Air Quality Index Forecasting Based on SVM and Moments
Autor: | Bin Chen, Wei Wang, Ya-xin Sun, Rong Zhu, Wei-guo Shen |
---|---|
Rok vydání: | 2018 |
Předmět: |
010504 meteorology & atmospheric sciences
business.industry Computer science Feature vector ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Stability (learning theory) Pattern recognition 010501 environmental sciences Color space 01 natural sciences Image (mathematics) Support vector machine Wavelet Feature (computer vision) Computer Science::Computer Vision and Pattern Recognition Artificial intelligence business Air quality index Physics::Atmospheric and Oceanic Physics Correlogram Color moments 0105 earth and related environmental sciences |
Zdroj: | ICSAI |
DOI: | 10.1109/icsai.2018.8599314 |
Popis: | A novel air quality index (AQI) forecasting method based on support vector machine (SVM) and moments is proposed in this paper. By using it, the AQI value of a sky image can be forecasted. In order to improve the forecasting accuracy and stability, color moments, color correlogram and wavelet features are used to extract the image features, which transfers the input image from color space to feature space. We train the SVM with the input of these extracted features. Then the trained SVM is utilized to achieve the AQI forecasting for new images. The experimental results improve that the proposed method has good AQI forecasting results, and the accuracy of the testing dataset is more than 82.3%, with 1300 training images and 200 test images. |
Databáze: | OpenAIRE |
Externí odkaz: |
načítá se...