基于FCS-SVM的建筑业碳排放预测研究

Carbon Emission Prediction of Construction Industry Based on FCS-SVM

科学预测建筑业碳排放对建筑的低碳发展具有重要意义。论文应用模糊布谷鸟搜索算法优化支持向量机模型对建筑业碳排放预测问题展开研究:首先构建建筑业碳排放测算模型,通过灰色关联度模型筛选建筑业碳排放的影响因素,在此基础上建立建筑业碳排放的模糊布谷鸟搜索算法优化的支持向量机(FCS-SVM)预测模型对建筑业碳排放进行预测。研究结果表明,FCS-SVM建筑业碳排放预测模型的精度高于BP神经网络预测模型以及混沌粒子群算法优化的BP神经网络(CPSO-BP)预测模型。

The scientific predictions of carbon emissions from the construction industry are important for the low carbon development of buildings. In this paper, the fuzzy cuckoo search algorithm(FSC) is used to optimize the support vector machine(SVM) model to study the carbon emission prediction of the construction industry. Firstly, we establish the carbon emission measurement model of the construction industry and use a model of grey incidence degree to filtrate the influence factors of carbon emissions of the construction industry. Then, the FCS-SVM prediction model for building carbon emissions is built and the model is used to predict the carbon emissions of the construction industry. The results show that the accuracy of the FCSSVM construction carbon emission prediction model is far superior to the BP neural network and CPSO algorithm.