Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model
Abstract The development of miniature air quality detectors makes it possible for humans to monitor air quality in real time and grid. However, the accuracy of measuring pollutants by miniature air quality detectors needs to be improved. In this paper, the PCA–RVM–NAR combined model is proposed to c...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-13531-4 |
| _version_ | 1811257390241153024 |
|---|---|
| author | Bing Liu Yirui Zhang |
| author_facet | Bing Liu Yirui Zhang |
| author_sort | Bing Liu |
| collection | DOAJ |
| description | Abstract The development of miniature air quality detectors makes it possible for humans to monitor air quality in real time and grid. However, the accuracy of measuring pollutants by miniature air quality detectors needs to be improved. In this paper, the PCA–RVM–NAR combined model is proposed to calibrate the measurement accuracy of the miniature air quality detector. First, correlation analysis is used to find out the main factors affecting pollutant concentrations. Second, principal component analysis is used to reduce the dimensionality of these main factors and extract their main information. Thirdly, taking the extracted principal components as independent variables and the observed values of pollutant concentrations as dependent variables, a PCA–RVM model is established by the relevance vector machine. Finally, the nonlinear autoregressive neural network is used to correct the error and finally complete the establishment of the PCA–RVM–NAR model. Root mean square error, goodness of fit, mean absolute error and relative mean absolute percent error are used to compare the calibration effect of PCA–RVM–NAR model and other commonly used models such as multiple linear regression model, support vector machine, multilayer perceptron neural network and nonlinear autoregressive models with exogenous input. The results show that, no matter which pollutant, the PCA–RVM–NAR model achieves better calibration results than other models in the four indicators. Using this model to correct the data of the miniature air quality detector can improve its accuracy by 77.8–93.9%. |
| first_indexed | 2024-04-12T17:55:41Z |
| format | Article |
| id | doaj.art-8e9432cae07f46acbe0b3a27e4e47759 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T17:55:41Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-8e9432cae07f46acbe0b3a27e4e477592022-12-22T03:22:21ZengNature PortfolioScientific Reports2045-23222022-06-0112111410.1038/s41598-022-13531-4Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination modelBing Liu0Yirui Zhang1Public Foundational Courses Department, Nanjing Vocational University of Industry TechnologySchool of Intelligent Manufacturing, Sanmenxia PolytechnicAbstract The development of miniature air quality detectors makes it possible for humans to monitor air quality in real time and grid. However, the accuracy of measuring pollutants by miniature air quality detectors needs to be improved. In this paper, the PCA–RVM–NAR combined model is proposed to calibrate the measurement accuracy of the miniature air quality detector. First, correlation analysis is used to find out the main factors affecting pollutant concentrations. Second, principal component analysis is used to reduce the dimensionality of these main factors and extract their main information. Thirdly, taking the extracted principal components as independent variables and the observed values of pollutant concentrations as dependent variables, a PCA–RVM model is established by the relevance vector machine. Finally, the nonlinear autoregressive neural network is used to correct the error and finally complete the establishment of the PCA–RVM–NAR model. Root mean square error, goodness of fit, mean absolute error and relative mean absolute percent error are used to compare the calibration effect of PCA–RVM–NAR model and other commonly used models such as multiple linear regression model, support vector machine, multilayer perceptron neural network and nonlinear autoregressive models with exogenous input. The results show that, no matter which pollutant, the PCA–RVM–NAR model achieves better calibration results than other models in the four indicators. Using this model to correct the data of the miniature air quality detector can improve its accuracy by 77.8–93.9%.https://doi.org/10.1038/s41598-022-13531-4 |
| spellingShingle | Bing Liu Yirui Zhang Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model Scientific Reports |
| title | Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model |
| title_full | Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model |
| title_fullStr | Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model |
| title_full_unstemmed | Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model |
| title_short | Calibration of miniature air quality detector monitoring data with PCA–RVM–NAR combination model |
| title_sort | calibration of miniature air quality detector monitoring data with pca rvm nar combination model |
| url | https://doi.org/10.1038/s41598-022-13531-4 |
| work_keys_str_mv | AT bingliu calibrationofminiatureairqualitydetectormonitoringdatawithpcarvmnarcombinationmodel AT yiruizhang calibrationofminiatureairqualitydetectormonitoringdatawithpcarvmnarcombinationmodel |