一种考虑风力作用的KNN城市AQI预测算法
|
摘要
考虑风力对城市空气质量指数(AQI)的重要影响,基于KNN算法提出一种新的模型对城市AQI进行预测。该模型主要依赖于数据间的局部相似性和依赖性,再将风力因素对城市AQI的影响进行量化并加入到KNN预测结果中,得到最终预测结果。实验对九个重点城市进行AQI预测,结果表明,该模型相较传统KNN方法预测得到的AQI值准确率大幅度提升,对城市AQI的预测具有指导意义。
Considering the important influence of wind on air quality index( AQI),this paper proposed a new model,which based on KNN algorithm to predict the urban AQI. The model mainly relied on the local similarity and dependence between data,and quantified the impact of wind factors on urban AQI and added it to the KNN forecast results to get the final forecast results. The experimental results of AQI in nine major cities show that the proposed model significantly improves the accuracy of AQI compared with the traditional KNN method. The model has guiding significance for the prediction of urban AQI.
Considering the important influence of wind on air quality index( AQI),this paper proposed a new model,which based on KNN algorithm to predict the urban AQI. The model mainly relied on the local similarity and dependence between data,and quantified the impact of wind factors on urban AQI and added it to the KNN forecast results to get the final forecast results. The experimental results of AQI in nine major cities show that the proposed model significantly improves the accuracy of AQI compared with the traditional KNN method. The model has guiding significance for the prediction of urban AQI.
引文
[1]杨思琪,赵丽华.随机森林算法在城市空气质量预测中的应用[J].统计与决策,2017(20):83-86.(Yang Siqi,Zhao Lihua. Application of random forest method in urban air quality prediction[J].Statistics and Decision,2017(20):83-86.)
[2]伦淑娴,林健,姚显双.基于小世界回声状态网的时间序列预测[J].自动化学报,2015,42(9):1669-1679.(Lun Shuxian,Lin Jian,Yao Xianshuang. Time series prediction with an improved echo state network using small world network[J]. Acta Automatica Sinica,2015,42(9):1669-1679.)
[3]席超,蔡成林,李思敏,等.基于ARMA模型的导航卫星钟差长期预报[J].天文学报,2014,55(1):78-88.(Xi Chao,Cai Chenglin,Li Simin,et al. Long-term satellite clock bias prediction based on ARMA model[J]. Acta Astronomica Sinica,2014,55(1):78-88.)
[4] Zhang Yang,Li Ce,Li Lian. Electricity price forecasting by a hybrid model,combining wavelet transform,ARMA and kernel-based extreme learning machine methods[J]. Applied Energy,2017,190(3):291-305.
[5]翟静,曹俊.基于时间序列ARIMA与BP神经网络的组合预测模型[J].统计与决策,2016(4):29-32.(Zhai Jing,Cao Jun. Combination forecasting model based on time series ARIMA and BP neural network[J]. Statistics and Decision,2016(4):29-32.)
[6] Ruby-Figueroaa R,Saavedrab J,Bahamondec N,et al. Permeate flux prediction in the ultrafiltration of fruit juices by ARIMA models[J]. Journal of Membrane Science,2017,524(2):108-116.
[7]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.(Liu Aiguo,Xue Yuntao,Hu Jianglu,et al. Ultra-short-term wind power forecasting based on SVM optimized by GA[J]. Power System Protection and Control,2015,43(2):90-95.)
[8] Direito B,Teixeira C A,Sales F,et al. A realistic seizure prediction study based on multiclass SVM[J/OL]. International Journal of Neural Systems, 2017, 27(3). https://doi. org/10. 1142/S012906571750006X.
[9]李博,王建国,李静文.基于神经网络的景气预测模型[J].统计与决策,2017(10):43-46.(Li Bo,Wang Jianguo,Li Jingwen. Prosperity prediction model based on neural network[J]. Statistics and Decision,2017(10):43-46.)
[10] Asencio-Cortés G,Martínez-álvarez F,Troncoso A,et al. Mediumlarge earthquake magnitude prediction in Tokyo with artificial neural networks[J]. Neural Computing and Applications,2017,28(5):1043-1055.
[11]Zheng Zuduo,Su Dongcai. Short-term traffic volume forecasting:a K-nearest neighborapproach enhanced by constrained linearly sewing principlecomponent algorithm[J]. Transportation Research Part C:Emerging Technologies,2014,43(6):143-157.
[12]Oliveira P J A,Boccelli D L. K-Nearest neighbor for short term water demand forecasting[C]//Proc of World Environmental and Water Resources Congress. 2017:201-510.
[13]罗辛,欧阳元新,熊璋,等.通过相似度支持度优化基于K近邻的协同过滤算法[J].计算机学报,2010,33(8):1440-1441.(Luo Xin,Ouyang Yuanxin,Xiong Zhang,et al. The effect of similarity support in K-nearest-neighborhood based collaborative filtering[J].Chinese Journal of Computers,2010,33(8):1440-1441.)
[2]伦淑娴,林健,姚显双.基于小世界回声状态网的时间序列预测[J].自动化学报,2015,42(9):1669-1679.(Lun Shuxian,Lin Jian,Yao Xianshuang. Time series prediction with an improved echo state network using small world network[J]. Acta Automatica Sinica,2015,42(9):1669-1679.)
[3]席超,蔡成林,李思敏,等.基于ARMA模型的导航卫星钟差长期预报[J].天文学报,2014,55(1):78-88.(Xi Chao,Cai Chenglin,Li Simin,et al. Long-term satellite clock bias prediction based on ARMA model[J]. Acta Astronomica Sinica,2014,55(1):78-88.)
[4] Zhang Yang,Li Ce,Li Lian. Electricity price forecasting by a hybrid model,combining wavelet transform,ARMA and kernel-based extreme learning machine methods[J]. Applied Energy,2017,190(3):291-305.
[5]翟静,曹俊.基于时间序列ARIMA与BP神经网络的组合预测模型[J].统计与决策,2016(4):29-32.(Zhai Jing,Cao Jun. Combination forecasting model based on time series ARIMA and BP neural network[J]. Statistics and Decision,2016(4):29-32.)
[6] Ruby-Figueroaa R,Saavedrab J,Bahamondec N,et al. Permeate flux prediction in the ultrafiltration of fruit juices by ARIMA models[J]. Journal of Membrane Science,2017,524(2):108-116.
[7]刘爱国,薛云涛,胡江鹭,等.基于GA优化SVM的风电功率的超短期预测[J].电力系统保护与控制,2015,43(2):90-95.(Liu Aiguo,Xue Yuntao,Hu Jianglu,et al. Ultra-short-term wind power forecasting based on SVM optimized by GA[J]. Power System Protection and Control,2015,43(2):90-95.)
[8] Direito B,Teixeira C A,Sales F,et al. A realistic seizure prediction study based on multiclass SVM[J/OL]. International Journal of Neural Systems, 2017, 27(3). https://doi. org/10. 1142/S012906571750006X.
[9]李博,王建国,李静文.基于神经网络的景气预测模型[J].统计与决策,2017(10):43-46.(Li Bo,Wang Jianguo,Li Jingwen. Prosperity prediction model based on neural network[J]. Statistics and Decision,2017(10):43-46.)
[10] Asencio-Cortés G,Martínez-álvarez F,Troncoso A,et al. Mediumlarge earthquake magnitude prediction in Tokyo with artificial neural networks[J]. Neural Computing and Applications,2017,28(5):1043-1055.
[11]Zheng Zuduo,Su Dongcai. Short-term traffic volume forecasting:a K-nearest neighborapproach enhanced by constrained linearly sewing principlecomponent algorithm[J]. Transportation Research Part C:Emerging Technologies,2014,43(6):143-157.
[12]Oliveira P J A,Boccelli D L. K-Nearest neighbor for short term water demand forecasting[C]//Proc of World Environmental and Water Resources Congress. 2017:201-510.
[13]罗辛,欧阳元新,熊璋,等.通过相似度支持度优化基于K近邻的协同过滤算法[J].计算机学报,2010,33(8):1440-1441.(Luo Xin,Ouyang Yuanxin,Xiong Zhang,et al. The effect of similarity support in K-nearest-neighborhood based collaborative filtering[J].Chinese Journal of Computers,2010,33(8):1440-1441.)