SVM-Based Factor Graph Design for Max-SR Problem of SCMA Networks

In this letter, a novel factor graph design based on the support vector machine (SVM) is proposed to maximize the sum-rate (Max-SR) of three-dimensional (3D) SCMA networks. A new iterative inter-group subcarrier allocation (IIGSCA) algorithm is proposed to train datasets. Hence, it effectively improves the multiclass classification accuracy of the proposed SVM-based scheme to predict the optimal factor graph matrix (FGM). The simulation results confirm that the IIGSCA-assisted SVM algorithm can approach the optimal FGM obtained by exhaustive search (ES).