Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Generative Domain Adaptation with Temporal Relation Knowledge for Cross-User Activity Recognition (2403.14682v1)

Published 12 Mar 2024 in cs.CV, cs.AI, cs.HC, and cs.LG

Abstract: In human activity recognition (HAR), the assumption that training and testing data are independent and identically distributed (i.i.d.) often fails, particularly in cross-user scenarios where data distributions vary significantly. This discrepancy highlights the limitations of conventional domain adaptation methods in HAR, which typically overlook the inherent temporal relations in time-series data. To bridge this gap, our study introduces a Conditional Variational Autoencoder with Universal Sequence Mapping (CVAE-USM) approach, which addresses the unique challenges of time-series domain adaptation in HAR by relaxing the i.i.d. assumption and leveraging temporal relations to align data distributions effectively across different users. This method combines the strengths of Variational Autoencoder (VAE) and Universal Sequence Mapping (USM) to capture and utilize common temporal patterns between users for improved activity recognition. Our results, evaluated on two public HAR datasets (OPPT and PAMAP2), demonstrate that CVAE-USM outperforms existing state-of-the-art methods, offering a more accurate and generalizable solution for cross-user activity recognition.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Activity recognition with evolving data streams: A review. ACM Computing Surveys (CSUR), 51(4):1–36, 2018.
  2. Universal sequence map (usm) of arbitrary discrete sequences. BMC bioinformatics, 3:1–11, 2002.
  3. Detection of eating and drinking arm gestures using inertial body-worn sensors. In Ninth IEEE international symposium on wearable computers (ISWC’05), pages 160–163. IEEE, 2005.
  4. A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR), 46(3):33, 2014.
  5. Multimodal recognition of reading activity in transit using body-worn sensors. ACM Transactions on Applied Perception (TAP), 9(1):1–21, 2012.
  6. The opportunity challenge: A benchmark database for on-body sensor-based activity recognition. Pattern Recognition Letters, 34(15):2033–2042, 2013.
  7. Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities. ACM Computing Surveys (CSUR), 54(4):1–40, 2021.
  8. Unsupervised visual domain adaptation using subspace alignment. In Proceedings of the IEEE international conference on computer vision, pages 2960–2967, 2013.
  9. Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell, 1:1–40, 2016.
  10. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016.
  11. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014.
  12. Non-intrusive human activity recognition and abnormal behavior detection on elderly people: A review. Artificial Intelligence Review, 53(3):1975–2021, 2020.
  13. Simultaneous semantic alignment network for heterogeneous domain adaptation. In Proceedings of the 28th ACM international conference on multimedia, pages 3866–3874, 2020.
  14. Learning under concept drift: A review. IEEE transactions on knowledge and data engineering, 31(12):2346–2363, 2018.
  15. Cross-domain activity recognition via substructural optimal transport. Neurocomputing, 454:65–75, 2021.
  16. Attnsense: Multi-level attention mechanism for multimodal human activity recognition. In IJCAI, pages 3109–3115, 2019.
  17. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009.
  18. Visual domain adaptation: A survey of recent advances. IEEE signal processing magazine, 32(3):53–69, 2015.
  19. A novel distribution-embedded neural network for sensor-based activity recognition. In IJCAI, volume 2019, pages 5614–5620, 2019.
  20. Introducing a new benchmarked dataset for activity monitoring. In 2012 16th international symposium on wearable computers, pages 108–109. IEEE, 2012.
  21. Autonomous training of activity recognition algorithms in mobile sensors: A transfer learning approach in context-invariant views. IEEE Transactions on Mobile Computing, 17(8):1764–1777, 2018.
  22. Personalized human activity recognition using convolutional neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  23. An introduction to deep generative modeling. GAMM-Mitteilungen, 44(2):e202100008, 2021.
  24. Simple and effective vae training with calibrated decoders. In International Conference on Machine Learning, pages 9179–9189. PMLR, 2021.
  25. Ensemble learning for human activity recognition. In Adjunct proceedings of the 2020 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2020 ACM international symposium on wearable computers, pages 335–339, 2020.
  26. Federated multi-task attention for cross-individual human activity recognition. In IJCAI, pages 3423–3429. IJCAI, 2022.
  27. Cross-subject transfer learning in human activity recognition systems using generative adversarial networks. Neurocomputing, 426:26–34, 2021.
  28. Supervised heterogeneous feature transfer via random forests. Artificial Intelligence, 268:30–53, 2019.
  29. Return of frustratingly easy domain adaptation. In Proceedings of the AAAI conference on artificial intelligence, volume 30, 2016.
  30. An activity monitoring system for elderly care using generative and discriminative models. Personal and ubiquitous computing, 14:489–498, 2010.
  31. Impact of sliding window length in indoor human motion modes and pose pattern recognition based on smartphone sensors. Sensors, 18(6):1965, 2018.
  32. A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11(5):1–46, 2020.
  33. Domain-attention conditional wasserstein distance for multi-source domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11(4):1–19, 2020.
  34. Enabling edge devices that learn from each other: Cross modal training for activity recognition. In Proceedings of the 1st International Workshop on Edge Systems, Analytics and Networking, pages 37–42, 2018.
  35. Xiaozhou Ye and Kevin I-Kai Wang. Cross-user activity recognition via temporal relation optimal transport. In International Conference on Mobile and Ubiquitous Systems: Computing, Networking, and Services, 2023.
  36. Gaussian mixture model clustering with incomplete data. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 17(1s):1–14, 2021.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now