Revealing disparities in different types of park visits based on cellphone signaling data in Guangzhou, China.

Urban parks play a crucial role in promoting the urban ecological environment and the health and well-being of dwellers. However, existing research on park visits and drivers has largely ignored the classification of parks. Using the four-level park system in Guangzhou as a case, this study first measured park visits based on cellphone signaling data. Then, the independent and interactive influences of driving factors on the visits of four types of parks were investigated and compared comprehensively based on the geographical detector model. The factor detector model preliminarily distinguished the functional and role differences of various park types. Nature and urban parks are more functional, and community and pocket parks mainly provide nearby residents with convenient relaxation spaces. The interaction detector further revealed the disparities in park visit drivers between four types of parks. The most significant finding is that nearby recreational facility is the key to the use of natural and urban parks, while the determining factor for the visits of community and pocket parks is the surrounding population. Based on these findings, the study recommends tailored strategies for each type of park, to promote effective management and increased utilization. In particular, the study highlights the importance of understanding the differences between park types and developing customized strategies to maximize the benefits of urban parks and foster a healthy and sustainable urban environment.

Accurate and lightweight MRI super-resolution via multi-scale bidirectional fusion attention network.

High-resolution magnetic resonance (MR) imaging has attracted much attention due to its contribution to clinical diagnoses and treatment. However, because of the interference of noise and the limitation of imaging equipment, it is expensive to generate a satisfactory image. Super-resolution (SR) is a technique that enhances an imaging system's resolution, which is effective and cost-efficient for MR imaging. In recent years, deep learning-based SR methods have made remarkable progress on natural images but not on medical images. Most existing medical images SR algorithms focus on the spatial information of a single image but ignore the temporal correlation between medical images sequence. We proposed two novel architectures for single medical image and sequential medical images, respectively. The multi-scale back-projection network (MSBPN) is constructed of several different scale back-projection units which consist of iterative up- and down-sampling layers. The multi-scale machine extracts different scale spatial information and strengthens the information fusion for a single image. Based on MSBPN, we proposed an accurate and lightweight Multi-Scale Bidirectional Fusion Attention Network(MSBFAN) that combines temporal information iteratively. That supplementary temporal information is extracted from the adjacent image sequence of the target image. The MSBFAN can effectively learn both the spatio-temporal dependencies and the iterative refinement process with only a lightweight number of parameters. Experimental results demonstrate that our MSBPN and MSBFAN are outperforming current SR methods in terms of reconstruction accuracy and parameter quantity of the model.