基于BP神经网络的道路交通环境影响综合评价模型

根据影响道路交通环境的各单项评价指标及其分级标准．利用随机分布理论生成足够多用于神经网络建模的样本数据。应用非线性模拟性很强的BP神经网络技术对道路交通环境质量进行综合评价，克服了物元分析等综合评价方法存在的不确定性和受人为因素影响等缺陷，提高了综合评价的客观性和合理性。评价实例表明：文中提出的生成训练样本和用BP神经网络建立道路交通环境质量的综合评价模型是合理的和可行的。

Artificial Neural Network-based Model for Road Traffic Environmental Quality Evaluation

According to the road traffic environmental quality evaluation indexes and their grade standards,efficient samples based on the random-distribution theory were produced.The BP neural network(BPNN)with high non-linearity-fitting capacity was applied to comprehensive evaluation of road traffic envitonmental quality,thus overcame the shortages such as uncertainty,man-influenced,etc.,in element matter analysis.The BPNN-based model possessed the objective and rationalization.The studied cases shown that the approach producing samples used for learning,verifying and testing the BPNN-based model and the application of BPNN to evaluation model were feasible and reasonable.