Protograph DCSK Transceiver Decoding Using Chaotic Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing transceiver decoding methods for DCSK systems suffer from lower decoding accuracy due to the failure to utilize correlation characteristics of chaotic sequences, affecting the performance of protograph DCSK coded modulation systems.
Innovation Solution
A transceiver decoding method and system based on protograph DCSK, utilizing a protograph DCSK transmitter, a wireless channel, a target extrinsic information-aided network, and an a-priori calculation decoder, which includes acquiring and modulating information bit sequences, determining a-posteriori probability vectors, and decoding using a CNN-LSTM and FC blocks for enhanced feature extraction and a-priori calculation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If energy detection is used as symbol detection via demodulators, then the decoding process can be completed, but the decoding accuracy is reduced due to failure to use correlation characteristics between chaotic sequences
Solution Approach 1:
The patent implements an iterative feedback mechanism where the decoder generates extrinsic information that is fed back to update the a-posteriori probability vectors in the neural network. This feedback loop allows the system to progressively refine decoding decisions by incorporating correlation characteristics of chaotic sequences, thereby improving decoding accuracy without requiring a complete redesign of the system architecture.
Solution Approach 2:
The patent introduces an intermediary neural network layer (CNN-LSTM-FC blocks) that acts as a mediator between the received signal and the final decoding decision. This intermediary processes the received M-ary DCSK symbols through feature extraction and generates enhanced a-posteriori probability vectors, allowing the system to utilize chaotic sequence correlations without directly modifying the core decoder structure.
2Measurement precision
If both received symbols and a-posteriori probability vectors are considered, then decoding accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the computational process into distinct functional blocks: CNN blocks for spatial feature extraction, LSTM blocks for temporal sequence processing, and FC blocks for probability vector generation. This segmentation allows each component to perform a specific computational task efficiently, reducing overall computational energy requirements while still considering both received symbols and a-posteriori probability vectors for improved decoding accuracy.
Solution Approach 2:
The patent performs preliminary feature extraction and probability vector generation through the neural network before the final decoding decision is made. By pre-processing the received symbols through CNN-LSTM-FC blocks to generate enhanced a-posteriori probability vectors, the system prepares optimized input data for the decoder, reducing the computational burden during the actual decoding process.
Data Source
AI summary
Disclosed are a transceiver decoding method and system based on protograph differential chaos shift keying (DCSK), the method including acquiring an information bit sequence, performing a coded modulation on the information bit sequence via a protograph DCSK transmitter, and outputting a plurality of modulated symbols; inputting each modulated symbol into a wireless channel for channel interference, and outputting a received symbol corresponding to each modulated symbol; using a target extrinsic information-aided network to determine a target a-posteriori probability vector corresponding to each received symbol; inputting each target a-posteriori probability vector into an a-priori calculation decoder for decoding, and outputting an initial decoded bit sequence; and determining a target decoded bit sequence according to the initial decoded bit sequence and a preset check matrix. The technical problem of lower decoding accuracy caused by the existing transceiver decoding methods designed for a DCSK system is solved.