The Prediction of Metro Shield Construction Cost Based on a Backpropagation Neural Network Improved by Quantum Particle Swarm Optimization

Table 4

Prediction results of different training and testing split ratio.

The training and testing split ratio	90% : 10%	80% : 20%	70% : 30%
Average absolute error	5.278	7.313	12.763
Average relative error (%)	1.10	2.29	3.98