Filters








2,332 Hits in 6.4 sec

A Survey on Trajectory Data Management, Analytics, and Learning [article]

Sheng Wang, Zhifeng Bao, J. Shane Culpepper, Gao Cong
2020 arXiv   pre-print
Deep trajectory learning is also reviewed for the first time. Finally, we outline the essential qualities that a trajectory data management system should possess in order to maximize flexibility.  ...  The trajectory similarity based on the learned representations is robust to non-uniform, low sampling rates, and noisy sample points. Yao et al.  ...  When compared with d kBCT , d CPD is more robust when erroneous points exist in a trajectory.  ... 
arXiv:2003.11547v2 fatcat:5gf5h5skqjbrhf67cflygggnky

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.  ...  Recently, with the advances of deep learning techniques, deep leaning models such as convolutional neural network (CNN) and recurrent neural network (RNN) have enjoyed considerable success in various machine  ...  [146] proposed a new topological framework called Linkage Network to model the road networks and presented the propagation patterns of traffic flow.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

Simulation and Learning for Urban Mobility: City-scale Traffic Reconstruction and Autonomous Driving [article]

Weizi Li
2019 arXiv   pre-print
I propose various techniques combining simulation and machine learning to tackle the problem of traffic from two perspectives: city-scale traffic reconstruction and autonomous driving.  ...  Traffic congestion has become one of the most critical issues worldwide.  ...  Figure 1 1 Figure 1.8: My technique shows robustness when the number of samples used in recovering a traffic signal decreases.  ... 
arXiv:1908.06131v1 fatcat:w2cjlgfhnfhf7o3fyptqjzdrum

A Survey on Theories and Applications for Self-Driving Cars Based on Deep Learning Methods

Jianjun Ni, Yinan Chen, Yan Chen, Jinxiu Zhu, Deena Ali, Weidong Cao
2020 Applied Sciences  
Finally, the future challenges in the applications of deep learning for self-driving cars are given out.  ...  This paper presents a review of recent research on theories and applications of deep learning for self-driving cars.  ...  The semantic segmentation network is employed to detect traffic lights and the fully convolutional network is used for traffic light classification.  ... 
doi:10.3390/app10082749 fatcat:iohm7uqj2vbojmnao6kyhzeliu

Toward Intelligent Vehicular Networks: A Machine Learning Framework

Le Liang, Hao Ye, Geoffrey Ye Li
2019 IEEE Internet of Things Journal  
After a brief introduction of the major concepts of machine learning, we discuss its applications to learn the dynamics of vehicular networks and make informed decisions to optimize network performance  ...  Machine learning, as an effective approach to artificial intelligence, can provide a rich set of tools to exploit such data for the benefit of the networks.  ...  The latent factors that affect the trajectories, such as drivers' intention, traffic patterns, and road structures, may also be implicitly learned from the historical data using deep neural networks.  ... 
doi:10.1109/jiot.2018.2872122 fatcat:n25uma5isfduvk3hh5mvnai4fy

Spatial-Temporal Conv-sequence Learning with Accident Encoding for Traffic Flow Prediction [article]

Zichuan Liu, Rui Zhang, Chen Wang, Hongbo Jiang
2021 arXiv   pre-print
Current state-of-the-art methods for traffic flow forecasting are based on graph architectures and sequence learning models, but they do not fully exploit spatial-temporal dynamic information in the traffic  ...  Specifically, the temporal dependence of the short-range is diluted by recurrent neural networks, and the existing sequence model ignores local spatial information because the convolution operation uses  ...  Moreover, FT-block should also be able to learn a more robust representation of traffic flow, which is the ability to extract correct ST information regardless of traffic flow.  ... 
arXiv:2105.10478v2 fatcat:wjcl5zecknhnlh7lpkcsdqxlpq

Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles

Szilard Aradi
2020 IEEE transactions on intelligent transportation systems (Print)  
Strategic decisions on different layers and the observation models, e.g., continuous and discrete state representations, grid-based, and camera-based solutions are presented.  ...  A wide range of techniques in Machine Learning itself have been developed, and this article describes one of these fields, Deep Reinforcement Learning (DRL).  ...  It can convert networks from other traffic simulators such as VISUM, Vissim, or MATSim and also reads other standard digital road network formats, such as OpenStreetMap or OpenDRIVE.  ... 
doi:10.1109/tits.2020.3024655 fatcat:wk4c2ked3jho3jtqdn4o5ys4zu

Spatiotemporal Data Fusion in Graph Convolutional Networks for Traffic Prediction

Baoxin Zhao, Xitong Gao, Jianqi Liu, Juanjuan Zhao, Chengzhong Xu
2020 IEEE Access  
INDEX TERMS Data fusion, graph convolutional networks, multi-source data, traffic prediction. 76632 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  data as the input to the graph convolutional network(GCN), we designed a fine-grained feature transformer to match the ones generated by GCN.  ...  As we all know, urban traffic has different patterns and people travel patterns also differs from each other at different time.  ... 
doi:10.1109/access.2020.2989443 fatcat:rihfw7o4jbacpm2bcnl6ochjpq

Contrastive Learning with Adversarial Perturbations for Conditional Text Generation [article]

Seanie Lee, Dong Bok Lee, Sung Ju Hwang
2021 arXiv   pre-print
To tackle this problem, we propose a principled method to generate positive and negative samples for contrastive learning of seq2seq models.  ...  However, training the model with naive contrastive learning framework using random non-target sequences as negative examples is suboptimal, since they are easily distinguishable from the correct output  ...  framework rather than trying to learn the model to be robust to them.  ... 
arXiv:2012.07280v6 fatcat:yaf3e76onjetjhfcc5pl6g2h4m

L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving

Weixin Lu, Yao Zhou, Guowei Wan, Shenhua Hou, Shiyu Song
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Multiple trials of repetitive data collection over the same road and areas make our dataset ideal for testing localization systems.  ...  Rather than relying on these handcrafted modules, we innovatively implement the use of various deep neural network structures to establish a learningbased approach.  ...  trials traveling at different times on the same roads, that is well suitable for the localization task.  ... 
doi:10.1109/cvpr.2019.00655 dblp:conf/cvpr/LuZWHS19 fatcat:tojehf5ysbhltfz4k32mnleuhu

Hierarchical and Networked Vehicle Surveillance in ITS: A Survey

Bin Tian, Brendan Tran Morris, Ming Tang, Yuqiang Liu, Yanjie Yao, Chao Gou, Dayong Shen, Shaohu Tang
2017 IEEE transactions on intelligent transportation systems (Print)  
Moreover, existing related research is mainly on a single video sensor node, which is incapable of addressing the surveillance of traffic road networks.  ...  Traffic surveillance has become an important topic in intelligent transportation systems (ITSs), which is aimed at monitoring and managing traffic flow.  ...  [214] used the Bayesian inference with a grid representation of the road network.  ... 
doi:10.1109/tits.2016.2552778 fatcat:hkc7ug3rgballl4gtfp2a2nu2i

Hierarchical and Networked Vehicle Surveillance in ITS: A Survey

Bin Tian, Brendan Tran Morris, Ming Tang, Yuqiang Liu, Yanjie Yao, Chao Gou, Dayong Shen, Shaohu Tang
2014 IEEE transactions on intelligent transportation systems (Print)  
Moreover, existing related research is mainly on a single video sensor node, which is incapable of addressing the surveillance of traffic road networks.  ...  Traffic surveillance has become an important topic in intelligent transportation systems (ITSs), which is aimed at monitoring and managing traffic flow.  ...  [214] used the Bayesian inference with a grid representation of the road network.  ... 
doi:10.1109/tits.2014.2340701 fatcat:ibm5rputr5gv5o2kazayjr6wkq

Machine learning and data analytics for the IoT [article]

Erwin Adi, Adnan Anwar, Zubair Baig, Sherali Zeadally
2020 arXiv   pre-print
These barriers prevent current intelligent IoT applications to adaptively learn from other IoT applications.  ...  In this paper, we critically review how IoT-generated data are processed for machine learning analysis and highlight the current challenges in furthering intelligent solutions in the IoT environment.  ...  A periodic pattern mining based algorithm is deployed for determining the passenger and road flows.  ... 
arXiv:2007.04093v1 fatcat:no4spywa75esjel7dol3pi4etm

A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance

B.T. Morris, M.M. Trivedi
2008 IEEE transactions on circuits and systems for video technology (Print)  
The scene topology is automatically learned and is distinguished by points of interest and motion characterized by activity paths.  ...  Here suspicious meetings or luggage drops may be monitored as well as characterization of the conflicts for safety on shared roads.  ...  These range from low-level vision problems such as robust object detection to high-level semantic interpretation as well as developing a concrete definition of what truly is an abnormality. A.  ... 
doi:10.1109/tcsvt.2008.927109 fatcat:uyv2bx4h2fghtmh4qwpwhu5ohq

A Deep Learning Based Multi-Block Hybrid Model for Bike-Sharing Supply-Demand Prediction

Miao Xu, Hongfei Liu, Hongbo Yang
2020 IEEE Access  
INDEX TERMS Bike-sharing, data visualization, deep learning, supply-demand prediction, spatial-temporal analysis. 85826 This work is licensed under a Creative Commons Attribution 4.0 License.  ...  As a new type of short distance commuting, the station-free sharing bike effectively alleviates urban traffic congestion. Thus, they are deployed in a large scale in many cities.  ...  The geographic data in this study include administrative division, road network, and land use information.  ... 
doi:10.1109/access.2020.2987934 fatcat:svbk3pq36jgu7oz7wh6mdcjhly
« Previous Showing results 1 — 15 out of 2,332 results