Method and apparatus for transmitting and receiving signals of user equipment and base station in wireless communication system
A method of operating a user equipment (UE) and a base station in a wireless communication system and an apparatus supporting this are disclosed. The method of operating the UE may comprise encoding input data based on a neural network and transmitting the encoded input data to a base station. In this case, the neural network may be determined to be at least one of a real neural network or a complex neural network.
1. A method of operating a user equipment (UE) in a wireless communication system, the method comprising:
encoding input data based on a neural network; and
generating at least one codeword based on the encoded input data;
generating modulation symbols based on the at least one codeword; and
transmitting a signal including the modulation symbols to a base station,
wherein the neural network includes a real neural network and a complex neural network,
wherein the input data is grouped based on input bits, and is mapped to a plurality of input levels, and
wherein the mapped plurality of input levels is determined as an input value of a neural encoder in the real neural network.
2. The method of claim 1 , wherein input levels adjacent to each other among the plurality of input levels have a uniform spacing.
3. The method of claim 1 , wherein input levels adjacent to each other among the plurality of input levels have a non-uniform spacing.
4. The method of claim 1 , wherein an input value of a neural encoder in the complex neural network is determined,
wherein the complex neural network comprises a first real neural network and a second real neural network.
5. The method of claim 4 ,
wherein the input data is divided into a real part and an imaginary part,
wherein the real part of the input data is grouped based on input bits of the real part and mapped to a plurality of input levels based on a real value,
wherein the plurality of mapped input levels is determined as an input value of a neural encoder of the first real neural network,
wherein the imaginary part of the input data is grouped based on input bits of the imaginary part and mapped to a plurality of input levels based on a real value, and
wherein the plurality of mapped input levels is determined as an input value of a neural encoder of the second real neural network.
6. The method of claim 4 ,
wherein the input value of the neural encoder in the complex neural network is determined to be a complex value.
7. The method of claim 1 ,
wherein encoding of the input data is performed based on the real value through the neural network,
wherein two symbols in the encoded input data are mapped to one complex symbol,
wherein one of the two symbol is mapped to a real part, and
wherein the other one of the two symbol is mapped to an imaginary part.
8. The method of claim 7 ,
wherein an odd-numbered symbol of the encoded input data is mapped to the real part, and
wherein an even-numbered symbol of the encoded input data is mapped to the imaginary part.
9. The method of claim 1 ,
wherein the neural encoder is composed of a plurality of filter layers,
wherein the plurality of filter layers is divided into a plurality of groups, and
wherein an input value of the neural encoder is uniformly divided into the plurality of groups and input.
10. A user equipment (UE) operating in a wireless communication system, the UE comprising:
at least one transmitter;
at least one receiver;
at least one processor; and
at least one memory operably connected to the at least one processor and configured to store instructions which, when executed, cause the at least one processor to perform a specific operation,
wherein the specific operation comprises:
encoding input data based on a neural network;
generating at least one codeword based on the encoded input data;
generating modulation symbols based on the at least one codeword; and
transmitting a signal including the modulation symbols to a base station, and
wherein the neural network includes a real neural network and a complex neural network,
wherein the input data is grouped based on input bits, and is mapped to a plurality of input levels, and
wherein the mapped plurality of input levels is determined as an input value of a neural encoder in the real neural network.
11. The UE of claim 10 , wherein the UE communicates with at least one of a mobile terminal, a network or an autonomous vehicle other than a vehicle including the UE.
12. A base station operating in a wireless communication system, the base station comprising:
at least one transmitter;
at least one receiver;
at least one processor; and
at least one memory operably connected to the at least one processor and configured to store instructions which, when executed, cause the at least one processor to perform a specific operation,
wherein the specific operation comprises:
receiving a signal including modulation symbols from a user equipment (UE); and
decoding the signal based on a neural network,
wherein the modulation symbols are generated based on the at least one codeword, and the at least one codeword is generated based on an encoded input data, and
wherein the neural network includes a real neural network and a complex neural network,
wherein the encoded input data is grouped based on input bits, and is mapped to a plurality of input levels, and
wherein the mapped plurality of input levels is determined as an input value of a neural encoder in the real neural network.