Abstract
Ambient Assisted Living facilities provide assistance and care for the elderly, where it is useful to infer their daily activity for ensuring their safety and successful ageing. In this work, we present an Activity Recognition system that classifies a set of common daily activities exploiting both the data sampled by accelerometer sensors carried out by the user and the reciprocal Received Signal Strength (RSS) values coming from worn wireless sensor devices and from sensors deployed in the environment. To this end, we model the accelerometer and the RSS stream, obtained from a Wireless Sensor Network (WSN), using Recurrent Neural Networks implemented as efficient Echo State Networks (ESNs), within the Reservoir Computing paradigm. Our results show that, with an appropriate configuration of the ESN, the system reaches a good accuracy with a low deployment cost.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Choudhury, T., LaMarca, A., LeGrand, L., Rahimi, A., Rea, A., Borriello, G., Hemingway, B., Koscher, K., Lan, J.A., Lester, J., Wyatt, D., Haehnel, D., et al.: The mobile sensing platform: An embedded activity recognition system (2008)
Khawandi, S., Daya, B., Chauvet, P.: Automated monitoring system for fall detection in the elderly. International Journal of Image Processing 4(5) (2010)
Bocca, M., Kaltiokallio, O., Patwari, N.: Radio tomographic imaging for ambient assisted living. In: Chessa, S., Knauth, S. (eds.) EvAAL 2012. CCIS, vol. 362, pp. 108–130. Springer, Heidelberg (2013)
Lukosevicius, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Computer Science Review 3(3), 127–149 (2009)
Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. Technical report, GMD (2001)
Bacciu, D., Gallicchio, C., Lenzi, A., Chessa, S., Micheli, A., Pelagatti, S., Vairo, C.: Distributed neural computation over WSN in ambient intelligence. In: van Berlo, A., Hallenborg, K., Rodríguez, J.M.C., Tapia, D.I., Novais, P. (eds.) Ambient Intelligence – Software & Applications. AISC, vol. 219, pp. 147–154. Springer, Heidelberg (2013)
Ravi, N., Dandekar, N., Mysore, P., Littman, M.L.: Activity recognition from accelerometer data. In: Proceedings of the Seventeenth Conference on Innovative Applications of Artificial Intelligence (IAAI), pp. 1541–1546. AAAI Press (2005)
Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Ferscha, A., Mattern, F. (eds.) PERVASIVE 2004. LNCS, vol. 3001, pp. 1–17. Springer, Heidelberg (2004)
Mannini, A., Sabatini, A.M.: Machine learning methods for classifying human physical activity from on-body accelerometers. Sensors 10(2), 1154–1175 (2010)
Bacciu, D., Barsocchi, P., Chessa, S., Gallicchio, C., Micheli, A.: An experimental characterization of reservoir computing in ambient assisted living applications. Neural Computing and Applications, 1–14 (2013)
Bacciu, D., Chessa, S., Gallicchio, C., Micheli, A., Barsocchi, P.: An experimental evaluation of reservoir computation for ambient assisted living. In: Apolloni, B., Bassis, S., Esposito, A., Morabito, F.C. (eds.) Neural Nets and Surroundings. SIST, vol. 19, pp. 41–50. Springer, Heidelberg (2013)
Gallicchio, C., Micheli, A., Barsocchi, P., Chessa, S.: User movements forecasting by reservoir computing using signal streams produced by mote-class sensors. In: Ser, J., Jorswieck, E., Miguez, J., Matinmikko, M., Palomar, D., Salcedo-Sanz, S., Gil-Lopez, S. (eds.) MOBILIGHT 2011. LNICST, vol. 81, pp. 151–168. Springer, Heidelberg (2012)
Bacciu, D., Gallicchio, C., Micheli, A., Barsocchi, P., Chessa, S.: Predicting user movements in heterogeneous indoor environments by reservoir computing. In: Proceedings of the 22nd International Joint Conference on Artificial Intelligence (IJCAI 2011), Space, Time and Ambient Intelligence Workshop (STAMI 2011), July 16-22, pp. 1–8 (2011)
Guraliuc, A., Barsocchi, P., Potort, F., Nepa, P.: Limb movements classification using wearable wireless transceivers. IEEE Transactions on Information Technology in Biomedicine 15(3), 474–480 (2011)
Barsocchi, P.: Position recognition to support bedsores prevention. IEEE Journal of Biomedical and Health Informatics 17(1), 53–59 (2013)
TelosB: Tmote sky, http://www.capsil.org/capsilwiki/index.php/TELOSB/TMote_Sky (accessed: May 18, 2013)
Moog: Crossbow, http://www.xbow.com (accessed: May 18, 2013)
TinyOS: Tinyos, http://www.tinyos.net/ (accessed: May 18, 2013)
Ashford, S., De Souza, L.: A comparison of the timing of muscle activity during sitting down compared to standing up. Physiotherapy Research International 5(2), 111–128 (2000)
Kralj, A., Jaeger, R.J., Munih, M.: Analysis of standing up and sitting down in humans: definitions and normative data presentation. Journal of Biomechanics 23(11), 1123–1138 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Palumbo, F., Barsocchi, P., Gallicchio, C., Chessa, S., Micheli, A. (2013). Multisensor Data Fusion for Activity Recognition Based on Reservoir Computing. In: Botía, J.A., Álvarez-García, J.A., Fujinami, K., Barsocchi, P., Riedel, T. (eds) Evaluating AAL Systems Through Competitive Benchmarking. EvAAL 2013. Communications in Computer and Information Science, vol 386. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41043-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-41043-7_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41042-0
Online ISBN: 978-3-642-41043-7
eBook Packages: Computer ScienceComputer Science (R0)