ANN Decoder Multilevel Activation for Wireless Signal Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wireless communication systems face challenges in decoding radio signals due to the complexity of artificial neural networks (ANNs) required for efficient decoding, which demand significant computing resources, making them resource-intensive.
Innovation Solution
The implementation of multiple level activation functions (MLAFs) in ANN decoders reduces the number of neurons needed, decreasing complexity and resource requirements by enabling multiclass classification with fewer nodes, thereby optimizing decoding processes in wireless communication systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If artificial neural networks are used for decoding radio signals, then decoding efficiency is improved, but computing resource requirements increase
Solution Approach 1:
The patent changes the parameter of activation functions from traditional single-level or binary types to multi-level activation functions. This parameter change enables the neural network to process multiple signal levels (e.g., 4-level, 8-level QAM) more efficiently, reducing the computational burden while maintaining decoding efficiency. The multi-level activation functions are specifically designed to match the signal constellation levels, optimizing the balance between productivity and resource consumption.
2Device complexity
If traditional activation functions are used in ANN decoders, then the network structure remains simple, but the number of neurons required increases, leading to higher complexity
Solution Approach 1:
The multi-level activation functions serve multiple functions simultaneously: they perform classification, thresholding, and signal level mapping in a single operation. This multi-functionality allows the neural network to achieve the same decoding capability with fewer neurons, as each neuron can handle multiple signal levels and classification tasks that would otherwise require multiple separate neurons with traditional activation functions.
3Measurement precision
If more neurons are used to improve decoding accuracy, then accuracy increases, but computational complexity and resource requirements increase
Solution Approach 1:
Instead of using multiple neurons to represent different signal levels, the patent uses multi-level activation functions that inherently encode multiple levels within a single neuron's response. This copying approach allows the network to maintain high decoding accuracy by preserving all signal level information in the activation function's output, eliminating the need for redundant neurons while maintaining measurement precision.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method for decoding at least M0 symbols X10,...,XM00 received from a transmitter through a wireless communication medium, said received symbols representing symbols encoded by an encoder E of the transmitter, said method comprising: inputting in a decoder the M0 symbols X10,...,XM00, said decoder comprising an artificial neural network system, wherein at least an activation function of the artificial neural network system is a multiple level activation function.