Abstract
The Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge considers the problem of human activity recognition from inertial sensor data collected at 100 Hz from an Android smartphone. We propose a data analysis pipeline that contains three stages: a pre-processing stage, a classification stage, and a time stabilization stage. We find that performing classification on “raw” data features (i.e. without feature extraction) over extremely short time windows (e.g. 0.1 s of data) and then stabilizing the activity predictions over longer time windows (e.g. 15 s) results in much higher accuracy than directly performing classification on the longer windows when evaluated on a 10% hold-out sample of the training data. However, this finding does not hold on the competition test data, where we find that accuracy drops with decreasing window size. Our submitted model uses a random forest classifier and attains a mean F1 score over all activities of about 0.97 on the hold-out sample, but only about 0.54 on the competition test data, indicating that our model does not generalize well despite the use of a hold-out sample to prevent test set leakage.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
F1 scores for the hold-out set may not match results in Sect. 14.5.1 exactly due to a different 80/20 random stratified split being used.
References
Bao L, Intille SS (2004) Activity recognition from user-annotated acceleration data. In: Proceedings of the 2nd international conference on pervasive computing, pp 1–17
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Chollet F et al (2015) Keras. https://keras.io
Choudhury T, Borriello G, Consolvo S, Haehnel D, Harrison B, Hemingway B, Hightower J, Klasnja P, Koscher K, LaMarca A, Landay JA, LeGrand L, Lester J, Rahimi A, Rea A, Wyatt D (2008) The mobile sensing platform: an embedded activity recognition system. IEEE Pervasive Comput 7(2):32–41
Gjoreski H, Ciliberto M, Wang L, Morales FJO, Mekki S, Valentin S, Roggen D (2018) The University of Sussex-Huawei locomotion and transportation dataset for multimodal analytics with mobile devices. IEEE Access 6:42592–42604
Hammerla NY, Halloran S, Plötz T (2016) Deep, convolutional, and recurrent models for human activity recognition using wearables. In: Proceedings of the 25th international joint conference on artificial intelligence, pp 1533–1540
Hammerla NY, Plötz T (2015) Let’s (not) stick together: pairwise similarity biases cross-validation in activity recognition. In: Proceedings of the ACM international joint conference on pervasive and ubiquitous computing, pp 1041–1051
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Lara OD, Labrador MA (2013) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 15:1192–1209
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Ravi N, Dandekar N, Mysore P, Littman ML (2005) Activity recognition from accelerometer data. In: Proceedings of the 17th conference on innovative applications of artificial intelligence, pp 1541–1546
Sloma M, Arastuie M, Xu KS (2018) Activity recognition by classification with time stabilization for the SHL recognition challenge. In: Proceedings of the ACM international joint conference on pervasive and ubiquitous computing adjunct, pp 1616–1625
Wang L, Gjoreskia H, Murao K, Okita T, Roggen D (2018) Summary of the Sussex-Huawei locomotion-transportation recognition challenge. In: Proceedings of the ACM international joint conference on pervasive and ubiquitous computing adjunct. ACM, pp 1521–1530
Widhalm P, Leodolter M, Brändle N (2018) Top in the lab, flop in the field?: evaluation of a sensor-based travel activity classifier with the SHL dataset. In: Proceedings of the ACM international joint conference on pervasive and ubiquitous computing adjunct. ACM, pp 1479–1487
Acknowledgements
We would like to thank the University of Toledo’s Office of Undergraduate Research for providing funding for Michael Sloma through the Undergraduate Summer Research and Creative Activities Program (USRCAP).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Sloma, M., Arastuie, M., Xu, K.S. (2019). Effects of Activity Recognition Window Size and Time Stabilization in the SHL Recognition Challenge. In: Kawaguchi, N., Nishio, N., Roggen, D., Inoue, S., Pirttikangas, S., Van Laerhoven, K. (eds) Human Activity Sensing. Springer Series in Adaptive Environments. Springer, Cham. https://doi.org/10.1007/978-3-030-13001-5_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-13001-5_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-13000-8
Online ISBN: 978-3-030-13001-5
eBook Packages: Computer ScienceComputer Science (R0)