No abstract

The opening of a gated community to expand the micro-road network in an urban traffic system is an importance research topic related to urban congestion. To satisfy the demands of opening an early choosing case, this paper proposes a comprehensive selection framework on qualified communities and their appropriate opening times by describing the traffic state at the boundary road network accurately. The traffic entropy model and fuzzy c-means (FCM) method are used in this paper. In the framework, a new opening evaluation entropy model is built using basic theory of the thermodynamic traffic entropy method. The traffic state entropy values of the boundary road network and entropy production are calculated to determinate the opening time. In addition, a specific fuzzy range evaluation standard at a preset gated community is drawn with an FCM algorithm to verify the opening determination. A case study based on the traffic information in a simulated gated community in Shanghai is evaluated and proves that the findings of opening evaluation are in accordance with the actual situation. It is found that the micro-inter-road network of a gated community should be opened as the entropy value reaches 2.5. As the travel time is less than 20 s, the correlation between the opening entropy value and the journey delay time exhibits a good linear correlation, which indicates smooth traffic flow.

Deep learning–based segmentation models usually require substantial data, and the model usually suffers from poor generalization due to the lack of training data and inefficient network structure. We proposed to combine the deformable model and medical transformer neural network on the image segmentation task to alleviate the aforementioned problems. The proposed method first employs a statistical shape model to generate simulated contours of the target object, and then the thin plate spline is applied to create a realistic texture. Finally, a medical transformer network was constructed to segment three types of medical images, including prostate MR image, heart US image, and tongue color images. The segmentation accuracy of the three tasks achieved 89.97%, 91.90%, and 94.25%, respectively. The experimental results show that the proposed method improves medical image segmentation performance. Graphical abstract

No abstract

No abstract