Adaptive Interpolation Algorithms for Temporal-Oriented Datasets

Spatiotemporal datasets can be classified into two categories: temporal-oriented and spatial-oriented datasets depending on whether missing spatiotemporal values are closer to the values of its temporal or spatial neighbors. We present an adaptive spatiotemporal interpolation model that can estimate the missing values in both categories of spatiotemporal datasets. The key parameters of the adaptive spatiotemporal interpolation model can be adjusted based on experience

Authors

• Jun Gao

Keywords

• Interpolation
• Spatiotemporal phenomena
• Data visualization
• Voting
• Nominations and elections
• Temperature
• Pollution
• Computer science
• Data engineering
• Shape
• Spatiotemporal Model
• Interpolation Model
• Spatiotemporal Datasets
• Root Mean Square Error
• Linear Function
• Estimated Values
• Forecasting
• Data Logger
• Step Function
• Kriging
• Presidential Election
• Forecasting Model
• Interpolation Method
• Sum Of Weights
• State Of California
• Closest Neighbors
• Temporal Distance
• Inverse Distance Weighting
• Florida State
• US Presidential Election
• Inverse Distance Weighting Method
• Percentage Of Votes
• Spatiotemporal Method