A5087764544- Non-Invasive Vital Sign Monitoring
- Radiomics and Machine Learning in Medical Imaging
- Heart Rate Variability and Autonomic Control
- ECG Monitoring and Analysis
- Medical Imaging and Analysis
- Advanced Neural Network Applications
- AI in cancer detection
- Advanced Radiotherapy Techniques
- Medical Image Segmentation Techniques
UMIT - Private Universität für Gesundheitswissenschaften, Medizinische Informatik und Technik
2020-2021
Statistics Austria
2019
Health University of Applied Sciences Tyrol
2019
Objective.Ballistocardiography (BCG) is an unobtrusive approach for cost-effective and patient-friendly health monitoring. In this work, deep learning methods are used heart rate estimation from BCG signals compared against five digital signal processing found in literature.Approach.The models evaluated on a dataset featuring recordings 42 patients, acquired with pneumatic system. Several different architectures, including convolutional, recurrent combination of both investigated. Besides...
We present a new algorithm for peak detection in ballistocardiographic (BCG) signals and use it heart rate estimation. Systolic complexes of the BCG signal are enhanced coarse beat locations estimated. Ejection waves I, J K detected simultaneously around locations, only using local maxima weighted summation heights. Due to lack reference annotations, algorithm's performance is assessed by peaks On dataset acquired with pneumatic system, we evaluate estimation compare introduced against other...