Jonas Fuchs

TL;DR: Using the detected heart sounds considerably improves radar-based heartbeat monitoring, while the achieved performance is also competitive to phonocardiography.

TL;DR: An autoencoder based convolutional neural network is proposed to perform image based denoising and shows significant improvement with respect to signal-to-noise-plus-interference ratio in comparison to other state-of-the-art mitigation techniques, while better preserving phase information of the spectrum compared to other techniques.

TL;DR: This dataset consists of synchronised data which are acquired using a Six-Port-based radar system operating at 24 GHz, a digital stethoscope, an ECG, and a respiration sensor and can be used to either test algorithms for monitoring the heart rate, but also to gain insights about characteristic effects of radar-based vital sign monitoring.

TL;DR: An alternative approach to high-resolution direction-of-arrival estimation in the context of automotive FMCW signal processing is shown by training a neural network with simulation as well as experimental data to estimate the mean and distance of the azimuth angles from two targets.

TL;DR: In this article, the authors proposed an integrated Bayesian framework by augmenting state vector with feature embedding as appearance parameter together with localization parameter for automotive vulnerable road users (VRUs) such as pedestrian and cyclist.