The consultative committee for space data system recommended the 4-dimension 8-ary phase shift keying trellis coded modulation (4D-8PSK-TCM). The 4D-8PSK-TCM has the advantage of low decoding latency over iterative error correction codes. The T-algorithm, which makes feasible to eliminate unnecessary additions and comparisons, can be applided to the 4D-8PSK-TCM to lower the decoding complexity. In this paper, we design the 4D-8PSK-TCM simulator with Hybrid T-algorithm based on deep learning to lower decoding complexity. The deep neural network predicts threshold of branch metric and path metric. Simulation results validate that the designed 4D-8PSK-TCM has lower complexity than the ideal 4D-8PSK-TCM while it maintain bit error rate performance of the ideal 4D-8PSK-TCM.
This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2018-0-01424) supervised by the IITP(Institute for Information and communications Technology Promotion). All authors have equal contributions.
