Evaluating Spatial Accessibility to General Hospitals with Navigation and Social Media Location Data: A Case Study in Nanjing.

Spatial accessibility to general hospitals is an important indicator of the convenience and ability of residents to obtain medical services. Therefore, developing a model for measuring accessibility to general hospitals by multiple transportation modes is necessary. In this study, considering that the increase in travel time will reduce the attractiveness of general hospitals, we used the Two-Step Floating Catchment Area with the Gaussian attenuation function, in which the supply was presented by capacity of hospitals (i.e., number of beds), and the demand was presented by population in each grid derived with social media data mapping real-time locations of active users. The Gaussian Two-Step Floating Catchment Area (Ga2SFCA) simulates the attenuation tendency of the general hospital service capabilities over transit time. To obtain a highly precise understanding of accessibility to hospitals, transit time on Baidu Maps' navigation service was used as the impedance condition, and the study area was divided into 1 square kilometer grids as the basic unit of research. Taking Nanjing city as a case study, it is found that the accessibility distribution shape changes from a multi-centered circular pattern to a multi-peak distribution, as the time threshold increases. By comparing the accessibility among 11 districts varying from main urban area to suburbs, the accessibility to general hospitals in Nanjing is significantly regionally unbalanced in both travel modes. By calculating and mapping the Modal Accessibility Gap (MAG) of the two travel modes, different modes of transportation resulted in different general hospital accessibility distributions. Generally, private car is superior in access to general hospitals to public transit in most areas. In the central area, public traffic may not contribute to the access to medical services as much as we thought, rather it plays a role in areas far from hospitals along metro lines and bus routes.

Simulated annealing based hybrid forecast for improving daily municipal solid waste generation prediction.

A simulated annealing (SA) based variable weighted forecast model is proposed to combine and weigh local chaotic model, artificial neural network (ANN), and partial least square support vector machine (PLS-SVM) to build a more accurate forecast model. The hybrid model was built and multistep ahead prediction ability was tested based on daily MSW generation data from Seattle, Washington, the United States. The hybrid forecast model was proved to produce more accurate and reliable results and to degrade less in longer predictions than three individual models. The average one-week step ahead prediction has been raised from 11.21% (chaotic model), 12.93% (ANN), and 12.94% (PLS-SVM) to 9.38%. Five-week average has been raised from 13.02% (chaotic model), 15.69% (ANN), and 15.92% (PLS-SVM) to 11.27%.