Objective To develop a kind of algorithm for fall detection based on human acceleration. Methods From September to November, 2017, six healthy postgraduates participating in the experiment completed 13 acts of falls and eleven of activities of daily life. The information of activities was collected through two acceleration sensors, 81 acceleration features were extracted from each sensor, and were reduced dimension through principal component analysis. K-nearest neighbor was used to detect the falls and activities of daily living. Results The sensitivity of fall detection was 100%, the specificity was 99.76%, and the detection time was 216 ms. Conclusion The algorithm of multi-feature fusion of human body acceleration and K-nearest neighbor is accurate and timely.
HUA Xian
,
XI Xu-gang
. Fall Detection Based on Multi-feature Fusion of Human Body Acceleration and K-Nearest Neighbor[J]. Chinese Journal of Rehabilitation Theory and Practice, 2018
, 24(7)
: 865
-868
.
DOI: 10.3969/j.issn.1006-9771.2018.07.022
[1] 朱图陵. 辅助技术在老年人康复中的应用[J]. 中国康复理论与实践, 2017, 23(8): 971-975.
[2] Khan SS, Hoey J.Review of fall detection techniques: a data availability perspective[J]. Med Eng Phys, 2017, 39: 12-22.
[3] Rodríguez-Martín D, Pérez-López C, Samà A, et al.A wearable inertial measurement unit for long-term monitoring in the dependency care area[J]. Sensors, 2013, 13(10): 14079-14104.
[4] 徐欣,温子星. 人体动态稳定性控制理论在老年人防跌倒中的应用[J]. 中国康复理论与实践, 2017, 23(11): 1254-1257.
[5] Leone A, Rescio G, Caroppo A, et al.An EMG-based system for pre-impact fall detection[C]. 2015 IEEE Sensors. IEEE, 2015: 1-4.
[6] Mubashir M, Shao L, Seed L.A survey on fall detection: principles and approaches[J]. Neurocomputing, 2013, 100: 144-152.
[7] Hegde R, Sudarshan B, Kumar SP, et al.Technical advances in fall detection system—a review[J]. Int J Comput Sci Mob Comput, 2013, 2: 152-160.
[8] Gonzálezvillanueva L, Cagnoni S, Ascari L.Design of a wearable sensing system for human motion monitoring in physical rehabilitation[J]. Sensors, 2013, 13(6): 7735-7755.
[9] Cheng WC, Jhan DM.Triaxial accelerometer-based fall detection method using a self-constructing cascade-AdaBoost-SVM classifier[J]. IEEE J Biomed Health Inform, 2013, 17(2): 411-419.
[10] Abbate S, Avvenuti M, Corsini P, et al.Monitoring of human movements for fall detection and activities recognition in elderly care using wireless sensor network: a survey[M]// Merret GV, Tan YK. Wireless Sensor Networks: Application-Centric Design. Rijeka: InTech, 2010.
[11] Soran B, Farhadi A, Shapiro L.Action recognition in the presence of one egocentric and multiple static cameras[C]. Asian Conference on Computer Vision, Springer, Cham, 2014: 178-193.
[12] Sevrin L, Noury N, Abouchi N, et al.Characterization of a multi-user indoor positioning system based on low cost depth vision (Kinect) for monitoring human activity in a smart home[C]. Engineering in Medicine and Biology Society (EMBC), 2015 37th Annual International Conference of the IEEE, IEEE, 2015: 5003-5007.
[13] Staranowicz A, Brown GR, Mariottini GL.Evaluating the accuracy of a mobile Kinect-based gait-monitoring system for fall prediction[C]. Proceedings of the 6th international conference on PErvasive technologies related to assistive environments, ACM, 2013: 57.
[14] Vuegen L, van den Broeck B, Karsmakers P, et al. Automatic monitoring of activities of daily living based on real-life acoustic sensor data: a preliminary study[C]. Proceedings of the Fourth Workshop on Speech and Language Processing for Assistive Technologies, 2013: 113-118.
[15] Siantikos G, Giannakopoulos T, Konstantopoulos S.Monitoring activities of daily living using audio analysis and a RaspberryPI: a use case on bathroom activity monitoring[C]. International Conference on Information and Communication Technologies for Ageing Well and e-Health, Springer, Cham, 2016: 20-32.
[16] Fortino G, Gravina R.Fall-MobileGuard: a smart real-time fall detection system[C]. Proceedings of the 10th EAI International Conference on Body Area Networks. ICST, 2015: 44-50.
[17] Yi YJ, Yu YS.Emergency monitoring system based on a newly-developed fall detection algorithm[J]. J Inf Commun Converg Eng, 2013, 11(3): 199-206.
[18] Kangas M, Vikman I, Wiklander J, et al.Sensitivity and specificity of fall detection in people aged 40 years and over[J]. Gait Posture, 2009, 29(4): 571-574.
[19] Ahmed M, Mehmood N, Nadeem A, et al.Fall detection system for the elderly based on the classification of shimmer sensor prototype data[J]. Healthc Inform Res, 2017, 23(3): 147-158.
[20] Aziz O, Klenk J, Schwickert L, et al.Validation of accuracy of SVM-based fall detection system using real-world fall and non-fall datasets[J]. PLoS One, 2017, 12(7): e0180318.
[21] 刘鹏,卢潭城,吕愿愿,等. 基于MEMS三轴加速度传感器的摔倒检测[J]. 传感技术学报, 2014, 27(4): 570-574.
[22] Yu S, Chen H, Brown RA.Hidden Markov model-based fall detection with motion sensor orientation calibration: a case for real-life home monitoring[J]. IEEE J Biomed Health, 2017. [Epub ahead of print]. doi: 10.1109/JBHI.2017.2782079.
[23] Chen KH, Yang JJ, Jaw FS.Accelerometer-based fall detection using feature extraction and support vector machine algorithms[J]. Instrum Sci Technol, 2016, 44(4): 333-342.
[24] Rescio G, Leone A, Siciliano P.Support vector machine for tri-axial accelerometer-based fall detector[C]. Advances in Sensors and Interfaces (IWASI), 2013 5th IEEE International Workshop on IEEE, 2013: 25-30.
[25] Nii M, Iwamoto T, Ishibashi Y, et al.Improvement of fuzzy neural network based human activity estimation system[C]. Systems, Man, and Cybernetics (SMC), 2015 IEEE International Conference on IEEE, 2015: 2310-2315.
