A Comparative Study of the Effect of Sensor Noise on Activity Recognition Models
To provide a better understanding of the relative strengths of Machine Learning based Activity Recognition methods, in this paper we present a comparative analysis of the robustness of three popular methods with respect to sensor noise. Specifically we evaluate the robustness of Naive Bayes classifier, Support Vector Machine, and Random Forest based activity recognition models in three cases which span sensor errors from dead to poorly calibrated sensors. Test data is partially synthesized from a recently annotated activity recognition corpus which includes both interleaved activities and a range of both temporally long and short activities. Results demonstrate that the relative performance of Support Vector Machine classifiers over Naive Bayes classifiers reduces in noisy sensor conditions, but that overall the Random Forest classifier provides best activity recognition accuracy across all noise conditions synthesized in the corpus. Moreover, we find that activity recognition is equally robust across classification techniques with the relative performance of all models holding up under almost all sensor noise conditions considered.
KeywordsActivity Recognition Sensor Noise Support Vector Machines Naive Bayes Random Forests
Unable to display preview. Download preview PDF.
- 1.Geib, C.W., Steedman, M.: On natural language processing and plan recognition. In: International Joint Conference on Artificial Intelligence (2007)Google Scholar
- 4.Bui, H.: A general model for online probabilistic plan recognition. In: Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 1309–1315 (2003)Google Scholar
- 5.Singla, G., Cook, D., Schmitter-Edgecombe, M.: Tracking activities in complex settings using smart environment technologies. International Journal of BioSciences, Psychiatry and Technology 1, 25–35 (2009)Google Scholar
- 9.Pynadath, D.V., Wellman, M.P.: Accounting for context in plan recognition, with application to traffic monitoring. In: Besnard, P., Hanks, S. (eds.) Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence (UAI 1995), pp. 472–481. Morgan Kaufmann Publishers, San Francisco (1995)Google Scholar
- 10.Krishnan, N., Cook, D.: Activity recognition on streaming sensor data. In: Pervasive and Mobile Computing (2012)Google Scholar
- 11.Ross, R., Kelleher, J.D.: Accuracy and timeliness in ml based activity recognition. In: Proceedings of AAAI Workshop on Plan, Activity, and Intent Recognition 2013 (PAIR 2013), Seattle, USA (2013)Google Scholar
- 13.Das, B., Cook, D.: Data mining challenges in automated prompting systems. In: Workshop on Interacting with Smart Objects (2011)Google Scholar
- 16.Kipp, M.: ANVIL - A generic annotation tool for multimodal dialogue. In: Dalsgaard, P., Lindberg, B., Benner, H., Tan, Z.H. (eds.) INTERSPEECH, ISCA, pp. 1367–1370 (2001)Google Scholar