CEEMDAN-SAE-based miner suspected occupational disease identification method

Abstract

The invention relates to a CEEMDAN-SAE-based miner suspected occupational disease identification method. The method comprises the following steps: (1) establishing a miner occupational health detection system for collecting miner health data; (2) collecting miner occupational health data by using an occupational health detection system, adding a manually marked label, and establishing a miner health standard database; (3) performing de-noising processing on the original electroencephalogram signals, the original electrocardio signals and the original electromyographic signals by adopting CEEMDAN to avoid interference of noise signals in data; (4) dividing the preprocessed data into a training set and a test set according to a certain proportion by adopting a hold-out method; (5) employing the SAE for feature extraction of the data, reducing the dimension of the data, and extracting important features; and (6) establishing an LVQ-based miner suspected occupational disease recognition model by using data optimized by the important features, and evaluating the recognition performance of the model. According to the method, CEEMDAN-SAE is combined with LVQ to identify suspected occupational diseases of miners, and the method is suitable for research in the field of intelligent occupational health identification.

Description

Technical field [0001] The present invention relates to the field of occupational health intelligence identification, and is specifically a method of suspected occupational disease recognition method based on Ceemdan-SAE. Background technique [0002] Under the prerequisite conditions of the continuous increase in the depth of coal mines, the underground work environment conditions also present a gradual deterioration. The harsh environment in the downhole workplace will seriously affect the health of miners, so that the possibility of miners' occupational disease has increased significantly. If the miner has undergone health damage, it has reached an abnormal level of occupational diseases, which requires precise and rapid identification before occupational disease diagnosis, which has significant research significance for occupational health and occupational disease auxiliary diagnosis. [0003] Artificial intelligence algorithm technology is increasingly widely used in miners'...

AI Technical Summary

Problems solved by technology

However, there is currently a problem that useless interfering noise signals in the data can seriously affect the evaluation results

A large amount of high-dimensional medical data makes the discriminant model too complex and the analysis efficiency is low, which is not conducive to researchers' understanding of the process of data generation

Images