基于目标均衡度量的核增量学习跌倒检测方法

doi:10.11772/j.issn.1001-9081.2017092315

计算机应用 ›› 2018, Vol. 38 ›› Issue (4): 928-934.DOI: 10.11772/j.issn.1001-9081.2017092315

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. 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

收稿日期:2017-09-25 修回日期:2017-11-20 出版日期:2018-04-10 发布日期:2018-04-09
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）。

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. 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).

摘要/Abstract

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

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

中图分类号:

TP181

忽丽莎, 王素贞, 陈益强, 胡春雨, 蒋鑫龙, 陈振宇, 高兴宇. 基于目标均衡度量的核增量学习跌倒检测方法[J]. 计算机应用, 2018, 38(4): 928-934.

HU Lisha, WANG Suzhen, CHEN Yiqiang, HU Chunyu, JIANG Xinlong, CHEN Zhenyu, GAO Xingyu. Objective equilibrium measurement based kernelized incremental learning method for fall detection[J]. Journal of Computer Applications, 2018, 38(4): 928-934.

参考文献

[1] ROBIE K. Falls in older people:risk factors and strategies for prevention[J]. The Journal of the American Medical Association, 2010, 304(17):1958-1959.
[2] 沈秉乾,武志勇, 贺前华, 等. 人体姿势状态判决的跌倒检测方法[J]. 计算机应用, 2014, 34(增刊1):223-227, 264.(SHEN B Q, WU Z Y, HE Q H, et al. Falling detection method based on human body posture judgment[J]. Journal of Computer Applications, 2014, 34(S1):223-227, 264.)
[3] 罗丹, 罗海勇. 基于随机森林的跌倒检测算法[J]. 计算机应用, 2015, 35(11):3157-3160, 3165.(LUO D, LUO H Y. Fall detection algorithm based on random forest[J]. Journal of Computer Applications, 2015, 35(11):3157-3160, 3165.)
[4] YU X. Approaches and principles of fall detection for elderly and patient[C]//HealthCom 2008:Proceedings of the 10th International Conference on E-health Networking, Applications and Services. Piscataway, NJ:IEEE, 2008:42-47.
[5] HU F, HAO Q, SUN Q, et al. Cyber physical system with virtual reality for intelligent motion recognition and training[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2017, 47(2):347-363.
[6] AUVINET E, MULTON F, SAINT-ARNAUD A, et al. Fall detection with multiple cameras:an occlusion-resistant method based on 3-D silhouette vertical distribution[J]. IEEE Transactions on Information Technology in Biomedicine, 2011, 15(2):290-300.
[7] TOREYIN B U, SOYER E B, ONARAN I, et al. Falling person detection using multi-sensor signal processing[J]. EURASIP Journal on Advances in Signal Processing, 2008, 2008:Article No. 29.
[8] ZHUANG X, HUANG J, POTAMIANOS G, et al. Acoustic fall detection using Gaussian mixture models and GMM supervectors[C]//ICASSP 2009:Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2009:69-72.
[9] GJORESKI H, KOZINA S, GAMS M, et al. RAReFall-real-time activity recognition and fall detection system[C]//Proceedings of the 2014 IEEE International Conference on Pervasive Computing and Communications Workshops. Piscataway, NJ:IEEE, 2014:145-147.
[10] RAKHECHA S, HSU K. Reliable and secure body fall detection algorithm in a wireless mesh network[C]//BodyNets 2013:Proceedings of the 8th International Conference on Body Area Networks. Brussels, Belgium:ICST, 2013:420-426.
[11] CHEN Z, CHEN Y, HU L, et al. Leveraging two-stage weighted ELM for multimodal wearables based fall detection[C]//Proceedings of ELM-2014. Berlin:Springer, 2015, 2:161-168.
[12] QU W, LIN F, WANG A, et al. Evaluation of a low-complexity fall detection algorithm on wearable sensor towards falls and fall-alike activities[C]//Proceedings of the 2015 IEEE Signal Processing in Medicine and Biology Symposium. Piscataway, NJ:IEEE, 2015:1-6.
[13] WANNENBURG J, MALEKIAN R. Physical activity recognition from smartphone accelerometer data for user context awareness sensing[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2016, 47(12):3142-3149.
[14] HU L, CHEN Y, WANG S, et al. Less annotation on personalized activity recognition using context data[C]//Proceedings of the 2016 International IEEE Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress. Piscataway, NJ:IEEE, 2016:327-332.
[15] HU L, CHEN Y, WANG S, et al. b-COELM:a fast, lightweight and accurate activity recognition model for mini-wearable devices[J]. Pervasive and Mobile Computing, 2014, 15:200-214.
[16] HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:theory and applications[J]. Neurocomputing, 2006, 70(1):489-501.
[17] HUANG G B, ZHU Q Y, SIEW C K. Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. IEEE Transactions on Neural Networks, 2006, 17(4):879-892.
[18] HUANG G B, ZHOU H, DING X, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2):513-529.
[19] SCARDAPANE S, COMMINIELLO D, SCARPINITI M, et al. Online sequential extreme learning machine with kernels[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(9):2214-2220.
[20] LIANG N Y, HUANG G B, SARATCHANDRAN P, et al. A fast and accurate online sequential learning algorithm for feedforward networks[J]. IEEE Transactions on Neural networks, 2006, 17(6):1411-1423.
[21] GU Y, LIU J, CHEN Y, et al. Constraint online sequential extreme learning machine for lifelong indoor localization system[C]//Proceedings of the 2014 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2014:732-738.
[22] GUO L, HAO J H, LIU M. An incremental extreme learning machine for online sequential learning problems[J]. Neurocomputing, 2014, 128:50-58.
[23] GAO X, HOI S, ZHANG Y, et al. Sparse online learning of image similarity[J]. ACM Transactions on Intelligent Systems and Technology, 2017, 8(5):Article No. 64.
[24] GAO X, CHEN Z, TANG S, et al. Adaptive weighted imbalance learning with application to abnormal activity recognition[J]. Neurocomputing, 2016, 173:1927-1935.
[25] JIANG X, LIU J, CHEN Y, et al. Feature adaptive online sequential extreme learning machine for lifelong indoor localization[J]. Neural Computing and Applications, 2016, 27(1):215-225.
[26] CHEN Z, CHEN Y, GAO X, et al. Unobtrusive sensing incremental social contexts using fuzzy class incremental learning[C]//Proceedings of the 2015 IEEE International Conference on Data Mining. Piscataway, NJ:IEEE, 2015:71-80.
[27] XIANG Z, CHEN Z, GAO X, et al. Solving large-scale TSP using a fast wedging insertion partitioning approach[J]. Mathematical Problems in Engineering, 2015, 2015:Article ID 854218.
[28] JIANG X, CHEN Y, LIU J, et al. Real-time and accurate indoor localization with fusion model of Wi-Fi fingerprint and motion particle filter[J]. Mathematical Problems in Engineering, 2015, 2015:Article ID 545792.
[29] CHEN Z, CHEN Y, HU L, et al. ContextSense:unobtrusive discovery of incremental social context using dynamic bluetooth data[C]//UbiComp 2014:Proceedings of the 2014 Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing:Adjunct Publication. New York:ACM, 2014:23-26.
[30] ZHANG H, YUAN J, GAO X, et al. Boosting cross-media retrieval via visual-auditory feature analysis and relevance feedback[C]//MM 2014:Proceedings of the 22nd ACM International Conference on Multimedia. New York:ACM, 2014:953-956.
[31] GAO X, HOI S, ZHANG Y, et al. SOML:sparse online metric learning with application to image retrieval[C]//AAAI 2014:Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence. Menlo Park:AAAI Press, 2014:1206-1212.
[32] CHEN Z, CHEN Y, WANG S, et al. Inferring social contextual behavior from bluetooth traces[C]//UbiComp 2013:Proceedings of the 2013 ACM Conference on Pervasive and Ubiquitous Computing Adjunct Publication. New York:ACM, 2013:267-270.
[33] CHEN Z, WANG S, SHEN Z, et al. Online sequential ELM based transfer learning for transportation mode recognition[C]//Proceedings of the 2013 IEEE Conference on Cybernetics and Intelligent Systems. Piscataway, NJ:IEEE, 2013:78-83.
[34] HU L, CHEN Y, WANG S, et al. OKRELM:online kernelized and regularized extreme learning machine for wearable-based activity recognition[J]. International Journal of Machine Learning and Cybernetics, 2016:1-14.
[35] HAGER W W. Updating the inverse of a matrix[J]. SIAM Review, 1989, 31(2):221-239.
[36] WANG W, HOU Z G, CHENG L, et al. Toward patients' motion intention recognition:dynamics modeling and identification of iLeg-an LLRR under motion constraints[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2016, 46(7):980-992.
[37] OJETOLA O, GAURA E, BRUSEY J. Data set for fall events and daily activities from inertial sensors[C]//MMSys 2015:Proceedings of the 6th ACM Multimedia Systems Conference. New York:ACM, 2015:243-248.
[38] OJETOLA O. Detection of human falls using wearable sensors[D]. Coventry, UK:Coventry University, 2014:49-66.
[39] ALTUN K, BARSHAN B. Human activity recognition using inertial/magnetic sensor units[C]//HBU 2010:Proceedings of the First International Workshop on Human Behavior Understanding, LNCS 6219. Berlin:Springer, 2010:38-51.

基于目标均衡度量的核增量学习跌倒检测方法

Objective equilibrium measurement based kernelized incremental learning method for fall detection

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[2]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[3]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[4]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[5]	刘晓光, 靳少康, 韦子辉, 梁铁, 王洪瑞, 刘秀玲. 基于阈值和极端随机树的实时跌倒检测方法[J]. 计算机应用, 2021, 41(9): 2761-2766.
[6]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[7]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[8]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[9]	刘子辰, 李小娟, 韦伟. 基于循环神经网络的专利价格自动评估[J]. 计算机应用, 2021, 41(9): 2532-2538.
[10]	丁尹, 桑楠, 李晓瑜, 吴飞舟. 基于循环神经网络的电信行业容量数据预测方法[J]. 计算机应用, 2021, 41(8): 2373-2378.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	黄程程, 董霄霄, 李钊. 基于二维Winograd算法的深流水线5×5卷积方法[J]. 计算机应用, 2021, 41(8): 2258-2264.
[13]	曾祥银, 郑伯川, 刘丹. 基于深度卷积神经网络和聚类的左右轨道线检测[J]. 计算机应用, 2021, 41(8): 2324-2329.
[14]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[15]	武维, 李泽平, 杨华蔚, 林川, 王忠德. 融合内容特征和时序信息的深度注意力视频流行度预测模型[J]. 计算机应用, 2021, 41(7): 1878-1884.