Improving Route Choice Models by Incorporating Contextual Factors via Knowledge Distillation

Route Choice Models predict the route choices of travelers traversing an urban area. Most of the route choice models link route characteristics of alternative routes to those chosen by the drivers. The models play an important role in prediction of traffic levels on different routes and thus assist in development of efficient traffic management strategies that result in minimizing traffic delay and maximizing effective utilization of transport system. High fidelity route choice models are required to predict traffic levels with higher accuracy. Existing route choice models do not take into account dynamic contextual conditions such as the occurrence of an accident, the socio-cultural and economic background of drivers, other human behaviors, the dynamic personal risk level, etc. As a result, they can only make predictions at an aggregate level and for a fixed set of contextual factors. For higher fidelity, it is highly desirable to use a model that captures significance of subjective or contextual factors in route choice. This paper presents a novel approach for developing high-fidelity route choice models with increased predictive power by augmenting existing aggregate level baseline models with information on drivers’ responses to contextual factors obtained from Stated Choice Experiments carried out in an Immersive Virtual Environment through the use of knowledge distillation.

[1]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[2]  Carlo G. Prato,et al.  Route choice modeling: past, present and future research directions , 2009 .

[3]  P. Bonsall,et al.  Drivers' requirements for route guidance , 1990 .

[4]  Klaus Bogenberger,et al.  Learning user preferences of route choice behaviour for adaptive route guidance , 2007 .

[5]  Eran Ben-Elia,et al.  Which road do I take? A learning-based model of route-choice behavior with real-time information , 2010 .

[6]  Wei Zhang,et al.  Learning Efficient Detector with Semi-supervised Adaptive Distillation , 2019, BMVC.

[7]  M Pursula,et al.  URBAN ROUTE CHOICE MODELLING WITH MULTINOMIAL LOGIT MODELS , 1993 .

[8]  Junmo Kim,et al.  A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Brian Wolshon,et al.  Sustained Flow Index: Stochastic Measure of Freeway Performance , 2016 .

[10]  Supratik Mukhopadhyay,et al.  DeepSat: a learning framework for satellite imagery , 2015, SIGSPATIAL/GIS.

[11]  Supratik Mukhopadhyay,et al.  A Semiautomated Probabilistic Framework for Tree-Cover Delineation From 1-m NAIP Imagery Using a High-Performance Computing Architecture , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[12]  P. Bovy,et al.  ROUTE CHOICE: WAYFINDING IN TRANSPORT NETWORKS , 1990 .

[13]  Mark D. Uncles,et al.  Discrete Choice Analysis: Theory and Application to Travel Demand , 1987 .

[14]  Huchuan Lu,et al.  Deep Mutual Learning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  Supratik Mukhopadhyay,et al.  Deep neural networks for texture classification - A theoretical analysis , 2018, Neural Networks.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Wolfgang Broll,et al.  Comparing VR and non-VR driving simulations: An experimental user study , 2017, 2017 IEEE Virtual Reality (VR).

[18]  Antonio Lima,et al.  Understanding individual routing behaviour , 2016, Journal of The Royal Society Interface.

[19]  Moshe Ben-Akiva,et al.  Discrete Choice Models with Applications to Departure Time and Route Choice , 2003 .

[20]  Supratik Mukhopadhyay,et al.  Pixel-Level Reconstruction and Classification for Noisy Handwritten Bangla Characters , 2018, 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR).

[21]  E. Miller,et al.  A computerized household activity scheduling survey , 2000 .

[22]  Michael Weber,et al.  Virtual Reality Driving Simulator Based on Head-Mounted Displays , 2017 .

[23]  Shiming Ge,et al.  Low-Resolution Face Recognition in the Wild via Selective Knowledge Distillation , 2018, IEEE Transactions on Image Processing.

[24]  Le Minh Kieu,et al.  Deep learning methods in transportation domain: a review , 2018, IET Intelligent Transport Systems.

[25]  Shlomo Bekhor,et al.  Route Choice Models , 2004 .

[26]  Supratik Mukhopadhyay,et al.  Unsupervised Learning using Pretrained CNN and Associative Memory Bank , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[27]  Bohyung Han,et al.  Learning to Specialize with Knowledge Distillation for Visual Question Answering , 2018, NeurIPS.

[28]  Henry X. Liu,et al.  Boundedly rational route choice behavior: A review of models and methodologies , 2016 .

[29]  Qun Liu,et al.  SafeRNet: Safe transportation routing in the era of Internet of vehicles and mobile crowd sensing , 2018, 2017 14th IEEE Annual Consumer Communications & Networking Conference (CCNC).

[30]  Asad J. Khattak,et al.  Commuters' enroute diversion and return decisions: Analysis and implications for advanced traveler information systems , 1993 .

[31]  Rich Caruana,et al.  Model compression , 2006, KDD '06.