15 October 2015 Automatic body flexibility classification using laser doppler flowmeter
Author Affiliations +
Body flexibility is an important indicator that can measure whether an individual is healthy or not. Traditionally, we need to prepare a protractor and the subject need to perform a pre-defined set of actions. The measurement takes place at the same time when the subject performs required action, which is clumsy and inconvenient. In this paper, we propose a statistical learning model using the technique of random forest. The proposed system can classify body flexibility based on LDF signals analyzed in the frequency domain. The reasons of using random forest are because of their efficiency (fast in classification), interpretable structures and their ability to filter out irrelevant features. In addition, using random forest can prevent the problem of over-fitting, and the output model will become more robust to noises. In our experiment, we use chirp Z-transform (CZT), to transform a LDF signal into its energy values in five frequency bands. Combining the power of the random forest algorithm and frequency band analysis methods, a maximum recognition rate of 66% is achieved. Compared to traditional flexibility measuring process, the proposed system shortens the long and tedious stages of measurement to a simple, fast and pre-defined activity set. The major contributions of our work include (1) a novel body flexibility classification scheme using non-invasive biomedical sensor; (2) a set of designed protocol which is easy to conduct and practice; (3) a high precision classification scheme which combines the power of spectrum analysis and machine learning algorithms.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
I-Chan Lien, I-Chan Lien, Yung-Hui Li, Yung-Hui Li, Jian-Guo Bau, Jian-Guo Bau, } "Automatic body flexibility classification using laser doppler flowmeter", Proc. SPIE 9672, AOPC 2015: Advanced Display Technology; and Micro/Nano Optical Imaging Technologies and Applications, 96720L (15 October 2015); doi: 10.1117/12.2199503; https://doi.org/10.1117/12.2199503

Back to Top