Students manipulative ability in physics experiment (MAPE) is the key of physics experiment ability.

物理实验操作能力是物理实验能力的核心。

Comparing the linear regress analysis with the time series analysis, the latter's MAPE are less than the former.

将线性回归与时间序列分析进行比较，发现时序分析的平均绝对百分误差(MAPE)远远小于线性回归分析。

Forecast results show that Bayesian neural network MAPE and RMSE are less than artificial neural network, Bayesian neural network with better performance, it can be applied to predict the actual work.

预测结果表明，贝叶斯神经网络的MAPE和RMSE均小于人工神经网络，贝叶斯神经网络具有更好的性能，它可利用于实际预测工作中。