Recognition of human activities based on single triaxial accelerometer

被引：0
|
作者：
Li W. [1 ]
Yao B. [1 ]
机构：
[1] School of Logistics Engineering, Wuhan University of Technology, Wuhan
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2016年 / 44卷 / 04期
关键词：
Accelerometer; Real time; Sliding time window; State recognition; Threshold;
D O I：
10.13245/j.hust.160412
中图分类号：
学科分类号：
摘要：
There are many problems in the current methods of recognition of human activities such as many sensors, complicated recognition algorithms, poor implementation, bad real-time performance and so on. Thus, an algorithm of human activities recognition based on single triaxial accelerometer was proposed. The acceleration data of the waist of body were collected whose features were extracted from within sliding time windows and processed via an algorithm based-on threshold. Four activities were recognized, which were long-term strenuous exercise, long-term stationary state, fall and normal activities. This method used single sensor with simplicity of soft hardware, and was easy to implement and carry. Furthermore, the results of the experiments show that the average response time of the algorithm is less than 1 s and the average accuracy is up to 99.3%, indicating its real-time performance and effectiveness. © 2016, Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：58 / 62
页数：4
相关论文
共 10 条
  • [1] Khan A.M., Lee Y.K., Lee S.Y., Et al., A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer, IEEE Transactions on Information Technology in Biomedicine, 14, 5, pp. 1166-1172, (2010)
  • [2] Tang W., Sazonov E.S., Highly accurate recognition of human postures and activities through classification with rejection, IEEE Journal of Biomedical and Health Informatics, 18, 1, pp. 309-315, (2014)
  • [3] Wang L., Gu T., Chen H., Et al., Real-time activity recognition in wireless body sensor networks: from simple gestures to complex activities, Proc of 16th IEEE International Conference on Embedded and Real-time Computing Systems and Applications, pp. 43-52, (2010)
  • [4] Martin H., Bernardos A.M., Tarrio P., Et al., Enhancing activity recognition by fusing inertial and biometric information, Proc of the 14th International Conference on Information Fusion, pp. 1-8, (2011)
  • [5] Alzubi H.S., Gerrard-Longworth S., Al-Nuaimy W., Et al., Human activity classification using a single accelerometer, Proc of 14th UK Workshop on Computational Intelligence, pp. 1-6, (2014)
  • [6] Huang C., Chung C., A real-time model-based human motion tracking and analysis for human computer interface systems, Eurasip Journal on Applied Signal Processing, 2004, 11, pp. 1648-1662, (2004)
  • [7] Bourke A.K., Lyons G.M., A threshold-based fall-detection algorithm using a bi-axial gyroscope sensor, Medical Engineering & Physics, 30, 1, pp. 84-90, (2008)
  • [8] Maarit K., Antti K., Ilkka W., Et al., Determination of simple thresholds for accelerometry-based parameters for fall detection, Proc of 29th International Conference of the IEEE Engineering in Medicine & Biology Society, pp. 1367-1370, (2007)
  • [9] Bourke A.K., O'Brien J.V., Lyons G.M., Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm, Gait & Posture, 26, 2, pp. 194-199, (2007)
  • [10] Liu S., Cheng W., Fall detection with the support vector machine during scripted and continuous unscripted activities, Sensors, 12, 9, pp. 12301-12316, (2012)
1