Tucker Tensor Decomposition Research Articles

Multidimensional compressed sensing and their applications

Compressed sensing (CS) comprises a set of relatively new techniques that exploit the underlying structure of data sets allowing their reconstruction from compressed versions or incomplete information. CS reconstruction algorithms are essentially nonlinear, demanding heavy computation overhead and large storage memory, especially in the case of multidimensional signals. Excellent review papers discussing CS state‐of‐the‐art theory and algorithms already exist in the literature, which mostly consider data sets in vector forms. In this paper, we give an overview of existing techniques with special focus on the treatment of multidimensional signals (tensors). We discuss recent trends that exploit the natural multidimensional structure of signals (tensors) achieving simple and efficient CS algorithms. The Kronecker structure of dictionaries is emphasized and its equivalence to the Tucker tensor decomposition is exploited allowing us to use tensor tools and models for CS. Several examples based on real world multidimensional signals are presented, illustrating common problems in signal processing such as the recovery of signals from compressed measurements for magnetic resonance imaging (MRI) signals or for hyper‐spectral imaging, and the tensor completion problem (multidimensional inpainting). WIREs Data Mining Knowl Discov 2013, 3:355–380. doi: 10.1002/widm.1108This article is categorized under: Algorithmic Development > Spatial and Temporal Data Mining Algorithmic Development > Structure Discovery Application Areas > Science and Technology

Research on exponential regularization approach for nonnegative Tucker3 decomposition

Methods of nonnegative tensor factorization (NTF), such as NTF1, NTF2, etc., are extension of nonnegative matrix factorization (NMF) for multi-way data analysis. As an existing NTF method, nonnegative Tucker3 decomposition (NTD) is researched for three-way decomposition in this paper. Firstly, an approach utilizing matrix exponentials built on Tikhonov-type regularization to enforce sparseness is proposed to extract image features instead of exclusively using Tucker tensor decomposition. Meanwhile, updating algorithms, derived from updating rules of NMF, are allowed to efficiently implement updating of mode matrices and core tensors alternatively for accuracy. Then, experimental cases of alternating least squares (ALS) and conjugate nonnegative constraints, called nonnegative alternating least squares (NALS), are studied to remedy data overfitting in computing procedures. Lastly, the proposed method exhibits more advantageous results than other algorithms of Tucker3 for feature extraction, thanks to computer simulations performed in the context of data analysis.