Tensor Decomposition of Gait Dynamics in Parkinson's Disease
2018 (English)In: IEEE Transactions on Biomedical Engineering, ISSN 0018-9294, E-ISSN 1558-2531, Vol. 65, no 8, p. 1820-1827Article in journal (Refereed) Published
Abstract [en]
Objective: The study of gait in Parkinson's disease is important because it can provide insights into the complex neural system and physiological behaviors of the disease, of which understanding can help improve treatment and lead to effective developments of alternative neural rehabilitation programs. This paper aims to introduce an effective computational method for multi-channel or multi-sensor data analysis of gait dynamics in Parkinson's disease.
Method: A model of tensor decomposition, which is a generalization of matrix-based analysis for higher dimensional analysis, is designed for differentiating multi-sensor time series of gait force between Parkinson's disease and healthy control cohorts.
Results: Experimental results obtained from the tensor decomposition model using a PhysioNet database show several discriminating characteristics of the two cohorts, and the achievement of 100% sensitivity and 100% specificity under various cross-validations.
Conclusion: Tensor decomposition is a useful method for the modeling and analysis of multi-sensor time series in patients with Parkinson's disease.
Significance: Tensor-decomposition factors can be potentially used as physiological markers for Parkinson's disease, and effective features for machine learning that can provide early prediction of the disease progression.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2018. Vol. 65, no 8, p. 1820-1827
Keywords [en]
Parkinson's disease, gait dynamics, time series, multi-sensors, tensor decomposition, pattern classification, Tensile stress, Foot, Parkinson's disease, Databases, Time series analysis, Feature extraction, Force
National Category
Other Medical Engineering
Identifiers
URN: urn:nbn:se:liu:diva-143304DOI: 10.1109/TBME.2017.2779884ISI: 000439382300016Scopus ID: 2-s2.0-85037623890OAI: oai:DiVA.org:liu-143304DiVA, id: diva2:1162054
2017-12-012017-12-012018-08-17Bibliographically approved