Automatic Classification of the Stand-to-Sit Phase in the TUG Test Using Machine Learning

Authors: Y. A. Adla, R. Soubra, M. Kasab, M. O. Diab, A. Chkeir

Abstract:

Over the past several years, researchers have shown a great interest in assessing the mobility of elderly people to measure their functional status. Usually, such an assessment is done by conducting tests that require the subject to walk a certain distance, turn around, and finally sit back down. Consequently, this study aims to provide an at home monitoring system to assess the patient’s status continuously. Thus, we proposed a technique to automatically detect when a subject sits down while walking at home. In this study, we utilized a Doppler radar system to capture the motion of the subjects. More than 20 features were extracted from the radar signals out of which 11 were chosen based on their Intraclass Correlation Coefficient (ICC > 0.75). Accordingly, the sequential floating forward selection wrapper was applied to further narrow down the final feature vector. Finally, five features were introduced to the Linear Discriminant Analysis classifier and an accuracy of 93.75% was achieved as well as a precision and recall of 95% and 90% respectively.

Keywords: Doppler radar system, stand-to-sit phase, TUG test, machine learning, classification

References:

[1] R. Soubra, A. Chkeir, F. Mourad-Chehade, D. Alshamaa, B. Dauriac and J. Duchene, "Doppler Radar System for an Automatic Transfer Phase Detection Using Wavelet Transform Analysis," in 3rd International Conference on Bio-engineering for Smart Technologies (BioSMART), Paris, France, 2019.
[2] Podsiadlo, D. and S. Richardson, The timed “Up & Go”: a test of basic functional mobility for frail elderly persons. Journal of the American geriatrics Society, 1991. 39(2): p. 142-148.
[3] Sprint, G., D.J. Cook, and D.L. Weeks, Toward automating clinical assessments: a survey of the timed up and go. IEEE reviews in biomedical engineering, 2015. 8: p. 64-77.
[4] Microwave Solutions Ltd. Available from: https://www.microwave-solutions.com/datasheets.
[5] C. Neipp, A. Hernández, J. Rodes, A. Márquez, T. Beléndez and A. Beléndez, "An analysis of the classical Doppler effect," European Journal of Physics, vol. 24, 2003.
[6] P. Molchanov, J. Astola, K. Egiazarian, Totsky and Alexander, "Classification of ground moving targets using bicepstrum-based features extracted from Micro-Doppler radar signatures," EURASIP Journal on Advances in Signal Processing, 2013.
[7] S. Hozo, B. Djulbegovic and H. I, "Estimating the mean and variance from the median, range, and the size of a sample," BMC Medical Research Methodology, 2005.
[8] S. Yusoff and Y. Wah, "Comparison of conventional measures of skewness and kurtosis for small sample size," in Statistics in Science, Business, and Engineering (ICSSBE), 2012.
[9] Q. Yuan, J. Shang, X. Cao, C. Zhang, X. Geng and J. Han, "Detecting Multiple Periods and Periodic Patterns in Event Time Sequences," in 2017 ACM on Conference on Information and Knowledge Management, 2017.
[10] P. Petrovic, "Root-mean-square measurement of periodic, band-limited signals," in Instrumentation and Measurement Technology Conference (I2MTC), IEEE International, 2012.
[11] Z. Ke and Z. Zhang, "Testing autocorrelation and partial autocorrelation: Asymptotic methods versus resampling techniques," British Journal of Mathematical and Statistical Psychology, vol. 7, no. 1, pp. 96-116, 2017.
[12] M. Akçay and K. Oguz, "Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers," Speech Comminucation, vol. 116, pp. 56-76, 2020.
[13] T. Freeborn, "Fatigue monitoring techniques using wearable systems," in Wearable Sensors (Second Edition) Fundamentals, Implementation and Applications, Academic Press, 2021, pp. 575-592.
[14] T. Giannakopoulos and A. Pikrakis, "Audio Features," in Introduction to Audio Analysis - A MATLAB Approach, Academic Press, 2014, pp. 59-103.
[15] G. Peeters, "A large set of audio features for sound description (similarity and classification) in the CUIDADO project," 2004.
[16] A. Shah, M. Kattel, A. Nepal and Shrestha, "Chroma Feature Extraction," in Chroma Feature Extraction using Fourier Transform, 2019.
[17] B. Zhang, J. Leitner & S. Thornton, "Audio Recognition using Mel Spectrograms and Convolution Neural Networks," 2019.
[18] L. Muda, M. Begam and I. Elamvazuthi, "Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques," JOURNAL OF COMPUTING, vol. 2, no. 3, 2010.
[19] D. Mitrović, M. Zeppelzaue and C. Breiteneder, "Features for Content-Based Audio Retrieval," in Advances in Computers, ELSEVIER, 2010, pp. 71-150.
[20] J. Yang, F.-L. Luo and A. Nehorai, "Spectral contrast enhancement: Algorithms and comparisons," Speech Communication, pp. 33-46, 2002.
[21] E. Karabulut, S. Ozel and T. İbrikçi, "A comparative study on the effect of feature selection on classification accuracy," in First World Conference on Innovation and Computer Sciences (INSODE 2011), 2012.
[22] McGraw, K.O. and S.P. Wong, Forming inferences about some intraclass correlation coefficients. Psychological methods, 1996. 1(1): p. 30.
[23] Shrout, P.E. & J.L. Fleiss, Intraclass correlations: uses in assessing rater reliability. Psycho. bulletin, 1979. 86(2): p. 420.
[24] T. Koo and M. Li, "A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research," Journal of Chiropractic Medicine, 2016.
[25] N. El Aboudi and L. Benhlima, "Review on wrapper feature selection approaches," in International Conference on Engineering & MIS (ICEMIS), 2016.
[26] P. Lang, X. Fu, M. Martorella, J. Dong, R. Qin, X. Meng and M. Xie, "A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing," 2020.