[1]牛德姣,刘亚文,蔡涛,等.基于递归神经网络的跌倒检测系统[J].智能系统学报,2018,13(03):380-387.[doi:10.11992/tis.201710013]
 NIU Dejiao,LIU Yawen,CAI Tao,et al.Fall detection system based on recurrent neural network[J].CAAI Transactions on Intelligent Systems,2018,13(03):380-387.[doi:10.11992/tis.201710013]
点击复制

基于递归神经网络的跌倒检测系统(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第13卷
期数:
2018年03期
页码:
380-387
栏目:
出版日期:
2018-05-05

文章信息/Info

Title:
Fall detection system based on recurrent neural network
作者:
牛德姣 刘亚文 蔡涛 彭长生 詹永照 梁军
江苏大学 计算机科学与通信工程学院, 江苏 镇江 212013
Author(s):
NIU Dejiao LIU Yawen CAI Tao PENG Changsheng ZHAN Yongzhao LIANG Jun
School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang 212001, China
关键词:
跌倒检测接近跌倒检测传感器数据递归神经网络大数据跌倒检测算法训练算法RNNFD
Keywords:
fall detectionnear fall detectionsensor datarecurrent neural networkbig datafall detection algorithmtraining algorithmRNNFD
分类号:
TP391
DOI:
10.11992/tis.201710013
摘要:
针对现有跌倒检测方法存在适应性差和功能较单一等问题,引入递归神经网络,通过发掘位置传感器数据之间的内在联系提高检测跌倒行为的效果。首先,设计了传感器、训练与检测输入数据的序列化表示方法,为发掘其中与跌倒和接近跌倒行为相关的内在关联提供了基础;接着,给出了用于跌倒检测的RNN训练算法以及基于RNN的跌倒检测算法,将跌倒检测转换为输入序列的分类问题;最后,在前期实现的基于分布式神经元大规模RNN系统的基础上,在Spark平台上实现了基于RNN的跌倒检测系统,使用Fall_adl_data数据集进行了测试与分析,验证了其能有效提高跌倒检测的准确率和召回率,F值相比现有跌倒检测系统提高12%和7%,同时能有效检测出接近跌倒的行为,有助于及时采取保护措施减少伤害。
Abstract:
The existing methods of fall detection have poor adaptability and limited functions. In this paper, a recurrent neural network based fall detection system is introduced to improve the performance of fall detection and to make it able to identify more dangerous near-falls by exploring the relationship of the position sensor data. Firstly, a serialization representation method on position sensor data, training and test data is designed as the basis for intrinsic relationship exploration. Then, the training algorithm for RNN based fall detection is proposed, where the fall detection is transformed into a classification problem of the input sequence. Finally, using the large-scale RNN system based on distributed neurons, the fall detection system is implemented on the Spark platform. Evaluations are carried out on Fall_adl_data. The experimental results prove that the proposed system can improve the precision and recall of fall detection effectively. Compared with the existing fall detection systems, F-measure has improved by 12% and 7%, respectively. Moreover, the system is also able to detect the near-fall behavior effectively which helps provide timely protective measures to reduce the damage caused by falls.

参考文献/References:

[1] 吴天昊. 基于3轴加速度传感器及陀螺仪的老年人摔倒识别[D]. 北京:北京工业大学, 2013:2-3. WU Tianhao. Identification of old people ’s fall-downing based on 3-axis acceleration sensor and gyroscope[D]. Beijing, China:Beijing University of Technology, 2013:2-3.
[2] ROUGIER C, MEUNIER J, ST-ARNAUD A. 3D head tracking for fall-down detection using a single calibrated camera[J]. Image and Vision Computing, 2013, 31(3):246-254.
[3] MUBASHIR M, SHAO L, SEED L. A survey on fall-down detection:Principles and approaches[J]. Neurocomputing, 2013, 100(2):144-152.
[4] MATHIE M J, BASILAKIS J, CELLER B G. A system for monitoring posture and physical activity using accelerometers[C]//International Conference of the IEEE Engineering in Medicine and Biology Society. Istanbul, Turkey, 2001:3654-3657.
[5] 卢先领, 王洪斌, 王莹莹, 等. 一种基于加速度传感器的人体跌倒识别方法[J]. 计算机应用研究, 2013, 30(4):1109-1111. LU Xianling, WANG Hongbin, WANG Yingying, et al. Human fall-downing detection based on accelerometer[J]. Computer Application Research, 2013, 30(4):1109-1111.
[6] FANG-YIE LEU, CHIA-YIN KO, YI-CHEN LIN, et al. Smart Sensors Networks[M]. United Kingdom:Mara Conner, 2017:205-237.
[7] CHEN L, MA H T, LIU S, et al. Posture estimation by Bayesian Network with Belief Propagation[C]//TENCON 2013-2013 IEEE Region 10 Conference. Xi’an, China, 2013:1-4.
[8] Duan K B, Keerthi S S. Which is the best multiclass SVM method? An empirical study[M]//Multiple Classifier Systems. Springer Berlin Heidelberg, 2005:278-285.
[9] BREIMAN L. Random forest[J]. Machine learning, 2001, 45(1):5-32.
[10] SZ Erdogan, TT Bilgin, J Cho. Fall-down detection by using K-nearest neighbor algorithm on WSN data[C]//GLOBECOM Workshops. Houston, USA, 2011:2054-2058.
[11] WU G, XUE S. Portable preimpact fall-down detector with inertial sensors[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2008, 16(2):178-183.
[12] OJETOLA O, GAURA E, BRUSEY J. Data set for fall-down events and daily activities from inertial sensors[C]//ACM Multimedia Systems Conference. Oregon, USA, 2015:243-248.
[13] CHEN J, KWONG K, CHANG D, et al. Wearable sensors for reliable fall-down detection[C]//International Conference of the IEEE, NEW YORK, USA, 2006:3551-3554.
[14] LI Q, STANKOVIC J A, HANSON M A, et al. Accurate fast fall-down detection using gyroscopes and accelerometer-derived posture information[C]//Sixth International Workshop on Wearable and Implantable Body Sensor Networks. CA, USA, 2009:138-143.
[15] VAIDEHI V, GANAPATHY K, MOHAN K, et al. Video based automatic fall-down detection in indoor environment[C]//International Conference on Recent Trends in Information Technology. Chennai, INDIA, 2011:1016-1020.
[16] BOSCH-JORGE M, SÁNCHEZ-SALMERÓN A J, ÁNGEL VALERA, et al. Fall-down detection based on the gravity vector using a wide-angle camera[J]. Expert Systems with Applications, 2014, 41(17):7980-7986.
[17] 佟丽娜, 宋全军, 葛运建. 基于时序分析的人体摔倒预测方法[J]. 模式识别与人工智能, 2012, 25(2):273-279. TONG Linna, SONG Quanjun, GE Yunjian. Time series analysis based human fall prediction method[J]. Pattern recognition & artificial intelligence, 2012, 25(2):273-279.
[18] GIBSON R M, AMIRA A, CASASECA-DE-LA-HIGUERA P, et al. An efficient user-customisable multiresolution classifier fall-down detection and diagnostic system[C]//International Conference on Microelectronics. Changchun, China, 2015:228-231.
[19] LUO D, LUO H, SCHOOL I. Fall detection algorithm based on random forest[J]. Journal of computer applications, 2015, 35(11):3157-3160.
[20] 胡二雷, 冯瑞. 基于深度学习的图像检索系统[J]. 计算机系统应用, 2017, 26(3):8-19. HU Erlei, FENG Rui. Image retrieval system based on deep learning[J]. Computer systems & applications, 2017, 26(3):8-19.
[21] 焦李成, 杨淑媛, 刘芳, 等. 神经网络七十年:回顾与展望[J]. 计算机学报, 2016, 39(8):1697-1716. JIAO Licheng, YANG Shuyuan, LIU Fang, et al. Seventy years beyond neural networks:retrospect and prospect[J]. Chinese Journal of Computers, 2016, 39(8):1697-1716.
[22] DEJIAO NIU, RUI XUE, TAO CAI, HAI LI, EFFAH KINGSLEY. The new large-scale RNNLM system based on distributed neuron[C]//Parallel and Distributed Processing Symposium Workshops. Florida, USA, 2017:433-436.
[23] YONG Z, MENG J E, VENKATESAN R, et al. Sentiment classification using comprehensive attention recurrent models[C]//International Joint Conference on Neural Networks. Vancouver, Canada, 2016:1562-1569.
[24] CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN Encoder-Decoder for statistical machine translation[C]//Conference on Empirical Methods in Natural Language Processing. Doha, Qatar, 2014:1724-1734.
[25] 张舸, 张鹏远, 潘接林, 等. 基于递归神经网络的语音识别快速解码算法[J]. 电子与信息学报, 2017, 39(4):930-937. ZHANG Ge, ZHANG Pengyuan, PAN Jielin, et al. Fast decoding algorithm for automatic speech recognition based on recurrent neural networks[J]. Journal of Electronics Information Technology, 2017, 39(4):930-937.
[26] MEI H, BANSAL M, WALTER M R. Coherent dialogue with attention-based language models[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. San Francisco, America, 2017:3252-3258.
[27] BAI J, WU Y. SAE-RNN Deep learning for RGB-D based object recognition[C]//International Conference on Intelligent Computing. Odisha, India, 2014:235-240.
[28] FAN H, LING H. Sanet:structure-aware network for visual tracking[C]//Computer Vision and Pattern Recognition Workshops. Honolulu, USA, 2017:2217-2224.
[29] 蔡政. 面向社交网络的GIF视频情感标注与分析技术研究[D]. 福建:厦门大学, 2016:10-15. CAI Zheng. Research on the emotional annotation and analysis of GIF video for social network[D]. Fujian:Xiamen University, 2016:10-15.
[30] ZHANG H, LI J, JI Y, et al. A character-level sequence-to-sequence method for subtitle learning[C]//International Conference on Industrial Informatics. Poitiers,France, 2016:780-783.
[31] SHETTY R, LAAKSONEN J. Video captioning with recurrent networks based on frame- and video-level features and visual content classification[C]. Santiago, ICCV workshop, 2015.
[32] MALINOWSKI M, ROHRBACH M, FRITZ M. Ask your neurons:a deep learning approach to visual question answering[J]. International journal of computer vision, 2017, 125(1—3):110-135.
[33] 姜春福, 余跃庆. 基于状态延迟动态递归神经网络的机器人动态自适应跟踪辨识[J]. 自动化学报, 2003, 29(5):741-747. JIANG Chunfu, YU Yueqing. Sdidrnn based dynamical adaptive tracking identification of robot manipulators[J]. Proceedings of the CSU-EPSA, 2003, 29(5):741-747.
[34] MIKOLOV T A. Statistical language models based on neural networks[D]. Brno, Czech Republic: Brno University of Technology, 2012:27-43.

备注/Memo

备注/Memo:
收稿日期:2017-10-17。
基金项目:江苏省科技厅重点研发计划产业前瞻与共性关键技术项目(BE2015137);江苏省自然科学基金项目(BK20140570);中国博士后基金项目(2016M601737).
作者简介:牛德姣,女,1978年生,副教授,博士,主要研究方向为神经网络、新型非易失存储器。发表SCI和EI检索论文10余篇;刘亚文,女,1994年生,硕士研究生,主要研究方向为神经网络、大数据计算;蔡涛,男,1976年生,副教授,博士,CCF会员,主要研究方向为面向大数据人工智能和新型非易失存储器。发表SCI和EI检索论文30余篇。
通讯作者:牛德姣.E-mail:djniu@ujs.edu.cn.
更新日期/Last Update: 2018-06-25