Motion Analysis Using Global Navigation Satellite System and Physiological Data

• Main Authors: Charvatova, H. (Author), Geman, O. (Author), Molcanova, A. (Author), Prochazka, A. (Author), Vysata, O. (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2023
• Subjects: Bayesian networks; Biomedical monitoring; Biomedical signal processing; cardiology; Cardiology; classification; Classification (of information); computational intelligence; Different slopes; Extraction; feature extraction; Feature extraction; Features extraction; Global navigation satellite system; global navigation satellite systems; Global Navigation Satellite Systems; Global positioning system; Heart; Heart rate; Heart-rate; Learning systems; machine learning; Machine-learning; Monitoring; Motion analysis; Multichannel signal processing; Multi-channel signal processing; Navigation; Network layers; physical activity monitoring; Physical activity monitoring; Robots; Satellites; Sensors; Smart phones; Smartphones
• Online Access: View Fulltext in Publisher; View in Scopus
• Physical Description: 1
• ISBN: 21693536 (ISSN)
• DOI: 10.1109/ACCESS.2023.3270102

Motion analysis by wearable sensors forms a very important research topic with a general mathematical background and applications in different areas including engineering, robotics, and neurology. This paper presents the use of the global navigation satellite system (GNSS) for detecting and recording the position of a moving body and the simultaneous acquisition of signals from further sensors. The application is related to the monitoring of physical activity and the analysis of the heart rate dynamics during the run at route segments of different slopes with changing speed, forming an alternative to the heart monitoring on the treadmill ergometer. The proposed computational method includes digital methods of data preprocessing, time synchronization, and data resampling to enable their correlation, feature extraction both in time and frequency domains, and classification. The datasets include signals acquired during ten experimental runs in the selected area. The detection of the patterns of motion includes segmenting the signals by analysing the GNSS data, evaluating the patterns, and classifying the motion signals under different terrain conditions. This method of classification provides a comparison of neural networks, support vector machine, Bayesian, and <italic>k</italic>-nearest neighbour methods. The highest accuracy of 93.3 % was achieved by using combined features and a two-layer neural network for classification into three classes with different slopes. The proposed method and graphical user interface suggest the efficiency of multi-channel and multi-dimensional signal processing with applications in rehabilitation, fitness movement monitoring, neurology, cardiology, engineering, and robotic systems as well. Author