The average value of absolute error is 2.05% and the biggest error is 5.12% in the model of loom efficiency. The results indicate that ANN model has high forecast precision.
对于织机效率模型，预报误差绝对值的平均为2.05%，最大误差为5.12%，可知模型具有较高的预报精度，人工神经网络对此模型的预报可行有效。
The result showed average absolute error is 0.17% and average relative error is 8.58%. It is concluded that self-made TDR probe can be used in the other area of Loess Plateau.
并在田间与中子仪测定结果进行了对比，结果表明，平均绝对偏差为0.17%，平均相对偏差为8.58%，说明tdr自制探头可以在黄土高原地区推广应用。
Some data were chosen to train the network model. The results show that the convergence rate was faster, the model had higher accuracy, the average absolute error can reach 0.002 7%.
对现场收集的数据进行仿真学习，结果表明，该预测模型收敛速度快，具有较高的预测精度，平均绝对误差可达到0.002 7%。
As the name suggests, the mean absolute error is an average of the absolute errors, where is the prediction and the true value.
顾名思义，平均绝对误差是绝对误差的平均值，其中fi是预测值而yi是实际值。
The absolute values of the prediction error of the middle-late rice were between 0.02% and 3.77%, the average error was 1.9%. The precision was high, so the damage assessment method was feasible.
中晚稻单产灾损率的预估误差的绝对值在0.02~3.77个百分点，平均误差为1.9个百分点，预估精度较高，灾损评估方法可行。
The absolute values of the prediction error of the middle-late rice were between 0.02% and 3.77%, the average error was 1.9%. The precision was high, so the damage assessment method was feasible.
中晚稻单产灾损率的预估误差的绝对值在0.02~3.77个百分点，平均误差为1.9个百分点，预估精度较高，灾损评估方法可行。
应用推荐