Wearable Method for Fall Detection Based on Kalman Filter and k-NN Algorithm
HE Jian①② ZHOU Mingwo② WANG Xiaoyi①②
①(Advanced Innovation Center for Future Internet Technology, Beijing 100124, China) ②(Beijing Engineering Research Center for IOT Software and Systems, Beijing 100124, China)
Abstract：According to the accurate and real-time requirement for fall detection. An activity model based on attitude angles is firstly established. A sensor board integrated with trial-axil accelerator and gyroscope is developed, which can capture the accelerations and angular velocities of human activities and transmit them to a smart phone by Bluetooth. Secondly, the three-dimensional attitude angle and acceleration signal vector magnitude are selected as features for fall detection. The collected data is preprocessed using Kalman filter to reduce noise and enhance the precision of attitude angle calculation. The k-Nearest Neighbor (k-NN) algorithm and appropriate sliding window are introduced to develop the fall detection and alert system. At last, the experimental results show that the system discriminates falls from the activities of daily living with accuracy of 98.9%, while the sensitivity and specificity are 98.9%, and 98.5% respectively. It proves that the method has favorable accuracy and reliability.
何坚,周明我,王晓懿. 基于卡尔曼滤波与k-NN算法的可穿戴跌倒检测技术研究[J]. 电子与信息学报, 2017, 39(11): 2627-2634.
HE Jian, ZHOU Mingwo, WANG Xiaoyi. Wearable Method for Fall Detection Based on Kalman Filter and k-NN Algorithm. JEIT, 2017, 39(11): 2627-2634.
TIAN Xueyuan. Population aging and endowment insurance system innovation[J]. Population Journal, 2014, 36(1): 5-15. doi: 10.3969/j.issn.1004-129X.2014.01.001.
TANG Yuxin, GUO Xiaomu, QIAO Zhijiao, et al. Analysis on prevalence and risk factors for falls among the elderly in communities of Beijing and Shanghai[J]. Chinese Journal of Disease Control & Prevention, 2017, 21(1): 72-76. doi 10. 16462/j.cnki.zhjbkz. 2017.01.017.
[3]
KOSHMAK Gregory, LOUTFI Amy, and LINDEN Maria. Challenges and issues in multisensor fusion approach for fall detection: Review paper[J]. Journal of Sensors, 2016, 2016: Article ID 837459. doi: 10.1155/2016/6931789.
[4]
DEBARD Glen, MERTENS Marc, DESCHODT Mieke, et al. Camera-based fall detection using real-world versus simulated data: How far are we from the solution?[J]. Journal of Ambient Intelligence & Smart Environments, 2016, 8(2): 149-168. doi: 10.3233/AIS-160369.
[5]
BALDEWIJNS Greet, DEBARD Glen, MERTES Gert, et al. Bridging the gap between real-life data and simulated data by providing a highly realistic fall dataset for evaluating camera-based fall detection algorithms[J]. Healthcare Technology Letters, 2016, 3(1): 6-11. doi: 10.1049/htl.2015. 0047
[6]
MAZUREK Pawel and MORAWSKI Roman Z. Application of naïve Bayes classifier in fall detection systems based on infrared depth sensors[C]. Proceedings of the IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing System-Technology and Applications (IDAACS), Warsaw, Poland, 2015: 717-722. doi: 10.1109/ IDAACS.2015.7341397.
[7]
SALMAN KHAN Muhammad, YU Miao, FENG Pengming, et al. An unsupervised acoustic fall detection system using source separation for sound interference suppression[J]. Signal Processing, 2015, 110(C): 199-210. doi: 10.1016/j. sigpro.2014.08.021.
[8]
BECKER C, SCHWICKERT L, MELLONE S, et al. Proposal for a multiphase fall model based on real-world fall recordings with body-fixed sensors[J]. Zeitschrift Für Gerontologie Und Geriatrie, 2012, 45(8): 707-715. doi: 10.1007/s00391-012-0403-6.
[9]
WANG Jin, ZHANG Zhongqi, LI Bin, et al. An enhanced fall detection system for elderly person monitoring using consumer home networks[J]. IEEE Transactions on Consumer Electronics, 2014, 60(1): 23-29. doi: 10.1109/ TCE.2014.6780921.
[10]
QU Weihao, LIN Feng, WANG Aosen, et al. Evaluation of a low-complexity fall detection algorithm on wearable sensor towards falls and fall-alike activities[C]. Proceedings of the IEEE Signal Processing in Medicine and Biology Symposium. Philadelphia, PA, United States, 2015: 1-6. doi: 10.1109/ SPMB.2015.7405427.
[11]
QU Weihao, LIN Feng, and XU Wenyao. A real-time low-complexity fall detection system on the smartphone[C]. Proceedings of the IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies. Washington, DC, United States, 2016: 354-356. doi: 10.1109/CHASE.2016.73.
[12]
SALGADO Paulo and AFONSO Paulo. Body fall detection with Kalman filter and SVM[C]. Proceedings of the 11th Portuguese Conference on Automatic Control, Porto, Portugal, 2015, 321 LNEE: 407-416. doi: 10.1007/978-3-319- 10380-8_39.
[13]
BOURKE A K and LYONS G M. A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor[J]. Medical Engineering & Physics, 2008, 30(1): 84-90. doi: 10.1016/j.medengphy.2006.12.001.
CHEN Hangke, ZHANG Dongsheng, SHENG Xiaochao, et al. Research on signal fusion technology of attitude sensor based on Kalman filtering algorithm[J]. Transducer and Microsystem Technologies, 2013, 32(12): 82-85. doi: 10.3969/ j.issn.1000-9787. 2013.12.023.
[15]
LI Qiang, STANKOVIC John A, HANSON Mark A, et al. Accurate, fast fall detection using gyroscopes and accelerometer derived posture information[C]. Proceedings of the Sixth International Workshop on Wearable and Implantable Body Sensor Networks, Berkeley, CA, United States, 2009: 138-143. doi: 10.1109/BSN.2009.46.
[16]
HE Jian and HU Chen. A portable fall detection and alerting system based on k-NN algorithm and remote medicine[J]. China Communications, 2015, 12(4): 23-31. doi: 10.1109/CC. 2015.7114066.
[17]
ERDOGAN Senol Zafer and BILGIN Turgay Tugay. A data mining approach for fall detection by using k-Nearest Neighbour algorithm on wireless sensor network data[J]. IET Communications, 2012, 6(18): 3281-3287. doi: 10.1049/ iet-com.2011.0228.
