基于可穿戴传感器的人体活动识别研究综述

doi:10.11772/j.issn.1001-9081.2017112715

计算机应用 ›› 2018, Vol. 38 ›› Issue (5): 1223-1229.DOI: 10.11772/j.issn.1001-9081.2017112715

• 人工智能 • 下一篇

基于可穿戴传感器的人体活动识别研究综述

郑增威¹, 杜俊杰^1,2, 霍梅梅¹, 吴剑钟¹

1. 浙江大学城市学院杭州市物联网技术与应用重点实验室, 杭州 310015;
2. 浙江大学计算机科学与技术学院, 杭州 310015

收稿日期:2017-11-16 修回日期:2017-12-25 出版日期:2018-05-10 发布日期:2018-05-24
通讯作者: 霍梅梅
作者简介:郑增威(1969-),男,浙江温州人,教授,博士,CCF会员,主要研究方向:无线传感器网络、普适计算、物联网;杜俊杰(1993-),男,浙江金华人,硕士研究生,主要研究方向:普适计算、数据挖掘、机器学习;霍梅梅(1977-),女,山东德州人,副教授,硕士,主要研究方向:无线传感器网络、嵌入式系统;吴剑钟(1967-),男,浙江湖州人,教授,硕士,主要研究方向:物联网、智能终端、移动互联网。
基金资助:
杭州市科技发展计划项目（20150533B15）；浙江省自然科学基金资助项目（LY17F020008）。

Review of human activity recognition based on wearable sensors

ZHENG Zengwei¹, DU Junjie^1,2, HUO Meimei¹, WU Jianzhong¹

1. Hangzhou Key Laboratory for IoT Technology & Application, City College of Zhejiang University, Hangzhou Zhejiang 310015, China;
2. College of Computer Science and Technology, Zhejiang University, Hangzhou Zhejiang 310015, China

Received:2017-11-16 Revised:2017-12-25 Online:2018-05-10 Published:2018-05-24
Contact: 霍梅梅
Supported by:
This work is partially supported by the Hangzhou Science and Technology Development Plan (20150533B15), the Natural Science Foundation of Zhejiang Provincial Province (LY17F020008).

摘要/Abstract

摘要： 人体活动识别（HAR）在医疗、安全、娱乐等方面有着广泛的应用。随着传感器器件的发展，各类能准确采集人体行为活动数据的传感器在手环、手表、手机等可穿戴设备上得到了广泛使用，相比基于视频图像的行为识别方法，基于传感器的行为识别具有成本低、灵活、可移植性好的特点，因此，基于可穿戴传感器的人体活动识别研究成为行为识别中的研究热点。介绍了人体活动识别研究中原始数据采集、特征提取、特征选择以及分类方法，对识别流程中每一部分常用的技术以及研究现状进行了综述总结，最后分析人体活动识别研究当前存在的主要问题并展望了今后可能的研究方向。

关键词: 人体活动识别, 可穿戴传感器, 特征工程, 数据处理, 机器学习

Abstract: Human Activity Recognition (HAR) has a wide range of applications in medical care, safety, and entertainment. With the development of sensor industry, sensors that can accurately collect human activity data have been widely used on wearable equipments such as wristband, watch and mobile phones. Compared with the behavior recognition method based on video images, sensor-based behavior recognition has the characteristics of low cost, flexibility and portability. Therefore, human activity recognition research based on wearable sensors has become an important research field. Data collection, feature extraction, feature selection and classification methods of HAR were described in detail, and the techniques commonly used in each process were analyzed. Finally, the main problems of HAR and the development directions were pointed out.

Key words: Human Activity Recognition (HAR), wearable sensor, feature engineering, data processing, machine learning

中图分类号:

TP391.4

郑增威, 杜俊杰, 霍梅梅, 吴剑钟. 基于可穿戴传感器的人体活动识别研究综述[J]. 计算机应用, 2018, 38(5): 1223-1229.

ZHENG Zengwei, DU Junjie, HUO Meimei, WU Jianzhong. Review of human activity recognition based on wearable sensors[J]. Journal of Computer Applications, 2018, 38(5): 1223-1229.

参考文献

[1] FOERSTER F, SMEJA M, FAHRENBERG J. Detection of posture and motion by accelerometry:a validation study in ambulatory monitoring[J]. Computers in Human Behavior, 1999, 15(5):571-583.
[2] MANTYJARVI J, HIMBERG J, SEPPANEN T. Recognizing human motion with multiple acceleration sensors[C]//Proceedings of the 2001 IEEE International Conference on Systems, Man, and Cybernetics. Piscataway, NJ:IEEE, 2001:747-752.
[3] OLGUIN D O, PENTLAND A S. Human activity recognition:Accuracy across common locations for wearable sensors[C]//Proceedings of 200610th IEEE International Symposium on Wearable Computers. Piscataway, NJ:IEEE, 2006:11-14.
[4] WANG L, GU T, TAO X, et al. Sensor-based human activity recognition in a multi-user scenario[C]//Proceedings of the European Conference on Ambient Intelligence. Berlin:Springer-Verlag, 2009:78-87.
[5] KWAPISZ J R, WEISS G M, MOORE S A. Activity recognition using cell phone accelerometers[J]. ACM SIGKDD Explorations Newsletter, 2011, 12(2):74-82.
[6] ALTUN K, BARSHAN B. Human activity recognition using inertial/magnetic sensor units[C]//Proceedings of the 1st International Conference on Human Behavior Understanding. Berlin:Springer, 2010:38-51.
[7] ANGUITA D, GHIO A, ONETO L, et al. A public domain dataset for human activity recognition using smartphones[EB/OL].[2017-06-20]. http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2013-84.pdf.
[8] MEDRANO C, IGUAL R, PLAZA I, et al. Detecting falls as novelties in acceleration patterns acquired with smartphones[J]. PLoS One, 2014, 9(4):e94811.
[9] SHOAIB M, BOSCH S, INCEL O D, et al. Fusion of smartphone motion sensors for physical activity recognition[J]. Sensors, 2014, 14(6):10146-10176.
[10] VAVOULAS G, PEDIADITIS M, CHATZAKI C, et al. The MobiFall dataset:fall detection and classification with a smartphone[J]. International Journal of Monitoring & Surveillance Technologies Research, 2014, 2(1):44-56.
[11] REYES-ORTIZ J L, ONETO L, PARRA X, et al. Transition-aware human activity recognition using smartphones[J]. Neurocomputing, 2016, 171(C):754-767.
[12] VAVOULAS G, CHATZAKI C, MALLIOTAKIS T, et al. The mobiact dataset:recognition of activities of daily living using smartphones[EB/OL].[2017-06-20].https://www.researchgate.net/publication/https://www.researchgate.net/profile/Manolis_Tsiknakis/publication/302973506_The_MobiAct_Dataset_Recognition_of_Activities_of_Daily_Living_using_Smartphones/links/59c73ef1aca272c71bc3f374/The-MobiAct-Dataset-Recognition-of-Activities-of-Daily-Living-using-Smartphones.pdf?ev=auth_pub.
[13] MICUCCI D, MOBILIO M, NAPOLETANO P. UniMiB SHAR:a new dataset for human activity recognition using acceleration data from smartphones[EB/OL].[2017-06-20]. http://www.mdpi.com/2076-3417/7/10/1101/pdf.
[14] KEFER K, HOLZMANN C, FINDLING R D. Comparing the placement of two arm-worn devices for recognizing dynamic hand gestures[C]//Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media. New York:ACM, 2016:99-104.
[15] CLELAND I, KIKHIA B, NUGENT C, et al. Optimal placement of accelerometers for the detection of everyday activities[J]. Sensors, 2013, 13(7):9183-9200.
[16] PANNURAT N, THIEMJARUS S, NANTAJEEWARAWAT E, et al. Analysis of optimal sensor positions for activity classification and application on a different data collection scenario[J]. Sensors, 2017, 17(4):774.
[17] MULLER P, TENBOHLEN S, MAIER R, et al. Characteristics of series and parallel low current arc faults in the time and frequency domain[C]//Proceedings of the 56th IEEE Holm Conference on Electrical Contacts. Piscataway, NJ:IEEE, 2010:1-7.
[18] 于亚萍, 孙立宁, 张峰峰,等. 基于小波变换的多特征融合sEMG模式识别[J]. 传感技术学报, 2016, 29(4):512-518.(YU Y P, SUN L N, ZHANG F F, et al. sEMG pattern recognition based on multi feature fusion of wavelet transform[J]. Journal of Transduction Technology,2016,29(4):512-518.)
[19] PREECE S J, GOULERMAS J Y, KENNEY L P, et al. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data[J]. IEEE Transactions on Biomedical Engineering, 2009, 56(3):871-879.
[20] ATALLAH L, LO B, KING R, et al. Sensor placement for activity detection using wearable accelerometers[C]//Proceedings of the 2010 International Conference on Body Sensor Networks. Piscataway, NJ:IEEE, 2010:24-29.
[21] CHEN Y, SHEN C. Performance analysis of smartphone-sensor behavior for human activity recognition[J]. IEEE Access, 2017(5):3095-3110.
[22] YAZDANSEPAS D, NIAZI A H, GAY J L, et al. A multi-featured approach for wearable sensor-based human activity recognition[C]//Proceedings of the 2016 IEEE International Conference on Healthcare Informatics. Piscataway, NJ:IEEE, 2016:423-431.
[23] XIAO D, YU Z, YI F, et al. SmartSwim:an infrastructure-free swimmer localization system based on smartphone sensors[C]//International Conference on Smart Homes and Health Telematics. Berlin:Springer, 2016:222-234.
[24] LI Q, MARK R G, CLIFFORD G D. Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter[J]. Physiological Measurement, 2008, 29(1):15-32.
[25] 潘泉,孟晋丽,张磊,等.小波滤波方法及应用[J].电子与信息学报,2007,29(1):236-242.(PAN Q, MENG J L, ZHANG L, et al. Wavelet filtering method and its application[J]. Journal of Electronics and Information Technology, 2007, 29(1):236-242.)
[26] SZTYLER T, STUCKENSCHMIDT H, PETRICH W. Position-aware activity recognition with wearable devices[J]. Pervasive & Mobile Computing, 2017, 38(2):281-295.
[27] NOOR M H M, SALCIC Z, KEVIN I, et al. Adaptive sliding window segmentation for physical activity recognition using a single tri-axial accelerometer[J]. Pervasive and Mobile Computing, 2017, 38(1):41-59.
[28] 姚旭,王晓丹,张玉玺,等.特征选择方法综述[J]. 控制与决策,2012,27(2):161-166.(YAO X, WANG X D, ZHANG Y X, et al. Summary of feature selection algorithms[J]. Control and Decision, 2012,27(2):161-166.)
[29] 刘艺,曹建军,刁兴春,等.特征选择稳定性研究综述[J].软件学报,2018,29(9).http://www.jos.org.cn/1000-9825/5394.htm.(LIU Y, CAO J J, DIAO X C, et al. A survey on stability of feature selection[J]. Journal of Software, 2018,29(9). http://www.jos.org.cn/1000-9825/5394.htm.)
[30] GAO L, LI T, YAO L, et al. Research and application of data mining feature selection based on relief algorithm[J]. Journal of Software, 2014, 9(2):515-522.
[31] 李军怀,付静飞,蒋文杰,等. 基于MRMR的文本分类特征选择方法[J]. 计算机科学,2016,43(10):225-228.(LI J H, FU J F, JIANG W J, et al. Feature selection method based on MRMR for text classification[J]. Computer Science, 2016, 43(10):225-228.)
[32] RODGERS J L, NICEWANDER W A. Thirteen ways to look at the correlation coefficient[J]. American Statistician, 1988, 42(1):59-66.
[33] 陈学松,杨宜民. 强化学习研究综述[J]. 计算机应用研究,2010,27(8):2834-2838.(CHEN X S, YANG Y M. Reinforcement learning:survey of recent work[J]. Application Research of Computers, 2010,27(8):2834-2838.)
[34] BEILY M D E, BADJOWAWO M D, BEKAK D O, et al. A sensor based on recognition activities using smart phone[C]//Proceedings of the 2016 International Seminar on Intelligent Technology and Its Applications. Piscataway, NJ:IEEE, 2016:393-398.
[35] 姚潍, 王娟, 张胜利. 基于决策树与朴素贝叶斯分类的入侵检测模型[J]. 计算机应用, 2015, 35(10):2883-2885.(YAO W, WANG J, ZHANG S L. Intrusion detection model based on decision tree and Naive-Bayes classification[J]. Journal of Computer Applications, 2015,35(10):2883-2885.)
[36] OHGI Y, KANEDA K, TAKAKURA A. Sensor data mining on the kinematical characteristics of the competitive swimming[J]. Procedia Engineering, 2014, 72:829-834.
[37] LOMBRISER C, BHARATULA N B, ROGGEN D, et al. On-body activity recognition in a dynamic sensor network[C]//Proceedings of the ICST 2nd International Conference on Body Area Networks. Belgium:ICST, 2007:Article No. 17.
[38] 徐学良. 人工神经网络的发展及现状[J]. 微电子学,2017,47(2):239-242.(XU X L. The development and status of artificial neural network[J]. Microelectronics, 2017,47(2):239-242.)
[39] PANHWAR M, SHAH S M S, SHAH S M Z S, et al. Smart phone based fall detection using auto regression modeling in a non-restrictive setting[J]. Indian Journal of Science & Technology, 2017, 10(5):1-6.
[40] KHARRAT M, WAKUDA Y, KOSHIZUKA N, et al. Near drowning pattern recognition using neural network and wearable pressure and inertial sensors attached at swimmer's chest level[EB/OL].[2017-06-20]. https://www.deepdyve.com/lp/institute-of-electrical-and-electronics-engineers/near-drowning-pattern-recognition-using-neural-network-and-wearable-qyM3F056vS.
[41] LIANG W, ZHANG Y, TAN J, et al. A novel approach to ECG classification based upon two-layered HMMs in body sensor networks[J]. Sensors, 2014, 14(4):5994-6011.
[42] CHENG L, GUAN Y, ZHU K, et al. Recognition of human activities using machine learning methods with wearable sensors[C]//Proceedings of the 2017 IEEE 7th Annual Computing and Communication Workshop and Conference. Piscataway, NJ:IEEE, 2017:1-7.
[43] RONAO C A, CHO S B. Human activity recognition with smartphone sensors using deep learning neural networks[J]. Expert Systems with Applications, 2016, 59(C):235-244.
[44] HAMMERLA N Y, HALLORAN S, PLOETZ T. Deep, convolutional, and recurrent models for human activity recognition using wearables[J]. Journal of Scientific Computing, 2016, 61(2):454-476.
[45] ROS M, CUÉLLAR M P, DELGADO M, et al. Online recognition of human activities and adaptation to habit changes by means of learning automata and fuzzy temporal windows[J]. Information Sciences, 2013, 220(1):86-101.
[46] LIU Y, NIE L, LIU L, et al. From action to activity:sensor-based activity recognition[J]. Neurocomputing, 2016, 181:108-115.

基于可穿戴传感器的人体活动识别研究综述

Review of human activity recognition based on wearable sensors

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]	郭棉, 张锦友. 移动边缘计算环境中面向机器学习的计算迁移策略[J]. 计算机应用, 2021, 41(9): 2639-2645.
[2]	毛铭泽, 曹芮浩, 闫春钢. 基于权值多样性的半监督分类算法[J]. 计算机应用, 2021, 41(9): 2473-2480.
[3]	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.
[4]	姜倩玉, 王凤英, 贾立鹏. 基于感知哈希算法和特征融合的恶意代码检测方法[J]. 计算机应用, 2021, 41(3): 780-785.
[5]	秦静, 左长青, 汪祖民, 季长清, 王宝凤. 基于堆叠分类器的心电异常监测模型设计[J]. 计算机应用, 2021, 41(3): 887-890.
[6]	孟祥瑞, 杨文忠, 王婷. 基于图文融合的情感分析研究综述[J]. 计算机应用, 2021, 41(2): 307-317.
[7]	刘晓龙, 王士同. 渐进式分离的开放集模糊域自适应算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3127-3131.
[8]	楼豪杰, 郑元林, 廖开阳, 雷浩, 李佳. 基于Siamese-YOLOv4的印刷品缺陷目标检测[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3206-3212.
[9]	王雅辉, 钱宇华, 刘郭庆. 基于模糊优势互补互信息的有序决策树算法[J]. 计算机应用, 2021, 41(10): 2785-2792.
[10]	蒋阳升, 王胜男, 涂家祺, 李莎, 王红军. 面向高铁站的热舒适度和能耗综合预测[J]. 计算机应用, 2021, 41(1): 249-257.
[11]	张晨曦, 唐曙, 唐珂. 迁移学习下的火箭发动机参数异常检测策略[J]. 计算机应用, 2020, 40(9): 2774-2780.
[12]	朱琳, 于海涛, 雷新宇, 刘静, 王若凡. 基于MRI图像的阿尔茨海默症患者脑网络特征识别算法[J]. 计算机应用, 2020, 40(8): 2455-2459.
[13]	梁登高, 周安民, 郑荣锋, 刘亮, 丁建伟. 基于大小突发块划分的微信支付行为识别模型[J]. 计算机应用, 2020, 40(7): 1970-1976.
[14]	朱小杰, 赵子豪, 杜一. 模型驱动的大数据流水线框架PiFlow[J]. 计算机应用, 2020, 40(6): 1638-1647.
[15]	徐周波, 杨健, 刘华东, 黄文文. 基于XGBoost与拓扑结构信息的蛋白质复合物识别算法[J]. 计算机应用, 2020, 40(5): 1510-1514.