Design Optimization of Activity Recognition System on an Embedded Platform
Activity Recognition (AR) is a subset of pervasive computing that attempts to identify physical actions performed by a user. Previous sensor-based AR systems involve computation and energy overheads incurred by the use of heterogeneous and large number of sensors, however it is possible to arrive at an optimized system where the design involves optimization of energy consumption through number of sensors, computation through minimal set of features and cost through a nominal hardware platform ideally making it a multidimensional optimization. The above mentioned modelling was reflected in the construction of this optimized system as the design employs a single accelerometer and extracts only 7 time-domain features resulting in ease of computation to classify the activities, thus encouraging it to be inherently deployable on an embedded platform. The system was trained and tested on the accelerometer data acquired from three publicly available datasets. The performance of four chosen machine learning based classification models from an initial set of eight was evaluated, analysed and ranked on the grounds of efficiency and computation. The model was implemented on a Raspberry Pi Zero (USD 5) and the average time for feature computation and the maximum time taken to classify an instance of an activity was found to be 0.015 s and 1.094 s respectively, thus validating the viability of the system on an embedded platform and making it affordable to the population in the low-income groups.
KeywordsMachine learning Pervasive computing Activity recognition
The authors would like to acknowledge Solarillion Foundation for its support and funding of the research work carried out.
- 2.Lester, J., Choudhury, T., Borriello, G.: A practical approach to recognizing physical activities. In: Pervasive, vol. 3968, pp. 1–16 (2006)Google Scholar
- 4.Anguita, D., Ghio, A., Oneto, L., Parra, X., Reyes-Ortiz, J.L.: A public domain dataset for human activity recognition using smartphones. In: ESANN (2013)Google Scholar
- 6.Casale, P., Pujol, O., Radeva, P.: Human activity recognition from accelerometer data using a wearable device. In: IbPRIA, vol. 6669, pp. 289–296 (2011)Google Scholar
- 7.Ronao, C.A., Cho, S.B.: Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models. In: 2014 10th International Conference on Natural Computation (ICNC), Xiamen, pp. 681–686 (2014)Google Scholar
- 8.Garcia-Ceja, E., Brena, R.F.: Building personalized activity recognition models with scarce labeled data based on class similarities. In: UCAmI, vol. 9454, pp. 265–276 (2015)Google Scholar
- 9.Nguyen, L.T., Tague, P., Zeng, M., Zhang, J.: SuperAD: supervised activity discovery. In: UbiComp/ISWC Adjunct, pp. 1463–1472 (2015)Google Scholar
- 10.Ravi, N., Dandekar, N., Mysore, P., Littman, M.L.: Activity recognition from accelerometer data. In: AAAI, pp. 1541–1546 (2005)Google Scholar
- 11.Bao, L., Intille, S.S.: Activity recognition from user-annotated acceleration data. In: Pervasive, vol. 3001, pp. 1–17 (2004)Google Scholar
- 12.Bedogni, L., Di Felice, M., Bononi, L.: By train or by car? Detecting the user’s motion type through smartphone sensors data. In: 2012 IFIP Wireless Days, Dublin, pp. 1–6 (2012). https://doi.org/10.1109/WD.2012.6402818
- 13.Keally, M., Zhou, G., Xing, G., Wu, J., Pyles, A.: PBN: towards practical activity recognition using smartphone-based body sensor networks. In: Proceedings of the 9th ACM Conference on Embedded Networked Sensor Systems, Seattle, Washington, pp. 246–259 (2011)Google Scholar
- 14.Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system, CoRR, vol. abs/1603.02754 (2016)Google Scholar