SVM Versus MAP on Accelerometer Data to Distinguish Among Locomotor Activities Executed at Different Speeds

Overview

Journal Comput Math Methods Med

Publisher Hindawi

Specialty Medical Informatics

Date 2013 Dec 31

PMID 24376469

Citations 3

Authors

Maurizio Schmid

Francesco Riganti-Fulginei

Ivan Bernabucci

Antonino Laudani

Daniele Bibbo

Rossana Muscillo

Alessandro Salvini

Silvia Conforto

Affiliations

Soon will be listed here.

Abstract

Two approaches to the classification of different locomotor activities performed at various speeds are here presented and evaluated: a maximum a posteriori (MAP) Bayes' classification scheme and a Support Vector Machine (SVM) are applied on a 2D projection of 16 features extracted from accelerometer data. The locomotor activities (level walking, stair climbing, and stair descending) were recorded by an inertial sensor placed on the shank (preferred leg), performed in a natural indoor-outdoor scenario by 10 healthy young adults (age 25-35 yrs.). From each segmented activity epoch, sixteen features were chosen in the frequency and time domain. Dimension reduction was then performed through 2D Sammon's mapping. An Artificial Neural Network (ANN) was trained to mimic Sammon's mapping on the whole dataset. In the Bayes' approach, the two features were then fed to a Bayes' classifier that incorporates an update rule, while, in the SVM scheme, the ANN was considered as the kernel function of the classifier. Bayes' approach performed slightly better than SVM on both the training set (91.4% versus 90.7%) and the testing set (84.2% versus 76.0%), favoring the proposed Bayes' scheme as more suitable than the proposed SVM in distinguishing among the different monitored activities.

Citing Articles

Modeling Energy Expenditure Estimation in Occupational Context by Actigraphy: A Multi Regression Mixed-Effects Model.

Lucena A, Guedes J, Vaz M, Silva L, Bustos D, Souza E Int J Environ Res Public Health. 2021; 18(19).

PMID: 34639718 PMC: 8508338. DOI: 10.3390/ijerph181910419.

Use of Accelerometry for Long Term Monitoring of Stroke Patients.

Lucas A, Hermiz J, Labuzetta J, Arabadzhi Y, Karanjia N, Gilja V IEEE J Transl Eng Health Med. 2019; 7:2100310.

PMID: 31475079 PMC: 6588341. DOI: 10.1109/JTEHM.2019.2897306.

The importance of prediction model validation and assessment in obesity and nutrition research.

Ivanescu A, Li P, George B, Brown A, Keith S, Raju D Int J Obes (Lond). 2015; 40(6):887-94.

PMID: 26449421 PMC: 4826636. DOI: 10.1038/ijo.2015.214.

References

Patel S, Park H, Bonato P, Chan L, Rodgers M . A review of wearable sensors and systems with application in rehabilitation. J Neuroeng Rehabil. 2012; 9:21. PMC: 3354997. DOI: 10.1186/1743-0003-9-21. View

Karantonis D, Narayanan M, Mathie M, Lovell N, Celler B . Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans Inf Technol Biomed. 2006; 10(1):156-67. DOI: 10.1109/titb.2005.856864. View

Parkka J, Ermes M, Korpipaa P, Mantyjarvi J, Peltola J, Korhonen I . Activity classification using realistic data from wearable sensors. IEEE Trans Inf Technol Biomed. 2006; 10(1):119-28. DOI: 10.1109/titb.2005.856863. View

Wu D, Warwick K, Ma Z, Gasson M, Burgess J, Pan S . Prediction of Parkinson's disease tremor onset using a radial basis function neural network based on particle swarm optimization. Int J Neural Syst. 2010; 20(2):109-16. DOI: 10.1142/S0129065710002292. View

Muscillo R, Conforto S, Schmid M, Caselli P, DAlessio T . Classification of motor activities through derivative dynamic time warping applied on accelerometer data. Annu Int Conf IEEE Eng Med Biol Soc. 2007; 2007:4930-3. DOI: 10.1109/IEMBS.2007.4353446. View

Troiano R, Berrigan D, Dodd K, Masse L, Tilert T, McDowell M . Physical activity in the United States measured by accelerometer. Med Sci Sports Exerc. 2007; 40(1):181-8. DOI: 10.1249/mss.0b013e31815a51b3. View

Meijer E, Goris A, Wouters L, Westerterp K . Physical inactivity as a determinant of the physical activity level in the elderly. Int J Obes Relat Metab Disord. 2001; 25(7):935-9. DOI: 10.1038/sj.ijo.0801644. View

Najafi B, Aminian K, Paraschiv-Ionescu A, Loew F, Bula C, Robert P . Ambulatory system for human motion analysis using a kinematic sensor: monitoring of daily physical activity in the elderly. IEEE Trans Biomed Eng. 2003; 50(6):711-23. DOI: 10.1109/TBME.2003.812189. View

Bouten C, Verboeket-Van De Venne W, Westerterp K, Verduin M, Janssen J . Daily physical activity assessment: comparison between movement registration and doubly labeled water. J Appl Physiol (1985). 1996; 81(2):1019-26. DOI: 10.1152/jappl.1996.81.2.1019. View

10.

Conforto S, DAlessio T . Real time monitoring of muscular fatigue from dynamic surface myoelectric signals using a complex covariance approach. Med Eng Phys. 1999; 21(4):225-34. DOI: 10.1016/s1350-4533(99)00049-1. View

11.

Preece S, Goulermas J, Kenney L, Howard D, Meijer K, Crompton R . Activity identification using body-mounted sensors--a review of classification techniques. Physiol Meas. 2009; 30(4):R1-33. DOI: 10.1088/0967-3334/30/4/R01. View

12.

Bouten C, Westerterp K, Verduin M, Janssen J . Assessment of energy expenditure for physical activity using a triaxial accelerometer. Med Sci Sports Exerc. 1994; 26(12):1516-23. View

13.

Staudenmayer J, Pober D, Crouter S, Bassett D, Freedson P . An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. J Appl Physiol (1985). 2009; 107(4):1300-7. PMC: 2763835. DOI: 10.1152/japplphysiol.00465.2009. View

14.

Chen K, Sun M . Improving energy expenditure estimation by using a triaxial accelerometer. J Appl Physiol (1985). 1998; 83(6):2112-22. DOI: 10.1152/jappl.1997.83.6.2112. View

15.

Jovanov E, Milenkovic A, Otto C, de Groen P . A wireless body area network of intelligent motion sensors for computer assisted physical rehabilitation. J Neuroeng Rehabil. 2005; 2(1):6. PMC: 552302. DOI: 10.1186/1743-0003-2-6. View

16.

ODonovan K, Kamnik R, OKeeffe D, Lyons G . An inertial and magnetic sensor based technique for joint angle measurement. J Biomech. 2007; 40(12):2604-11. DOI: 10.1016/j.jbiomech.2006.12.010. View

17.

Hao Y, Foster R . Wireless body sensor networks for health-monitoring applications. Physiol Meas. 2008; 29(11):R27-56. DOI: 10.1088/0967-3334/29/11/R01. View

18.

Muscillo R, Schmid M, Conforto S, DAlessio T . Early recognition of upper limb motor tasks through accelerometers: real-time implementation of a DTW-based algorithm. Comput Biol Med. 2011; 41(3):164-72. DOI: 10.1016/j.compbiomed.2011.01.007. View

19.

Muscillo R, Schmid M, Conforto S, DAlessio T . An adaptive Kalman-based Bayes estimation technique to classify locomotor activities in young and elderly adults through accelerometers. Med Eng Phys. 2010; 32(8):849-59. DOI: 10.1016/j.medengphy.2010.05.009. View

20.

Hendelman D, Miller K, Baggett C, Debold E, Freedson P . Validity of accelerometry for the assessment of moderate intensity physical activity in the field. Med Sci Sports Exerc. 2000; 32(9 Suppl):S442-9. DOI: 10.1097/00005768-200009001-00002. View