时空数据挖掘研究进展

Advances in Spatiotemporal Data Mining

近年来,随着全球定位系统、传感器网络和移动设备等的普遍使用,非时空数据和时空数据急剧增加,加之时空数据处理更为复杂,使数据处理任务日趋繁重的形势更加严峻.因此,寻找有效的时空数据挖掘方法具有十分重要的意义.针对这一背景,主要围绕时空模式发现、时空聚类、时空异常检测、时空预测、时空分类、时空数据挖掘与推理的结合等方面,对时空数据挖掘研究的现状进行了详细介绍,对其当前所面临的一些主要问题及可能的解决方案进行了探讨.

In recent years, the widespread use of the advanced technologies such as global positioning systems, sensor network and mobile devices, results in accumulation of a great amount of non- spatiotemporal data and spatiotemporal data. In addition, the processing of spatiotemporal data is more complex, which makes the increasing onerous situation of data processing tasks worse. To address these challenges, spatiotemporal data mining has emerged as an active research field, focusing on the development of theory, methodology, and practice for the extraction of useful information and knowledge from massive and complex spatiotemporal databases. Therefore, looking for effective spatiotemporal data mining methods is of great significance. This paper attempts to review the recent theoretical and applied research progress in spatiotemporal data mining and knowledge discovery. We mainly focus on spatiotemporal pattern discovery, spatiotemporal clustering, spatiotemporal anomaly detection, spatiotemporal prediction, spatiotemporal classification, and the combination of spatiotemporal data mining with reasoning. We have introduced the state-of-the-art research on spatiotemporal data mining in detail, and discussed the current major problems we are facing and its possible solutions.