Search

Endoscopic ultrasonography (EUS) has been found to be of great advantage in the diagnosis of digestive tract submucosal tumors. However, EUS-based diagnosis is limited by variability in subjective interpretation on the part of doctors. Tumor classification of ultrasound images with the computer-aided diagnosis system can significantly improve the diagnostic efficiency and accuracy of doctors. In this study, we proposed a multifeature fusion classification method for adaptive EUS tumor images. First, for different ultrasound tumor images, we selected the region of interest based on prior information to facilitate the estimation in the subsequent works. Second, we proposed a method based on image gray histogram feature extraction with principal component analysis dimensionality reduction, which learns the gray distribution of different tumor images effectively. Third, we fused the reduced grayscale features with the improved local binary pattern features and gray-level co-occurrence matrix features, and then used the multiclassification support vector machine. Finally, in the experiment, we selected the 431 ultrasound images of 109 patients in the hospital and compared the experimental effects of different features and different classifiers. The results revealed that the proposed method performed best, with the highest accuracy of 96.18% and an area under the curve of 99%. It is evident that the method proposed in this study can efficiently contribute to the classification of EUS tumor images. [ABSTRACT FROM AUTHOR]

Venipuncture is one of the common operations used by doctors in the outpatient blood drawing room. The success rate of puncture is not only related to the pain degree of the patient, but also affects the test results. In this study, we propose an ultrasound guided venipuncture vascular recognition system based on deep learning. First, kmeans++ clustering is performed for the vascular regions in the different B-mode ultrasound images to facilitate estimation in subsequent work. Second, a lightweight vascular ultrasound network (UV-YOLOv7) is designed, specifically, based on YOLOv7-tiny, a multi-scale feature fusion module (MFFM) is designed to better fuse the high-level semantic features and low-level detail features, and the speed and accuracy of model detection are enhanced by lightweighting the model structure and replacing the EIoU loss function. Finally, a Dynamic Neighborhood-Density Based Spatial Clustering of Applications with Noise (DN-DBSCAN) algorithm is proposed, which can cluster a series of local vascular regions using the localization results and confidence properties of the network output to remove the misdetected regions. In the experiment, We selected 303 artifact-free and 264 heavily artifacted vascular ultrasound images for offline expansion and trained on the experimental platform, The results show that the proposed method performed best with an mAP of 86.2% and an inference time of 0.6 ms. At the end of the experiment, more robust vascular localization results were obtained by DN-DBSCAN clustering. [ABSTRACT FROM AUTHOR]

IGBT power module is the key component of the power electronic converter, but it has the lowest reliability. The junction temperature is the crucial factor which affects power module’s reliability. To some extent, the power handling capability of the converter depends on the thermal stress of the power module. Thermal management is an effective method to improve the reliability of power device, as well as enhance the power capability. For this purpose, this paper introduces the reliability design to the power converter’s traditional compensation controller design for the first time. A new concept of generalized dual-loop controller, which includes temperature control loop and electric power control loop, is proposed. The reliability and stability of the system are both considered, with the help of the hybrid controller, the power converter can operate steadily with higher reliability. The novelty of this paper is to improve the thermal control method of carrier frequency adjustment through experimental implementation during the full life cycle of the converter. The target is to control the temperature variation to be almost a constant value as well as extend the lifetime of the converter. IR sensor is used to measure the chip temperature of the unpackaged IGBT module. The temperature variation and the average temperature are all considered in thermal management, from the reliability improvement point of view. At last, the idea is digital implemented based on a varying load of power inverter system with real-time measurement of the chip’s surface temperature. [ABSTRACT FROM AUTHOR]

We successfully synthesized a novel core-shell hybrid metal oxide via a simple one-step hydrothermal method without annealing. This composite of Co 3 O 4 particles covered with SnO 2 –SnO (Co 3 O 4 @SnO 2 –SnO) predicted better performance compared to pure Co 3 O 4 , which strongly depends on the synthetic temperature. The Co 3 O 4 @SnO 2 –SnO prepared at a temperature of 250 °C (labeled Co 3 O 4 @SnO 2 –SnO-250) exhibited an outstanding specific capacitance of 325 F g−1 under the current density of 1 A g−1, which was much higher than those of Co 3 O 4 (12.6 F g−1) and other composites. Additionally, the sample also exhibited good cycle stability performance with a retention rate of 100% after 5000 cycles at a current density of 5 A g−1. Through X-ray photoelectron spectroscopy analysis, the presumed mechanism was that Sn-O x decreases the surface electron densities of Co 3 O 4 , which is beneficial to OH− adsorption and specific capacitance improvement, and the synthetic temperature had a strong impact on the microstructure and thus on the surface electron densities. The most. obvious finding to emerge from this study is that the specific capacitance can be improved through adjusting the surface electron densities of transition metal oxides. [ABSTRACT FROM AUTHOR]

Chip fatigue inside an insulated gate bipolar transistor (IGBT) module is a kind of incipient defect. It can be considered as an indication of the impending failure, and is utmost important for the safe operation of IGBT modules. Therefore, monitoring the chip fatigue is one of crucial measures to enhance the operating reliability of IGBT modules. This paper presents a prognostic approach for the chip fatigue based on grey relational analysis (GRA), which uses dynamic change of the gate voltage as precursor parameter. This dynamic change is caused by aging of the intrinsic parasitic elements involved in gate drive circuit, which reflect the advent of chip fatigue. Grey relational grade is employed in this proposed prognostic approach to quantify the extent of those dynamic changes by little data, and find out potential chip fatigue. Then the operator would have a chance to schedule the maintenance and replace defective IGBT modules timely to avoid wear out. So it can be seen as a prefault diagnostic method. Finally, a confirmatory experiment is also carried out, and the correctness of the proposed approach is verified. [ABSTRACT FROM AUTHOR]