Daniel Teichmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Daniel Teichmann has a total of 135 co-authors. Here are the top co-authors by number of shared publications:
- Steffen Leonhardt
RWTH Aachen University
21 shared publications - Marian Walter
Institute for Medical Information Technology, RWTH Aachen University,Aachen,Germany
8 shared publications - Rifa Atul Izza Asyari
SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, 5230, Denmark
4 shared publications - Xinchi Yu
Department of Geriatric Medicine (Medical Clinic VI), RWTH Aachen University Hospital, Aachen, Germany
4 shared publications - Anna Boehm
Chair for Medical Information Technology, RWTH Aachen University, Pauwelsstr. 20, 52074 Aachen, Germany
3 shared publications - Carina Barbosa Pereira
Department of Anesthesiology, Faculty of Medicine, RWTH Aachen University, 52074 Aachen, Germany
3 shared publications
Latest Publications
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (8) , 2662-2665
Guest Editorial: Introducton to the 2025 EMBC Special Issue of the IEEE Transactions on Biomedical Engineering
- 1 August 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (8) , 2662-2665
Guest Editorial: Introducton to the 2025 EMBC Special Issue of the IEEE Transactions on Biomedical Engineering
- Open Access
MOE-ECG: Multi-Objective Ensemble Fusion for Robust Atrial Fibrillation Detection Using Electrocardiograms
Background: Atrial fibrillation (AFib) is the most common sustained arrhythmia in the world, imposing a heavy clinical and economic burden on global healthcare systems. Early detection of AFib can reduce mortality and morbidity, while helping to alleviate the growing economic burden of cardiovascular diseases. With the increasing availability of digital health technologies, computational solutions have great potential to support the timely diagnosis of cardiac abnormalities. Objectives: With the increasing availability of electrocardiogram (ECG) data from clinical and wearable devices, manual interpretation has become impractical due to its time-consuming and subjective nature. Existing automated approaches often rely on single classifiers or fixed ensembles that primarily optimize predictive accuracy while neglecting model diversity, which leads to limited robustness and generalization across heterogeneous datasets. Therefore, this study aims to develop a robust and diversity-aware framework for automatic AFib detection that simultaneously improves classification performance and model generalizability. To this end, we propose MOE-ECG, a multi-objective ensemble selection and fusion framework that explicitly optimizes both predictive performance and inter-model diversity for reliable AFib detection from ECG recordings. Methods: The proposed multi-objective ensemble (MOE) framework uses ensemble selection as a bi-objective optimization problem and employs multi-objective particle swarm optimization to identify complementary classifiers from a heterogeneous model pool. Unlike conventional ensembles, it explicitly optimizes both predictive performance and diversity and integrates Dempster–Shafer theory for uncertainty-aware decision fusion. After filtering the ECG signals to remove baseline wander and noise, they were segmented into windows of 20, 60, and 120 heartbeats with 50% overlap. The proposed approach was evaluated over five independent runs to assess its stability and generalization. Fifteen statistical and nonlinear features were obtained from the RR-intervals of the pre-processed ECG signals, of which eight features were selected with correlation analysis to capture subtle information from the ECG data. We trained and evaluated the performance of the proposed model in three open source databases, namely, the MIT-BIH Atrial Fibrillation Database, Saitama Heart Database Atrial Fibrillation, and Long-Term AF Database. Results: The proposed approach achieved the best overall performance on 60-beat segments, with an average accuracy of 89.85%, precision of 91.14%, recall of 94.19%, an F 1 -score of 92.64%, and area under the curve (AUC) of around 0.95. Statistical analysis using Holm-adjusted Wilcoxon tests confirmed significant improvements ( p < 0.05) compared to both the best individual classifier and the unoptimized average ensemble of all classifiers. These findings show that the proposed selection and evaluation methodology, rather than group aggregation alone, is the key driver of performance improvements. Conclusion: The results obtained demonstrate that the MOE-ECG model offers a robust, accurate, and reliable solution for the detection of AFib from short ECG segments. The empirical findings, in general, confirm that multi-objective ensemble fusion enhances diagnostic performance and offers robust predictions that will open up possibilities for real-time AFib detection in clinical and tele-health settings.
Open AccessMOE-ECG: Multi-Objective Ensemble Fusion for Robust Atrial Fibrillation Detection Using Electrocardiograms
Background: Atrial fibrillation (AFib) is the most common sustained arrhythmia in the world, imposing a heavy clinical and economic burden on global healthcare systems. Early detection of AFib can reduce mortality and morbidity, while helping to alleviate the growing economic burden of cardiovascular diseases. With the increasing availability of digital health technologies, computational solutions have great potential to support the timely diagnosis of cardiac abnormalities. Objectives: With the increasing availability of electrocardiogram (ECG) data from clinical and wearable devices, manual interpretation has become impractical due to its time-consuming and subjective nature. Existing automated approaches often rely on single classifiers or fixed ensembles that primarily optimize predictive accuracy while neglecting model diversity, which leads to limited robustness and generalization across heterogeneous datasets. Therefore, this study aims to develop a robust and diversity-aware framework for automatic AFib detection that simultaneously improves classification performance and model generalizability. To this end, we propose MOE-ECG, a multi-objective ensemble selection and fusion framework that explicitly optimizes both predictive performance and inter-model diversity for reliable AFib detection from ECG recordings. Methods: The proposed multi-objective ensemble (MOE) framework uses ensemble selection as a bi-objective optimization problem and employs multi-objective particle swarm optimization to identify complementary classifiers from a heterogeneous model pool. Unlike conventional ensembles, it explicitly optimizes both predictive performance and diversity and integrates Dempster–Shafer theory for uncertainty-aware decision fusion. After filtering the ECG signals to remove baseline wander and noise, they were segmented into windows of 20, 60, and 120 heartbeats with 50% overlap. The proposed approach was evaluated over five independent runs to assess its stability and generalization. Fifteen statistical and nonlinear features were obtained from the RR-intervals of the pre-processed ECG signals, of which eight features were selected with correlation analysis to capture subtle information from the ECG data. We trained and evaluated the performance of the proposed model in three open source databases, namely, the MIT-BIH Atrial Fibrillation Database, Saitama Heart Database Atrial Fibrillation, and Long-Term AF Database. Results: The proposed approach achieved the best overall performance on 60-beat segments, with an average accuracy of 89.85%, precision of 91.14%, recall of 94.19%, an F 1 -score of 92.64%, and area under the curve (AUC) of around 0.95. Statistical analysis using Holm-adjusted Wilcoxon tests confirmed significant improvements ( p < 0.05) compared to both the best individual classifier and the unoptimized average ensemble of all classifiers. These findings show that the proposed selection and evaluation methodology, rather than group aggregation alone, is the key driver of performance improvements. Conclusion: The results obtained demonstrate that the MOE-ECG model offers a robust, accurate, and reliable solution for the detection of AFib from short ECG segments. The empirical findings, in general, confirm that multi-objective ensemble fusion enhances diagnostic performance and offers robust predictions that will open up possibilities for real-time AFib detection in clinical and tele-health settings.
- 27 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (9) , 16151-16169
Facial Remote Photoplethysmography for Continuous Heart Rate, Stroke Volume, and Systemic Vascular Resistance Monitoring During Prolonged Warm/Cold Fluid Bolus Administration
Hemodynamic parameters—stroke volume (SV), systemic vascular resistance (SVR), and heart rate (HR)—are critical for clinical monitoring, particularly in emergency and critical care settings. This study evaluates the feasibility of a non-invasive, noncontact monitoring approach using imaging photoplethysmography (iPPG), which applies camera-based PPG and a signal processing pipeline implemented in MATLAB. A total of 25 prolonged video recordings ( 2500 minutes) were collected from 16 healthy volunteers at Odense University Hospital while they received intravenous infusions of warm (37°C) and cold (15°C) Ringer’s lactate. To ensure data reliability, video quality and head motion were systematically analyzed. HR estimation using the Plane-Orthogonal-to-Skin (POS) method achieved an average absolute error of 4.28 bpm, with a best accuracy of 2.18 bpm, while the CHROM method yielded similar performance (4.27 bpm average error, 2.55 bpm best accuracy). SV and SVR demonstrated moderate correlation with reference measures (r = 0.571 and r = 0.596, respectively) across five regions of interest. The best correlations for SV and SVR were r = 0.846 and r = 0.873, respectively, indicating strong potential for accurate noncontact monitoring. These results suggest that iPPG can provide real-time cardiovascular insights during fluid therapy, with potential applications in telemedicine and mobile health. However, to robustly generalize the findings of this study, limitations such as inter-individual variability and the need to include diverse patient populations should be considered. This study provides the first demonstration of iPPG feasibility for prolonged emergency fluid administration, paving the way for further research in dynamic clinical environments.
- 27 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (9) , 16151-16169
Facial Remote Photoplethysmography for Continuous Heart Rate, Stroke Volume, and Systemic Vascular Resistance Monitoring During Prolonged Warm/Cold Fluid Bolus Administration
Hemodynamic parameters—stroke volume (SV), systemic vascular resistance (SVR), and heart rate (HR)—are critical for clinical monitoring, particularly in emergency and critical care settings. This study evaluates the feasibility of a non-invasive, noncontact monitoring approach using imaging photoplethysmography (iPPG), which applies camera-based PPG and a signal processing pipeline implemented in MATLAB. A total of 25 prolonged video recordings ( 2500 minutes) were collected from 16 healthy volunteers at Odense University Hospital while they received intravenous infusions of warm (37°C) and cold (15°C) Ringer’s lactate. To ensure data reliability, video quality and head motion were systematically analyzed. HR estimation using the Plane-Orthogonal-to-Skin (POS) method achieved an average absolute error of 4.28 bpm, with a best accuracy of 2.18 bpm, while the CHROM method yielded similar performance (4.27 bpm average error, 2.55 bpm best accuracy). SV and SVR demonstrated moderate correlation with reference measures (r = 0.571 and r = 0.596, respectively) across five regions of interest. The best correlations for SV and SVR were r = 0.846 and r = 0.873, respectively, indicating strong potential for accurate noncontact monitoring. These results suggest that iPPG can provide real-time cardiovascular insights during fluid therapy, with potential applications in telemedicine and mobile health. However, to robustly generalize the findings of this study, limitations such as inter-individual variability and the need to include diverse patient populations should be considered. This study provides the first demonstration of iPPG feasibility for prolonged emergency fluid administration, paving the way for further research in dynamic clinical environments.
- Open Access
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (3) , 4157-4166
Reflective PPG Sensor Measures Heart Rate Through Clothing During Driving
This paper presents the development and validation of a reflective photoplethysmography (PPG) sensor designed for unobtrusive heart rate monitoring through clothing in automotive environments. The sensor is integrated into the backrest of a car seat and employs an optimized hardware configuration to enhance signal acquisition and mitigate motion artifacts during driving. Its performance was evaluated in two scenarios: a validation study with 12 participants driving for a total of 316 minutes and a longitudinal field study encompassing 1080 minutes of driving across three European countries. The validation study demonstrated a concordance correlation coefficient (CCC) of 0.89, a mean absolute error (MAE) of 2.51 bpm, and a mean absolute percentage error (MAPE) of 3.07%. Gender-specific analysis revealed minimal differences in performance, with an overall coverage rate of 77.60%. The longitudinal study confirmed the sensor’s reliability over prolonged periods, achieving a CCC of 0.976, MAE of 0.844 bpm, and MAPE of 1.04%, with a 95.92% coverage rate across diverse driving conditions.
- 16 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (3) , 4157-4166
Open AccessReflective PPG Sensor Measures Heart Rate Through Clothing During Driving
This paper presents the development and validation of a reflective photoplethysmography (PPG) sensor designed for unobtrusive heart rate monitoring through clothing in automotive environments. The sensor is integrated into the backrest of a car seat and employs an optimized hardware configuration to enhance signal acquisition and mitigate motion artifacts during driving. Its performance was evaluated in two scenarios: a validation study with 12 participants driving for a total of 316 minutes and a longitudinal field study encompassing 1080 minutes of driving across three European countries. The validation study demonstrated a concordance correlation coefficient (CCC) of 0.89, a mean absolute error (MAE) of 2.51 bpm, and a mean absolute percentage error (MAPE) of 3.07%. Gender-specific analysis revealed minimal differences in performance, with an overall coverage rate of 77.60%. The longitudinal study confirmed the sensor’s reliability over prolonged periods, achieving a CCC of 0.976, MAE of 0.844 bpm, and MAPE of 1.04%, with a 95.92% coverage rate across diverse driving conditions.
- Open Access
Innovative Seatbelt-Integrated Metasurface Radar for Enhanced In-Car Healthcare Monitoring
This study introduces a novel seatbelt-integrated, non-invasive, beam-focusing metamaterial sensing system characterized by its thinness and flexibility. The system comprises a flexible transmitarray lens and an FMCW radar sensor, enabling the accurate detection and analysis of seatbelt usage and positioning through human tissue. The metasurface design remains effective even when subjected to different bending angles. Our system closely tracks heart rate and respiration, validated against standard reference methods, highlighting its potential for enhancing in-car healthcare monitoring. Experimental results demonstrate the system’s reliability in monitoring physiological signals within dynamic vehicular environments.
Open AccessInnovative Seatbelt-Integrated Metasurface Radar for Enhanced In-Car Healthcare Monitoring
This study introduces a novel seatbelt-integrated, non-invasive, beam-focusing metamaterial sensing system characterized by its thinness and flexibility. The system comprises a flexible transmitarray lens and an FMCW radar sensor, enabling the accurate detection and analysis of seatbelt usage and positioning through human tissue. The metasurface design remains effective even when subjected to different bending angles. Our system closely tracks heart rate and respiration, validated against standard reference methods, highlighting its potential for enhancing in-car healthcare monitoring. Experimental results demonstrate the system’s reliability in monitoring physiological signals within dynamic vehicular environments.
- Open Access
- 18 October 2024
- Published by MDPI AG in Preprints.org
Innovative Seatbelt-Integrated Metasurface Radar for Enhanced In-Car Healthcare Monitoring
This study introduces a novel seatbelt-integrated, non-invasive beam-focusing metamaterial sensing system characterized by its thinness and flexibility. The system comprises a flexible transmitarray lens and an FMCW radar sensor, enabling accurate detection and analysis of seatbelt usage and positioning through human tissue. The metasurface design remains effective even when subjected to different bending angles. Our system closely tracks heart rate and respiration, validated against standard reference methods, highlighting its potential for enhancing in-car healthcare monitoring. Experimental results demonstrate the system’s reliability in monitoring physiological signals within dynamic vehicular environments.
- 18 October 2024
- Published by MDPI AG in Preprints.org
Open AccessInnovative Seatbelt-Integrated Metasurface Radar for Enhanced In-Car Healthcare Monitoring
This study introduces a novel seatbelt-integrated, non-invasive beam-focusing metamaterial sensing system characterized by its thinness and flexibility. The system comprises a flexible transmitarray lens and an FMCW radar sensor, enabling accurate detection and analysis of seatbelt usage and positioning through human tissue. The metasurface design remains effective even when subjected to different bending angles. Our system closely tracks heart rate and respiration, validated against standard reference methods, highlighting its potential for enhancing in-car healthcare monitoring. Experimental results demonstrate the system’s reliability in monitoring physiological signals within dynamic vehicular environments.
- Open Access
On-Road Evaluation of Unobtrusive In-Car Respiration Monitoring
This paper introduces and evaluates an innovative sensor for unobtrusive in-car respiration monitoring, mounted on the backrest of the driver’s seat. The sensor seamlessly integrates into the vehicle, measuring breathing rates continuously without requiring active participation from the driver. The paper proves the feasibility of unobtrusive in-car measurements over long periods of time. Operation of the sensor was investigated over 12 participants sitting in the driver seat. A total of 107 min of driving in diverse conditions with overall coverage rate of 84.45% underscores the sensor potential to reliably capture physiological changes in breathing rate for fatigue and stress detection.
Open AccessOn-Road Evaluation of Unobtrusive In-Car Respiration Monitoring
This paper introduces and evaluates an innovative sensor for unobtrusive in-car respiration monitoring, mounted on the backrest of the driver’s seat. The sensor seamlessly integrates into the vehicle, measuring breathing rates continuously without requiring active participation from the driver. The paper proves the feasibility of unobtrusive in-car measurements over long periods of time. Operation of the sensor was investigated over 12 participants sitting in the driver seat. A total of 107 min of driving in diverse conditions with overall coverage rate of 84.45% underscores the sensor potential to reliably capture physiological changes in breathing rate for fatigue and stress detection.
- Open Access
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
A Quasi-3-D Impedance Measurement Using the Square Wave Method With Parallactic Excitation for Detection of Biofilm Growth
The detection and monitoring of microorganisms is of emerging interest for various industries. In this regard, an extremely important issue is biofilm-related infections in the healthcare industry demanding their early detection and monitoring. For several decades, impedance sensors have garnered significant interest in detecting bacteria due to their simple and label-free measurements. A fast impedance measurement device based on time-domain analysis was developed and used for monitoring the formation of Escherichia coli (E. coli) biofilms in real time. Using an electrode array providing 2D information together with parallactic excitation yielded quasi-3D resolution. A chamber with 2x16 electrodes was designed for this purpose. For evaluation of the time-domain-based measurement, we compared it with impedance measurements in the frequency domain, which showed a similar trend in impedance measurement. A finite element method (FEM) modeling has been utilized for reverse problem-solving or image reconstruction. The reconstructed images were then compared with confocal laser scanning microscopy (CLSM) images yielding a promising correlation. Therewith, the feasibility of using the fast impedance measurement for the detection of biofilm growth with quasi-3d resolution has been demonstrated. This approach can serve as a viable method for the development of portable devices dedicated to the detection of tissue infections.
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-11
Open AccessA Quasi-3-D Impedance Measurement Using the Square Wave Method With Parallactic Excitation for Detection of Biofilm Growth
The detection and monitoring of microorganisms is of emerging interest for various industries. In this regard, an extremely important issue is biofilm-related infections in the healthcare industry demanding their early detection and monitoring. For several decades, impedance sensors have garnered significant interest in detecting bacteria due to their simple and label-free measurements. A fast impedance measurement device based on time-domain analysis was developed and used for monitoring the formation of Escherichia coli (E. coli) biofilms in real time. Using an electrode array providing 2D information together with parallactic excitation yielded quasi-3D resolution. A chamber with 2x16 electrodes was designed for this purpose. For evaluation of the time-domain-based measurement, we compared it with impedance measurements in the frequency domain, which showed a similar trend in impedance measurement. A finite element method (FEM) modeling has been utilized for reverse problem-solving or image reconstruction. The reconstructed images were then compared with confocal laser scanning microscopy (CLSM) images yielding a promising correlation. Therewith, the feasibility of using the fast impedance measurement for the detection of biofilm growth with quasi-3d resolution has been demonstrated. This approach can serve as a viable method for the development of portable devices dedicated to the detection of tissue infections.
- 14 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 8 (3) , 1-4
60 GHz FMCW Millimeter Wave Radar Assisted With Dual-Layer Wideband Flexible Metasurface for Accurate Wrist Pulse Monitoring
This letter presents a novel passive focusing metasurface designed for wrist pulse detection within the 60 GHz millimeter wave frequency range, incorporating a dual-layer transmitarray antenna. The proposed metasurface demonstrates exceptional polarization characteristics and a high degree of operational efficiency, as substantiated by rigorous far-field assessments. This innovative metasurface has significant potential for applications in human-device interfaces, health monitoring systems, and safety screening protocols, where the ability to focus and manipulate waves with flexibility is paramount. We rigorously evaluated its radiative safety and compared its efficacy with a conventional photoplethysmogram (PPG) reference. The results show a close agreement between our proposed design and the PPG.
- 14 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 8 (3) , 1-4
60 GHz FMCW Millimeter Wave Radar Assisted With Dual-Layer Wideband Flexible Metasurface for Accurate Wrist Pulse Monitoring
This letter presents a novel passive focusing metasurface designed for wrist pulse detection within the 60 GHz millimeter wave frequency range, incorporating a dual-layer transmitarray antenna. The proposed metasurface demonstrates exceptional polarization characteristics and a high degree of operational efficiency, as substantiated by rigorous far-field assessments. This innovative metasurface has significant potential for applications in human-device interfaces, health monitoring systems, and safety screening protocols, where the ability to focus and manipulate waves with flexibility is paramount. We rigorously evaluated its radiative safety and compared its efficacy with a conventional photoplethysmogram (PPG) reference. The results show a close agreement between our proposed design and the PPG.
- Open Access
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology
- Vol. 8 (1) , 36-50
A Novel Approach to Remote Detection in Medical Radar Applications Using Flexible Transmit Array Lenses
This study introduces a novel method employing adaptable transmitarray lenses for medical radar systems, enhancing the direction of electromagnetic beams in the far-field. The newly developed antenna array exhibited marked improvements in gain, bandwidth, return loss, and isolation within specific frequency ranges during testing. Comprehensive evaluations, including various focal lengths and bending scenarios, underscored the superior performance of this adaptable lens over prior techniques. Its exceptional precision and sensitivity render it an ideal tool for real-time remote health monitoring systems, particularly in pulse detection. The research findings consistently aligned the heart rates detected by this innovative method with standard reference rates, reaffirming its reliability and accuracy. This consistency highlights the potential of the transmitarray lenses as a valuable advancement in medical radar systems. The study not only validates the effectiveness and reliability of the lenses but also lays a solid foundation for further research and development in this field. The insights garnered are expected to significantly bolster the progression of radar technologies in healthcare, leading to more accurate, efficient, and non-invasive health monitoring solutions, thereby enhancing patient care and outcomes.
- 16 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology
- Vol. 8 (1) , 36-50
Open AccessA Novel Approach to Remote Detection in Medical Radar Applications Using Flexible Transmit Array Lenses
This study introduces a novel method employing adaptable transmitarray lenses for medical radar systems, enhancing the direction of electromagnetic beams in the far-field. The newly developed antenna array exhibited marked improvements in gain, bandwidth, return loss, and isolation within specific frequency ranges during testing. Comprehensive evaluations, including various focal lengths and bending scenarios, underscored the superior performance of this adaptable lens over prior techniques. Its exceptional precision and sensitivity render it an ideal tool for real-time remote health monitoring systems, particularly in pulse detection. The research findings consistently aligned the heart rates detected by this innovative method with standard reference rates, reaffirming its reliability and accuracy. This consistency highlights the potential of the transmitarray lenses as a valuable advancement in medical radar systems. The study not only validates the effectiveness and reliability of the lenses but also lays a solid foundation for further research and development in this field. The insights garnered are expected to significantly bolster the progression of radar technologies in healthcare, leading to more accurate, efficient, and non-invasive health monitoring solutions, thereby enhancing patient care and outcomes.