Silva Julio Cezar Soares, de Lima Silva Diogo Ferreira, Ferreira Júnior Nivan Roberto, de Almeida Filho Adiel Teixeira
Centro de informática, Universidade Federal de Pernambuco, Recife, Brazil.
Production Engineering Department, Universidade Federal Fluminense, Niterói, Brazil.
Appl Soft Comput. 2023 May;138:110177. doi: 10.1016/j.asoc.2023.110177. Epub 2023 Mar 8.
It is crucial to develop spatiotemporal analysis tools to mitigate risks during a pandemic. Many dashboards encountered in the literature do not consider how the geolocation characteristics and travel patterns may influence the spread of the virus. This work brings an interactive tool that is capable of crossing information about mobility patterns, geolocation characteristics and epidemiologic variables. To do so, our system uses a mobility network, generated through anonymized mobile location data, which enables the division of a region into representative clusters. The clusters' aggregated socioeconomic, and epidemiologic indicators can be analyzed through multiple coordinated views. The proposal is to enable users to understand how different locations commute citizens, monitor risk over time, and understand what locations need more assistance, considering different layers of visualization, such as clusters and individual locations. The main novelty is the interactive way to construct the mobility network that defines the social distancing level and the way that risks are managed, since many different geolocation characteristics can be considered and visualized, such as socioeconomic indicators of a location, the economic importance of a set of locations, and the connection of important neighborhoods of a city with other cities. The proposed tool was built and verified by experts assembled to give scientific recommendations to the city administration of Recife, the capital city of Pernambuco. Our analysis shows how a policymaker could use the tool to evaluate different isolation scenarios considering the trade-off between economic activity and contamination risk, where the practical insights can also be used to tighten and relax mitigation measures in other phases of a pandemic.
开发时空分析工具以减轻大流行期间的风险至关重要。文献中出现的许多仪表板并未考虑地理位置特征和出行模式如何影响病毒传播。这项工作带来了一种交互式工具，它能够交叉融合有关出行模式、地理位置特征和流行病学变量的信息。为此，我们的系统使用通过匿名移动位置数据生成的移动网络，该网络能够将一个地区划分为具有代表性的集群。集群的综合社会经济和流行病学指标可以通过多个协同视图进行分析。该提议旨在让用户了解不同地点的居民如何通勤，随时间监测风险，并考虑不同的可视化层（如集群和单个地点）来了解哪些地点需要更多援助。主要创新之处在于构建移动网络的交互式方式，该方式定义了社会距离水平以及管理风险的方式，因为可以考虑和可视化许多不同的地理位置特征，例如一个地点的社会经济指标、一组地点的经济重要性以及城市重要街区与其他城市的连接。所提议的工具由为伯南布哥州首府累西腓市行政管理部门提供科学建议而召集的专家构建并验证。我们的分析展示了政策制定者如何使用该工具来评估不同的隔离方案，同时考虑经济活动与污染风险之间的权衡，其中的实际见解也可用于在大流行的其他阶段收紧和放宽缓解措施。
