Key result
Optimized CNN + GRU model achieves ~96% accuracy classifying radar vital signs.
Why the study?
Does an optimized CNN+GRU model improve the classification accuracy of radar-detected vital signs compared to standard pre-trained CNN models?
Does an optimized CNN+GRU model improve the classification accuracy of radar-detected vital signs compared to standard pre-trained CNN models?
An optimized CNN+GRU model using spectrograms of radar data achieved >95% accuracy in classifying vital signs, demonstrating the potential of non-contact radar for monitoring conditions like sleep apnea.
May support contactless radar monitoring in sleep apnea; hypothesis-generating and requires prospective clinical validation.
Wearable devices may have significant disadvantages compared to non-contact sensors. In addition, heart and respiratory rate information may be insufficient for expert evaluation. Radar sensors allow vital signals to be detected without interfering with subject activities. In this study, a high performance Convolutional Neural Network (CNN) model is proposed to classify four different types of radar vital signs. Firstly, raw radar data is converted into 2-dimensional matrix form by spectrogram method in order to analyze raw radar data in time and frequency environment. Spectrogram processing on raw radar data is required for training and testing of pre-trained CNN networks. Afterwards, high-level features obtained from pre-trained CNN networks were fused by using Canonical Correlation Analysis (CCA). These features were used to train and test for Gated Recurrent Unit (GRU) block structure optimized by Whale Optimization algorithm (WOA). The proposed Spectrogram Content Based Optimized CNN + GRU Model performance is 95.52% Accuracy (ACC), 94.74% Sensitivity (SEN), 98.29% Specificity (SPE=, 96.35% Precision (PRE), 95.40% F1-Score and 93.96% Matthews Correlation Coefficient (MCC). Our proposed method showed that preferability potential of non-destructive radar technology is more valuable than wearable technologies.
No takes yet. Share an insight, caveat, or question.
Umut Özkaya (2023) studied Obstructive sleep apnea / Vital signs detection. Spectrogram Content Based Optimized CNN + GRU Model was evaluated on Classification Accuracy. The proposed Spectrogram Content Based Optimized CNN + GRU Model achieved 95.52% accuracy, 94.74% sensitivity, and 98.29% specificity in classifying four different types of radar vital signs.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: