Attila Répai, Sándor Földi, Péter Sótonyi, György Cserey
Measuring the blood pressure waveform is becoming a more frequently studied area. The development of sensor technologies opens many new ways to be able to measure high-quality signals. The development of such an aim-specific sensor can be time-consuming, expensive, and difficult to test or validate with known and consistent waveforms. In this paper, we present an open source blood pressure waveform simulator with an open source Python validation package to reduce development costs for early-stage sensor development and research. The simulator mainly consists of 3D printed parts which technology has become a widely available and cheap solution. The core part of the simulator is a 3D printed cam that can be generated based on real blood pressure waveforms. The validation framework can create a detailed comparison between the signal waveform used to design the cam and the measured time series from the sensor being validated. The presented simulator proved to be robust and accurate in short- and long-term use, as it produced the signal waveform consistently and accurately. To validate this solution, a 3D force sensor was used, which was proven earlier to be able to measure high-quality blood pressure waveforms on the radial artery at the wrist. The results showed high similarity between the measured and the nominal waveforms, meaning that comparing the normalized signals, the RMSE value ranged from $0.0276 \pm 0.0047$ to $0.0212 \pm 0.0023$, and the Pearson correlation ranged from $0.9933 \pm 0.0027$ to $0.9978 \pm 0.0005$. Our validation framework is available at https://github.com/repat8/cam-bpw-sim. Our hardware framework, which allows reproduction of the presented solution, is available at https://github.com/repat8/cam-bpw-sim-hardware. The entire design is an open source project and was developed using free software.
Rizal Maulana, Ádám Rák, Sándor Földi, György Cserey
Continuous monitoring of physiological signals is essential for the early detection of health problems. A measurement system that ensures high sensitivity, accuracy, and user comfort is needed. In this study, we designed and optimized a flexible piezoresistive yarn (FPY) sensor to achieve a high sensitivity and wide working range for detecting physiological signals. The representative sensor design was constructed by applying an FPY bonding pattern, utilizing tightly arranged triangular patterns and using minimal FPY. The prototype sensor operates in two measurement modes, strain and pressure, and was evaluated for measuring neck motion, finger bending, respiratory signals, and arterial blood pressure (ABP) waveforms. A qualitative evaluation, performed by comparing the characteristics of the measurement results of each physiological signal with those from related studies, indicates a high similarity in its morphological characteristics. Then, a quantitative evaluation through baseline drift analysis demonstrates that the FPY sensor displays high measurement stability. The ABP waveform measurement shows the most stable baseline, with a mean absolute error (MAE) of $0.0051 \pm 0.0029$ in terms of baseline drift, using normalized values from 0 to 1. Based on our results, the prototype sensor can be used as an innovative solution for physiological signal monitoring and can be further enhanced for personalized healthcare and sports applications.
Dániel Horváth, Gábor Erdős, Zoltán Istenes, Tomáš Horváth, Sándor Földi
Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% mAP50 scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.