[Research on portable airway impedance monitoring device based on expiratory oscillation].

Monitoring airway impedance has significant clinical value in accurately assessing and diagnosing pulmonary function diseases at an early stage. To address the issue of large oscillator size and high power consumption in current pulmonary function devices, this study adopts a new strategy of expiration-driven oscillation. A lightweight and low-power airway impedance monitoring system with integrated sensing, control circuitry, and dynamic feedback system, providing visual feedback on the system's status, was developed. The respiratory impedance measurement experiments and statistical comparisons indicated that the system could achieve stable measurement of airway impedance at 5 Hz. The frequency spectrum curves of respiratory impedance ( R and X) showed consistent trends with those obtained from the clinical pulmonary function instrument, specifically the impulse oscillometry system (IOS). The differences between them were all less than 1.1 cm H 2O·s/L. Additionally, there was a significant statistical difference in the respiratory impedance R5 between the exercise and rest groups, which suggests that the system can measure the variability of airway resistance parameters during exercise. Therefore, the impedance monitoring system developed in this study supports subjects in performing handheld, continuous measurements of dynamic changes in airway impedance over an extended period of time. This research provides a foundation for further developing low-power, portable, and even wearable devices for dynamic monitoring of pulmonary function.

Research on 3D virtual vision matching based on interactive color segmentation.

Given the prevalent issues surrounding accuracy and efficiency in contemporary stereo-matching algorithms, this research introduces an innovative image segmentation-based approach. The proposed methodology integrates residual and Swim Transformer modules into the established 3D Unet framework, yielding the Res-Swim-UNet image segmentation model. The algorithm estimates the disparateness of segmented outputs by employing regression techniques, culminating in a comprehensive disparity map. Experimental findings underscore the superiority of the proposed algorithm across all evaluated metrics. Specifically, the proposed network demonstrates marked improvements, with IoU and mPA enhancements of 2.9% and 162%, respectively. Notably, the average matching error rate of the algorithm registers at 2.02%, underscoring its efficacy in achieving precise stereoscopic matching. Moreover, the model's enhanced generalization capability and robustness underscore its potential for widespread applicability.