MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction

Iman Deznabi, Madalina Fiterau
Proceedings of the Conference on Health, Inference, and Learning, PMLR 209:509-525, 2023.

Abstract

The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets, as signals are typically sampled at different rates. To address these issues, we introduce MultiWave, a novel framework that enhances deep learning time series models by incorporating components that operate at the intrinsic frequencies of signals. MultiWave uses wavelets to decompose each signal into subsignals of varying frequencies and groups them into frequency bands. Each frequency band is handled by a different component of our model. A gating mechanism combines the output of the components to produce sparse models that use only specific signals at specific frequencies. Our experiments demonstrate that MultiWave accurately identifies informative frequency bands and improves the performance of various deep learning models, including LSTM, Transformer, and CNN-based models, for a wide range of applications. It attains top performance in stress and affect detection from wearables. It also increases the AUC of the best-performing model by 5% for in-hospital COVID-19 mortality prediction from patient blood samples and for human activity recognition from accelerometer and gyroscope data. We show that MultiWave consistently identifies critical features and their frequency components, thus providing valuable insights into the applications studied.

Cite this Paper

BibTeX
@InProceedings{pmlr-v209-deznabi23a, title = {MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction}, author = {Deznabi, Iman and Fiterau, Madalina}, booktitle = {Proceedings of the Conference on Health, Inference, and Learning}, pages = {509--525}, year = {2023}, editor = {Mortazavi, Bobak J. and Sarker, Tasmie and Beam, Andrew and Ho, Joyce C.}, volume = {209}, series = {Proceedings of Machine Learning Research}, month = {22 Jun--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v209/deznabi23a/deznabi23a.pdf}, url = {https://proceedings.mlr.press/v209/deznabi23a.html}, abstract = {The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets, as signals are typically sampled at different rates. To address these issues, we introduce MultiWave, a novel framework that enhances deep learning time series models by incorporating components that operate at the intrinsic frequencies of signals. MultiWave uses wavelets to decompose each signal into subsignals of varying frequencies and groups them into frequency bands. Each frequency band is handled by a different component of our model. A gating mechanism combines the output of the components to produce sparse models that use only specific signals at specific frequencies. Our experiments demonstrate that MultiWave accurately identifies informative frequency bands and improves the performance of various deep learning models, including LSTM, Transformer, and CNN-based models, for a wide range of applications. It attains top performance in stress and affect detection from wearables. It also increases the AUC of the best-performing model by 5% for in-hospital COVID-19 mortality prediction from patient blood samples and for human activity recognition from accelerometer and gyroscope data. We show that MultiWave consistently identifies critical features and their frequency components, thus providing valuable insights into the applications studied.} }
Endnote
%0 Conference Paper %T MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction %A Iman Deznabi %A Madalina Fiterau %B Proceedings of the Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2023 %E Bobak J. Mortazavi %E Tasmie Sarker %E Andrew Beam %E Joyce C. Ho %F pmlr-v209-deznabi23a %I PMLR %P 509--525 %U https://proceedings.mlr.press/v209/deznabi23a.html %V 209 %X The analysis of multivariate time series data is challenging due to the various frequencies of signal changes that can occur over both short and long terms. Furthermore, standard deep learning models are often unsuitable for such datasets, as signals are typically sampled at different rates. To address these issues, we introduce MultiWave, a novel framework that enhances deep learning time series models by incorporating components that operate at the intrinsic frequencies of signals. MultiWave uses wavelets to decompose each signal into subsignals of varying frequencies and groups them into frequency bands. Each frequency band is handled by a different component of our model. A gating mechanism combines the output of the components to produce sparse models that use only specific signals at specific frequencies. Our experiments demonstrate that MultiWave accurately identifies informative frequency bands and improves the performance of various deep learning models, including LSTM, Transformer, and CNN-based models, for a wide range of applications. It attains top performance in stress and affect detection from wearables. It also increases the AUC of the best-performing model by 5% for in-hospital COVID-19 mortality prediction from patient blood samples and for human activity recognition from accelerometer and gyroscope data. We show that MultiWave consistently identifies critical features and their frequency components, thus providing valuable insights into the applications studied.
APA
Deznabi, I. & Fiterau, M.. (2023). MultiWave: Multiresolution Deep Architectures through Wavelet Decomposition for Multivariate Time Series Prediction. Proceedings of the Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 209:509-525 Available from https://proceedings.mlr.press/v209/deznabi23a.html.

Related Material