A new windowed graph Fourier transform

Many practical networks can be mathematically modeled as graphs. Graph signal processing (GSP), intersecting graph theory and computational harmonic analysis, can be used to analyze graph signals. Just as short-time Fourier transform (STFT) for time-frequency analysis in classical signal processing, we have windowed graph Fourier transform (WGFT) for vertex-frequency analysis in GSP. In this paper, we introduced a new graph modulation operator that satisfies the property of spectral conservation, and a new graph translation operator with interesting properties. Based on these operators, we presented a new method to obtain the WGFT with a tight vertex-frequency frame. These GSP tools were developed based on the graph adjacency matrix. Using time-series graph, USA graph and random graph as examples, we showed by simulation the advantages of our proposed GSP tools over the state-of-the-arts.