Fvep feature point detection method based on caa-net and lightgbm

Abstract

The present invention proposes a FVEP feature point detection method based on CAA-Net and LightGBM, comprising the following steps: S1, data preprocessing: standardize the FVEP signal, as the input of the neural network model; S2, feature point sequence generation: S2 ‑1, the position coordinates of possible feature points are selected through the CAA‑Net model, and the candidate feature points with low probability are filtered; S2‑2, the sequence of feature points to be selected is generated: if the points in the feature point set to be selected If it is not an extremum point, search in the range where the distance between the feature points in the feature point set to be selected is less than 2. If no extremum point is found, discard the point. If an extremum point is found, replace it to be selected feature points; then, generate a preliminary set of feature point sequences to be selected according to the exhaustive method; S3, feature point sequence selection, and obtain the optimal feature point sequence. The invention can quickly and effectively obtain the characteristic points of the FVEP waveform, so as to perform clinical analysis on the patient's condition.

Description

technical field [0001] The invention relates to the field of medical data detection, in particular to a method for detecting FVEP feature points based on CAA-Net and LightGBM. Background technique [0002] The characteristic points of FVEP waveform are an important basis for clinicians to judge the condition; however, due to poor cooperation of patients, large inter-individual differences and large intra-individual variation of FVEP waveform, it is difficult to interpret clinical analysis. Therefore, the research on the characteristic points of FVEP waveform is an important subject to be solved urgently. Contents of the invention [0003] The present invention aims to at least solve the technical problems existing in the prior art, and particularly innovatively proposes a FVEP feature point detection method based on CAA-Net and LightGBM. [0004] In order to achieve the above-mentioned purpose of the present invention, the present invention provides the FVEP feature point...

AI Technical Summary

Problems solved by technology

[0002] The characteristic points of FVEP waveform are an important basis for clinicians to judge the condition; however, due to poor cooperation of patients, large inter-individual differences and large intra-individual variation of FVEP waveform, it is difficult to interpret clinical analysis

Images