2020/02/06 by Ibai Laña, Javier Medina, Lana, Ibai +5 · 2 citations
Computer Science · Decision Sciences · Engineering · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Data Quality and Management #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Traffic Prediction and Management Techniques
paper · pdf · doi:10.48550/arxiv.2002.02210
openalex publication_date 2020/02/06 · openalex created_date 2022/07/26 · openalex updated_date 2026/07/28
Advances in Data Science permeate every field of Transportation Science and\nEngineering, resulting in developments in the transportation sector that are\ndata-driven. Nowadays, Intelligent Transportation Systems (ITS) could be\narguably approached as a ``story'' intensively producing and consuming large\namounts of data. A~diversity of sensing devices densely spread over the\ninfrastructure, vehicles or the travelers' personal devices act as sources of\ndata flows that are eventually fed into software running on automatic\ndevices, actuators or control systems producing, in~turn, complex information\nflows among users, traffic managers, data analysts, traffic modeling\nscientists, etc. These~information flows provide enormous opportunities to\nimprove model development and decision-making. This work aims to describe how\ndata, coming from diverse ITS sources, can be used to learn and adapt\ndata-driven models for efficiently operating ITS assets, systems and processes;\nin~other words, for data-based models to fully become \actionable.\nGrounded in this described data modeling pipeline for ITS, we~define the\ncharacteristics, engineering requisites and challenges intrinsic to its three\ncompounding stages, namely, data fusion, adaptive learning and model\nevaluation. We~deliberately generalize model learning to be adaptive, since,\nin~the core of our paper is the firm conviction that most learners will have to\nadapt to the ever-changing phenomenon scenario underlying the majority of ITS\napplications. Finally, we~provide a prospect of current research lines within\nData Science that can bring notable advances to data-based ITS modeling, which\nwill eventually bridge the gap towards the practicality and actionability of\nsuch models.\n