Abstract
Identifying ways of monitoring this aging population in their home environment is very important. Sensor-based human activity recognition has proven to be a valid candidate in order to estimate the human activity. This paper proposes a human activity behavior recognition technology based on indoor positioning. Firstly, a location fingerprinted database is constructed by collecting RSSI values and each AP name. The relationship between the feature parameters and the activity was established based on the acceleration values. Secondly, the wearable device captures the RSSI values and acceleration when older people are indoors. Then the system given the corresponding position and action through support vector machine. The probability of positioning accuracy within 2 m is more than 90%, which meets the requirement of indoor positioning accuracy. The action recognition rate is 100%.
Similar content being viewed by others
References
Aviles-Cruz C, Rodriguez-Martinez E, Villegas-Cortez J, Ferreyra-Ramirez A (2019) Granger-causality: an efficient single user movement recognition using a smartphone accelerometer sensor. Pattern Recogn Lett 125:576–583. https://doi.org/10.1016/j.patrec.2019.06.029
Butler RN (1997) Population aging and health. Br Med J 315:1082–1084. https://doi.org/10.1016/S0140-6736(12)60519-4
Du C (2019) Study on lifestyle evaluation systems for the health of Chinese elderly. Int J Env Res Pub He 16:284. https://doi.org/10.3390/ijerph16020284
Han D, Bo L, Sminchisescu C (2009) Selection and context for action recognition. 2009 IEEE 12th ICCV. Kyoto 30:1933–1940. https://doi.org/10.1109/ICCV.2009.5459427
Liu T, Katpelly R (2007) An interactive system for video content exploration. IEEE T Consum Electr 52:1368–1376. https://doi.org/10.1109/TCE.2006.273158
Mario M (2019) Human activity recognition based on single sensor square HV acceleration images and convolutional neural networks. IEEE Sens J 19:1487–1498. https://doi.org/10.1109/JSEN.2018.2882943
Räty TD (2010) Survey on contemporary remote surveillance systems for public safety. IEEE T Syst Man CYC 40:493–515. https://doi.org/10.1109/TSMCC.2010.2042446
Shian-Ru K, Hoang T, Yong-Jin L, Jenq-Neng H, Jang-Hee Y, Kyong-Ho C (2013) A review on video-based human activity recognition. Computers 16:88–131. https://doi.org/10.3390/computers2020088
Vapnik VN (2000) The nature of statistical learning theory. Springer, New York. https://doi.org/10.1007/978-1-4757-3264-1_4
Wang L, Hu W, Tan T (2003) Recent developments in human motion analysis. Pattern Recogn 36:585–601. https://doi.org/10.1016/S0031-3203(02)00100-0
Acknowledgements
This work is partially supported by the Key Research and Development Program of Shaanxi (2019GY-107), Natural Science Foundation of Shaanxi Province (2019JQ-859) and the Scientific Research Program of Shaanxi Provincial Education Committee (18JK0715).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pan, Z., Wei, C. Human activity monitoring based on indoor map positioning. Microsyst Technol 27, 2919–2923 (2021). https://doi.org/10.1007/s00542-020-05124-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00542-020-05124-w