Abstract
Smart healthcare systems are generating a large scale of heterogenous high-dimensional data with complex relationships. It is hard for current methods to analyze such high-dimensional healthcare data. Specifically, the traditional data reduction methods can not keep the correlation among different modalities of data objects, while the latest methods based on tensor singular value decomposition are not effective for data reduction, although they can keep the correlation. This article presents a tensor train-tensor singular value decomposition (TT-TSVD) algorithm for data reduction. Particularly, the presented algorithm balances the correlation-preservation ability of modalities and data reduction ability by combining the advantages of the train structure of the tensor train decomposition and the association relationship between the tensor singular value decomposition retention mode. Extensive experiments are conducted on the convolutional neural network and the results clearly show that the presented algorithm performs effectively for data reduction with a low-loss classification accuracy; what is more, classification accuracy on medical image dataset has been improved a little.
- [1] . 2008. Fast multilinear singular value decomposition for structured tensors. SIAM J. Matrix Anal. Appl. 30, 3 (2008), 1008–1021. Google Scholar
Digital Library
- [2] . 2017. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 22 (2017), 2199–2210.Google Scholar
Cross Ref
- [3] . 2013. Solving multilinear systems via tensor inversion. SIAM J. Matrix Anal. Appl. 34, 2 (2013), 542–570.Google Scholar
Digital Library
- [4] . 1970. Analysis of individual differences in multidimensional scaling via an n-way generalization of “Eckart-Young” decomposition. Psychometrika 35, 3 (1970), 283–319.Google Scholar
Cross Ref
- [5] . 1997. Signal Processing based on Multilinear Algebra. Katholieke Universiteit Leuven Leuven.Google Scholar
- [6] . 2000. A multilinear singular value decomposition. SIAM J. Matrix Anal. Applic. 21, 4 (2000), 1253–1278. Google Scholar
Digital Library
- [7] . 2014. Exploiting linear structure within convolutional networks for efficient evaluation. arXiv preprint arXiv:1404.0736. Google Scholar
Digital Library
- [8] . 2016. Ultimate tensorization: Compressing convolutional and FC layers alike. arXiv preprint arXiv:1611.03214 (2016).Google Scholar
- [9] . 2021. A fuzzy detection system for rumors through explainable adaptive learning. IEEE Trans. Fuzzy Syst. (2021).
DOI: 10.1109/TFUZZ.2021.3052109Google ScholarDigital Library
- [10] . 1994. PARAFAC: Parallel factor analysis. Comput. Statist. Data Anal. 18, 1 (1994), 39–72. Google Scholar
Digital Library
- [11] . 1927. The expression of a tensor or a polyadic as a sum of products. J. Math. Phys. 6, 1–4 (1927), 164–189.Google Scholar
Cross Ref
- [12] . 2016. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250.Google Scholar
- [13] . 2009. Tensor decompositions and applications. SIAM Rev. 51, 3 (2009), 455–500. Google Scholar
Digital Library
- [14] . 2005. Higher-order web link analysis using multilinear algebra. In 5th IEEE International Conference on Data Mining (ICDM’05). 242–249. Google Scholar
Digital Library
- [15] Alex Krizhevsky, Geoffrey Hinton, et al. 2009. Learning Multiple Layers of Features from Tiny Images. Master’s thesis, Department of Computer Science, University of Toronto.Google Scholar
- [16] . 2021. An efficient ciphertext-policy weighted attribute-based encryption for the internet of health things. IEEE J. Biomed. Health Inform.
DOI: 10.1109/JBHI.2021.3075995Google Scholar - [17] . 2016. Towards better analysis of deep convolutional neural networks. IEEE Trans. Vis. Comput. Graph. 23, 1 (2016), 91–100. Google Scholar
Digital Library
- [18] . 2011. Tensor-train decomposition. SIAM J. Sci. Comput. 33, 5 (2011), 2295–2317. Google Scholar
Digital Library
- [19] . 2000. Parallel factor analysis in sensor array processing. IEEE Trans. Sig. Process. 48, 8 (2000), 2377–2388. Google Scholar
Digital Library
- [20] . 2005. CubeSVD: A novel approach to personalized web search. In 14th International Conference on World Wide Web. 382–390. Google Scholar
Digital Library
- [21] . 2017. Big data for cybersecurity: Vulnerability disclosure trends and dependencies. IEEE Trans. Big Data 5, 3 (2017), 317–329.Google Scholar
Cross Ref
- [22] . 1966. Some mathematical notes on three-mode factor analysis. Psychometrika 31, 3 (1966), 279–311.Google Scholar
Cross Ref
- [23] . 2020. IMCFN: Image-based malware classification using fine-tuned convolutional neural network architecture. Comput. Netw. 171 (2020), 107138.Google Scholar
Digital Library
- [24] . 2002. Multilinear analysis of image ensembles: Tensorfaces. In European Conference on Computer Vision. 447–460. Google Scholar
Digital Library
- [25] . 2018. Rotation equivariant CNNs for digital pathology. In International Conference on Medical Image Computing and Computer-assisted Intervention. Springer, 210–218.Google Scholar
Cross Ref
- [26] . 2018. Use of data visualisation for zero-day malware detection. Secur. Commun. Netw. (2018).Google Scholar
Digital Library
- [27] . 2020. HO-OTSVD: A novel tensor decomposition and its incremental decomposition for cyber-physical-social networks (CPSN). IEEE Trans. Netw. Sci. Eng. 7, 2 (2020), 713–725.Google Scholar
Cross Ref
- [28] . 2018. Challenges to the Israeli healthcare system: Attracting medical students to primary care and to the periphery. Israel J. Health Polic. Res. 7, 1 (2018), 28.Google Scholar
Cross Ref
- [29] . 2013. Data mining with big data. IEEE Trans. Knowl. Data Eng. 26, 1 (2013), 97–107. Google Scholar
Digital Library
- [30] . 2021. 3D reconstruction for motion blurred images using deep learning-based intelligent systems. Comput. Mater. Continua 66, 2 (2021), 2087–2104.Google Scholar
Cross Ref
Index Terms
TT-TSVD: A Multi-modal Tensor Train Decomposition with Its Application in Convolutional Neural Networks for Smart Healthcare
Recommendations
Tensor Completion via Fully-Connected Tensor Network Decomposition with Regularized Factors
AbstractThe recently proposed fully-connected tensor network (FCTN) decomposition has a powerful ability to capture the low-rankness of tensors and has achieved great success in tensor completion. However, the FCTN decomposition-based method is highly ...
Convolutional Neural Network Compression via Tensor-Train Decomposition on Permuted Weight Tensor with Automatic Rank Determination
Computational Science – ICCS 2022AbstractConvolutional neural networks (CNNs) are among the most commonly investigated models in computer vision. Deep CNNs yield high computational performance, but their common issue is a large size. For solving this problem, it is necessary to find ...
Multi-domain feature analysis method of MI-EEG signal based on Sparse Regularity Tensor-Train decomposition
AbstractTensor analysis can comprehensively retain multidomain characteristics, which has been employed in EEG studies. However, existing EEG tensor has large dimension, making it difficult to extract features. Traditional Tucker decomposition ...
Highlights- Motor-imagery classification based on EEG signals.
- MI-EEG signal analysis based ...






Comments