Position independent activity recognition using shallow neural architecture and empirical modeling

ABSTRACT

The goal of the SHL recognition challenge 2019 is to recognize transportation modalities in a sensor placement independent manner. In this paper, the performance of shallow neural networks is benchmarked by Team Orion in such a manner on the dataset provided in the challenge, using 156 handcrafted temporal and spectral features per sensor through the application of parallel processing and out-of-memory architecture. Using scaled conjugate gradient back-propagation (SCGB) algorithm, combining classes 7 and 8 and taking 5000 frames of bag-hips-torso data from validation set, classification accuracy of 87.2% was obtained on the validation dataset of the same labels for a shallow two-layer feed-forward network. 71% accuracy was obtained on the validation set of classes 7 and 8 via transfer of 2500 frames using another shallow neural network of similar architecture. Using empirically observed variable based transfer of 7088 frames from hand validation data to training dataset, 77.5% accuracy was obtained on hand validation data for classes 1 to 7/8, and 70% classification accuracy of classes 7 and 8 via transfer of 1809 frames from hand validation data. The results illustrate how carefully crafted features coupled with empirical transfer of labeled knowledge and combination of problematic classes can tune a neural classifier to work in a new feature space.

References

1. S. S. Saha, S. Rahman, M. J. Rasna, T. B. Zahid, A. K. M. M. Islam and M. A. R. Ahad, Feature Extraction, Performance Analysis and System Design Using the DU Mobility Dataset, in IEEE Access, vol. 6, pp. 44776--44786, 2018.
2. M. A. R. Ahad (2011). Computer Vision and Action Recognition: A Guide for Image Processing and Computer Vision Community for Action Understanding. (Vol 5), Springer Science & Business Media.
3. M. A. R. Ahad (2012). Motion History Images for Action Recognition and Understanding. Springer Science & Business Media.
4. M. A. R. Ahad, A. D. Antar and M. Ahmed, IoT Sensor-Based Activity Recognition - Human Activity Recognition, Springer Nature Switzerland AG {in press}, 2019.
5. R. Yang, and B. Wang. PACP: A Position-Independent Activity Recognition Method using Smartphone Sensors. Information 7.4 (2016): 72.
6. K. Pasupa and W. Sunhem, A Comparison Between Shallow and Deep Architecture Classifiers on Small Dataset, 2016 8th International Conference on Information Technology and Electrical Engineering (ICITEE), Yogyakarta, 2016, pp. 1--6.
7. S. S. Saha, S. Rahman, M. J. Rasna, T. Hossain, S. Inoue and M. A. R. Ahad, 2018. Supervised and Neural Classifiers for Locomotion Analysis. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp '18). ACM, New York, NY, USA, 1563--1570.
8. L. Wang, H. Gjoreski, K. Murao, T. Okita and D. Roggen, 2018. Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp '18). ACM, New York, NY, USA, 1521--1530.
9. S. J. Pan and Q. Yang, A Survey on Transfer Learning, in IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 10, pp. 1345--1359, Oct. 2010.
10. H. Gjoreski, M. Ciliberto, L. Wang, F.J.O. Morales, S. Mekki, S. Valentin, and D. Roggen, The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics with Mobile Devices, IEEE Access 6 (2018): 42592--42604.
11. L. Wang, H. Gjoreski, M. Ciliberto, S. Mekki, S. Valentin and D. Roggen, Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset, in IEEE Access, vol. 7, pp. 10870--10891, 2019.
12. M. Paluszek and S. Thomas. Representation of Data for Machine Learning in MATLAB. MATLAB Machine Learning. Apress, Berkeley, CA, 2017. 35--48.
13. M.F. Moller. A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning. Neural Networks 6.4 (1993): 525--533.
14. S. Inoue and X. Pan. 2016. Supervised and Unsupervised Transfer Learning for Activity Recognition from Simple In-home Sensors. In Proceedings of the 13th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MOBIQUITOUS 2016). ACM, New York, NY, USA, 20--27.
15. J. Wang, Y. Chen, L. Hu, X. Peng and P. S. Yu, Stratified Transfer Learning for Cross-domain Activity Recognition, 2018 IEEE International Conference on Pervasive Computing and Communications (PerCom), Athens, 2018, pp. 1--10.
16. D. H. Hu, V. W. Zheng and Q.Yang. Cross-domain Activity Recognition via Transfer Learning. Pervasive and Mobile Computing 7.3 (2011): 344--358.
17. P. Rashidi, and D. J. Cook. Multi Home Transfer Learning for Resident Activity Discovery and Recognition. KDD Knowledge Discovery from Sensor Data (2010): 56--63.
18. V. W. Zheng, D. H. Hu and Q. Yang. 2009. Cross-domain Activity Recognition. In Proceedings of the 11th international conference on Ubiquitous computing (UbiComp '09). ACM, New York, NY, USA, 61--70.
19. T. Diethe, N. Twomey and P. Flach (2016), Active Transfer Learning for Activity Recognition, European Symposium on Artificial Neural Networks, Bruges, UK.
20. U. Blanke and B. Schiele, Remember and Transfer What You Have Learned - Recognizing Composite Activities Based on Activity Spotting, International Symposium on Wearable Computers (ISWC) 2010, Seoul, 2010, pp. 1--8.
21. D. Roggen, K. Forster, A. Calatroni, and G. Troster. The Adarc Pattern Analysis Architecture for Adaptive Human Activity Recognition Systems. Journal of Ambient Intelligence and Humanized Computing 4.2 (2013): 169--186.
22. V. Janko, N. Rescic, M. Mlakar, V. Drobnic, M. Gams, G. Slapnicar, M. Gjoreski, J. Bizjak, M. Marinko, and M. Lustrek. 2018. A New Frontier for Activity Recognition: The Sussex-Huawei Locomotion Challenge. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp '18). ACM, New York, NY, USA, 1511--1520.
23. A. D. Antar, M. Ahmed, M. S. Ishrak, and M. A. R. Ahad. 2018. A Comparative Approach to Classification of Locomotion and Transportation Modes Using Smartphone Sensor Data. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (UbiComp '18). ACM, New York, NY, USA, 1497--1502
24. L. Wang, H. Gjoreski, M. Ciliberto, P. Lago, K. Murao, T. Okita, and D. Roggen, Summary of the Sussex-Huawei Locomotion-Transportation Recognition Challenge 2019, Proc. HASCA 2019.

Index Terms

• Human-centered computing

  • Ubiquitous and mobile computing