A divide-and-conquer method for space-time series prediction.
Min DengWentao YangQiliang LiuYunfei ZhangPublished in: J. Geogr. Syst. (2017)
Keyphrases
- high precision
- synthetic data
- high accuracy
- clustering method
- significant improvement
- experimental evaluation
- support vector machine
- fully automatic
- preprocessing
- pairwise
- dynamic programming
- probabilistic model
- optimization method
- data sets
- detection method
- non stationary
- theoretical analysis
- computationally efficient
- input data
- low dimensional
- cost function
- artificial neural networks
- computational complexity
- objective function