Abnormalities Detection of IMU Based on PCA in Motion Monitoring

Abstract:

Article Preview

Inertial measurement units (IMU) are used as an affordable and effective remote measurement method for health monitoring in body sensor networks (BSNs) based on tracking people’s daily motions and activities. These inertial sensors are mostly micro-electro-mechanical systems with a combination of multi-axis combinations of precision gyroscopes, accelerometers, and magnetometers to sense multiple degrees of freedom (DoF).Unfortunately in the process of motion monitoring actual sensor outputs may contain some abnormalities, which might result in the misinterpretations of activities. In this paper, we use Principal component analysis (PCA) combined with Hotelling’s T2 and SPE statistic to detect abnormal data in the process of motion monitoring with IMU to ensure the reliability and accuracy in application. The simulated results prove this method is effective and feasible.

Info:

Periodical:

Edited by:

Jing Guo

Pages:

533-538

Citation:

J. Zhou et al., "Abnormalities Detection of IMU Based on PCA in Motion Monitoring", Applied Mechanics and Materials, Vol. 224, pp. 533-538, 2012

Online since:

November 2012

Export:

Price:

$38.00

[1] B. Lo, S. Thiemjarus, R. King, and G. Yang: Body sensor network–a wireless sensor platform for pervasive healthcare monitoring, the 3rd International Conference on Pervasive Computing (2005), p.77.

[2] David Törnqvist: Statistical Fault Detection with Applications to IMU Disturbances, Licentiate's Thesis, Division of Automatic Control Department of Electrical Engineering Linköpings universitet, Linköping, Sweden (2006).

[3] Elcio Jeronimo de Oliveira: Fault Detection and Isolation in Inertial Measurement Units with Minimal Redundancy of Fiber Optic Gyros. PhD thesis, National Institute for Space Research (INPE), Brazil (2011).

[4] Shuguang Sun , Ruihua Liu: Error Calibration and FDI Technology of Gyros in Redundant IMU. International Workshop on Database Technology and Applications (2009), p.398.

DOI: https://doi.org/10.1109/dbta.2009.24

[5] Mitchell Yuwono, Bruce D Moulton, Steven W Su, Branko G Celler and Hung T Nguyen: Unsupervised machine-learning method for improving the performance of ambulatory fall-detection systems, BioMedical Engineering OnLine, Vol. 11(2012).

DOI: https://doi.org/10.1186/1475-925x-11-9

[6] W. Haerdle, L. Simar: Applied Multivariate Statistical Analysis, Second Edition, (Springer, Heidelberg 2007).

[7] Ling Yu, Jun-hua Zhu, Liu-jie Chen: Parametric Study on PCA-based Algorithm for Structural Health. Prognostics & System Health Management Conference(2010), p.1.

DOI: https://doi.org/10.1109/phm.2010.5413428

[8] Xie Tingfeng, Liu Honggang, Wu Jianjun: Fault Detection and Diagnosis for Sensors of LRE Based on PCA. Journal of Astronautics. Vol. 28 (2007), p.1668 (in Chinese).

[9] Ibaida, A., Khalil, I., Sufi, F: Cardiac abnormalities detection from compressed ECG in wireless telemonitoring using principal components analysis (PCA), Intelligent Sensors, Sensor Networks and Information Processing (2009), p.207.

DOI: https://doi.org/10.1109/issnip.2009.5416776