Neural congestion prediction system for trip modelling in heterogeneous spatio-temporal patterns.

To that end, a novel spatio-temporal deep learning architecture is proposed in this paper for forecasting demand and supply-demand gap in a ride-hailing system with anonymized spatial adjacency information ... However, due to spatio-temporal dependencies pertaining to demand and supply-demand gap in a ride-hailing system, making accurate forecasts for both demand and supply-demand gap is a difficult task. ... The authors are thankful to Didi Chuxing for the publicly released datasets. ...

arXiv:2012.08868v1 fatcat:aaz46sxgfzhubmmrrud4dbd434

Multiple Versions

To that end, a novel spatio-temporal deep learning architecture is proposed in this paper for forecasting demand and supply-demand gap in a ride-hailing system with anonymised spatial adjacency information ... However, due to spatio-temporal dependencies pertaining to demand and supply-demand gap in a ridehailing system, making accurate forecasts for both demand and supply-demand gap is a difficult task. ... The authors are thankful to Didi Chuxing for the publicly released datasets. FUNDING INFORMATION Miyan Research Institute, International University of Business Agriculture and Technology. ...

doi:10.1049/itr2.12073 fatcat:wzo2ifmhlvcbfmy77ncjmqdp6u

DOAJ

The resulting data, which equates to 17 million observations, is used to train separate models for the trip and stop level prediction. ... In this paper, we propose the use and fusion of data from multiple sources, cleaned, processed, and merged together, for use in training machine learning models to predict transit ridership. ... The problem then is, given a fleet of heterogeneous vehicles 2 , each equipped with automated passenger count systems, how are we able to model and accurately predict the maximum occupancy at any trip ...

arXiv:2210.04989v1 fatcat:zcsyo7hsffdeho4mtaqmlkzst4

We introduce a wide, deep, and multitask-learning (WD-MTL) framework that uses a transformer to extract spatial, temporal, and semantic correlation for predicting crime, accident, and traffic flow of particular ... However, most route recommendation systems only recommend trips based on time and distance, impacting quality-of-experience and route selection. ... The challenges in developing the system include heterogeneous data sources, sparsity, complex spatio-temporal relation, and multiobjective optimization. ...

doi:10.1145/3523227.3546787 fatcat:wcjnmatusjaolcmfeyz3nvzyam

This paper proposes UberNet, a deep learning convolutional neural network for short-time prediction of demand for ride-hailing services. ... UberNet employs a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services. ... The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. ...

doi:10.1007/s42421-021-00041-4 fatcat:s3kjmtekmfbaldbkqpidcu7s3i

Open Access Multiple Versions

In the case study, the Similarity-based Principle Spatio-temporal Graph Convolutional Neural Network (SP-STGCNN) model predicts demand for bicycle sharing in San Francisco. ... Specifically, the SP is applied to a Spatio-temporal Graph Convolutional Neural Network (STGCNN) model. ... Principle Spatio-temporal Graph Convolutional Neural Network (SP-STGCNN) model predicts the demand for bicycle sharing. ...

doi:10.5198/jtlu.2024.2348 fatcat:zlqkjo7sk5dfpjp5qu36ddqrt4

DOAJ OJS

In this paper, we present a comprehensive review of the development and recent advances in deep learning for trajectory computing (DL4Traj). ... Traditional methods, focusing on simplistic spatio-temporal features, face challenges of complex calculations, limited scalability, and inadequate adaptability to real-world complexities. ... Advancements in deep learning inspire several neural networks for trip recommendations. ...

arXiv:2403.14151v1 fatcat:ubqmy4zer5dr3kudyps76yxige

To alleviate costs associated with traffic congestion, some nations of the world have implemented Intelligent Transportation Systems (ITS). ... The collected information is then reviewed to discover possible key areas of concern in the TFP and ITS. Findings/Results: Traffic management in cities is important for smooth traffic flow. ... A clustering stage is used to look for commonalities or patterns in the TF data that each road sensor collects. This allows for the creation of prediction models for each of these patterns. ...

doi:10.5281/zenodo.6479157 fatcat:mei5u4hf5bft5mpgaawjfv77ru

Open Access

To solve these problems, we propose a new traffic state-forecasting model, namely, spatio-temporal attention-gated recurrent neural network (ST-AGRNN). ... Due to the existence of complex spatio-temporal relationships, there are some challenges in forecasting. ... [44] consider important daily patterns and present-day patterns from traffic data in addition to spatio-temporal characteristics to improve the accuracy of predictions. ...

doi:10.1155/2022/2806183 fatcat:aj5z5kg7q5gkvh3oc436cu6po4

DOAJ

INDEX TERMS Traffic congestion, spatio-temporal correlation, local Moran's I, short-term prediction. This work is licensed under a Creative Commons Attribution 4.0 License. ... In this paper, firstly, we analyze and study the spatio-temporal correlation characteristics of traffic states based on the existing floating car data. ... model training, and the regression tree uses the spatio-temporal congestion index as the feature for model training. ...

doi:10.1109/access.2019.2959125 fatcat:jxjganhycvcgnjxmdrtqljk3mq

DOAJ

Finally, we draw the overall conclusion of the survey, which is important for the development of robust next location prediction systems. ... Research efforts are spent on the put forward overall picture of next location prediction, and number of works has been done so as to realize robust next location prediction systems. ... Shasha T. et al. propose Spatio-temporal Position Prediction Model (SPPM) for Mobile Users Based on model in the mobile edge computing [95] . ...

doi:10.1186/s13638-022-02114-6 fatcat:s2ixs3ftibaobighbik6ikgfce

DOAJ

In this work, the problem of modeling and predicting transport demand in large cities with high spatio-temporal resolution is tackled. ... , and wind speed), and temporal information (e.g., weekday, time, and holiday) to predict mobility demand in every region of the mesh, for several forecast horizons. ... In this way, a global mobility model is trained for the whole city with fine spatio-temporal resolution. ...

doi:10.5281/zenodo.7371822 fatcat:j2tc4wemzvgsdik32ufgb6efeq

Open Access

Our goal is to investigate whether we can use similarities in the terrain and infrastructure to train a machine learning model that can predict speed in regions where we lack transportation data. ... A persistent challenge in the field of Intelligent Transportation Systems is to extract accurate traffic insights from geographic regions with scarce or no data coverage. ... After mapping all of the trips for an Individual Link Spatio-Temporal (ILSTM) for each OTR link. ...

arXiv:2402.07507v1 fatcat:qxwcy6aywzgsjeegioj76agwem

The results show that H-STGCN remarkably outperforms state-of-the-art methods in various metrics, especially for the prediction of non-recurring congestion. ... To address this issue, we propose the Hybrid Spatio-Temporal Graph Convolutional Network (H-STGCN), which is able to "deduce" future travel time by exploiting the data of upcoming traffic volume. ... INTRODUCTION Spatio-temporal forecasting has important applications such as weather prediction, transportation planning, etc. Traffic prediction is one classic example. ...

arXiv:2006.12715v1 fatcat:5klr4lxmo5h4hmeogvy7b3oniq

A deep learning model is applied for predicting block-level parking occupancy in real time. ... The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations. ... Acknowledgements This research is funded in part by National Science Foundation Award CNS-1544826 and Carnegie Mellon University's Mobility21, a National University Transportation Center for Mobility sponsored ...

arXiv:1901.06758v5 fatcat:qdcm3rx6gjar7ojpasqfwwazla

Multiple Versions

Using Spatio-temporal Deep Learning for Forecasting Demand and Supply-demand Gap in Ride-hailing System with Anonymized Spatial Adjacency Information [article]

Preserved Fulltext

Other Versions

Using spatio‐temporal deep learning for forecasting demand and supply‐demand gap in ride‐hailing system with anonymised spatial adjacency information

Preserved Fulltext

On Designing Day Ahead and Same Day Ridership Level Prediction Models for City-Scale Transit Networks Using Noisy APC Data [article]

Preserved Fulltext

MARRS: A Framework for multi-objective risk-aware route recommendation using Multitask-Transformer

Preserved Fulltext

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

Preserved Fulltext

Other Versions

Spatial-temporal deep learning model based on Similarity Principle for dock shared bicycles ridership prediction

Preserved Fulltext

Deep Learning for Trajectory Data Management and Mining: A Survey and Beyond [article]

Preserved Fulltext

Traffic Flow Prediction using Machine Learning Techniques - A Systematic Literature Review

Preserved Fulltext

ST-AGRNN: A Spatio-Temporal Attention-Gated Recurrent Neural Network for Traffic State Forecasting

Preserved Fulltext

Discrimination and Prediction of Traffic Congestion States of Urban Road Network Based on Spatio-temporal Correlation

Preserved Fulltext

A survey on next location prediction techniques, applications, and challenges

Preserved Fulltext

Combining heterogeneous data sources for spatio-temporal mobility demand forecasting

Preserved Fulltext

Clustering Dynamics for Improved Speed Prediction Deriving from Topographical GPS Registrations [article]

Preserved Fulltext

Hybrid Spatio-Temporal Graph Convolutional Network: Improving Traffic Prediction with Navigation Data [article]

Preserved Fulltext

A deep learning approach to real-time parking occupancy prediction in spatio-temporal networks incorporating multiple spatio-temporal data sources [article]

Preserved Fulltext

Other Versions