2 results
Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , CW Radar-based Non-Contact Respiration Monitoring using Complex-Valued Neural Networks(2024-09); ; ; Machine learning-based respiration monitoring using continuous wave (CW) radar has been studied. However, most of the models are real-valued (RV), which only takes the magnitude of signals as input. Complex-valued (CV) signals can be formulated from radar baseband signals. In this paper, we compare CV-based and equivalent RV-based neural networks (NN) models to reconstruct the respiration signal with the 61 GHz CW radar. We demonstrate two model structures, a fully connected NN (FCNN) and a combination of the convolutional network and bidirectional gated recurrent units (ConVGRU), in CV-based and equivalent RV-based models, respectively. Ten hours of measurements from a clinical study are used to validate the performance. ConVGRU surpasses FCNN in both RV and CV. CV-based ConVGRU outperforms the RV-based ConVGRU with a smaller average breathing rate error of 0.55 breaths per minute (bpm), with more than 93% of the measurements achieving an error of less than 2 bpm.Publicationtype: Conference Paper20 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Contactless in-bed movement in various scales classification with CW radarContinuous wave (CW) radar has been used to detect motions in various scenarios. In this paper, we first present a data-driven method to classify in-bed movement from various scales with CW radar. Data augmentation techniques are used to address the small sample size problem, resulting in a significant improvement of over 10% in accuracy. Three machine learning classifiers, namely random forest, k-nearest neighbor (k-NN), and multilayer perceptron (MLP), are evaluated, with random forest demonstrating the highest accuracy of 81.94% and relative improvement of 22.5% compared to k-NN. The movement sitting up from the bed can be classified with 97.5% accuracy. Additionally, the method can classify two types of movements involving only arm and leg movements, which are not visible to the radar, by detecting small-scale joint movements from the back with an accuracy of 74.8%.Publicationtype: Conference Paper24