Directional Human Fall Recognition Using a Pair of Accelerometer and Gyroscope Sensors

Abstract:

Human fall in the elderly population is one of the major causes of injury or bone fracture: it can be a cause of various injuries (e.g., fracture, concussion, and joint inflammation). It also could be a possible cause of death in a severe case. To detect human fall, various fall detection algorithms have been devised. Most fall detection algorithms rely on signals from a single accelerometer or gyroscope and use a threshold-based method to detect the human fall. However, these algorithms need careful adjustment of a threshold for each subject and cannot detect the direction of falls. In this study, we propose a novel fall recognition algorithm using a pair of a tri-axial accelerometer and a tri-axial gyroscope. Our fall recognition algorithm utilizes a set of augmented features including autoregressive (AR) modeling coefficients of signals, signal magnitude area (SMA), and gradients of angles from the sensors. After Linear Discriminant Analysis (LDA) of the augmented features, an Artificial Neural Nets (ANNs) is utilized to recognize four directional human falls: namely forward fall, backward fall, right-side fall, and left-side fall. Our recognition results show the mean recognition rate of 95.8%. Our proposed fall recognition technique should be useful in the investigation of fall-related injuries and possibly in the prevention of falls for the elderly.

• Periodical: Applied Mechanics and Materials (Volumes 135-136)
• Pages: 449-454
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.135-136.449
• Online since: October 2011
• Authors: Myeong Jun Lim, Jin Ho Cho, Young Sun Cho, Tae Seong Kim
• Keywords: Accelerometer, Directional Fall Recogntion, Fall Detection, Gyroscope

References

[1] J. S. Schiller, E. A. Kramarow, A. N. Dey, Fall Injury Episodes Among Non-institutionalized Older Adults: United States, 2001-2003, Department of Health and Human Services publication, Advance Data, no. 392, pp.1-16, Sept. (2007).

DOI: 10.1037/e671852007-001

[2] J. A. Stevens, K. A. Mack, L. J. Paulozzi, M. F. Ballesteros, Self-Reported Falls and Fall-Related Injuries Among Persons Aged >65 Years–United States, 2006, MMWR Weekly, vol. 57, no. 9, pp.225-229, Mar. (2008).

DOI: 10.1016/j.jsr.2008.05.002

[3] J. A. Stevens, Fatalities and Injuries from Falls Among Older Adults – United States, 1993–2003 and 2001–2005, MMWR Weekly, vol. 55, no. 45, pp.1221-1224, Nov. (2006).

DOI: 10.1001/jama.297.1.32

[4] M. Heron, B. Tejada-Vera Deaths, Leading causes for 2005, National vital statistics reports, Hyattsville, MD: National Center for Health Statistics. vol. 58, no. 8, pp.1-97, Dec. (2009).

DOI: 10.15620/cdc:104186

[5] U. Lindemann, A. Hock, M. Stuber, W. Keck, and C. Becker, Evaluation of a fall detector based on accelerometers: A pilot study, Medical and Biological Engineering and Computing, vol. 43, no. 5, p.548–551, Oct. (2005).

DOI: 10.1007/bf02351026

[6] J. Chen, K. Kwong, D. Chang, J. Luk, and R. Bajcsy, Wearable sensors for reliable fall detection, in Proceedings of the 27th Annual International Conference of the IEEE EMBS. Shanghai, China: IEEE, p.3551–3554, , Sept. (2005).

DOI: 10.1109/iembs.2005.1617246

[7] A. M. Khan, Y. K. Lee, and T. S. Kim, Accelerometer Signal-based Human Activity Recognition Using Augmented Autoregressive Model Coefficients and Artificial Neural Nets, 30th Annual International IEEE EMBS. Vancouver, Canada, pp.5172-5175 , Aug. (2008).

DOI: 10.1109/iembs.2008.4650379

[8] A.M. Khan, Y. K. Lee, S. Y. Lee, and T. S. Kim, A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer, IEEE Transaction on information technology in biomedicine, vol. 14, no. 5, pp.1166-1172, Sept. (2010).

DOI: 10.1109/titb.2010.2051955

[9] P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman, Eigenfaces vs. fisherfaces: Recognition using class specific linear projection, IEEE, vol. 19, no. 7, p.711–720, Jul. (1997).

DOI: 10.1109/34.598228

[10] D. Giansanti, V. Macellari, G. Maccioni, New neural network classifier of fall-risk based on the Mahalanobis distance and kinematic parameters assessed by a wearable device, Physiol. Meas., vol. 29, pp. N11–N19, Mar. (2008).

DOI: 10.1088/0967-3334/29/3/n01