基于GWO-LSTM的医院日门诊量预测研究OA

This study begins with a statistical analysis of factors influencing outpatient volume to form a multi-dimensional dataset.It then examines the global search capability of the grey wolf optimization(GWO)algorithm and the ability of long short-term memory(LSTM)networks to capture long-term dependencies in sequences.Building on these analyses,a hybrid prediction model integrating GWO and LSTM(GWO-LSTM)is proposed to enhance the accuracy and stability of hospital outpatient volume forecasting.The experimental phase validates the model ' s effectiveness in capturing non-linear features and learning long-term dependencies.Comparative analysis with traditional LSTM models further confirms its potential for improvement in prediction accuracy and robustness.