Radial basis function neural network adaptive enhancer circuit designed based on fpga

Abstract

The invention relates to a radial basis function neural network adaptive enhancer circuit based on FPGA design, and its technical characteristics are: connected by a signal conversion circuit, a radial basis function circuit, a signal adjustment circuit, an LMS filter circuit and an output adjustment circuit The input end of the signal conversion circuit is connected with the original signal, the output end is connected with the input end of the signal adjustment circuit and the radial basis function circuit, and the output end of the radial basis function circuit is connected with the other input end of the signal adjustment circuit The two output signals of the signal adjustment circuit are respectively connected to the LMS filter circuit, the input terminals of the output adjustment circuit are respectively connected to the output terminals of the LMS filter circuit, the adjustment signal m and the adjustment signal n and output the noise-removed Signal. The invention has a reasonable design, improves the performance of the conventional LMS filter, realizes the fast calculation function, ensures the stable and reliable performance, and can meet the requirement of real-time monitoring of the somatosensory evoked potential.

Description

technical field [0001] The invention relates to the technical field of digital filtering, in particular to an FPGA-based radial basis function neural network adaptive enhancer circuit. Background technique [0002] At present, the existing medical monitoring equipment on the market is based on the average superposition technology to pick up evoked potentials. The main disadvantages are: time-consuming and lack of dynamic variation information. Delay in the detection of evoked potentials may delay the diagnosis of spinal cord injury, and may miss the opportunity for the operator to perform remedial actions, resulting in irreversible neurological damage. With the continuous development of signal processing technology, various new methods and ideas have been applied to the rapid extraction of evoked potentials, but most of the algorithms are currently limited to the offline working mode of the laboratory, and are implemented on PCs, which cannot meet the requirements of real-ti...

AI Technical Summary

Problems solved by technology

[0002] At present, the existing medical monitoring equipment on the market is based on the average superposition technology to pick up evoked potentials. The main disadvantages are: time-consuming and lack of dynamic variation information

With the continuous development of signal processing technology, various new methods and ideas have been applied to the rapid extraction of evoked potentials, but most of the algorithms are currently limited to the offline working mode of the laboratory, and are implemented on PCs, which cannot meet the requirements of real-time monitoring. Requirements, only when the real-time and fast calculation of the algorithm is realized, can the productization be truly realized

Images