模拟测试数据集

基于复合神经网络结构的深度学习算法，求解多式联运全过程运输组织方案与调度优化。该数据来源于基于通用的随机数生成算法模拟的数据集；利用通用随机数生成算法设计了计算机模拟程序，通过随机种子测试严格保证了数据的随机性和可重复性；实施了Kolmogorov-Smirnov检验，保证了指定分布条件下的随机数生成，进一步通过生成的随机数与理论分布差异值对比，计算统计量和p值，确保了随机数与预期分布的高度吻合。

A deep learning algorithm based on composite neural network architecture is utilized to solve the whole-process transportation organization planning and scheduling optimization problems for intermodal transportation. The dataset is derived from simulations conducted using general-purpose random number generation algorithms. A computer simulation program was designed with the general-purpose random number generation algorithm, and rigorous random seed tests were carried out to strictly guarantee the randomness and reproducibility of the dataset. The Kolmogorov-Smirnov test was implemented to verify the random number generation under specified distribution conditions. Furthermore, by comparing the generated random numbers with their corresponding theoretical distributions and calculating the test statistic and p-value, the high degree of consistency between the generated random numbers and the expected distributions is ensured.

搜集汇总

背景与挑战

背景概述

该数据集是一个用于多式联运运输优化研究的模拟测试数据集，基于深度学习算法生成，通过随机数模拟确保数据的随机性和可重复性。它包含约11004个文件，总大小为38.0MB，主要应用于人工智能和交通运输工程领域，支持多式联运智能调度方案的开发与验证。