Robust Reconstruction for Body Area Wireless Sensor Networks (RoReyBaN)

• Applicants: Waltenegus Dargie, Ph.D.; Professor Dr.-Ing. Eduard Axel Jorswieck
• Subject Area: Electronic Semiconductors, Components and Circuits, Integrated Systems, Sensor Technology, Theoretical Electrical Engineering ; Security and Dependability, Operating-, Communication- and Distributed Systems
• Term: from 2018 to 2025
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 399332937

• Final Report Year: 2024

Final Report Abstract

The aging population requires new and innovative approaches to monitor and supervise medical and physical conditions in residential and rehabilitation environments. One of the essential medical devices for this purpose is the electrocardiogram (ECG), which measures heart activity on the body surface. However, the use of ECG measurements outside of controlled clinical settings is often corrupted by motion artifacts resulting from freedom of movement. In this project, motion artifacts in ECG are closely examined. We study the spectral characteristics of motion artifacts for a set of different motions representing everyday activities. Furthermore, we investigate to what extent reference motion sensors (accelerometer, gyroscope, and skin-electrode impedance) are able to characterize and remove the recorded motion artifacts from the measurements. Our results demonstrate that motion artifacts markedly change their characteristics with a change in motion. While low-intensity movements manifest in lower frequency bands, higher intensity exercises provoke motion artifacts that are much more complex in their composition. These characteristics are correspondingly reflected in the correlation between reference sensors and artifacts. To characterize and remove motion artifacts in mobile measurements, we use canonical polyadic decomposition (CPD) along with measurements obtained from different reference sensors. Wavelet transformation is utilized to transform ECG and reference data from vector to matrix format. Next, a 3D tensor is constructed by combining the heterogeneous measurements. We propose a methodology to predict the decomposition rank based on statistical features in the ECG that quantify the signal quality. To evaluate the performance of the decomposition process, we combine isolated motion artifacts recorded at the back with ECG obtained in rest to generate artificially corrupted data. The results suggest that CPD successfully removes motion artifacts from the data for all reference sensors regarded. For the statistical modeling of artifacts in ECG data, the joint distribution of the underlying stochastic processes is very relevant. During the investigation of different copulae for modeling dependencies in ECG data, we found the possibility to apply these methods and tools to the wireless sensor network itself. This shows that interdisciplinary research can lead to new approaches. Indeed, it turns out that dependency modeling allows to design reliable wireless systems. Based on the measurements of marginal distributions, it is possible to derive worst-case and best-case performance bounds. Within this project, we brought the concepts of dependency modeling to wireless communications and derived new bounds for multi-antenna and multi-user systems.

Publications

• Machine Learning Assisted Wiretapping. 2018 52nd Asilomar Conference on Signals, Systems, and Computers, 489-493. IEEE.
  Besser, Karl-L.; Lin, Pin-Hsun; Janda, Carsten R. & Jorswieck, Eduard A.
  
• Motion Artefacts Modelling in the Application of a Wireless Electrocardiogram. 2018 21st International Conference on Information Fusion (FUSION), 239-244. IEEE.
  Dargie, Waltenegus
  
• Application of SVD for Removing Motion Artifacts from the Measurements of a Wireless Electrocardiogram. 2019 22th International Conference on Information Fusion (FUSION), 1-8. IEEE.
  Dargie, Waltenegus & Lilienthal, Jannis
  
• Flexible Design of Finite Blocklength Wiretap Codes by Autoencoders. ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2512-2516. IEEE.
  Besser, Karl-Ludwig; Janda, Carsten R.; Lin, Pin-Hsun & Jorswieck, Eduard A.
  
• Bounds on the Outage Probability in Dependent Rayleigh Fading Channels. ICC 2020 - 2020 IEEE International Conference on Communications (ICC), 1-6. IEEE.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Deep Learning Based Resource Allocation: How Much Training Data is Needed?. 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 1-5. IEEE.
  Besser, Karl-Ludwig; Matthiesen, Bho; Zappone, Alessio & Jorswieck, Eduard A.
  
• Neural Network Wiretap Code Design for Multi-Mode Fiber Optical Channels. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 8738-8742. IEEE.
  Besser, Karl-Ludwig; Lonnstrom, Andrew & Jorswieck, Eduard A.
  
• On the Set of Joint Rayleigh Fading Distributions Achieving Positive Zero-Outage Capacities. 2020 54th Asilomar Conference on Signals, Systems, and Computers, 882-886. IEEE.
  Besser, Karl-Ludwig; Lin, Pin-Hsun & Jorswieck, Eduard A.
  
• Reliability Bounds for Dependent Fading Wireless Channels. IEEE Transactions on Wireless Communications, 19(9), 5833-5845.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Review of Motion Artifacts Removing Techniques for Wireless Electrocardiograms. 2020 IEEE 23rd International Conference on Information Fusion (FUSION), 1-8. IEEE.
  Dargie, Waltenegus & Lilienthal, Jannis
  
• Wiretap Code Design by Neural Network Autoencoders. IEEE Transactions on Information Forensics and Security, 15, 3374-3386.
  Besser, Karl-Ludwig; Lin, Pin-Hsun; Janda, Carsten R. & Jorswieck, Eduard A.
  
• “Bounds on the Ergodic Secret-Key Capacity for Dependent Fading Channels”. In: WSA 2020 – 24th International ITG Workshop on Smart Antennas. Hamburg, Germany: VDE, Feb. 2020.
  K.-L. Besser & E. A. Jorswieck
  
• Achievable Physical-Layer Secrecy in Multi-Mode Fiber Channels using Artificial Noise. 2021 17th International Symposium on Wireless Communication Systems (ISWCS), 1-6. IEEE.
  Jorswieck, Eduard; Lonnstrom, Andrew; Besser, Karl-Ludwig; Rothe, Stefan & Czarske, Juergen W.
  
• Artificial Fast Fading from Reconfigurable Surfaces Enables Ultra-Reliable Communications. 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications (SPAWC), 566-570. IEEE.
  Jorswieck, Eduard; Besser, Karl-Ludwig & Sun, Cong
  
• Automatic Motion Artifact Removal in ECG with Canonical Polyadic Decomposition. 2021 29th European Signal Processing Conference (EUSIPCO), 1291-1295. IEEE.
  Lilienthal, Jannis & Dargie, Waltenegus
  
• Bounds on the Secrecy Outage Probability for Dependent Fading Channels. IEEE Transactions on Communications, 69(1), 443-456.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Calculation of Bounds on the Ergodic Capacity for Fading Channels with Dependency Uncertainty. ICC 2021 - IEEE International Conference on Communications, 1-6. IEEE.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Comparison of Reference Sensor Types and Position for Motion Artifact Removal in ECG. 2021 29th European Signal Processing Conference (EUSIPCO), 1296-1300. IEEE.
  Lilienthal, Jannis & Dargie, Waltenegus
  
• Copula-Based Bounds for Multi-User Communications–Part I: Average Performance. IEEE Communications Letters, 25(1), 3-7.
  Jorswieck, Eduard A. & Besser, Karl-Ludwig
  
• Copula-Based Bounds for Multi-User Communications–Part II: Outage Performance. IEEE Communications Letters, 25(1), 8-12.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• On Fading Channel Dependency Structures With a Positive Zero-Outage Capacity. IEEE Transactions on Communications, 69(10), 6561-6574.
  Besser, Karl-Ludwig; Lin, Pin-Hsun & Jorswieck, Eduard A.
  
• Spectral Characteristics of Motion Artifacts in Wireless ECG and their Correlation with Reference Motion Sensors. 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 517-521. IEEE.
  Lilienthal, Jannis & Dargie, Waltenegus
  
• “RIS-Assisted Statistical Channel Shaping for Ultra-High Reliability”. In: WSA 2021 – 25th International ITG Workshop on Smart Antennas. Sophia Antipolis, France: VDE, Nov. 2021, pp. 167–172.
  K.-L. Besser & E. A. Jorswieck
  
• On the Zero-Outage Secrecy-Capacity of Dependent Fading Wiretap Channels. Entropy, 24(1), 99.
  Jorswieck, Eduard; Lin, Pin-Hsun & Besser, Karl-Ludwig
  
• Reconfigurable Intelligent Surface Phase Hopping for Ultra-Reliable Communications. IEEE Transactions on Wireless Communications, 21(11), 9082-9095.
  Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Reinforcement Learning-Based Global Programming for Energy Efficiency in Multi-Cell Interference Networks. ICC 2022 - IEEE International Conference on Communications, 5499-5504. IEEE.
  Raghunath, Ramprasad; Peng, Bile; Besser, Karl-Ludwig & Jorswieck, Eduard A.
  
• Human Activity Recognition Based on Wireless Electrocardiogram and Inertial Sensors. IEEE Sensors Journal, 24(5), 6490-6499.
  Farrokhi, Sajad; Dargie, Waltenegus & Poellabauer, Christian