کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
1124154 1488543 2011 11 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Modeling Arterial Travel Time with Limited Traffic Variables using Conditional Independence Graphs & State-Space Neural Networks
موضوعات مرتبط
علوم انسانی و اجتماعی علوم انسانی و هنر هنر و علوم انسانی (عمومی)
پیش نمایش صفحه اول مقاله
Modeling Arterial Travel Time with Limited Traffic Variables using Conditional Independence Graphs & State-Space Neural Networks
چکیده انگلیسی

This paper presents travel time prediction models for both congested and non-congested conditions on urban arterial using only limited basic traffic data. The state-space notion of traffic processes and State-Space Neural Network (SSSNNet) models are used on simulation generated traffic data. Conditional Independence (CI) graphs are used to identify independence and interaction between observable traffic parameters thus only relevant ones can be used to predict travel time. Even with limited data, the predictive performance and computational efficiency of Conditional Independence Graphs coupled with State-Space Neural Networks are practically accurate. They also outperformed a traditional Artificial Neural Network model.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Procedia - Social and Behavioral Sciences - Volume 16, 2011, Pages 207-217