In order to reduce the occurrence of safety accidents in building projects,a combined safety prediction model of building project based on RS-PCA-SVM is proposed.Rough set(RS)theory was adopted to perform attribute reduction for data,eliminating crossover and redundant information,re-ducing the dimension and computational complexity of input variables,and reducing the training time.On this basis,principal component analysis(PCA)was used for dimension reduction to remove the principal component with low contribution,and the principal component with high contribution was taken as the input variable of support vector machine(SVM).Particle swarm optimization(PSO)was used to optimize the parameters of SVM model to avoid the blindness of selecting parameters of SVM manually.The results show that the average prediction accuracy of this model is 93.78％.Compared with the traditional method,the prediction accuracy is higher and the calculation speed is faster.
关键词
属性约简/主成分分析(PCA)法/支持向量机(SVM)/预测模型
Key words
attribute reduction/principal component analysis(PCA)/support vector machine(SVM)/prediction model
维普
万方数据