Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 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

CLAN: A Contrastive Learning based Novelty Detection Framework for Human Activity Recognition (2401.10288v1)

Published 17 Jan 2024 in cs.LG and eess.SP

Abstract: In ambient assisted living, human activity recognition from time series sensor data mainly focuses on predefined activities, often overlooking new activity patterns. We propose CLAN, a two-tower contrastive learning-based novelty detection framework with diverse types of negative pairs for human activity recognition. It is tailored to challenges with human activity characteristics, including the significance of temporal and frequency features, complex activity dynamics, shared features across activities, and sensor modality variations. The framework aims to construct invariant representations of known activity robust to the challenges. To generate suitable negative pairs, it selects data augmentation methods according to the temporal and frequency characteristics of each dataset. It derives the key representations against meaningless dynamics by contrastive and classification losses-based representation learning and score function-based novelty detection that accommodate dynamic numbers of the different types of augmented samples. The proposed two-tower model extracts the representations in terms of time and frequency, mutually enhancing expressiveness for distinguishing between new and known activities, even when they share common features. Experiments on four real-world human activity datasets show that CLAN surpasses the best performance of existing novelty detection methods, improving by 8.3%, 13.7%, and 53.3% in AUROC, balanced accuracy, and [email protected] metrics respectively.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (87)
  1. 2022. U.S. Bureau of Labor Statistics. https://www.bls.gov/tus/ Accessed on September 15, 2023.
  2. A review of novelty detection. Signal processing 99 (2014), 215–249.
  3. Jake K. Aggarwal and Michael S. Ryoo. 2011. Human activity analysis: A review. Acm Computing Surveys (Csur) 43, 3 (2011), 1–43.
  4. Haldun Akoglu. 2018. User’s guide to correlation coefficients. Turkish journal of emergency medicine 18, 3 (2018), 91–93.
  5. ARAS human activity datasets in multiple homes with multiple residents. In 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops. 232–235.
  6. Arundo Analytics. 2020. tsaug: Python package for time series augmentation. https://tsaug.readthedocs.io/en/stable/ Accessed on September 15, 2023.
  7. Autoencoders. Machine Learning for Data Science Handbook: Data Mining and Knowledge Discovery Handbook (2023), 353–374.
  8. FewSOME: One-Class Few Shot Anomaly Detection With Siamese Networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2977–2986.
  9. Multioccupant activity recognition in pervasive smart home environments. ACM Computing Surveys (CSUR) 48, 3 (2015), 1–36.
  10. Liron Bergman and Yedid Hoshen. 2020. Classification-Based Anomaly Detection for General Data. In International Conference on Learning Representations.
  11. E. Oran Brigham. 1988. The fast Fourier transform and its applications. Prentice-Hall, Inc.
  12. Novelty detection via contrastive learning with negative data augmentation. arXiv:2106.09958 https://arxiv.org/abs/2106.09958
  13. Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities. ACM Computing Surveys (CSUR) 54, 4 (2021), 1–40.
  14. HMGAN: A Hierarchical Multi-Modal Generative Adversarial Network Model for Wearable Human Activity Recognition. In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 7. 1–27.
  15. A simple framework for contrastive learning of visual representations. In In International conference on machine learning. 1597–1607.
  16. Learning hierarchical time series data augmentation invariances via contrastive supervision for human activity recognition. Knowledge-Based Systems 276 (2023), 110789.
  17. Nuactiv: Recognizing unseen new activities using semantic attribute-based learning. In Proceeding of the 11th annual international conference on Mobile systems, applications, and services. 361–374.
  18. Ambient assisted living: a review of technologies, methodologies and future perspectives for healthy aging of population. Sensors 21, 10 (2021), 3549.
  19. Pearson correlation coefficient. Noise reduction in speech processing (2009), 1–4.
  20. Anomaly detection for IoT time-series data: A survey. IEEE Internet of Things Journal 7, 7 (2019), 6481–6494.
  21. Sensor-based and vision-based human activity recognition: A comprehensive survey. Pattern Recognition 108 (2020), 107561.
  22. Cocoa: Cross modality contrastive learning for sensor data. In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 6. 1–28.
  23. Van der Maaten Laurens and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).
  24. Time-series representation learning via temporal and contextual contrasting. arXiv:2106.14112 https://arxiv.org/abs/2106.14112
  25. Eleazar Eskin. 2000. Anomaly Detection over Noisy Data Using Learned Probability Distributions. In Proceedings of the Seventeenth International Conference on Machine Learning. 255–262.
  26. Ehab Essa and Islam R. Abdelmaksoud. 2023. Temporal-channel convolution with self-attention network for human activity recognition using wearable sensors. Knowledge-Based Systems 278 (2023), 110867.
  27. Human activity recognition and pattern discovery. IEEE pervasive computing 9, 1 (2009), 48–53.
  28. Donelson R Forsyth. 2018. Group dynamics. Cengage Learning, USA.
  29. Contributions of shape, texture, and color in visual recognition. In European Conference on Computer Vision. 369–386.
  30. Novelty detection: A perspective from natural language processing. Computational Linguistics 48, 1 (2022), 77–117.
  31. Generative adversarial networks. Commun. ACM 63, 11 (2020), 139–144.
  32. Robert M. Gray and David L. Neuhoff. 1998. Quantization. IEEE transactions on information theory 44, 6 (1998), 2325–2383.
  33. The elements of statistical learning: data mining, inference, and prediction. Vol. 2. New York: Springer.
  34. He, Kaiming and Xiangyu Zhang and Shaoqing Ren and Jian Sun 2016. Deep residual learning for image recognition.
  35. Christopher E. Heil and David F. Walnut. 1989. Continuous and discrete wavelet transforms. SIAM review 31, 4 (1989), 628–666.
  36. Using self-supervised learning can improve model robustness and uncertainty. In Advances in neural information processing systems, Vol. 32.
  37. Active learning enabled activity recognition. Pervasive and Mobile Computing 38 (2017), 312–330.
  38. Collossl: Collaborative self-supervised learning for human activity recognition. In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Vol. 6. 1–28.
  39. A survey on contrastive self-supervised learning. Technologies 9, 1 (2020), 2.
  40. One-class learned encoder-decoder network with adversarial context masking for novelty detection. In Proceedings of the IEEE/CVF winter conference on applications of computer vision. 3591–3601.
  41. Human activity recognition: A survey. Procedia Computer Science 155 (2019), 698–703.
  42. A smart, efficient, and reliable parking surveillance system with edge artificial intelligence on IoT devices. IEEE Transactions on Intelligent Transportation Systems 22, 8 (2020), 4962–4974.
  43. Hyunju Kim and Dongman Lee. 2021a. Adela: attention based deep ensemble learning for activity recognition in smart collaborative environments. In Proceedings of the 36th Annual ACM Symposium on Applied Computing. 436–444.
  44. Hyunju Kim and Dongman Lee. 2021b. AR-T: Temporal Relation Embedded Transformer for the Real World Activity Recognition. In In International Conference on Mobile and Ubiquitous Systems: Computing, Networking, and Services. 617–633.
  45. A review of machine learning-based human activity recognition for diverse applications. Neural Computing and Applications 34, 21 (2022), 18289–18324.
  46. A Survey on Out-of-Distribution Detection in NLP. arXiv:2305.03236 https://arxiv.org/abs/2305.03236
  47. Two-stream convolution augmented transformer for human activity recognition. In In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 286–293.
  48. Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 3220–3230.
  49. AttnSense: Multi-level attention mechanism for multimodal human activity recognition. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 3109–3115.
  50. Henrik Madsen. 2007. Time series analysis. CRC Press.
  51. Daisuke Nakai Kazuya Ohara Maekawa, Takuya and Yasuo Namioka. 2016. Toward practical factory activity recognition: unsupervised understanding of repetitive assembly work in a factory. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing. 1088–1099.
  52. A review of internet of things technologies for ambient assisted living environments. Future Internet 11, 12 (2019), 259.
  53. Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2809–2818.
  54. CNN-based sensor fusion techniques for multimodal human activity recognition. In Proceedings of the 2017 ACM international symposium on wearable computers. 158–165.
  55. Henri J. Nussbaumer. 1982. The fast Fourier transform. Springer Berlin Heidelberg.
  56. Deep learning for anomaly detection: A review. ACM computing surveys (CSUR) 54, 2 (2021), 1–38.
  57. Aroma: A deep multi-task learning based simple and complex human activity recognition method using wearable sensors. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2, 2, 1–16.
  58. Ocgan: One-class novelty detection using gans with constrained latent representations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2898–2906.
  59. John G Proakis. 2007. Digital signal processing: principles, algorithms, and applications. Pearson Education India.
  60. Federated learning for secure IoMT-applications in smart healthcare systems: A comprehensive review. Knowledge-Based Systems (2023), 110658.
  61. Collecting complex activity datasets in highly rich networked sensor environments. In Seventh International Conference on Networked Sensing Systems. 233–240.
  62. Deep one-class classification. In International conference on machine learning. 4393–4402.
  63. Mayu Sakurada and Takehisa Yairi. 2014’. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd workshop on machine learning for sensory data analysis. 4–11.
  64. Arae: Adversarially robust training of autoencoders improves novelty detection. Neural Networks 144 (2021), 726–736.
  65. A unified survey on anomaly, novelty, open-set, and out-of-distribution detection: Solutions and future challenges. arXiv:2110.14051 https://arxiv.org/abs/2110.14051
  66. Support vector method for novelty detection. In Advances in neural information processing systems, Vol. 12.
  67. A three-way clustering approach for novelty detection. Information Sciences 569 (2021), 650–668.
  68. Jeffrey S Simonoff. 2012. Smoothing methods in statistics. Springer Science & Business Media.
  69. Recognizing independent and joint activities among multiple residents in smart environments. Journal of ambient intelligence and humanized computing 1 (2010), 57–63.
  70. Human activity recognition using inertial sensors in a smartphone: An overview. Sensors 19, 14 (2019), 3213.
  71. TASKED: Transformer-based Adversarial learning for human activity recognition using wearable sensors via Self-KnowledgE Distillation. Knowledge-Based Systems 260 (2023), 110143.
  72. Csi: Novelty detection via contrastive learning on distributionally shifted instances. In Advances in neural information processing systems, Vol. 33. 11839–11852.
  73. Hyperparameter-free out-of-distribution detection using cosine similarity. In Proceedings of the Asian conference on computer vision.
  74. Attention is all you need. Advances in neural information processing systems 30.
  75. Feng Wang and Huaping Liu. 2021. Understanding the behaviour of contrastive loss. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2495–2504.
  76. Deep learning for sensor-based activity recognition: A survey. Pattern recognition letters 119 (2019), 3–11.
  77. Deep Contrastive One-Class Time Series Anomaly Detection. In Proceedings of the 2023 SIAM International Conference on Data Mining (SDM). 694–702.
  78. Transformers in time series: A survey. arXiv:2202.07125 https://arxiv.org/abs/2202.07125
  79. Unsupervised feature learning via non-parametric instance discrimination. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3733–3742.
  80. A consensus novelty detection ensemble approach for anomaly detection in activities of daily living. Applied Soft Computing 83 (2019), 105613.
  81. Generalized out-of-distribution detection: A survey. arXiv:2110.11334 https://arxiv.org/abs/2110.11334
  82. Full-spectrum out-of-distribution detection. (2023), 1–16.
  83. A transformer-based framework for multivariate time series representation learning. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining. 2114–2124.
  84. TFAD: A decomposition time series anomaly detection architecture with time-frequency analysis. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management. 2497–2507.
  85. Self-supervised contrastive pre-training for time series via time-frequency consistency.. In Advances in Neural Information Processing Systems, Vol. 35. 3988–4003.
  86. Deep residual bidir-LSTM for human activity recognition using wearable sensors. Mathematical Problems in Engineering (2018), 1–13.
  87. Adaptive preference transfer for personalized IoT entity recommendation. Pattern Recognition Letters 162 (2022), 40–46.

Summary

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

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

Tweets