Traditional silicon-based micro-electro-mechanical system (MEMS) safety and arming devices, such as electro-thermal and electrostatically driven MEMS safety and arming devices, experience problems of high insecurity and require high voltage drive. For the current electromagnetic drive mode, the electromagnetic drive device is too large to be integrated. In order to address this problem, we present a new micro electromagnetically driven MEMS safety and arming device, in which the electromagnetic coil is small in size, with a large electromagnetic force. We firstly designed and calculated the geometric structure of the electromagnetic coil, and analyzed the model using COMSOL multiphysics field simulation software. The resulting error between the theoretical calculation and the simulation of the mechanical and electrical properties of the electromagnetic coil was less than 2% under the same size. We then carried out a parametric simulation of the electromagnetic coil, and combined it with the actual processing capacity to obtain the optimized structure of the electromagnetic coil. Finally, the electromagnetic coil was processed by deep silicon etching and the MEMS casting process. The actual electromagnetic force of the electromagnetic coil was measured on a micro-mechanical test system, compared with the simulation, and the comparison results were analyzed.

Background: Wound treatment in emergency care requires the rapid assessment of wound size by medical staff. Limited medical resources and the empirical assessment of wounds can delay the treatment of patients, and manual contact measurement methods are often inaccurate and susceptible to wound infection. This study aimed to prepare an Automatic Wound Segmentation Assessment (AWSA) framework for real-time wound segmentation and automatic wound region estimation. Methods: This method comprised a short-term dense concatenate classification network (STDC-Net) as the backbone, realizing a segmentation accuracy–prediction speed trade-off. A coordinated attention mechanism was introduced to further improve the network segmentation performance. A functional relationship model between prior graphics pixels and shooting heights was constructed to achieve wound area measurement. Finally, extensive experiments on two types of wound datasets were conducted. Results: The experimental results showed that real-time AWSA outperformed state-of-the-art methods such as mAP, mIoU, recall, and dice score. The AUC value, which reflected the comprehensive segmentation ability, also reached the highest level of about 99.5%. The FPS values of our proposed segmentation method in the two datasets were 100.08 and 102.11, respectively, which were about 42% higher than those of the second-ranked method, reflecting better real-time performance. Moreover, real-time AWSA could automatically estimate the wound area in square centimeters with a relative error of only about 3.1%. Conclusion: The real-time AWSA method used the STDC-Net classification network as its backbone and improved the network processing speed while accurately segmenting the wound, realizing a segmentation accuracy–prediction speed trade-off.

Vehicle target detection is a key technology for reconnaissance unmanned aerial vehicles (UAVs). However, in order to obtain a larger reconnaissance field of view, this type of UAV generally flies at a higher altitude, resulting in a relatively small proportion of vehicle targets in its imaging images. Moreover, due to the unique nature of the mission, previously unseen vehicle types are prone to appearing in the surveillance area. Additionally, it is challenging for large-scale detectors based on deep learning to achieve real-time performance on UAV computing equipment. To address these problems, we propose a vehicle object detector specifically designed for UAVs in this paper. We have made modifications to the backbone of Faster R-CNN based on the target and scene characteristics. We have improved the positioning accuracy of small-scale imaging targets by adjusting the size and ratio of anchors. Furthermore, we have introduced a postprocessing method for out-of-distribution detection, enabling the designed detector to detect and distinguish untrained vehicle types. Additionally, to tackle the scarcity of reconnaissance images, we have constructed two datasets using modeling and image rendering techniques. We have evaluated our method on these constructed datasets. The proposed method achieves a 96% mean Average Precision at IoU threshold 0.5 (mAP₅₀) on trained objects and a 71% mAP₅₀ on untrained objects. Equivalent flight experiments demonstrate that our model, trained on synthetic data, can achieve satisfactory detection performance and computational efficiency in practical applications.