基于BP神经网络的监护仪配置数量评估研究

Evaluation of number of configured monitors based on BP neural network

目的:基于误差反向传播(error back propagation,BP)神经网络评估监护仪配置数量的合理性。方法:选用平均住院人数、平均手术量、平均住院天数、设备报废数量、设备平均使用年限和设备维修次数6个指标作为BP神经网络的输入,选用设备在用台数作为BP神经网络的输出,建立BP神经网络模型。以季度为单位收集2020—2021年全年以及2022年前2个季度9个内科科室的数据作为训练集,以2022年第三季度的数据作为测试集对学习结果进行验证。采用均方根误差、平均绝对误差及决定系数对模型的性能进行验证。结果:该模型的预测值与期望值的均方根误差为1.1357、平均绝对误差为0.89372、决定系数为0.95871,预测性能较好。结论:基于BP神经网络对监护仪的配置数量进行评估具有可行性,可为设备的优化配置提供科学的指导依据。

Objective To evaluate the rationality of the number of configured monitors based on error back propagation(BP)neural network.Methods A BP neural network model was established with the number of the equipment in use as the output result and the average number of inpatients,the average number of operations,the average days of hospitalization,the number of scrapped equipment,the average age of equipment and times of equipment maintenance as the input indicators.The data of 9 internal medicine departments in the whole year of 2020—2021 and the first 2 quarters of 2022 were collected on a quarterly basis as the training set,and the data of the third quarter of 2022 was used as the test set to verify the learning results.The performance of the model was analyzed using the root mean square error,mean absolute error and coefficient of determination.Results The model established behaved well in prediction with the root mean square error between the predicted and expected values of the model being 1.1357,the mean absolute error being 0.89372 and the coefficient of determination being 0.95871.Conclusion The BP neural network-based evaluation is feasible for the number of configured monitors,and guidance is provided for the optimized configuration of the equipment.