2,832 Hits in 10.2 sec

Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph [article]

Yuandong Wang and Hongzhi Yin and Tong Chen and Chunyang Liu and Ben Wang and Tianyu Wo and Jie Xu
2021 arXiv   pre-print
representations for passenger demand prediction.  ...  However, existing graph-based solutions fail to simultaneously consider those three crucial aspects of dynamic, directed, and weighted (DDW) graphs, leading to limited expressiveness when learning graph  ...  ., the constructed graphs are dynamic, directed, and weighted.  ... 
arXiv:2101.00752v1 fatcat:ja4jm3mbrzcu5ho7dwlysmcbvy

Deep learning for intelligent traffic sensing and prediction: recent advances and future challenges

Xiaochen Fan, Chaocan Xiang, Liangyi Gong, Xin He, Yuben Qu, Saeed Amirgholipour, Yue Xi, Priyadarsi Nanda, Xiangjian He
2020 CCF Transactions on Pervasive Computing and Interaction  
In this paper, we present an up-to-date literature review on the most advanced research works in deep learning for intelligent traffic sensing and prediction.  ...  Deep learning, with its powerful capabilities in representation learning and multi-level abstractions, has recently become the most effective approach in many intelligent sensing systems.  ...  In the following, we briefly highlight four research directions. (1) Passenger demand prediction.  ... 
doi:10.1007/s42486-020-00039-x fatcat:c3c2b3fvpzdqdlxy2ke7ckxlpu

Table of Contents

2022 IEEE Transactions on Cybernetics  
Tan 252 Hallucinating Color Face Image by Learning Graph Representation in Quaternion Space . . . . . . . L. Liu, C. L. P. Chen, and S.  ...  Liu 654 Hierarchical Granular Computing-Based Model and Its Reinforcement Structural Learning for Construction of Long-Term Prediction Intervals . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tcyb.2021.3138650 fatcat:zwcf4txyx5dafbdtm6rayoeoae

A Continuous Taxi Pickup Path Recommendation under The Carbon Neutrality Context

Mengmeng Chang, Yuanying Chi, Zhiming Ding, Jing Tian, Yuhao Zheng
2021 ISPRS International Journal of Geo-Information  
For individual taxis, they lack macroscopic horizon in their choice of passenger pickup paths.  ...  First, an adaptive learning spatiotemporal neural network was used to predict the coarse-grained distribution of potential trips.  ...  Origin-destination matrix prediction via graph convolution: A new perspective of passenger demand modeling.  ... 
doi:10.3390/ijgi10120821 fatcat:h2f3yabouveuzdckbfxu6u3nwy

Hercules Routes: Presentation of business requirements, business processes and statistics

Arnold Horvath
2021 Zenodo  
Transported workers can see up-to-date information on their journeys via a mobile app, and drivers can receive information on the route and the people they are transporting via a driver's mobile or tablet  ...  for companies transporting their employees and for companies contracted to transport their employees.  ...  Transported workers can see up-to-date information on their journeys via a mobile app, and drivers can receive information on the route and the people they are transporting via a driver's mobile or tablet  ... 
doi:10.5281/zenodo.5804606 fatcat:tuhseacmyjemdhpsqafoijplee

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models

Benedek Rozemberczki, Paul Scherer, Yixuan He, George Panagopoulos, Alexander Riedel, Maria Astefanoaei, Oliver Kiss, Ferenc Beres, Guzmán López, Nicolas Collignon, Rik Sarkar
2021 Proceedings of the 30th ACM International Conference on Information & Knowledge Management  
The main goal of the library is to make temporal geometric deep learning available for researchers and machine learning practitioners in a unified easyto-use framework.  ...  We present PyTorch Geometric Temporal a deep learning framework combining state-of-the-art machine learning algorithms for neural spatiotemporal signal processing.  ...  These types of models serve as templates for the temporal block of spatiotemporal deep learning models. Static Graph Representation Learning.  ... 
doi:10.1145/3459637.3482014 fatcat:gzljodd7c5cqjg2cdnbfawq7hq

Deep Learning for Spatio-Temporal Data Mining: A Survey [article]

Senzhang Wang, Jiannong Cao, Philip S. Yu
2019 arXiv   pre-print
predictive learning, representation learning, anomaly detection and classification.  ...  Finally, we conclude the limitations of current research and point out future research directions.  ...  A collective embedding learning framework was presented to learn urban community structures by unifying both static POIs data and dynamic human mobility graph spatial map data.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

IoT Based Bus Arrival Time Prediction Using Artificial Neural Network (ANN) for Smart Public Transport System (SPTS)

Jalaney Jabamony, Noorul Islam Centre for Higher Education, Ganesh Shanmugavel, Noorul Islam Centre for Higher Education
2020 International Journal of Intelligent Engineering and Systems  
Here, Artificial Neural Network (ANN) is used as a prediction algorithm and ANN is trained with different traffic parameters and environmental conditions.  ...  These parameters and the measured real-time arrival time of the bus in different stops for 10 days is used for training the ANN. This trained ANN is implemented on the server-side.  ...  During this learning phase, the network trains by adjusting the weights to predict the correct class label of input samples.  ... 
doi:10.22266/ijies2020.0229.29 fatcat:gorvsilmwbc4zkj5z5lhvpdife

Integrating Geovisual Analytics with Machine Learning for Human Mobility Pattern Discovery

Tong Zhang, Jianlong Wang, Chenrong Cui, Yicong Li, Wei He, Yonghua Lu, Qinghua Qiao
2019 ISPRS International Journal of Geo-Information  
We use two machine learning methods, including a clustering algorithm to extract transit corridors to represent primary mobility connections between different regions and a graph-embedding algorithm to  ...  To address these challenges, this study leverages advanced machine learning methods to identify time-varying mobility patterns based on smart card data and other urban data.  ...  We define a directed weighted graph G t (V, E) for a time interval t. V is the set of grid groups, and E represents transit connection edges between nodes in V.  ... 
doi:10.3390/ijgi8100434 fatcat:5vruozxmtngdpktzvnjvfmohgq

Graph Neural Networks in IoT: A Survey [article]

Guimin Dong, Mingyue Tang, Zhiyuan Wang, Jiechao Gao, Sikun Guo, Lihua Cai, Robert Gutierrez, Bradford Campbell, Laura E. Barnes, Mehdi Boukhechba
2022 arXiv   pre-print
Continuous sensing generates massive amounts of data and presents challenges for machine learning.  ...  source code from the collected publications, and future research directions.  ...  Graph autoencoders: graph auto-encoder and its variants have been primarily used for representation learning on graph-structured data.  ... 
arXiv:2203.15935v2 fatcat:jkqg5ukg5fezbewu5mr5hqsp4e

Online Metro Origin-Destination Prediction via Heterogeneous Information Aggregation [article]

Lingbo Liu, Yuying Zhu, Guanbin Li, Ziyi Wu, Lei Bai, Liang Lin
2022 arXiv   pre-print
DO matrices) to jointly learn the evolutionary patterns of OD and DO ridership.  ...  Extensive experiments conducted on two large-scale benchmarks demonstrate the effectiveness of our method for online metro origin-destination prediction.  ...  Graph convolution and gated recurrent units are then integrated for representation learning.  ... 
arXiv:2107.00946v5 fatcat:glgtdvkjjfh2pofjumzi7wxpo4

Understanding and predicting the spatio‐temporal spread of COVID‐19 via integrating diffusive graph embedding and compartmental models

Tong Zhang, Jing Li
2021 Transactions on GIS  
We propose a hybrid data-driven learning approach to capture the mobility-related spreading mechanism of infectious diseases, utilizing multi-sourced mobility and attributed data.  ...  In addition, integrated embeddings also support daily prediction of infected cases and role analysis of each area unit during the transmission of the virus.  ...  By accounting for transmission dynamics and local attributes via representation learning, our approach outperforms the classical compartment model in prediction performance. 2.  ... 
doi:10.1111/tgis.12803 pmid:34512104 pmcid:PMC8420127 fatcat:qqlhkg4ja5egnbknuqkqay3qqm

Mining Urban Congestion Evolution Characteristics Based on Taxi GPS Trajectories

Weiyan Xu, Yumei Huang
2020 American Journal of Traffic and Transportation Engineering  
Second, the average speed of the road segments is obtained according to the taxi GPS trajectories and a dynamic weighted graph of urban road network is constructed to capture complicated urban traffic  ...  The taxi GPS trajectories involve sufficient temporal and spatial characteristics and make it easy for us to obtain potential knowledge for understanding human mobility pattern and urban traffic network  ...  Huifang Feng for providing the GPS data used in this work. This work is partially supported by the National Natural Science Foundation of China under Grant (11571156, 71761031).  ... 
doi:10.11648/j.ajtte.20200501.11 fatcat:fvgemjqy2zgd5d6xnhu6367iju

Scanning the Issue

Azim Eskandarian
2020 IEEE transactions on intelligent transportation systems (Print)  
The datasets repository is available at: Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends M. Veres and M.  ...  To evaluate the ACF model, they performed the simulation for car-following pairs and conducted a comparison analysis with the existing models: Newell, Gipps, GM, and IDM.  ...  The mobile devices carried by bus passengers can be exploited to estimate passenger waiting time at a bus stop without the passenger's direct participation.  ... 
doi:10.1109/tits.2020.3008809 fatcat:etol5qoilvdnbj6gtjxk3gheaa

Text/Conference Paper

Lukas Galke, Tetyana Melnychuk, Eva Seidlmayer, Steffen Trog, Konrad U. Förstner, Carsten Schultz, Klaus Tochtermann
2019 Jahrestagung der Gesellschaft für Informatik  
We pursue a new direction for the analysis of research dynamics with graph neural networks.  ...  We propose to use an unsupervised training objective for concept representation learning that is tailored towards bibliographic data with millions of research papers and thousands of concepts from a controlled  ...  In the graph domain, link prediction is a common choice for learning node representations. The representation is trained for predicting whether a link between two nodes exists.  ... 
doi:10.18420/inf2019_26 dblp:conf/gi/GalkeMSTFST19 fatcat:zzjikey6obc4hkh7fpc2hzp2hy
« Previous Showing results 1 — 15 out of 2,832 results