DIGS-Module: A Deformable Information Gain-Guided Scale Selection Structure Based on Physiological Signals for Classification
- 25 February 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (14) , 25989-26002
Abstract
Multiscale convolutional neural networks are widely utilized in the analysis of physiological signals to assess human health due to their large receptive field and rich feature domain. However, current scale selection for multiscale networks relies heavily on data and empirical knowledge, leading to information redundancy and reduced generalization capability, which hinders clinical application. To address these, we propose a novel paradigm of deformable information gain-guided scale (DIGS), which adaptively selects the appropriate scale for feature extraction according to the input signal. Specifically, we employ an information entropy-based hierarchical calculation of the information gain between the input and output features of each multiscale branch. This information gain determines the optimal branches for feature extraction. Additionally, we utilize 1-D deformable module to achieve overall convolutional shifts, enabling scale information to match the distribution of the dataset. Extensive experiments conducted on five datasets demonstrate that our proposed multiscale paradigm outperforms previous baseline networks in four classification tasks of physiological signals. Furthermore, integrating our structure with the best performing network on current private wearable PPG datasets improves accuracy by approximately 1%, sensitivity by 1%–3%, and reduces computational load by nearly half. These findings indicate that our new structure enhances both classification performance and computational efficiency of multiscale networks.Keywords
Funding Information
- Key Laboratory of Sensing Technology and Biomedical Instrument of Guangdong Province
- Shenzhen Science and Technology Plan for fundamental research (JCY20190807162003696)
This publication has 52 references indexed in Scilit:
- RETRACTED: Arrhythmia classification using ECG signal: A meta-heuristic improvement of optimal weighted feature integration and attention-based hybrid deep learning modelBiomedical Signal Processing and Control, 2023
- AmtNet: Attentional multi-scale temporal network for phonocardiogram signal classificationBiomedical Signal Processing and Control, 2023
- One-dimensional VGGNet for high-dimensional dataApplied Soft Computing, 2023
- MS-Net: Sleep apnea detection in PPG using multi-scale block and shadow module one-dimensional convolutional neural networkComputers in Biology and Medicine, 2023
- Automated detection of obstructive sleep apnea in more than 8000 subjects using frequency optimized orthogonal wavelet filter bank with respiratory and oximetry signalsComputers in Biology and Medicine, 2022
- Enhancing dynamic ECG heartbeat classification with lightweight transformer modelArtificial Intelligence in Medicine, 2022
- Global hybrid multi-scale convolutional network for accurate and robust detection of atrial fibrillation using single-lead ECG recordingsComputers in Biology and Medicine, 2021
- Sleep apnea screening based on Photoplethysmography data from wearable bracelets using an information-based similarity approachComputer Methods and Programs in Biomedicine, 2021
- Intention Recognition from Spatio-Temporal Representation of EEG Signals2021
- SAN: Learning Relationship Between Convolutional Features for Multi-scale Object Detection2018