Exploring the parameter space of human activity recognition with mobile devices

Motion sensors available on smart phones make it possible to recognize human activities. Accelerometer, gyroscope, magnetometer, and their various combinations are used to classify, particularly, locomotion activities, ranging from walking to biking. In most of the studies, the focus is on the collection of data and on the analysis of the impact of different parameters on the recognition performance. The parameter space includes the types of sensors used, features, classification algorithms, and position/orientation of the mobile device. In most of the studies, the impact of some of these parameters is partially analyzed; however, in this work, we investigate the parameter space in detail with a global focus. Particularly, we investigate the impact of using different feature-sets, the impact of using different sensors individually and in combination, the impact of different classifiers, and the impact of phone position. Using an ANOVA analysis, we investigate the importance of various parameters on the recognition performance. We show that these parameters are ranked according to their impact on the recognition performance in the following order: sensor, position, classifier, feature. We believe that such an analysis is important since we can statistically show how much a parameter is affecting the recognition performance. Our observations can be used in future studies by only focusing on the important parameters. We present our findings as a discussion to guide the further studies in this domain.

PDF

___

[1] Shoaib M, Bosch S, Incel OD, Scholten H, Havinga P. A survey of online activity recognition using mobile phones. Sensors 2015; 15 (1): 2059-2085. doi: 10.3390/s150102059
[2] Shoaib M, Bosch S, Incel OD, Scholten H, Havinga P. Fusion of smartphone motion sensors for physical activity recognition. Sensors 2014; 14 (6): 10146-10176. doi: 10.3390/s140610146
3] Plötz T, Hammerla NY, Olivier PL. Feature learning for activity recognition in ubiquitous computing. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence; Barcelona, Catalonia, Spain; 2011. pp. 1729-1734.
[4] Niazi AHK. A study in human activity recognition. PhD, University of Georgia. Athens, GA, USA, 2016.
[5] Bulling A, Blanke U, Schiele B. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR) 2014; 46 (3): 33. doi: 10.1145/2499621
[6] Gjoreski H, Lustrek M, Gams M. Accelerometer placement for posture recognition and fall detection. In: Intelligent Environments (IE), 7th International Conference on Intelligent Environments; Nottingham, United Kingdom; 2011. pp. 47-54.
[7] Altun K, Barshan B. Human activity recognition using inertial/magnetic sensor units. In: International Workshop on Human Behavior Understanding; Berlin, Heidelberg, Germany; 2010. pp. 38-51.
[8] Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL. Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine. In: International Workshop on Ambient Assisted Living; Berlin, Heidelberg, Germany; 2012. pp. 216-223.
[9] Su L, Zhang D, Li B, Guo B, Li S. Activity recognition on an accelerometer embedded mobile phone with varying positions and orientations. In: International Conference on Ubiquitous Intelligence and Computing; Berlin, Heidelberg, Germany; 2010. pp. 548-562.
[10] Susi M, Renaudin V, Lachapelle G. Motion mode recognition and step detection algorithms for mobile phone users. Sensors 2013; 13 (3): 1539-1562. doi: 10.3390/s130201539
[11] Anjum A, Ilyas MU. Activity recognition using smartphone sensors. In: IEEE 10th Consumer Communications and Networking Conference (CCNC); Las Vegas, NV, USA; 2013. pp. 914-919.
[12] Wu W, Dasgupta S, Ramirez E et al. Classification accuracies of physical activities using smartphone motion sensors. Journal of Medical Internet Research 2012; 14 (5): e130. doi: 10.2196/jmir.2208
[13] Martín H, Bernardos Ana M, Iglesias J, Casar José R. Activity logging using lightweight classification techniques in mobile devices. Personal and Ubiquitous Computing 2013; 17 (4): 675-695. doi: 10.1007/s00779-012-0515-4
[14] Zhang L, Suganthan P. Benchmarking ensemble classifiers with novel co-trained kernal ridge regression and random vector functional link ensembles [Research Frontier]. IEEE Computational Intelligence Magazine 2017; 12 (4): 61-72. doi: 10.1109/MCI.2017.2742867
[15] Liu L, Wang S, Su G, Huang ZG, Liu M. Towards complex activity recognition using a Bayesian network-based probabilistic generative framework. Pattern Recognition 2017; 68: 295-309. doi: 10.1016/j.patcog.2017.02.028
[16] Oniga S, Suto J. Human activity recognition using neural networks. In: Proceedings of the 2014 15th International Carpathian Control Conference (ICCC); Velke Karlovice, Czech Republic; 2014. pp. 403-406.
[17] Ordóñez FJ, Roggen D. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 2016; 16 (1): 115. doi: 10.3390/s16010115
[18] Preece SJ, Goulermas JY, Kenney LPJ, Howard D. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Transactions on Biomedical Engineering; 56 (3): 871-879. doi: 10.1109/TBME.2008.2006190
[19] Shoaib M. Sitting is the new smoking: online complex human activity recognition with smartphones and wearables. PhD, University of Twente. Enschede, Netherlands, 2017.
[20] Dehghani A, Sarbishei O, Glatard T, Shihab E. A quantitative comparison of overlapping and non-overlapping sliding windows for human activity recognition using inertial sensors. Sensors 2019; 19 (22): 5026. doi: 10.3390/s19225026
[21] Chen Z, Zhu Q, Yeng CS, Zhang L. Robust human activity recognition using smartphone sensors via CT-PCA and online SVM. IEEE Transactions on Industrial Informatics 2017; 13 (6): 3070-3080. doi: 10.1109/TII.2017.2712746
22] Coskun D, Incel OD, Ozgovde A. Phone position/placement detection using accelerometer: Impact on activity recognition. In: Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2015 IEEE Tenth International Conference; Singapore; 2015. pp. 1-6.
[23] Figo D, Diniz PC, Ferreira DR, Cardoso JMP. Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing 2010; 14 (7): 645-662. doi: 10.1007/s00779-010-0293-9
[24] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research 2011; 12: 2825-2830.
[25] Shoaib M, Incel OD, Scholten H, Havinga P. Resource consumption analysis of online activity recognition on mobile phones and smartwatches. In: 36th IEEE International Performance Computing and Communication Conference; New York, USA; 2017. pp.1-20.
[26] Saylam B. A detailed analysis of human activity recognition using smartphone motion sensors. MSc, Galatasaray University, İstanbul, Turkey, 2017.