A Temperature Data Prediction Method Using Graph Filter and Lp-Norm Minimization

In this paper, a temperature data prediction method using graph filter and Lp-norm minimization is presented. First, the graph filter based on graph Laplacian matrix is briefly reviewed. Then, the filter coefficients of the prediction graph filter are estimated from the temperature measurement data by using the Lp-norm minimization approach. Finally, the real measurement temperature data in the cities of the south Taiwan are used to demonstrate the effectiveness of the proposed graph filter prediction method.