Low-complexity OTFS system symbol detection method based on deep neural network

• Main Authors: LIU WEI, YU TONGYANG, BAI BAOMING
• Format: Patent
• Language: Chinese; English
• Published: 18.04.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention discloses an OTFS system symbol detection method based on a deep neural network, and mainly solves the problems of relatively high symbol detection complexity and relatively slow symbol detection and reception speed in the prior art. The method comprises the following implementation steps: 1, obtaining a training set; 2, constructing a neural network; 3, training the deep neural network by using the training set; 4, receiving a time domain signal sent by the transmitting end, and performing Wigner transformation on the time domain signal to obtain a time-frequency domain signal; 5, carrying out the Sextile Fourier transform of the time-frequency domain signal, and obtaining a receiving symbol of a time delay-Doppler domain; and 6, using the trained deep neural network to detect a received symbol, and obtaining an estimated value of a sent symbol. According to the method, the overall symbol detection complexity of the OTFS system is reduced, the receiving symbol detection speed is increased, and