论文部分内容阅读
目的初步探讨支持向量机(support vector machines,简称SVMs)模型在有机溶剂职业危害评价中的应用。方法选择17家使用有机溶剂企业,对其使用有机溶剂作业进行调查,根据现场检测、职业卫生学调查、劳动者职业健康检查等资料,筛选构建评价模型指标体系。运用SVMs方法,采用R软件的e1071软件包,对17家企业14种有机溶剂作业职业危害进行训练和预测。结果当选用10项评价指标时,预测准确率为85.45%,当选用8项评价指标时,预测准确率为69.09%,当选用4项评价指标时,预测准确率为80.00%。结论 SVMs模型可以对有机溶剂职业危害进行预测,对建设项目职业危害评价工作具有一定参考意义,但其实际应用需进一步验证。
Objective To investigate the application of support vector machines (SVMs) in the evaluation of occupational hazards in organic solvents. Methods Seventeen companies using organic solvents were selected to investigate their use of organic solvents. According to the field testing, occupational hygiene investigation and occupational health examination of workers, the index system of evaluation model was constructed. Using SVMs method, using R software e1071 package, training and forecasting occupational hazards of 14 organic solvents in 17 enterprises. Results When 10 evaluation indexes were selected, the accuracy of prediction was 85.45%. When 8 evaluation indexes were selected, the accuracy of prediction was 69.09%. When 4 evaluation indexes were selected, the accuracy of prediction was 80.00%. Conclusion The SVMs model can predict the occupational hazards of organic solvents and has certain reference value for the occupational hazards assessment of construction projects, but its practical application needs further verification.