A method of soft-decision decoding including training a machine learning agent with communication signal training data; providing to the trained machine learning agent a signal that has been received via a communications channel; operating the machine learning agent to determine respective probabilities that the received signal corresponds to each of a plurality of symbols; and, based on the determined probabilities, performing soft decision decoding on the received signal.

The present disclosure relates to a pre-5th-generation (5G) or 5G communication system to be provided for supporting higher data rates beyond 4th-generation (4G) communication system such as a long term evolution (LTE). A method of a receiving apparatus in a communication system supporting a low density parity check (LDPC) code is provided. The method includes deactivating variable nodes of which absolute values of log likelihood ratio (LLR) values are greater than or equal to a first threshold value; changing LLR values of variable nodes of which absolute values of LLR values are less than a second threshold value among variable nodes other than the deactivated variable nodes to a preset value, and detecting LLR values of check nodes based on LLR values of the variable nodes other than the deactivated variable nodes.

The invention discloses a convolutional code decoder and a convolutional code decoding method. The convolutional code decoder performs decoding operation according to a received data and an auxiliary data to obtain a target data and includes an error detection data generation circuit, a channel coding circuit, a selection circuit, and a Viterbi decoding circuit. The error detection data generation circuit performs an error detection operation on the auxiliary data to obtain an error detection data. The channel coding circuit, coupled to the error detection data generation circuit, performs channel coding on the auxiliary data and the error detection data to obtain an intermediate data. The selection circuit, coupled to the channel coding circuit, generates a to-be-decoded data according to the received data and the intermediate data. The Viterbi decoding circuit, coupled to the selection circuit, decodes the to-be-decoded data to obtain the target data.

An embodiment encoder device for encoding an information word c=[c.sub.0, c.sub.1, . . . , c.sub.K-1] having K information bits, c.sub.i, includes an encoder for a tail biting convolutional code having a constraint length, L, where K<L1; the encoder being configured to receive the K information bits; and encode the K information bits so as to provide an encoded code word. An embodiment decoder device for determining an information word c=[c.sub.0, c.sub.1, . . . , c.sub.K-1], having K information bits, c.sub.i, includes a decoder for a tail biting convolutional code having a constraint length, L, where K<L1; the decoder being configured to: receive an input sequence; compute at least one reliability parameter based on the received input sequence; and determine an information word c based on the at least one reliability parameter.

The invention discloses a convolutional code decoder and a convolutional code decoding method. The convolutional code decoder performs decoding operation according to a received data and an auxiliary data to obtain a target data and includes an error detection data generation circuit, a channel coding circuit, a selection circuit, and a Viterbi decoding circuit. The error detection data generation circuit performs an error detection operation on the auxiliary data to obtain an error detection data. The channel coding circuit, coupled to the error detection data generation circuit, performs channel coding on the auxiliary data and the error detection data to obtain an intermediate data. The selection circuit, coupled to the channel coding circuit, generates a to-be-decoded data according to the received data and the intermediate data. The Viterbi decoding circuit, coupled to the selection circuit, decodes the to-be-decoded data to obtain the target data.

A method of soft-decision decoding including training a machine learning agent with communication signal training data; providing to the trained machine learning agent a signal that has been received via a communications channel; operating the machine learning agent to determine respective probabilities that the received signal corresponds to each of a plurality of symbols; and, based on the determined probabilities, performing soft decision decoding on the received signal.

Method and system for soft decision decoding are provided. A soft decision decoding method implemented by a receiver in a communication network may include: receiving a signal frame carrying a message through a communication network; obtaining data structure of the message; obtaining at least one bit of the message based on the data structure and known information; and decoding the received signal frame based on the at least one bit using soft decision decoding to obtain a decoding result. Decoding efficiency and accuracy may be improved.

The present disclosure relates to a pre-5th-generation (5G) or 5G communication system to be provided for supporting higher data rates beyond 4th-generation (4G) communication system such as a long term evolution (LTE). A method of a receiving apparatus in a communication system supporting a low density parity check (LDPC) code is provided. The method includes deactivating variable nodes of which absolute values of log likelihood ratio (LLR) values are greater than or equal to a first threshold value; changing LLR values of variable nodes of which absolute values of LLR values are less than a second threshold value among variable nodes other than the deactivated variable nodes to a preset value, and detecting LLR values of check nodes based on LLR values of the variable nodes other than the deactivated variable nodes.

The disclosure relates to a decoding device, comprising: a receiver configured to provide a sequence of information bits comprising context redundancy information, wherein the sequence of information bits is encoded based on a predefined channel code; a trellis generation logic configured to generate a plurality of trellis states based on the sequence of information bits and the channel code; a trellis reduction logic configured to reduce the plurality of trellis states by at least one trellis state based on the context redundancy information; and a decoder configured to decode the sequence of information bits by using a metric based on the reduced number of trellis states.

A method for decoding a variable length coded input including a plurality of binary code symbols into an output symbol includes: setting, by a decoder including a processor and memory storing a lookup table including a plurality of states, a current state to an initial state and a current branch length to an initial branch length; and identifying, by the decoder using the lookup table, a next state or a symbol of the output symbols based on a current state, a current branch length, and a next binary code symbol of the variable length coded input.