现代医院门诊量的灰色RBF神经网络预测

门诊量预测是现代医院电梯交通以及医疗资源优化配置的重要前提。为了有效地预测医院的门诊量，提出一种将灰色预测方法与RBF神经网络有机结合的灰色神经网络组合预测方法。该方法利用灰色预测中的累加生成运算（AGO）对原始观测数据进行变换，得到规律性较强的累加数据，作为神经网络的建模和训练样本。所提出的方法既避免了灰色预测方法存在的理论误差，又提高了神经网络的训练速度和预测精度，对短期的医院门诊量预测具有较强的实用价值。结果表明：所提出的方法具有良好的预测精度。

Grey RBF neural network based forecasting of outpatient capacity in modern hospital

The outpatient capacity forecasting is the important premise for hospital lift traffic dispatching and allocation of medical resources.To efficiently forecast the outpatient capacity in a hospital, a method combining grey forecasting and RBF Neural Network（RBFNN） to construct the grey method based RBFNN（GM-RBFNN） forecasting model is proposed.The accumulated generating operation in gray forecasting is used to converse the initial observed outpatient data to obtain the accumulated outpatient data with strong regularity which are employed to model and train the GM-RBFNN.The presented method not only avoids the theoretical error of grey model, but enhances greatly both the training speed and the prediction accuracy of the neural network,implying that GM-RBFNN is very practical for short period forecasting of outpatient capacity in a hospital.Experimental results prove the validity of the proposed method.