Application of Nonnegative Tucker Decomposition in Medical Data Analysis

Abstract:

In recent years, we have been studied about medical data analysis, especially for the rehabilitation data provided by a hospital, and extracted the recovery tendency of patients from their Functional Independence Measure (FIM) data. This time, we adopt the nonnegative Tucker decomposition (NTD) method, which is known as an extension of the nonnegative matrix factorization (NMF) to higher-dimensional data, to the medical data built up by piling each FIM data at some time points for several patients. Since the all elements of the tensor and matrices obtained by the NTD are nonnegative, it is expected that this method makes the interpretation of the characteristic vectors which are obtained from the resulting matrices easy and intelligible in comparison with our former approach, which used the multi-dimensional principal component analysis (MPCA). The experimental results show the effectiveness of proposed approach.

• Periodical: Advanced Materials Research (Volumes 971-973)
• Pages: 1874-1883
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.971-973.1874
• Online since: June 2014
• Authors: Akio Ishida*, Kei Fujii, Naoki Yamamoto, Jun Murakami, Satoko Saito, Nozomi Kano
• Keywords: Functional Independence Measure, HOSVD, Medical Data Analysis, Nonnegative Matrix Factorization, Nonnegative Tucker Decomposition

References

[1] A. Cichocki, R. Zdunek, A.H. Phan, and S. Amari: Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation, John Wiley & Sons, West Sussex (2009), pp.55-59, pp.384-392.

DOI: 10.1002/9780470747278

[2] D.D. Lee and H.S. Seung: Algorithms for non-negative matrix factorization, Adv. Neural Info. Proc. Syst. 13 (2001), pp.552-562.

[3] A.H. Phan and A. Cichocki: Extended HALS algorithm for nonnegative Tucker decomposition and its applications for multiway analysis and classification, Neurocompt. 74 (2011), p.1956-(1969).

DOI: 10.1016/j.neucom.2010.06.031

[4] H. Hetherington, R.J. Earlam and C.J.C. Kirk: The disability status of injured patients measured by the functional independence measure (FIM) and their use of rehabilitation services, Injury 26 (1995), pp.97-101.

DOI: 10.1016/0020-1383(95)92185-d

[5] N. Yamamoto, J. Murakami, C. Okuma, Y. Shigeto, S. Saito, T. Izumi, and N. Hayashida: Application of multi-dimensional principal component analysis to medical data, Int. J. Eng. Phys. Sci. 6 (2012), pp.260-266.

[6] N. Yamamoto, J. Murakami, K. Fujii, C. Okuma, S. Saito, T. Izumi, and N. Hayashida: Measurement and analysis of the functional independence measure data by using nonnegative matrix factorization method, Adv. Mater. Res. 718-720 (2013), pp.630-635.

DOI: 10.4028/www.scientific.net/amr.718-720.630

[7] Y. -D. Kim and S. Choi: Nonnegative Tucker decomposition, Proc. IEEE Conf. CVPR (2007), pp.1-8.

[8] L. D. Lathauwer, B. D. Moor, J. Vandewalle: A multilinear singular value decomposition, SIAM J. Mat. Anal. Appl. 21 (2000), pp.1253-1278.

DOI: 10.1137/s0895479896305696

[9] G.H. Golub and C. Reinsch: Singular value decomposition and least squares solutions, Numer. Math. 14(1970), pp.403-420.

DOI: 10.1007/bf02163027