Improved adaptive particle swarm for BP neural network optimization in hospital outpatient volume prediction

Real-time and accurate prediction of hospital outpatients is an important basis for the hospital to resolve the current contradiction between doctors and patients. However, the traditional hospital outpatients cannot accurately predict the data and reveal the internal laws of its time series, which cannot effectively adjust the treatment resources. This paper proposes the new particle swarm optimization (PSO) algorithm to optimize the BP neural network to predict outpatient timing. Specifically, it uses improved adaptive acceleration factor and inertia weight to iteratively optimize weight values and threshold values of the BP neural network, trains the BP neural network model, and then conducts calculation work. Its results are compared with those of the BP neural network optimized by the standard particle swarm optimization algorithm and the traditional BP neural network model respectively. The data comparison results show that new prediction accuracy is significantly improved and iterative calculation is very stable, therefore the improved particle swarm optimization BP neural network model can better predict the trend of hospital outpatient flow over time.