A Blind Detection Method for Multilevel Signals Based on Discrete Full Feedback Neural Network

Abstract

The invention discloses a multilevel signal blind detection method based on a discrete full feedback neural network. According to the subspace relationship between the signal received by the gateway (Sink) node of the wireless sensor network and the signal sent by the intermediate processing node, the method establishes an optimal performance function for direct blind detection of the sent signal, and transforms the blind detection problem into a quadratic programming problem. Then a discrete complex multi-level Hopfield neural network is constructed. According to the specific requirements of multi-level signal blind detection, the neuron table energy function, operating equation and gain coefficient of the complex multi-level discrete Hopfield neural network are redefined. Ping Hopfield neural network is used as a blind detection algorithm for MQAM signals in wireless sensor networks. This algorithm can achieve the calculation goal only by receiving data in a very short time, and can be applied to occasions where statistics are meaningless. The search space is reduced, the difficulty is greatly reduced, the search time is significantly better than other blind detection algorithms, and the system performance is improved accordingly.

Description

technical field [0001] The invention relates to the field of wireless communication signal processing and the field of neural network, in particular to the multi-level signal blind detection between the intermediate processing node of the wireless sensor network and the receiving end of a gateway (Sink). Background technique [0002] Wireless sensor networks enable multiple devices to collaboratively detect stress and deformation of buildings and bridges, detect event threats, track hostile targets, support unmanned robot vehicles, etc., and have collaborative real-time detection, perception and collection of various environments Or monitor the object information and process it, and send it to the user who needs it. As a special wireless network, the wireless sensor network emphasizes the communication between devices. Because its network nodes use a small battery as a power source, they cannot be charged and replaced, so there are very strict capacity limitations. Reducing ...

AI Technical Summary

Problems solved by technology

[0004] Technical problem: the purpose of this invention is to provide a kind of multi-level signal blind detection method based on discrete full feedback neural network, which solves the problem of optimal solution in the complex number field under the condition of unknown signal, and provides a solution for wireless communication network, especially wireless sensor network. Sink provides an accurate blind detection method for signals

Images