CRIS
Permanent URI for this communityhttps://scripta.up.edu.mx/handle/20.500.12552/1
Browse
2 results
Search Results
Now showing 1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Non-Contact Oxygen Saturation Estimation Using Deep Learning Ensemble Models and Bayesian OptimizationMonitoring Peripheral Oxygen Saturation (SpO2) is an important vital sign both in Intensive Care Units (ICUs), during surgery and convalescence, and as part of remote medical consultations after of the COVID-19 pandemic. This has made the development of new SpO2-measurement tools an area of active research and opportunity. In this paper, we present a new Deep Learning (DL) combined strategy to estimate SpO2 without contact, using pre-magnified facial videos to reveal subtle color changes related to blood flow and with no calibration per subject required. We applied the Eulerian Video Magnification technique using the Hermite Transform (EVM-HT) as a feature detector to feed a Three-Dimensional Convolutional Neural Network (3D-CNN). Additionally, parameters and hyperparameter Bayesian optimization and an ensemble technique over the dataset magnified were applied. We tested the method on 18 healthy subjects, where facial videos of the subjects, including the automatic detection of the reference from a contact pulse oximeter device, were acquired. As performance metrics for the SpO2-estimation proposal, we calculated the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other parameters from the Bland–Altman (BA) analysis with respect to the reference. Therefore, a significant improvement was observed by adding the ensemble technique with respect to the only optimization, obtaining 14.32% in RMSE (reduction from 0.6204 to 0.5315) and 13.23% in MAE (reduction from 0.4323 to 0.3751). On the other hand, regarding Bland–Altman analysis, the upper and lower limits of agreement for the Mean of Differences (MOD) between the estimation and the ground truth were 1.04 and −1.05, with an MOD (bias) of −0.00175; therefore, MOD ±1.96𝜎 = −0.00175 ± 1.04. Thus, by leveraging Bayesian optimization for hyperparameter tuning and integrating a Bagging Ensemble, we achieved a significant reduction in the training error (bias), achieving a better generalization over the test set, and reducing the variance in comparison with the baseline model for SpO2 estimation. ©The authors ©Technologies ©MDPI. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Non-Contact Respiratory Rate Estimation in Newborns During Quiet Sleep Using Video Magnification Techniques and a 3D Convolutional Neural Network(IEEE, 2024); ; Cabon, SandieIn this paper, we present a new non-contact strategy to estimate the respiratory rate (RR) in a neonatal intensive care unit (NICU) based on the Eulerian motion video magnification technique and a 3D Convolutional Neural Network (3D CNN). The magnification procedure was carried out using the Hermite decomposition. The RR is estimated using a 3D CNN and a region of interest (ROI) detected manually. We have tested the method on 8 infants in NICU during quiet sleep. A contact respiratory signal is acquired synchronously to the videos to compute the RR as reference for training the CNN. To compare the performance of the method, we compute the Mean Absolute Error, the Root Mean Squared Error and metrics from the Bland and Altman analysis to investigate the agreement of the method with respect to the respiratory signal reference. The proposed solution shows an agreement with respect to the reference of 95% and root mean squared error of 2.88. ©The authors ©IEEE.11