http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Risk assessment of aviation DC series arc based on reconstructed CBAM‑CNN
Haoqi Yang,Cong Gao,Hongjuan Ge,Yiqin Sang,Yongshuai Wang 전력전자학회 2023 JOURNAL OF POWER ELECTRONICS Vol.23 No.5
The hazards of sustained arc and un-sustained arc are different. However, during the stage of arc development, there is a lack of effective methods to identify them, which is not conducive to the timely accurate assessment of arc risk. Therefore, this paper proposes a risk assessment method for aviation DC series arc based on a reconstructed CBAM-CNN. First, in the process of generating the feature set, a feature evaluation function is defined to screen the features. Then the existing convolution block attention module (CBAM) is improved by adding a reshaped layer and redefining spatial attention, which results in the reconstructed CBAM-CNN. Finally, the reconstructed CBAM-CNN takes the feature set as its input and output arc risk assessment results on the basis of enhancing the attention of important features. The validity of the reconstructed CBAM-CNN method is verified on an aviation DC arc generation platform. It is found that the proposed method has a higher training efficiency and evaluation accuracy than the CNN method and CBAM-CNN method. In addition, the reconstructed CBAM-CNN involves fewer parameters to be measured, which can reduce its dependence on computing resources.
Yi Qin,Zhao-hui Jin,Zhen-ying Zhang,Ke-ke Chen,Xin Yu,Hong-jiao Yan,Rui-dan Wang,Yuan Su,Ai-xian Liu,Jia-ning Xi,Bo-yan Fang 대한신경과학회 2023 Journal of Clinical Neurology Vol.19 No.1
Background and Purpose Orthostatic hypotension (OH) is common in patients with Parkinson’s disease (PD). Early recognition OH is required with sensitive assessments. The purpose of this study was to determine whether blood pressure (BP) changes during exercise can predict the occurrence of OH in PD. Methods This prospective cohort study included 80 consecutive patients with PD. All patients agreed to participate in a baseline evaluation and cardiopulmonary exercise test (CPET). According to the initial active standing test (AST), those without OH (PD-nonOH) at baseline had their AST results followed up for 6 months. The main outcome was defined as whether patients without OH at baseline would develop OH after 6 months. Logistic regression analysis was applied to identify the relevant variables. A nomogram was constructed based on clinical features and identified variables. The concordance index (C-index) and area under the receiver operating characteristic curve (AUC) were used to evaluate the accuracy and predictive ability of the nomogram, respectively. Results CPET results indicated that peak load, peak heart rate, heart rate recovery at 1 min, and systolic BP change (ΔSBP) were lower in those with OH than in the PD-nonOH group (p<0.05) at baseline. Logistic regression analysis indicated that peak load and ΔSBP during CPET had significant effects on OH (p<0.05). Age, sex, peak load, and ΔSBP were used to construct the nomogram model (C-index=0.761). The prediction model had an AUC of 0.782 (95% confidence interval=0.649–0.889) and a specificity and sensitivity of 70.0% and 81.8%, respectively. Conclusions This study has identified predictive factors for OH development in patients with PD. CPET could be used as a complementary examination to identify patients at a high risk of OH.