Inertial Sensor Based Modelling of Human Activity Classes: Feature Extraction and Multi-sensor Data Fusion Using Machine Learning Algorithms
- 1.9k Downloads
Wearable inertial sensors are currently receiving pronounced interest due to applications in unconstrained daily life settings, ambulatory monitoring and pervasive computing systems. This research focuses on human activity recognition problem, in which inputs are multichannel time series signals acquired from a set of body-worn inertial sensors and outputs are automatically classified human activities. A general-purpose framework has been presented for designing and evaluating activity recognition system with six different activities using machine learning algorithms such as support vector machine (SVM) and artificial neural networks (ANN). Several feature selection methods were explored to make the recognition process faster by experimenting on the features extracted from the accelerometer and gyroscope time series data collected from a number of volunteers. In addition, a detailed discussion is presented to explore how different design parameters, for example, the number of features and data fusion from multiple sensor locations - impact on overall recognition performance.
KeywordsInertial measurement unit Accelerometer data Feature extraction Data-fusion Machine learning algorithms Human Activity Recognition
Tahmina Zebin would like to thank the Presidents Doctoral Scholar award scheme, University of Manchester for funding her PhD.
- 2.Ugulino, W., Cardador, D., Vega, K., Velloso, E., Milidiú, R., Fuks, H.: Wearable computing: accelerometers’ data classification of body postures and movements. In: Barros, L.N., Finger, M., Pozo, A.T., Gimenénez-Lugo, G.A., Castilho, M. (eds.) SBIA 2012. LNCS, vol. 7589, pp. 52–61. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 7.Ronao, C.A., Sung-Bae, C.: Human activity recognition using smartphone sensors with two-stage continuous hidden Markov models. In: 10th International Conference on Natural Computation (ICNC-2014), pp. 681–686 (2014)Google Scholar
- 9.Fourati, H. (ed.): Multisensor Data Fusion: From Algorithms and Architectural Design to Applications, pp. 509–517. CRC Press, Taylor & Francis Group LLC, United States (2015)Google Scholar
- 11.Zeng, M., et al.: Convolutional neural networks for human activity recognition using mobile sensors. In: 6th International Conference on Mobile Computing, Applications and Services (MobiCASE) 2014, pp. 197–205 (2014)Google Scholar
- 12.Kaufman, K.R.: Future directions in gait analysis. In: RRDS Gait Analysis in the Science of Rehabilitation, pp. 85–112 (2011)Google Scholar
- 13.Classification learner app for supervised machine learning. http://uk.mathworks.com/help/stats/classificationlearner-app.html