Temporal Data Classification Using Linear Classifiers

Abstract

Abstract. Data classification is usually based on measurements recorded at the same time. This paper considers temporal data classification where the input is a temporal database that describes measurements over a period of time in history while the predicted class is expected to occur in the future. We describe a new temporal classification method that improves the accuracy of standard classification methods. The benefits of the method are tested on weather forecasting using the meteorological database from the Texas Commission on Environmental Quality.

Integration of Spatial Constraint Databases

“…Geospatial applications are increasingly relying on spatiotemporal data, where the data include a temporal dimension (see next section). Constraint databases provide a simple and elegant solution to store and process temporal data (Revesz and Triplet 2011): the constraints defining the spatial objects only need to be extended to include time as a new parameter. It is also possible to leverage constraint databases to represent historical geospatial data and reason about them to predict a value in space and time based on past data.…”

Applications of spatio-temporal data mining to north platter river reservoirs

“…Most data mining employ some linear classifiers [14] and integrate data from different sources [13,15], but to provide a good fit, a spatio-temporal data model needs to capture the nonlinear relationship among the spatial and temporal variables.…”