

    In this work, we study the processing of EEG signals in the image domain, i.e., visualizing the signal in the binary image and applying computer vision techniques for signal smoothing and classification. Some research questions are being investigated: 1. How well can we smooth the signal in the image domain? Here, we plot the interested […]

    Vision-based crack detection with crack propagation modeling

    In this work, the propagation of cracks on some materials, such as concrete, is analyzed, the best-fit model of which is employed for vision-based crack detection. Some research questions are being investigated: 1. What is the correlation between simulated crack propagation and real-world crack? Here, we measure the fitting errors between best-fit regression models of […]

    Machine learning based beacon placement optimization for indoor robots localization

    Indoor localization systems usually consist of transceiver with fixed positions, which are called beacons. These beacons act as landmarks for localizing objects that need to be positioned. One can easily see that the positions of beacons have a great impact on the performance of the localization system. The problem of beacon placement optimization is to […]