基于双向LSTM神经网络可穿戴跌倒检测研究Wearable Fall Detection Based on Bi-directional LSTM Neural Network
段美玲;潘巨龙;
摘要(Abstract)：
针对老年人跌倒后不能得到及时救助带来的伤害，研究跌倒检测算法和及时告警，可以减轻跌倒给老年人带来的严重危害和后果。为了提高跌倒检测精确度和实时性，本文提出基于双向长短期记忆神经网络的可穿戴跌倒检测算法，该算法可以对输入的数据(取自惯性传感器)自动提取跌倒行为内部更深层的数据特征，实现数据从预处理到检测结果的过程处理。算法模型通过神经网络提取加速度传感器的特征向量，并利用双向长短期记忆神经网络进行跌倒检测。通过跌倒公开数据集SisFall验证算法模型，结果表明该算法在SisFall实验数据集上具备较高的检测精度，满足准实时检测要求，具有较好的实用性和较强的泛化能力。
关键词(KeyWords)： 跌倒检测;长短期记忆;加速度传感器;神经网络;特征提取
基金项目(Foundation): 浙江省基础公益研究计划项目(LGF21F020017)
作者(Authors): 段美玲;潘巨龙;
DOI: 10.16088/j.issn.1001-6600.2021071003
参考文献(References)：
- [1] 师昉，李福亮，张思佳，等.中国老年跌倒研究的现状与对策[J].中国康复，2018,33(3):246-248.DOI:10.3870/zgkf.2018.03.021.
- [2] 吕艳，张萌，姜吴昊，等.采用卷积神经网络的老年人跌倒检测系统设计[J].浙江大学学报(工学版),2019,53(6):1130-1138.DOI:10.3785/j.issn.1008-973X.2019.06.012.
- [3] DE CILLIS F,DE SIMIO F,GUIDO F,et al.Fall-detection solution for mobile platforms using accelerometer and gyroscope data[C]// Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Piscataway:IEEE,2015:3727-3730.DOI:10.1109/EMBC.2015.7319203.
- [4] 李沛峰，冯飞龙，黄淑芬，等.基于Kinect V2的老人跌倒检测系统设计[J].电子设计工程，2021,29(19):112-116.
- [5] SUCERQUIA A,LóPEZ J D,VARGAS F.Two-threshold energy based fall detection using a triaxial accelerometer[C]// Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Piscataway:IEEE,2016:3101-3104.DOI:10.1109/EMBC.2016.7591385.
- [6] BIANCHI F,REDMOND S J,NARAYANAN M R,et al.Barometric pressure and triaxial accelerometry-based falls event detection[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2010,18(6):619-627.DOI:10.1109/TNSRE.2010.2070807.
- [7] BOURKE A K,O′BRIEN J V,LYONS G M.Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm[J].Gait & Posture,2007,26(2):194-199.DOI:10.1016/j.gaitpost.2006.09.012.
- [8] 忽丽莎，王素贞，陈益强，等.基于可穿戴设备的跌倒检测算法综述[J].浙江大学学报(工学版),2018,52(9):1717-1728.DOI:10.3785/j.issn.1008-973X.2018.09.012.
- [9] NOURY N,FLEURY A,RUMEAU P,et al.Fall detection-principles and methods[C]// Proceedings of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Piscataway:IEEE,2007:1663-1666.DOI:10.1109/IEMBS.2007.4352627.
- [10] DAVIS K,OWUSU E,BASTANI V,et al.Activity recognition based on inertial sensors for ambient assisted living[C]// Proceedings of the 19th International Conference on Information Fusion.Piscataway:IEEE,2016:371-378.
- [11] CHEN Y,WANG Z L.A hierarchical method for human concurrent activity recognition using miniature inertial sensors[J].Sensor Review,2017,37(1):101-109.DOI:10.1108/SR-05-2016-0085.
- [12] TSINGANOS P,SKODRAS A.A smartphone-based fall detection system for the elderly[C]// Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis.Piscataway:IEEE,2017:53-58.DOI:10.1109/ISPA.2017.8073568.
- [13] 任小奎，李锋，程琳.基于PSO模式搜索的跌倒检测算法研究[J].计算机应用研究，2020,37(4):1077-1080.
- [14] NWEKE H F,TEH Y W,MUJTABA G,et al.Data fusion and multiple classifier systems for human activity detection and health monitoring:review and open research directions[J].Information Fusion,2019,46:147-170.DOI:10.1016/j.inffus.2018.06.002.
- [15] SHI J Y,CHEN D S,WANG M.Pre-impact fall detection with CNN-based class activation mapping method[J].Sensors,2020,20(17):4750.DOI:10.3390/s20174750.
- [16] 王晶晶，黄勇，陈宝欣，等.基于独立循环神经网络的跌倒检测方法[J].实验室研究与探索，2020,39(7):20-23,40.
- [17] LI H B,SHRESTHA A,HEIDARI H,et al.Bi-LSTM network for multimodal continuous human activity recognition and fall detection[J].IEEE Sensors Journal,2020,20(3):1191-1201.DOI:10.1109/JSEN.2019.2946095.
- [18] 胡双杰，秦建邦，郭薇.基于特征自动提取的跌倒检测算法[J].传感技术学报，2018,31(12):1842-1847.DOI:10.3969/j.issn.1004-1699.2018.012.011.
- [19] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.DOI:10.1162/neco.1997.9.8.1735.
- [20] ISTIAKE SUNNY M A,MASWOOD M M S,ALHARBI A G.Deep learning-based stock price prediction using LSTM and bi-directional LSTM model[C]// Proceedings of the 2nd Novel Intelligent and Leading Emerging Sciences Conference.Piscataway:IEEE,2020:87-92.DOI:10.1109/NILES50944.2020.9257950.
- [21] SUCERQUIA A,LóPEZ J D,VARGAS-BONILLA J F.SisFall:a fall and movement dataset[J].Sensors,2017,17(1):198.DOI:10.3390/s17010198.
- [22] HUSSAIN F,HUSSAIN F,EHATISHAM-UL-HAQ M,et al.Activity-aware fall detection and recognition based on wearable sensors[J].IEEE Sensors Journal,2019,19(12):4528-4536.DOI:10.1109/JSEN.2019.2898891.
- [23] CASILARI E,LORA-RIVERA R,GARCíA-LAGOS F.A study on the application of convolutional neural networks to fall detection evaluated with multiple public datasets[J].Sensors,2020,20(5):1466.DOI:10.3390/s20051466.
- [24] MUSCI M,DE MARTINI D,BLAGO N,et al.Online fall detection using recurrent neural networks on smart wearable devices[J].IEEE Transactions on Emerging Topics in Computing,2021,9(3):1276-1289.DOI:10.1109/TETC.2020.3027454.
- [25] LUNA-PEREJóN F,DOMíNGUEZ-MORALES M J,CIVIT-BALCELLS A.Wearable fall detector using recurrent neural networks[J].Sensors,2019,19(22):4885.DOI:10.3390/s19224885.
- [26] WARDEN P,SITUNAYAKE D.TinyML:machine learning with tensorflow lite on arduino and ultya-low-power microcontrollers[M].Sebastopol:O’Reilly Media,2019.