Semi-supervised and semi-learned atmospheric pollutant system

Abstract

The invention discloses a semi-supervised and semi-learned atmospheric pollutant system and relates to the technical field of atmospheric pollutants, and the system comprises a data processing module,a data preprocessing module, a learning classification module, a comprehensive analysis module, an auxiliary arrangement module and a computer terminal module. The output end of the data processing module is electrically connected with the input end of a data preprocessing module; the output end of the data preprocessing module is electrically connected with the input end of a learning classification module; data can be acquired and collected through the data acquisition module. Dimensionality reduction processing of the data is realized through the data preprocessing module; the acquired data parameters can be transmitted to the data classification module; data classification is achieved through the learning classification module, then data analysis processing is achieved through the comprehensive analysis module, the analyzed data is sorted through the auxiliary sorting module, and then watching monitoring of the sorted data can be achieved through the computer terminal module.

Description

technical field [0001] The invention relates to the technical field of air pollutants, in particular to a semi-supervised and half-learning air pollutant system. Background technique [0002] Atmospheric environment refers to the physical, chemical and biological characteristics of the air on which organisms live. Harmful gases such as ammonia, sulfur dioxide, carbon monoxide, nitrogen compounds and fluorides discharged from human life or industrial and agricultural production can change the composition of the original air, and Cause pollution, cause global climate change, destroy ecological balance; [0003] Semi-supervised learning (Semi-Supervised Learning, SSL) is a key issue in the field of pattern recognition and machine learning. It is a learning method that combines supervised learning and unsupervised learning. Semi-supervised learning uses a large amount of unlabeled data, and Use labeled data to carry out pattern recognition work. When semi-supervised learning is...

AI Technical Summary

Problems solved by technology

[0003] Semi-supervised learning (Semi-Supervised Learning, SSL) is a key issue in the field of pattern recognition and machine learning. It is a learning method that combines supervised learning and unsupervised learning. Semi-supervised learning uses a large amount of unlabeled data, and Use labeled data to carry out pattern recognition work. When semi-supervised learning is used, as few people as possible will be required to do the work. At the same time, it can bring relatively high accuracy. Using semi-supervised learning to associate with air pollutants The combined method to realize the monitoring of air pollutants is the development direction of the new era and can effectively reduce the workload of the staff. The traditional method is to realize the analysis of the detection data of air pollutants through a semi-supervised learning machine. , during the analysis process, the estimation of the concentration index of air pollutants is realized, but due to the different heights, the degree of air pollution is different, so it is easy to cause inaccurate evaluation. For this reason, we propose a semi-supervised and semi-learning air pollution system to solve the above problems

Images