Spatio-Temporal Point Processes With Attention for Traffic Congestion Event Modeling
نویسندگان
چکیده
We present a novel framework for modeling traffic congestion events over road networks. Using multi-modal data by combining count from sensors with police reports that report incidents, we aim to capture two types of triggering effect events. Current at one location may cause future the network, and incidents spread congestion. To model non-homogeneous temporal dependence event on past, use attention-based mechanism based neural networks embedding point processes. incorporate directional spatial induced adapt “tail-up” context statistics network setting. demonstrate our approach’s superior performance compared state-of-the-art methods both synthetic real data.
منابع مشابه
Spatial and Spatio-temporal Point Processes
The present paper gives the background to point processes in space and time. Some special types of spatial and spatio-temporal models of point processes are introduced with the emphasis to Cox processes. Their basic properties are described and some characteristics are calculated. The simulation of one of these models is shown. Introduction At present, the theory of point processes is well esta...
متن کاملA J-function for Inhomogeneous Spatio-temporal Point Processes
We propose a new summary statistic for inhomogeneous intensity-reweighted moment stationarity spatio-temporal point processes. The statistic is defined in terms of the n-point correlation functions of the point process, and it generalizes the J -function when stationarity is assumed. We show that our statistic can be represented in terms of the generating functional and that it is related to th...
متن کاملSpatio-temporal càdlàg functional marked point processes: Unifying spatio-temporal frameworks
This paper defines the class of càdlàg functional marked point processes (CFMPPs). These are (spatio-temporal) point processes marked by random elements which take values in a càdlàg function space, i.e. the marks are given by càdlàg stochastic processes. We generalise notions of marked (spatio-temporal) point processes and indicate how this class, in a sensible way, connects the point process ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Intelligent Transportation Systems
سال: 2022
ISSN: ['1558-0016', '1524-9050']
DOI: https://doi.org/10.1109/tits.2021.3068139