TY  - RPRT
CY  - Hanoi, Vietnam
N1  - UET-AVITECH-2019001
ID  - SisLab3443
UR  - https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3443/
A1  - Le, Trung Thanh
A1  - Nguyen, Linh Trung
A1  - Nguyen, Viet Dung
A1  - Abed-Meraim, Karim
Y1  - 2019/04/18/
N2  - Signal processing on graphs is an emerging topic of signal processing, considering graphs as signals. Hence, similar concepts and tools in signal processing can be extended, for understanding graph signals, such as graph frequency, graph operators, graph Fourier transform. In this report, we focus on the joint relationship of vertex-frequency representation of graphs. Motivated by the existing relationship between the incidence matrix and the Laplacian matrix for undirected graphs, we define a generalized Laplacian matrix for directed graphs. This allows us to propose a unified framework for the graph Fourier transform, graph modulation and graph translation. Then, built upon the graph modulation and translation operators, we propose a new windowed graph Fourier transform which a tight vertex-frequency frame. The experimental results indicate that our proposed methods are better than state-of-the-art methods and beneficial for analyzing various different types of graphs, including directed, undirected, weighted, unweighted and connected graphs.
PB  - University of Engineering and Technology, Vietnam National University
VL  - UET-AVITECH-2019001
M1  - technical_report
TI  - A new windowed digraph Fourier transform
AV  - restricted
EP  - 27
ER  -