TY - JOUR
T1 - Supervised learning applied to the decoding of SCMA codewords
AU - Vidal-Beltran, Sergio
AU - Martinez-Pinon, Fernando
AU - Lopez-Bonilla, Jose Luis
N1 - Publisher Copyright:
© 2003-2012 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - This work puts together two technologies that are in the interest of the scientific community, on the one hand, access methods for fifth generation systems of mobile communications, in this case Sparse Code Multiple Access (SCMA), and on the other hand supervised learning based on neural networks. SCMA is one of the proposed access techniques for fifth generation mobile communication systems. Until now, the detection algorithm in the receiver is based on Message Passing Algorithm (MPA) or minimum Euclidean distance. In this work, a new approach is proposed, which is based on supervised learning using neural networks to decode SCMA codewords. The simulation results show that the receiver based on neural networks learns quickly and obtains 100% accuracy in predictions on channels with high noise. In addition to being simpler in its implementation than its predecessors (MPA and minimum Euclidean distance).
AB - This work puts together two technologies that are in the interest of the scientific community, on the one hand, access methods for fifth generation systems of mobile communications, in this case Sparse Code Multiple Access (SCMA), and on the other hand supervised learning based on neural networks. SCMA is one of the proposed access techniques for fifth generation mobile communication systems. Until now, the detection algorithm in the receiver is based on Message Passing Algorithm (MPA) or minimum Euclidean distance. In this work, a new approach is proposed, which is based on supervised learning using neural networks to decode SCMA codewords. The simulation results show that the receiver based on neural networks learns quickly and obtains 100% accuracy in predictions on channels with high noise. In addition to being simpler in its implementation than its predecessors (MPA and minimum Euclidean distance).
KW - 5G
KW - Adam Optimization
KW - Neural networks
KW - SCMA
KW - SGD
KW - Supervised Learning
UR - http://www.scopus.com/inward/record.url?scp=85079641012&partnerID=8YFLogxK
U2 - 10.1109/TLA.2019.8986422
DO - 10.1109/TLA.2019.8986422
M3 - Artículo
SN - 1548-0992
VL - 17
SP - 1843
EP - 1848
JO - IEEE Latin America Transactions
JF - IEEE Latin America Transactions
IS - 11
M1 - 8986422
ER -