RESUMO
Spatio-temporal interpolation provides estimates of observations in unobserved locations and time slots. In smart cities, interpolation helps to provide a fine-grained contextual and situational understanding of the urban environment, in terms of both short-term (e.g., weather, air quality, traffic) or long term (e.g., crime, demographics) spatio-temporal phenomena. Various initiatives improve spatio-temporal interpolation results by including additional data sources such as vehicle-fitted sensors, mobile phones, or micro weather stations of, for example, smart homes. However, the underlying computing paradigm in such initiatives is predominantly centralized, with all data collected and analyzed in the cloud. This solution is not scalable, as when the spatial and temporal density of sensor data grows, the required transmission bandwidth and computational capacity become unfeasible. To address the scaling problem, we propose EDISON: algorithms for distributed learning and inference, and an edge-native architecture for distributing spatio-temporal interpolation models, their computations, and the observed data vertically and horizontally between device, edge and cloud layers. We demonstrate EDISON functionality in a controlled, simulated spatio-temporal setup with 1 M artificial data points. While the main motivation of EDISON is the distribution of the heavy computations, the results show that EDISON also provides an improvement over alternative approaches, reaching at best a 10% smaller RMSE than a global interpolation and 6% smaller RMSE than a baseline distributed approach.
RESUMO
BACKGROUND: In the past two decades, the number of maternity hospitals in Finland has been reduced from 42 to 22. Notwithstanding the benefits of centralization for larger units in terms of increased safety, the closures will inevitably impair geographical accessibility of services. METHODS: This study aimed to employ a set of location-allocation methods to assess the potential impact on accessibility, should the number of maternity hospitals be reduced from 22 to 16. Accurate population grid data combined with road network and hospital facilities data is analyzed with three different location-allocation methods: straight, sequential and capacitated p-median. RESULTS: Depending on the method used to assess the impact of further reduction in the number of maternity hospitals, 0.6 to 2.7% of mothers would have more than a two-hour travel time to the nearest maternity hospital, while the corresponding figure is 0.5 in the current situation. The analyses highlight the areas where the number of births is low, but a maternity hospital is still important in terms of accessibility, and the areas where even one unit would be enough to take care of a considerable volume of births. CONCLUSIONS: Even if the reduction in the number of hospitals might not drastically harm accessibility at the level of the entire population, considerable changes in accessibility can occur for clients living close to a maternity hospital facing closure. As different location-allocation analyses can result in different configurations of hospitals, decision-makers should be aware of their differences to ensure adequate accessibility for clients, especially in remote, sparsely populated areas.
