计算机应用 ›› 2021, Vol. 41 ›› Issue (9): 2761-2766.DOI: 10.11772/j.issn.1001-9081.2020111816

所属专题: 前沿与综合应用

• 前沿与综合应用 • 上一篇    下一篇

基于阈值和极端随机树的实时跌倒检测方法

刘晓光1,2, 靳少康1,2, 韦子辉3, 梁铁1,2, 王洪瑞1,2, 刘秀玲1,2   

  1. 1. 河北大学 电子信息工程学院, 河北 保定 071002;
    2. 河北省数字医疗工程重点实验室(河北大学), 河北 保定 071000;
    3. 河北大学 质量技术监督学院, 河北 保定 071002
  • 收稿日期:2020-11-20 修回日期:2021-01-27 出版日期:2021-09-10 发布日期:2021-05-12
  • 通讯作者: 刘秀玲
  • 作者简介:刘晓光(1983-),男,河北保定人,副教授,博士,主要研究方向:人体生理信号处理、智能人机交互;靳少康(1996-),男,河北邢台人,硕士研究生,主要研究方向:跌倒检测;韦子辉(1977-),男,河北保定人,副教授,博士,主要研究方向:仪器创新设计、创新方法学;梁铁(1985-),男,广西恭城人,助理工程师,硕士,主要研究方向:自动化控制、信息融合;王洪瑞(1956-),男,黑龙江克山人,教授,博士,主要研究方向:并联机构的测控理论;刘秀玲(1977-),女,河北沧州人,教授,博士,主要研究方向:医学工程。
  • 基金资助:
    国家重点研发计划项目(2017YFB1401200);河北省高等学校科学技术研究重点项目(ZD2020146);保定市科技局重点研究项目(1911Q001);河北省博士后科研项目(B2019005001);河北省高等学校创新人才百强计划项目(SLRC2017022)。

Real-time fall detection method based on threshold and extremely randomized tree

LIU Xiaoguang1,2, JIN Shaokang1,2, WEI Zihui3, LIANG Tie1,2, WANG Hongrui1,2, LIU Xiuling1,2   

  1. 1. College of Electronic Information Engineering, Hebei University, Baoding Hebei 071002, China;
    2. Key Laboratory of Digital Medical Engineering of Hebei Province(Hebei University), Baoding Hebei 071000, China;
    3. School of Quality and Technical Supervision, Hebei University, Baoding Hebei 071002, China
  • Received:2020-11-20 Revised:2021-01-27 Online:2021-09-10 Published:2021-05-12
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2017YFB1401200), the Science and Technology Research Key Project of Colleges and Universities in Hebei Province (ZD2020146), the Key Research Program of Baoding City Science and Technology Bureau (1911Q001), the Postdoctoral Scientific Research Project of Hebei Province (B2019005001), the Program for Top 100 Innovative Talents in Colleges and Universities of Hebei Province (SLRC2017022).

摘要: 针对基于可穿戴设备的跌倒检测存在的实时性与准确性无法兼得的问题,提出一种阈值和极端随机树融合的实时跌倒检测方法。在该方法中,可穿戴设备只需计算阈值量,无需确保跌倒检测的准确率,从而减少了计算量;同时,上位机利用极端随机树算法确保了跌倒检测的准确率。可穿戴设备通过阈值的方法过滤了大部分日常动作,因此减少了上位机检测的动作数据量。这样一来所提方法既满足了跌倒检测的高准确率,又满足了实时性。另外,为了降低跌倒检测的假阳性率,可穿戴设备融合了姿态角度传感器和压力传感器,上位机中加入了反馈机制。当检测结果出现假阳性时,通过上位机将检测错误的样本加入非跌倒数据集中进行再训练,模型经过这样的不断学习会生成适合个人的报警模型,且这种反馈机制为降低跌倒检测的假阳性率提供了新思路。实验结果表明,在1 259个测试样本中,所提方法具有平均99.7%的准确率,最低0.08%的假阳性率。

关键词: 跌倒检测, 实时性, 可穿戴设备, 反馈机制, 个人报警模型, 阈值, 极端随机树

Abstract: Aiming at the problem that wearable device-based fall detection cannot have good accuracy real-timely, a real-time fall detection method based on the fusion of threshold and extremely randomized tree was proposed. In this method, the wearable devices only needed to calculate the threshold value and did not need to ensure the accuracy of fall detection, which reduced the amount of calculation; at the same time, the host computer used the extremely randomized tree algorithm to ensure the accuracy of fall detection. Most of the daily actions were filtered by the wearable devices through the threshold method, so as to reduce the amount of action data detected by the host computer. In this way, the proposed method had high accuracy of fall detection in real time. In addition, in order to reduce the false positive rate of fall detection, the attitude angle sensor and the pressure sensor were integrated into the wearable devices, and the feedback mechanism was added to the host computer. When the detection result was false positive, the wrong detected sample was added to the non-fall dataset for retraining through the host computer. Through this kind of continuous learning, the model would generate an alarm model suitable for the individual. And this feedback mechanism provided a new idea for reducing the false positive rate of fall detection. Experimental results show that in 1 259 test samples, the proposed method has an average accuracy of 99.7% and the lowest false positive rate of 0.08%.

Key words: fall detection, real-time, wearable device, feedback mechanism, personal alarm model, threshold, extremely randomized tree

中图分类号: