A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation
In recent advancements within the data-driven world, cyclic time series have become indispensable in industries such as healthcare, manufacturing, and energy. Deep learning methodologies have significantly improved predictions for cyclic time series across these domains. This study investigates the...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10820351/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533432330452992 |
|---|---|
| author | Shang-Wei Chao Feng-Li Lian |
| author_facet | Shang-Wei Chao Feng-Li Lian |
| author_sort | Shang-Wei Chao |
| collection | DOAJ |
| description | In recent advancements within the data-driven world, cyclic time series have become indispensable in industries such as healthcare, manufacturing, and energy. Deep learning methodologies have significantly improved predictions for cyclic time series across these domains. This study investigates the impact of various filtering techniques on the accuracy of deep learning models in medical signal estimation, specifically using photoplethysmography (PPG) signals as input. We argue that conventional filtering techniques, when applied as preprocessing to noisy signals, often distort the waveform and hinder the representation learning capabilities of deep learning models. Additionally, diverse and dynamic noise sources in clinical environments remain significant challenges to overcome. To address these challenges, we propose a self-adaptive frequency decomposition approach with regularization weighting policy. Through experimentation with different combinations of filtering methods and sequence-to-sequence deep learning models, our results demonstrate a 45% improvement in MSE over the Butterworth filter, 56% over the FIR filter, and 18% over the wavelet-based filter, confirming that self-adaptive decomposition filters offer superior performance for noisy cyclic time series in deep learning applications. |
| format | Article |
| id | doaj-art-afefadec1ce842d8b01b6eb028c69f9d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-afefadec1ce842d8b01b6eb028c69f9d2025-01-16T00:01:25ZengIEEEIEEE Access2169-35362025-01-01135236524710.1109/ACCESS.2024.352515210820351A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal EstimationShang-Wei Chao0https://orcid.org/0009-0000-1385-5073Feng-Li Lian1https://orcid.org/0000-0002-1260-4894Department of Electrical Engineering, National Taiwan University, Taipei, TaiwanDepartment of Electrical Engineering, National Taiwan University, Taipei, TaiwanIn recent advancements within the data-driven world, cyclic time series have become indispensable in industries such as healthcare, manufacturing, and energy. Deep learning methodologies have significantly improved predictions for cyclic time series across these domains. This study investigates the impact of various filtering techniques on the accuracy of deep learning models in medical signal estimation, specifically using photoplethysmography (PPG) signals as input. We argue that conventional filtering techniques, when applied as preprocessing to noisy signals, often distort the waveform and hinder the representation learning capabilities of deep learning models. Additionally, diverse and dynamic noise sources in clinical environments remain significant challenges to overcome. To address these challenges, we propose a self-adaptive frequency decomposition approach with regularization weighting policy. Through experimentation with different combinations of filtering methods and sequence-to-sequence deep learning models, our results demonstrate a 45% improvement in MSE over the Butterworth filter, 56% over the FIR filter, and 18% over the wavelet-based filter, confirming that self-adaptive decomposition filters offer superior performance for noisy cyclic time series in deep learning applications.https://ieeexplore.ieee.org/document/10820351/Adaptive frequency band decompositionphotoplethysmographyprediction algorithmssensor systemssignal denoisingtime series analysis |
| spellingShingle | Shang-Wei Chao Feng-Li Lian A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation IEEE Access Adaptive frequency band decomposition photoplethysmography prediction algorithms sensor systems signal denoising time series analysis |
| title | A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation |
| title_full | A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation |
| title_fullStr | A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation |
| title_full_unstemmed | A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation |
| title_short | A Self-Adaptive Frequency Decomposition Approach for Denoising to Enhance Data-Driven Learning of Cyclic Time Series in Medical Signal Estimation |
| title_sort | self adaptive frequency decomposition approach for denoising to enhance data driven learning of cyclic time series in medical signal estimation |
| topic | Adaptive frequency band decomposition photoplethysmography prediction algorithms sensor systems signal denoising time series analysis |
| url | https://ieeexplore.ieee.org/document/10820351/ |
| work_keys_str_mv | AT shangweichao aselfadaptivefrequencydecompositionapproachfordenoisingtoenhancedatadrivenlearningofcyclictimeseriesinmedicalsignalestimation AT fenglilian aselfadaptivefrequencydecompositionapproachfordenoisingtoenhancedatadrivenlearningofcyclictimeseriesinmedicalsignalestimation AT shangweichao selfadaptivefrequencydecompositionapproachfordenoisingtoenhancedatadrivenlearningofcyclictimeseriesinmedicalsignalestimation AT fenglilian selfadaptivefrequencydecompositionapproachfordenoisingtoenhancedatadrivenlearningofcyclictimeseriesinmedicalsignalestimation |