Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Joint Alignment of Multivariate Quasi-Periodic Functional Data Using Deep Learning (2312.09422v1)

Published 14 Nov 2023 in eess.SP, cs.LG, math.FA, and stat.ME

Abstract: The joint alignment of multivariate functional data plays an important role in various fields such as signal processing, neuroscience and medicine, including the statistical analysis of data from wearable devices. Traditional methods often ignore the phase variability and instead focus on the variability in the observed amplitude. We present a novel method for joint alignment of multivariate quasi-periodic functions using deep neural networks, decomposing, but retaining all the information in the data by preserving both phase and amplitude variability. Our proposed neural network uses a special activation of the output that builds on the unit simplex transformation, and we utilize a loss function based on the Fisher-Rao metric to train our model. Furthermore, our method is unsupervised and can provide an optimal common template function as well as subject-specific templates. We demonstrate our method on two simulated datasets and one real example, comprising data from 12-lead 10s electrocardiogram recordings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. “TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems”, 2015 URL: https://www.tensorflow.org/
  2. “keras: R Interface to ’Keras”’ R package version 2.10.0, 2022 URL: https://CRAN.R-project.org/package=keras
  3. “tensorflow: R Interface to ’TensorFlow”’ R package version 2.10.0, 2022 URL: https://CRAN.R-project.org/package=tensorflow
  4. “Nonparametric Inference on Manifolds: With Applications to Shape Spaces” Cambridge University Press, 2012 DOI: 10.1017/CBO9781139094764
  5. Bachir Boucheham “Matching of quasi-periodic time series patterns by exchange of block-sorting signatures” In Pattern Recognition Letters 29.4, 2008, pp. 501–514 DOI: 10.1016/j.patrec.2007.11.004
  6. “QP-DTW: Upgrading Dynamic Time Warping to Handle Quasi Periodic Time Series Alignment” In Journal of Information Processing Systems 14.4, 2018, pp. 851–876 DOI: 10.3745/JIPS.02.0090
  7. “SrvfRegNet: Elastic Function Registration Using Deep Neural Networks” In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops Nashville, TN, USA: IEEE, 2021, pp. 4462–4471 DOI: 10.1109/CVPRW53098.2021.00503
  8. François Chollet “Keras”, 2015 URL: https://keras.io
  9. “Subclinical Coronary Atherosclerosis and Risk for Myocardial Infarction in a Danish Cohort: A Prospective Observational Cohort Study” In Annals of Internal Medicine 176.4, 2023, pp. 433–442 DOI: 10.7326/M22-3027
  10. “What is inside the electrocardiograph?” In Journal of Electrocardiology 41.1, 2008, pp. 8–14 DOI: 10.1016/j.jelectrocard.2007.08.059
  11. B.Milan Horáček “Lead Theory” In Comprehensive Electrocardiology London, UK: Springer, 2010
  12. Diederik P. Kingma and Jimmy Ba “Adam: A Method for Stochastic Optimization” In Proceedings of the 3rd International Conference on Learning Representations San Diego, CA, USA: ICLR, 2015 DOI: 10.48550/ARXIV.1412.6980
  13. David C. Klonoff “Continuous Glucose Monitoring: Roadmap for 21st century diabetes therapy” In Diabetes Care 28.5, 2005, pp. 1231–1239 DOI: 10.2337/diacare.28.5.1231
  14. Alois Kneip and James O Ramsay “Combining Registration and Fitting for Functional Models” In Journal of the American Statistical Association 103.483, 2008, pp. 1155–1165 DOI: 10.1198/016214508000000517
  15. “Left ventricular hypertrophy identified by cardiac computed tomography and ECG in hypertensive individuals: a population-based study” In Journal of Hypertension 37.4, 2019, pp. 739–746 DOI: 10.1097/HJH.0000000000001962
  16. Yann LeCun, Yoshua Bengio and Geoffrey Hinton “Deep learning” In Nature 521.7553, 2015, pp. 436–444 DOI: 10.1038/nature14539
  17. Suhas Lohit, Qiao Wang and Pavan Turaga “Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping” In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Long Beach, CA, USA: IEEE, 2019, pp. 12418–12427 DOI: 10.1109/CVPR.2019.01271
  18. “NeuroKit2: A Python toolbox for neurophysiological signal processing” In Behavior Research Methods 53.4 Springer ScienceBusiness Media LLC, 2021, pp. 1689–1696 DOI: 10.3758/s13428-020-01516-y
  19. “Functional Data Analysis of Amplitude and Phase Variation” In Statistical Science 30.4, 2015, pp. 468–484 DOI: 10.1214/15-STS524
  20. “Registration of 24-hour accelerometric rest-activity profiles and its application to human chronotypes” In Biological Rhythm Research 53.8, 2022, pp. 1299–1319 DOI: 10.1080/09291016.2021.1929673
  21. Meinard Müller “Information retrieval for music and motion” Berlin, Heidelberg: Springer, 2007
  22. Elvis Nunez and Shantanu H. Joshi “Deep Learning of Warping Functions for Shape Analysis” In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Seattle, WA, USA: IEEE, 2020, pp. 3782–3790 DOI: 10.1109/CVPRW50498.2020.00441
  23. Elvis Nunez, Andrew Lizarraga and Shantanu H. Joshi “SrvfNet: A Generative Network for Unsupervised Multiple Diffeomorphic Functional Alignment” In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops Nashville, TN, USA: IEEE, 2021, pp. 4476–4484 DOI: 10.1109/CVPRW53098.2021.00505
  24. Jeeheh Oh, Jiaxuan Wang and Jenna Wiens “Learning to Exploit Invariances in Clinical Time-Series Data Using Sequence Transformer Networks” In Proceedings of the 3rd Machine Learning for Healthcare Conference 85, Proceedings of Machine Learning Research PMLR, 2018, pp. 332–347
  25. James O Ramsay and Bernard W Silverman “Functional Data Analysis”, Springer Series in Statistics New York, NY: Springer, 2005 URL: https://doi.org/10.1007/b98888
  26. Jasper Snoek, Hugo Larochelle and Ryan P Adams “Practical Bayesian Optimization of Machine Learning Algorithms” In Proceedings of the Advances in Neural Information Processing Systems 25 Tahoe, NV, USA: Curran Associates, Inc., 2012
  27. Anuj Srivastava and Eric P. Klassen “Functional and Shape Data Analysis”, Springer Series in Statistics New York, NY: Springer New York, 2016 DOI: 10.1007/978-1-4939-4020-2
  28. Guo-Zheng Sun, Hsing-Hen Chen and Yee-Chun Lee “Time Warping Invariant Neural Networks” In Advances in Neural Information Processing Systems 5 Denver, CO, USA: Morgan-Kaufmann, 1992
  29. “Can recurrent neural networks warp time?” In arXiv, 2018 DOI: 10.48550/ARXIV.1804.11188
  30. J.Derek Tucker “fdasrvf: Elastic Functional Data Analysis”, 2022 URL: https://CRAN.R-project.org/package=fdasrvf
  31. J.Derek Tucker, Wei Wu and Anuj Srivastava “Generative models for functional data using phase and amplitude separation” In Computational Statistics & Data Analysis 61, 2013, pp. 50–66 DOI: 10.1016/j.csda.2012.12.001
  32. “Diffeomorphic temporal alignment nets” In Advances in Neural Information Processing Systems 32 Vancouver, BC, Canada: Curran Associates, Inc., 2019

Summary

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

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