SCMA Decoding via Deep Learning
Chia-Po Wei, Han Yang, Chih–Peng Li, Yen‐Ming Chen
Abstract
Sparse code multiple access (SCMA) has become a highly competitive technology for future cellular systems. For the receiver of the SCMA system, besides the traditional maximum likelihood and message passing algorithm solutions, a deep neural network (DNN) method that causes whirlwinds in image recognition can reduce the computational complexity of the decoder. We expect low complexity while maintaining a satisfactory bit error rate (BER) performance. As shown in our simulations, our proposed solution has better BER performance and lower computational complexity than other previously studied DNN solutions.
Topics & Concepts
Computer scienceDecoding methodsComputational complexity theoryBit error rateMessage passingCode (set theory)Artificial neural networkWord error rateDeep learningAlgorithmArtificial intelligenceComputer engineeringTheoretical computer scienceParallel computingProgramming languageSet (abstract data type)Advanced Wireless Communication TechnologiesAdvanced Wireless Communication TechniquesWireless Communication Security Techniques