TRIP DISTRIBUTION FORECASTING WITH MULTILAYER PERCEPTRON NEURAL NETWORKS: A CRITICAL EVALUATION
TRIP DISTRIBUTION FORECASTING WITH MULTILAYER PERCEPTRON NEURAL NETWORKS: A CRITICAL EVALUATION
复制标题
DOI：
10.1016/s0191-2615(99)00014-4
复制
发表时间：
2000
影响因子：
6.8
通讯作者：
M. Mozolin;J. Thill;E. L. Usery
中科院分区：
文献类型：
--
作者：
M. Mozolin;J. Thill;E. L. Usery
本研究比较多层感知器类神经网路与最大似然双约束模型在通勤者出行分布上的表现。我们的实验产生了压倒性的证据与现有文献的差异，神经网络空间相互作用模型的预测精度是劣于最大似然双约束模型的距离衰减的指数函数。该研究指出了神经网络性能不佳的几个可能原因，包括模型的不可转移性，泛化能力不足，以及对sigmoid激活函数的依赖，以及它们的归纳性质。它的结论是，目前的感知器神经网络不提供一个适当的建模方法来预测出行分布在规划范围内的分布预测（工人数量，居民数量，通勤距离）超出其基准年域的定义。
This study compares the performance of multilayer perceptron neural networks and maximum-likelihood doubly-constrained models for commuter trip distribution. Our experiments produce overwhelming evidence at variance with the existing literature that the predictive accuracy of neural network spatial interaction models is inferior to that of maximum-likelihood doubly-constrained models with an exponential function of distance decay. The study points to several likely causes of neural network underperformance, including model non-transferability, insufficient ability to generalize, and reliance on sigmoid activation functions, and their inductive nature. It is concluded that current perceptron neural networks do not provide an appropriate modeling approach to forecasting trip distribution over a planning horizon for which distribution predictors (number of workers, number of residents, commuting distance) are beyond their base-year domain of definition.