Forecasting Traffic Speed for a Segment Network Using GraphSAGE with Sparse Data PROJECT TITLE : GraphSAGE-Based Traffic Speed Forecasting for Segment Network With Sparse Data ABSTRACT: The ability to accurately anticipate the flow of traffic is an essential component of intelligent traffic management systems. Because of the widespread use of massive vehicle trajectory data, agencies invariably run into problems with missing data, which makes it more difficult to predict how much traffic will flow on an urban road network. Using I a data recovery algorithm to impute missing speed data for the segment network with nonlinear spatial and temporal correlations and (ii) forecasting of spatially heterogeneous traffic speed within the road network using the GraphSAGE model, this article investigates the urban network-wide short-term forecasting of traffic speed with consideration to missing link speed data. This is accomplished by I a data recovery algorithm to impute missing speed data for the segment network; and (ii) forecasting It is investigated how the forecasting of traffic speeds is affected by the influences of partially missing data as well as recovered data. A case study of the urban area in Hangzhou, China, is presented, and it is discovered that the proposed recovery algorithm has the best performance when compared to benchmark methods in terms of traffic speed information reconstruction. When compared to the scenario in which the original data was used without recovery, the case study demonstrates that making use of the recovered data results in a short-term speed forecast that is more accurate and utilizes resources more effectively. The problems associated with missing traffic data and the difficulties associated with forecasting in the presence of missing data in an urban road network are addressed by the proposed methods. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest HarMI Recognizing Human Activity Using Multi-Modality Incremental Learning Deep Features for Pedestrian Detection and Handcrafted Design A Study