Key result
Generative adversarial network reconstructs noisy PPG signals without movement sensors, achieving ~1.3 bpm error.
Why the study?
PPG signals are easily distorted by motion artifacts, prompting exploration of alternatives to movement sensors for signal reconstruction.
Does a generative adversarial network with fully connected layers accurately reconstruct noisy PPG signals without movement sensor inputs?
Does a generative adversarial network with fully connected layers accurately reconstruct noisy PPG signals without movement sensor inputs?
A GAN with fully connected layers effectively reconstructs noisy PPG signals, offering a promising approach for real-time denoising without needing accelerometer or gyroscope inputs.
Objective. The detection of arterial pulsating signals at the skin periphery with Photoplethysmography (PPG) are easily distorted by motion artifacts. This work explores the alternatives to the aid of PPG reconstruction with movement sensors (accelerometer and/or gyroscope) which to date have demonstrated the best pulsating signal reconstruction. Approach. A generative adversarial network with fully connected layers is proposed for the reconstruction of distorted PPG signals. Artificial corruption was performed to the clean selected signals from the BIDMC Heart Rate dataset, processed from the larger MIMIC II waveform database to create the training, validation and testing sets. Main results. The heart rate (HR) of this dataset was further extracted to evaluate the performance of the model obtaining a mean absolute error of 1.31 bpm comparing the HR of the target and reconstructed PPG signals with HR between 70 and 115 bpm. Significance. The model architecture is effective at reconstructing noisy PPG signals regardless the length and amplitude of the corruption introduced. The performance over a range of HR (70–115 bpm), indicates a promising approach for real-time PPG signal reconstruction without the aid of acceleration or angular velocity inputs.
No takes yet. Share an insight, caveat, or question.
Castro et al. (2025) studied Distorted PPG signals. Generative adversarial network with fully connected layers was evaluated on Mean absolute error of heart rate. A generative adversarial network effectively reconstructed noisy PPG signals without movement sensors, achieving a mean absolute error of 1.31 bpm for heart rates between 70 and 115 bpm.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: