STHAN: Transportation Demand Forecasting with Compound Spatio-Temporal Relationships
نویسندگان
چکیده
Transportation demand forecasting is a critical precondition of optimal online transportation dispatch, which will greatly reduce drivers’ wasted mileage and customers’ waiting time, contributing to economic environmental sustainability. Though various methods have been developed, the core spatio-temporal complexity remains challenging from three perspectives: (1) Compound spatial relationships. According our empirical analysis, these relationships widely exist. Previous studies focus on capturing different using multi-homogeneous graphs. However, information flow across not modeled explicitly. (2) Heterogeneity in A region’s neighbors under same relationship may weights for this region. Meanwhile, also weigh differently. (3) Synchronicity between compound temporal research considers synchronous influences homogeneous fashion while are captured synchronicity. To address aforementioned perspectives, we propose S patio- T emporal H eterogeneous graph ttention N etwork (STHAN), where key intuition via meta-paths We first construct heterogeneous including multiple use depict capture heterogeneity, hierarchical attention, contains node level attention meta-path attention. The synchronicity relationships, ones, meta-path-level Our framework outperforms state-of-the-art models by reducing 6.58%, 4.57%, 4.20% WMAPE experiments real-world datasets, respectively.
منابع مشابه
Spatio-temporal Matching for Urban Transportation Applications
In this paper we present a search problem in which mobile agents are searching for static resources. Each agent wants to obtain exactly one resource. Both agents and resources are spatially located on a road network and the movement of the agents is constrained to the road network. This problem applies to various transportation applications including: vehicles (agents) searching for parking (re...
متن کاملSpatio-temporal Databases in Urban Transportation
In this paper we describe applications, research issues, and approaches related to Intelligent Transportation Systems (ITS). More specifically, we focus on spatio-temporal databases in urban transportation. We address the issues of trip planning and navigation, abstraction of concepts from spatio-temporal sensor data, mobile peer-to-peer data management, and social networks and crowd-sourcing. ...
متن کاملWind speed forecasting using spatio-temporal indicators
Abstract. From small farms to electricity markets the interest and importance of wind power production is continuously increasing. This interest is mainly caused by the fact that wind is a continuous resource of clean energy. To take full advantage of the potential of wind power production it is crucial to have tools that accurately forecast the expected wind speed. However, forecasting the win...
متن کاملAn investigation into machine learning approaches for forecasting spatio-temporal demand in ride-hailing service
In this paper, we present machine learning approaches for characterizing and forecasting the short-term demand for on-demand ride-hailing services. We propose the spatio-temporal estimation of the demand that is a function of variable effects related to traffic, pricing and weather conditions. With respect to the methodology, a single decision tree, bootstrap-aggregated (bagged) decision trees,...
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: ACM Transactions on Knowledge Discovery From Data
سال: 2023
ISSN: ['1556-472X', '1556-4681']
DOI: https://doi.org/10.1145/3565578