基于人体加速度多特征融合和K近邻算法的跌倒检测

doi:10.3969/j.issn.1006-9771.2018.07.022

《中国康复理论与实践》 ›› 2018, Vol. 24 ›› Issue (7): 865-868.doi: 10.3969/j.issn.1006-9771.2018.07.022

• 康复工程与辅助技术 • 上一篇

基于人体加速度多特征融合和K近邻算法的跌倒检测

华仙¹, 席旭刚²

1.金华市人民医院,浙江金华市 321000;
2.杭州电子科技大学智能控制与机器人研究所,浙江杭州市 310018

收稿日期:2017-12-25 修回日期:2018-05-21 出版日期:2018-07-25 发布日期:2018-08-01
通讯作者: 席旭刚。E-mail: xixugang@hdu.edu.cn
作者简介:华仙(1986-),女,汉族,浙江金华市人,硕士,主治医师,主要研究方向：老年人康复训练、中西医结合心血管疾病。通讯作者：席旭刚(1975-),男,汉族,浙江金华市人,博士,副教授,主要研究方向：生物医学信号处理,康复机器人。
基金资助:
1.国家自然科学基金项目(No. 61671197); 2.浙江省基础公益研究计划项目(No. LGF18F010006)

Fall Detection Based on Multi-feature Fusion of Human Body Acceleration and K-Nearest Neighbor

HUA Xian¹, XI Xu-gang²

1. Jinhua People's Hospital, Jinhua, Zhejiang 321000, China;
2. Intelligent Control & Robotics Institute of Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China

Received:2017-12-25 Revised:2018-05-21 Published:2018-07-25 Online:2018-08-01
Contact: XI Xu-gang. E-mail: xixugang@hdu.edu.cn
Supported by:
Supported by National Natural Science Foundation of China (No. 61671197) and Zhejiang Public Basic Research Plan (No. LGF18F010006)

摘要/Abstract

摘要： 目的探索基于人体加速度的跌倒检测方法。方法 2017年9月至11月,6例健康青年志愿者完成13个跌倒动作和11个日常活动动作。通过两个加速度传感器采集人体动作信息,每个加速度传感器提取81个加速度特征参数。通过主成分分析降维,输入K近邻(KNN)算法分类器对跌倒和日常动作进行识别。结果跌倒检测敏感性100%,特异性99.76%,检测时间216 ms。结论加速度多特征融合和KNN算法可以实现跌倒的及时有效检测。

关键词: 跌倒, 检测, 人体加速度, 动作, 特征提取

Abstract: 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.

Key words: fall, detection, human body acceleration, acts, feature extraction

中图分类号:

R592

华仙, 席旭刚. 基于人体加速度多特征融合和K近邻算法的跌倒检测[J]. 《中国康复理论与实践》, 2018, 24(7): 865-868.

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.

参考文献

[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.

基于人体加速度多特征融合和K近邻算法的跌倒检测

Fall Detection Based on Multi-feature Fusion of Human Body Acceleration and K-Nearest Neighbor

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	宋以玲, 任园春, 朱飞龙, 匡冬青, 曹庆久, 林杨, 王芳. 注意缺陷多动障碍儿童粗大动作技能与执行功能发展的特点及关系[J]. 《中国康复理论与实践》, 2024, 30(1): 1-9.
[2]	毕小羽, 朱笑彤, 朱飞龙, 匡冬青, 宋以玲, 范碧瑶, 任园春. 注意缺陷多动障碍学龄儿童精细动作技能的性别差异[J]. 《中国康复理论与实践》, 2023, 29(9): 1029-1034.
[3]	张意彬, 吕杰, 喻洪流. 基于模糊逻辑算法的智能膝关节假肢步态相位识别[J]. 《中国康复理论与实践》, 2023, 29(8): 896-902.
[4]	孙志杰, 郭欣, 兰陟, 王强. 助行器智能转弯意图感知和摔倒检测[J]. 《中国康复理论与实践》, 2023, 29(7): 849-855.
[5]	张翔, 张一, 谢凡, 陈程. 增强现实镜像疗法对脑卒中患者注意力的效果[J]. 《中国康复理论与实践》, 2023, 29(6): 720-724.
[6]	朱晓敏, 刘惠林, 刘元旻, 闫志宇, 杜雪晶, 王亚囡, 张通. 脑卒中患者步行中自发性转身方向与平衡和跌倒风险间的关系[J]. 《中国康复理论与实践》, 2023, 29(5): 510-515.
[7]	蓝诗玲, 庞伟, 李鑫, 刘梦云, 战玉军. 动作观察疗法对脑性瘫痪患儿上肢功能作用的系统综述[J]. 《中国康复理论与实践》, 2023, 29(5): 558-564.
[8]	陈瑾瑾,茹菲那·阿尔肯,吴思琳,孟殿怀,周蕴弢. 吞咽障碍患者误吸干预中Chin-Down动作的研究进展[J]. 《中国康复理论与实践》, 2022, 28(7): 816-821.
[9]	刘晓燕,丁霞,董晨,李荣,孙驰. 社区与住院老年人跌倒的现状及影响因素[J]. 《中国康复理论与实践》, 2022, 28(4): 389-398.
[10]	李欣欣,刘卉,马沐佳. 太极拳与其他运动降低老年人跌倒风险的Meta分析[J]. 《中国康复理论与实践》, 2022, 28(10): 1169-1177.
[11]	康海琼,周红俊,卫波,刘根林,郑樱,张缨,郝春霞,王一吉,逯晓蕾,袁媛,蒙倩茹. 老年脊髓损伤患者的临床特点分析[J]. 《中国康复理论与实践》, 2021, 27(8): 943-950.
[12]	张峻霞,邵洋洋,王喆豪,杨芳. 跨越水平障碍物时的步态特征[J]. 《中国康复理论与实践》, 2021, 27(7): 745-750.
[13]	曹丽辉,黄富表,徐筱婧媛. 中国人简易上肢功能检查测试结果分析[J]. 《中国康复理论与实践》, 2021, 27(6): 730-736.
[14]	郭静霞,陈亮,余启超,吴渔. 运动对预防老年人跌倒效果的网状Meta分析[J]. 《中国康复理论与实践》, 2021, 27(5): 563-573.
[15]	朱玲玲, 常红, 蔡卫新, 宋海庆, 朱以诚, 绳宇. 认知-运动双重任务训练对血管性轻度认知障碍老年患者的效果[J]. 《中国康复理论与实践》, 2021, 27(1): 37-42.