BIMO: Bootstrap Inter–Intra Modality at Once Unsupervised Learning for Multivariate Time Series
Source abstract
Abstract
It is difficult to learn meaningful representations of time-series data since they are sparsely labeled and unpredictable. Hence, we propose bootstrap inter–intra modality at once (BIMO), an unsupervised representation learning method based on time series. Unlike previous works, the proposed BIMO method learns both inter-sample and intra-temporal modality representations simultaneously without negative pairs. BIMO comprises a main network and two auxiliary networks, namely inter-auxiliary and intra-auxiliary networks. The main network is trained to learn inter–intra modality representations sequentially by regulating the use of each auxiliary network dynamically. Thus, BIMO thoroughly learns inter–intra modality representations simultaneously. The experimental results demonstrate that the proposed BIMO method outperforms the state-of-the-art unsupervised methods and achieves comparable performance to existing supervised methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Time Series Analysis and Forecasting · Anomaly Detection Techniques and Applications · Music and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Computer Science, Kookmin University, Seoul 02707, Republic of Korea
Funding
National Research Foundation (NRF) · Korea government(MSIT)
References (44)
Show source-provided references
1. Signal processing and machine learning for mental health research and clinical applications [perspectives]10.1109/MSP.2017.2718581 ↗
2. A machine learning approach to predict metabolic pathway dynamics from time-series multiomics data10.1038/s41540-018-0054-3 ↗
3. Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model10.1016/j.ins.2019.01.076 ↗
4. Stress Detection With Single PPG Sensor by Orchestrating Multiple Denoising and Peak-Detecting Methods10.1109/ACCESS.2021.3060441 ↗
5. Wang, Z., Yan, W., and Oates, T. (2017, January 14–19). Time series classification from scratch with deep neural networks: A strong baseline. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.10.1109/IJCNN.2017.7966039 ↗
6. Deep learning for time series classification: A review10.1007/s10618-019-00619-1 ↗
7. Inceptiontime: Finding alexnet for time series classification10.1007/s10618-020-00710-y ↗
8. ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels10.1007/s10618-020-00701-z ↗
9. Kim, I., Kim, D., Kwon, S., Lee, S., and Lee, J. (2022, January 21–25). Fall detection using biometric information based on multi-horizon forecasting. Proceedings of the 2022 26th International Conference on Pattern Recognition (ICPR), Montreal, QC, Canada.10.1109/ICPR56361.2022.9956568 ↗
10. Human Activity Recognition via Temporal Fusion Contrastive Learning10.1109/ACCESS.2024.3357143 ↗
11. He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13–19). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00975 ↗
12. Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13–18). A simple framework for contrastive learning of visual representations. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.
13. Chen, T., Kornblith, S., Swersky, K., Norouzi, M., and Hinton, G. (2020). Big self-supervised models are strong semi-supervised learners. arXiv.
14. Chen, X., Fan, H., Girshick, R., and He, K. (2020). Improved baselines with momentum contrastive learning. arXiv.
15. Grill, J.B., Strub, F., Altché, F., Tallec, C., Richemond, P.H., Buchatskaya, E., Doersch, C., Pires, B.A., Guo, Z.D., and Azar, M.G. (2020). Bootstrap your own latent: A new approach to self-supervised learning. arXiv.
16. Kim, D., Yoo, Y., Park, S., Kim, J., and Lee, J. (2021, January 11–17). Selfreg: Self-supervised contrastive regularization for domain generalization. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00948 ↗
17. Inter-domain curriculum learning for domain generalization10.1016/j.icte.2021.11.009 ↗
18. Chen, X., and He, K. (2021, January 20–25). Exploring simple siamese representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.01549 ↗
19. Tsay, R.S. (2005). Analysis of Financial Time Series, John Wiley & Sons.10.1002/0471746193 ↗
20. Cowpertwait, P.S., and Metcalfe, A.V. (2009). Introductory Time Series with R, Springer Science & Business Media.10.1007/978-0-387-88698-5_1 ↗
21. Pascual, S., Ravanelli, M., Serra, J., Bonafonte, A., and Bengio, Y. (2019). Learning problem-agnostic speech representations from multiple self-supervised tasks. arXiv.10.21437/Interspeech.2019-2605 ↗
22. Sarkar, P., and Etemad, A. (2020, January 4–8). Self-supervised learning for ecg-based emotion recognition. Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9053985 ↗
23. Franceschi, J.Y., Dieuleveut, A., and Jaggi, M. (2019). Unsupervised scalable representation learning for multivariate time series. arXiv.
24. Schneider, S., Baevski, A., Collobert, R., and Auli, M. (2019). wav2vec: Unsupervised pre-training for speech recognition. arXiv.10.21437/Interspeech.2019-1873 ↗
25. The UCR time series archive10.1109/JAS.2019.1911747 ↗
26. Bagnall, A., Dau, H.A., Lines, J., Flynn, M., Large, J., Bostrom, A., Southam, P., and Keogh, E. (2018). The UEA multivariate time series classification archive, 2018. arXiv.
27. Fan, H., Zhang, F., and Gao, Y. (2020). Self-Supervised Time Series Representation Learning by Inter-Intra Relational Reasoning. arXiv.
28. Bengio, Y. (2009). Learning Deep Architectures for AI, Now Publishers Inc.10.1561/9781601982957 ↗
29. Oord, A.v.d., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv.
30. Bai, S., Kolter, J.Z., and Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv.
31. Schmidt, P., Reiss, A., Duerichen, R., Marberger, C., and Van Laerhoven, K. (2018, January 16–18). Introducing wesad, a multimodal dataset for wearable stress and affect detection. Proceedings of the 20th ACM International Conference on Multimodal Interaction, Boulder CO, USA.10.1145/3242969.3242985 ↗
32. Dosovitskiy, A., Springenberg, J.T., Riedmiller, M., and Brox, T. (2014). Discriminative unsupervised feature learning with convolutional neural networks. Adv. Neural Inf. Process. Syst., 27.
33. Doersch, C., Gupta, A., and Efros, A.A. (2015, January 7–13). Unsupervised visual representation learning by context prediction. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.167 ↗
34. Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., and Efros, A.A. (2016, January 27–30). Context encoders: Feature learning by inpainting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.278 ↗
35. Wen, Q., Sun, L., Yang, F., Song, X., Gao, J., Wang, X., and Xu, H. (2020). Time series data augmentation for deep learning: A survey. arXiv.10.24963/ijcai.2021/631 ↗
36. Um, T.T., Pfister, F.M., Pichler, D., Endo, S., Lang, M., Hirche, S., Fietzek, U., and Kulić, D. (2017, January 13–17). Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks. Proceedings of the 19th ACM International Conference on Multimodal Interaction, Glasgow, UK.10.1145/3136755.3136817 ↗
37. Lei, Q., Yi, J., Vaculin, R., Wu, L., and Dhillon, I.S. (2017). Similarity Preserving Representation Learning for Time Series Clustering. arXiv.
38. Wu, L., Yen, I.E.H., Yi, J., Xu, F., Lei, Q., and Witbrock, M. (2018, January 9–11). Random warping series: A random features method for time-series embedding. Proceedings of the International Conference on Artificial Intelligence and Statistics, PMLR, Lanzarote, Spain.
39. Proximity forest: An effective and scalable distance-based classifier for time series10.1007/s10618-019-00617-3 ↗
40. Lee, Y.K., Kwon, O.W., Shin, H.S., Jo, J., and Lee, Y. (2011, January 6–8). Noise reduction of PPG signals using a particle filter for robust emotion recognition. Proceedings of the 2011 IEEE International Conference on Consumer Electronics-Berlin (ICCE-Berlin), Berlin, Germany.10.1109/ICCE-Berlin.2011.6031807 ↗
41. An optimal filter for short photoplethysmogram signals10.1038/sdata.2018.76 ↗
42. Hanyu, S., and Xiaohui, C. (2017, January 28–30). Motion artifact detection and reduction in PPG signals based on statistics analysis. Proceedings of the 2017 29th Chinese Control and Decision Conference (CCDC), Chongqing, China.10.1109/CCDC.2017.7979043 ↗
43. Sadhukhan, D., Pal, S., and Mitra, M. (2018, January 16–18). PPG Noise Reduction based on Adaptive Frequency Suppression using Discrete Fourier Transform for Portable Home Monitoring Applications. Proceedings of the 2018 15th IEEE India Council International Conference (INDICON), Coimbatore, India.10.1109/INDICON45594.2018.8987004 ↗
44. Detection and removal of motion artifacts in PPG signals10.1007/s11036-019-01323-6 ↗