9 results
Now showing1 - 9 of 9
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , POSTER: Discrete wavelets as zero-parameter front-end for near-sensor cardiac-interval estimation from seismocardiographyWe present the Discrete Wavelet Transform (DWT) as a zero-parameter front-end for near-sensor cardiac-interval estimation from Seismocardiography (SCG), preserving timing-critical structure under embedded constraints. Across 10 wavelet families, we benchmark reconstruction, peak-timing fidelity, and energy on an nRF52840 SoC, showing that energy scales with filter length, while signal fidelity depends on wavelet family. This yields an energy-fidelity Pareto frontier for principled wavelet selection, with ongoing work extending this representation into neural network pipelines for cardiac interval estimation with morphology-dependent inductive bias.Publicationtype: Conference Paper3 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , At the edge of the heart: ULP FPGA-based CNN for on-device cardiac feature extraction in smart health sensors for astronauts(IEEE, 2026-06); ; ; ; The convergence of accelerating human spaceflight ambitions and critical terrestrial health monitoring demands is driving the unprecedented requirements for reliable and real-time feature extraction capabilities on extremely resource-constraint wearable health sensors. We present a ULP FPGA-based solution for real-time Seismocardiography (SCG) feature classification using Convolutional Neural Networks (CNNs). Our approach combines quantization-aware training with a systolic-array accelerator to enable efficient integer-only inference on the Lattice iCE40UP5K FPGA, which offers an ideal platform for battery-powered deployments - particularly in space environments - for their power efficiency and radiation resilience. The implementation achieves a validation accuracy of 98% while consuming only 8.55 mW of power, completing inference in 95.5 ms with minimal hardware resources (2,861 LUTs and 7 DSP blocks). These results demonstrate that fully on-device SCG-based cardiac feature extraction is feasible on resource-constrained hardware, enabling energy-efficient, autonomous health monitoring for astronauts in long-duration space missions.Publicationtype: Conference Paper23 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Undervolting experiments with LP-FPGAs in space(2026); ; ; Publicationtype: Conference Presentation6 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , At the edge of the heart: ULP FPGA-based CNN for on-device cardiac feature extraction in smart health sensors for astronautsThe convergence of accelerating human spaceflight ambitions and critical terrestrial health monitoring demands is driving the unprecedented requirements for reliable and real-time feature extraction capabilities on extremely resource-constraint wearable health sensors. We present a ULP FPGA-based solution for real-time Seismocardiography (SCG) feature classification using Convolutional Neural Networks (CNNs). Our approach combines quantization-aware training with a systolic-array accelerator to enable efficient integer-only inference on the Lattice iCE40UP5K FPGA, which offers an ideal platform for battery-powered deployments — particularly in space environments – for their power efficiency and radiation resilience. The implementation achieves a validation accuracy of 98% while consuming only 8.55 mW of power, completing inference in 95.5 ms with minimal hardware resources (2,861 LUTs and 7 DSP blocks). These results demonstrate that fully on-device SCG-based cardiac feature extraction is feasible on resource-constrained hardware, enabling energy-efficient, autonomous health monitoring for astronauts in long-duration space missions.Publicationtype: Conference Paper20 14 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Sorn-Based Cross-Correlation for Scg Signal Peak Detection in Resource-Constrained SystemsIn this paper, a novel computation scheme of the cross-correlation for seismocardiography (SCG) peak detection in resource-constrained systems is proposed. As cost-optimized FPGAs are usually considered in this scope that contain only a small number of DSPs, the excessive use of multipliers quickly exceeds the available fabric resources. To overcome this drawback, Sets-Of-Real-Numbers (SORNs) are taken into account, which generally leads to a significant reduction of complexity at the cost of precision impairments. For evaluation, cross-correlation hardware architecture is implemented in VHDL considering SORN-based multipliers into account and compared to standard fixed-point. The results show a reduction in complexity for LUTs of up to 46 %, highlighting our approach as a feasible solution for resource-constrained systems.Publicationtype: Conference Paper10 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Wavelet-driven denoising and cross-axis fusion for automated SCG systolic/diastolic window extractionReliable labeling of systolic and diastolic events in time-series seismocardiography (SCG) signals presents significant challenges due to morphological variability and susceptibility to motion artifacts. This research addresses this critical limitation through a novel signal processing framework leveraging triaxial SCG acquisition (SCGx, SCGy , SCGz ) and wavelet-based denoising. Our approach integrates multi-level Discrete Wavelet Transform decomposition for physiological band isolation, adap- tive coefficient thresholding for noise-robust feature preservation, and Inverse DWT reconstruction with moving-average filtering to extract systolic/diastolic envelopes. By exploiting inherent axis redundancy through cross-channel consensus and using synchro- nized ECG for cycle-level timing reference, we achieve robust automated segmentation of cardiac windows under real-world noise conditions. The resulting high-confidence labels establish a foundation for training resource-efficient neural networks to extract complex mechanical biomarkers directly at the sen- sor—advancing wearable cardiac monitoring beyond electrical activity toward precise mechanical function quantification.Publicationtype: Conference Paper15 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Hardware-accelerated Compression Core on RISC-V for Online-BCG Data ReductionEfficient compression of Ballistocardiography (BCG) data is critical for wearable and Ultra-Low-Power (ULP) applications, particularly in space-bound missions. This paper presents a hardware accelerator for data compression integrated into a NEORV32 RISC-V system specifically designed to enhance the performance of BCG sensors in resource-constraint environments. Utilizing hardware-accelerated Modified-Delta encoding with a software-based simple bit-packing compression can significantly improve real-time data transmission and storage efficiency. Implemented on the Lattice iCE40UP5K FPGA, the proposed method can achieve up to 13× speed improvement over traditional software solutions while maintaining a minimal footprint of 3719 Look-Up Tables (LUTs). This technique paves the way for ultra-efficient, wearable BCG sensors, which are crucial for, e.g. deep-space missions where energy and storage are at a premium.Publicationtype: Conference Paper15 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Identifying Gravity-Related Artifacts on Ballistocardiography Signals by Comparing Weightlessness and Normal Gravity Recordings (ARTIFACTS) : Protocol for an Observational Study(JMIR Publications, 2024-09-26); ; ; Background: Modern ballistocardiography (BCG) and seismocardiography (SCG) use acceleration sensors to measure oscillating recoil movements of the body caused by the heartbeat and blood flow, which are transmitted to the body surface. Acceleration artifacts occur through intrinsic sensor roll, pitch, and yaw movements, assessed by the angular velocities of the respective sensor, during measurements that bias the signal interpretation. Objective: This observational study aims to generate hypotheses on the detection and elimination of acceleration artifacts due to the intrinsic rotation of accelerometers and their differentiation from heart-induced sensor accelerations. Methods: Multimodal data from 4 healthy participants (3 male and 1 female) using BCG-SCG and an electrocardiogram will be collected and serve as a basis for signal characterization, model modulation, and location vector derivation under parabolic flight conditions from µg to 1.8g. The data will be obtained during a parabolic flight campaign (3 times 30 parabolas) between September 24 and July 25 (depending on the flight schedule). To detect the described acceleration artifacts, accelerometers and gyroscopes (6-degree-of-freedom sensors) will be used for measuring acceleration and angular velocities attributed to intrinsic sensor rotation. Changes in acceleration and angular velocities will be explored by conducting descriptive data analysis of resting participants sitting upright in varying gravitational states. Results: A multimodal data set will serve as a basis for research into a noninvasive and gentle method of BCG-SCG with the aid of low-noise and synchronous 3D gyroscopes and 3D acceleration sensors. Hypotheses will be generated related to detecting and eliminating acceleration artifacts due to the intrinsic rotation of accelerometers and gyroscopes (6-degree-of-freedom sensors) and their differentiation from heart-induced sensor accelerations. Data will be collected entirely and exclusively during the parabolic flights, taking place between September 2024 and July 2025. Thus, as of June 2024, no data have been collected yet. The data will be analyzed until December 2025. The results are expected to be published by June 2026. Conclusions: The study will contribute to understanding artificial acceleration bias to signal readings. It will be a first approach for a detection and elimination method.Publicationtype: Journal Article8 12 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , ISFD : Efficient and Fault-tolerant In-System-Failure-Detection for LP FPGA-based Smart-Sensors in Space Expeditions(IEEE, 2024-04); ; 10