|
| SVM Joint-decision Method for Atmospheric Environment Classification |
| |
| View Full Text View/Add Comment Download reader |
| DOI：10.7643/issn.1672-9242.2022.08.018 |
| KeyWord:environment classification SVM hierarchical clustering PCA joint-decision method machine learning |
| Author | Institution |
| WANG Jing-cheng |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
| ZHANG Lun-wu |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
| YANG Xiao-kui |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
| HU Xue-bu |
College of Chemistry and Chemical Engineering, Chongqing University of Technology, Chongqing , China |
| ZHOU Jun-yan |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
| LI Ze-hua |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
| WU Shuai |
CSGC Key Laboratory of Ammunition Storage Environmental Effects, Southwest Technology and Engineering Research Institute, Chongqing , China |
|
| Hits: |
| Download times: |
| Abstract: |
| The paper aims to conduct a quick accurate prediction for atmospheric environment classification of different cities. SVM is used to construct a joint-decision algorithm for multi-classification problems, and the principal component clustering results of a large number of urban environmental factor data are input. Through machine learning training, the SVM joint-decision model of atmospheric environment is constructed. In the 91 cities, Hanoi and Haiphong are the most similar couple, while Padang and Golmud turn out to be the most different cities. The joint-decision model formed by 9 SVM binary classifiers forms a partitioned prediction cloud image in the principal component data space by point prediction. Results show that the prediction accuracy is higher than 95%, therefore atmospheric environment of different types can be recognized swiftly by the established model. |
| Close |
|
|
|