Journal of Computer Applications ›› 2018, Vol. 38 ›› Issue (4): 928-934.DOI: 10.11772/j.issn.1001-9081.2017092315

Previous Articles     Next Articles

Objective equilibrium measurement based kernelized incremental learning method for fall detection

HU Lisha1, WANG Suzhen1, CHEN Yiqiang2, HU Chunyu2, JIANG Xinlong2, CHEN Zhenyu3, GAO Xingyu4   

  1. 1. Institute of Information Technology, Hebei University of Economics and Business, Shijiazhuang Hebei 050061, China;
    2. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China;
    3. China Electric Power Research Institute, Beijing 100192, China;
    4. Institute of Microelectronics, Chinese Academy of Sciences, Beijing 100029, China
  • Received:2017-09-25 Revised:2017-11-20 Online:2018-04-10 Published:2018-04-09
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61702491), the Research Foundation of Hebei University of Economics and Business (2016KYZ05), the Science and Technology Program of State Grid Corporation of China (5442DZ170019), the Science and Technology Innovation Program of China Electric Power Research Institute (5242001600H5).

基于目标均衡度量的核增量学习跌倒检测方法

忽丽莎1, 王素贞1, 陈益强2, 胡春雨2, 蒋鑫龙2, 陈振宇3, 高兴宇4   

  1. 1. 河北经贸大学 信息技术学院, 石家庄 050061;
    2. 中国科学院计算技术研究所, 北京 100190;
    3. 中国电力科学研究院, 北京 100192;
    4. 中国科学院微电子研究所, 北京 100029
  • 通讯作者: 陈益强
  • 作者简介:忽丽莎(1986-),女,河北石家庄人,讲师,博士,主要研究方向:机器学习、可穿戴计算;王素贞(1964-),女,河北石家庄人,教授,博士,主要研究方向:移动云计算、大数据处理;陈益强(1973-),男,湖南湘潭人,研究员,博士,主要研究方向:普适计算、人机交互;胡春雨(1990-),女,山东威海人,博士研究生,主要研究方向:机器学习、可穿戴计算;蒋鑫龙(1988-),男,甘肃兰州人,博士研究生,主要研究方向:机器学习、可穿戴计算;陈振宇(1985-),男,湖南长沙人,高级工程师,博士,主要研究方向:机器学习、可穿戴计算;高兴宇(1985-),男,湖南长沙人,副研究员,博士,主要研究方向:机器学习、可穿戴计算、多媒体。
  • 基金资助:
    国家自然科学基金资助项目(61702491);河北经贸大学校内科研基金资助项目(2016KYZ05);国家电网公司总部科技项目(5442DZ170019);中国电科院科技创新基金资助项目(5242001600H5)。

Abstract: In view of the problem that conventional incremental learning models may go through a way of performance degradation during the update stage, a kernelized incremental learning method was proposed based on objective equilibrium measurement. By setting the optimization term of "empirical risk minimization", an optimization objective function fulfilling the equilibrium measurement with respect to training data size was designed. The optimal solution was given under the condition of incremental learning training, and a lightweight incremental learning classification model was finally constructed based on the effective selection strategy of new data. Experimental results on a publicly available fall detection dataset show that, when the recognition accuracy of representative methods falls below 60%, the proposed method can still maintain the recognition accuracy more than 95%, while the computational consumption of the model update is only 3 milliseconds. In conclusion, the proposed method contributes to achieving a stable growth of recognition performance as well as efficiently decreasing the time consumptions, which can effectively realize wearable devices based intellectual applications in the cloud service platform.

Key words: incremental learning, neural network, kernel function, fall detection, wearable device

摘要: 针对增量学习模型在更新阶段的识别效果不稳定的问题,提出一种基于目标均衡度量的核增量学习方法。通过设置经验风险均值最小化的优化目标项,设计了均衡度量训练数据个数的优化目标函数,以及在增量学习训练条件下的最优求解方案;再结合基于重要性分析的新增数据有效选择策略,最终构建出了一种轻量型的增量学习分类模型。在跌倒检测公开数据集上的实验结果显示:当已有代表性方法的识别精度下滑至60%以下时,所提方法仍能保持95%以上的精度,同时模型更新的计算消耗仅为3 ms。实验结果表明,所提算法在显著提高增量学习模型更新阶段识别能力稳定性的同时,大大降低了时间消耗,可有效实现云服务平台中关于可穿戴设备终端的智能应用。

关键词: 增量学习, 神经网络, 核函数, 跌倒检测, 可穿戴设备

CLC Number: