Filters








1,045 Hits in 7.6 sec

Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning

Chenxing Wang, Fang Zhao, Haichao Zhang, Haiyong Luo, Yanjun Qin, Yuchen Fang
2022
It is significant to achieve the fine-grained Trajectory-based Travel Time Estimation (TTTE) for multi-city scenarios, namely to accurately estimate travel time of the given trajectory for multiple city  ...  To tackle these challenges, we propose a meta learning based framework, MetaTTE, to continuously provide accurate travel time estimation over time by leveraging well-designed deep neural network model  ...  In this paper, we focus on the fine-grained end-to-end Trajectory-based Travel Time Estimation (TTTE) for multicity scenarios.  ... 
doi:10.48550/arxiv.2201.08017 fatcat:zgamqtjwpva2bhh35k7vhbz4iy

Estimation of Travel Time Based on Ensemble Method with Multi-Modality Perspective Urban Big Data

Zhiqiang Zou, Haoyu Yang, A-Xing Zhu
2020 IEEE Access  
This paper puts forward to one optimized method to estimate travel time, which is based on ensemble method with multi-modality urban big data, namely Travel Time Estimation-Ensemble (TTE-Ensemble).  ...  Predicting the travel time between the two specified points accurately is great significance for applications, such as travel plan.  ...  In order to estimate travel time better on a wider city scale, truck travel data and taxi travel data are fused to perform TTE by using the mean travel time between grid regions [20] , in which multi-view  ... 
doi:10.1109/access.2020.2971008 fatcat:ie5pm6rdezglxhp7y5b6s47c5a

GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation [article]

Zhiwen Zhang, Hongjun Wang, Jiyuan Chen, Zipei Fan, Xuan Song, Ryosuke Shibasaki
2022 arXiv   pre-print
To address the above challenges, we introduce GOF-TTE for the mobile user group, Generative Online Federated Learning Framework for Travel Time Estimation, which I) utilizes the federated learning approach  ...  Estimating the travel time of a path is an essential topic for intelligent transportation systems.  ...  Deep Learning Based Methods. With the development of deep learning in these years, various studies have been designed to enhance the performance of travel time estimation.  ... 
arXiv:2207.00838v1 fatcat:xwbktwzaxjf3vdpb3injjcv4dm

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.  ...  Wang et al. (2018) proposed DeepTEE, an end-to-end deep learning framework for travel time estimation, for predicting the travel time of the whole path directly.  ... 
doi:10.1007/s42486-020-00039-x fatcat:c3c2b3fvpzdqdlxy2ke7ckxlpu

A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Haitao Yuan, Guoliang Li
2021 Data Science and Engineering  
Third, we focus on three kinds of traffic prediction problems (i.e., classification, generation and estimation/forecasting).  ...  ., intelligent traffic light) makes our travel more convenient and efficient.  ...  In particular, the authors first use MLP to estimate the travel distance based on given origin and destination points and then use MLP to estimate the travel time based on the estimated distance and given  ... 
doi:10.1007/s41019-020-00151-z fatcat:nnnnxnpo3bgk3l4hpr7kk2n4xa

2019 Index IEEE Transactions on Intelligent Transportation Systems Vol. 20

2019 IEEE transactions on intelligent transportation systems (Print)  
., +, TITS Sept. 2019 3283-3293 Missing Value Imputation for Traffic-Related Time Series Data Based on a Multi-View Learning Method.  ...  ., +, TITS Oct. 2019 3613-3622 Missing Value Imputation for Traffic-Related Time Series Data Based on a Multi-View Learning Method.  ... 
doi:10.1109/tits.2020.2966388 fatcat:xkvww7uabzhlzgfz3yiecyb75y

2021 Index IEEE Transactions on Intelligent Transportation Systems Vol. 22

2021 IEEE transactions on intelligent transportation systems (Print)  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TITS Nov. 2021 7169-7183 Fine-Grained Service-Level Passenger Flow Prediction for Bus Transit Systems Based on Multitask Deep Learning.  ...  Zhang, J., +, TITS Nov. 2021 7004-7014 Fine-Grained Service-Level Passenger Flow Prediction for Bus Transit Systems Based on Multitask Deep Learning.  ... 
doi:10.1109/tits.2021.3139738 fatcat:p2mkawtrsbaepj4zk24xhyl2oa

Recent Advances in Vision-Based On-Road Behaviors Understanding: A Critical Survey

Rim Trabelsi, Redouane Khemmar, Benoit Decoux, Jean-Yves Ertaud, Rémi Butteau
2022 Sensors  
Much of the excitement about on-road behavior understanding has been the labor of advancement witnessed in the fields of computer vision, machine, and deep learning.  ...  On-road behavior analysis is a crucial and challenging problem in the autonomous driving vision-based area.  ...  By assuming inputs as coarse-grained videos, the main contribution here is the proposition of a novel reasoning block composed of two layers; the first one consists of fine-grained 3D convolution and the  ... 
doi:10.3390/s22072654 pmid:35408269 pmcid:PMC9003377 fatcat:2vrmgz3b25eyxbijeurx5aijv4

VLUC: An Empirical Benchmark for Video-Like Urban Computing on Citywide Crowd and Traffic Prediction [article]

Renhe Jiang, Zekun Cai, Zhaonan Wang, Chuang Yang, Zipei Fan, Xuan Song, Kota Tsubouchi, Ryosuke Shibasaki
2019 arXiv   pre-print
Based on this idea, a series of methods have been proposed to address video-like prediction for citywide crowd and traffic.  ...  In particular, by meshing a large urban area to a number of fine-grained mesh-grids, citywide crowd and traffic information in a continuous time period can be represented like a video, where each timestamp  ...  [10] , multitask learning for travel time estimation [20] , or meta learning for tra c prediction [31] .  ... 
arXiv:1911.06982v1 fatcat:bwbd6mprcbhmvp3lo4lrbjbxxq

CARLA: An Open Urban Driving Simulator [article]

Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun
2017 arXiv   pre-print
learning.  ...  The approaches are evaluated in controlled scenarios of increasing difficulty, and their performance is examined via metrics provided by CARLA, illustrating the platform's utility for autonomous driving  ...  We thank artists Mario Gonzalez, Juan Gonzalez, and Ignazio Acerenza for their contributions, and programmer Francisco Molero for his support. Antonio M.  ... 
arXiv:1711.03938v1 fatcat:ol6s3znpvjc2rmbvv7zvxizixi

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
Fashion is the way we present ourselves to the world and has become one of the world's largest industries.  ...  For each task, the benchmark datasets and the evaluation protocols are summarized. Furthermore, we highlight promising directions for future research.  ...  [125] proposed a deep temporal sequence learning framework to predict the fine-grained fashion popularity of an outfit look.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

A Survey on Deep Learning for Human Mobility [article]

Massimiliano Luca, Gianni Barlacchi, Bruno Lepri, Luca Pappalardo
2021 arXiv   pre-print
Our survey is a guide to the leading deep learning solutions to next-location prediction, crowd flow prediction, trajectory generation, and flow generation.  ...  At the same time, it helps deep learning scientists and practitioners understand the fundamental concepts and the open challenges of the study of human mobility.  ...  Deep Learning for Human Mobility: a Survey on Data and Models • 23 , Vol. 1 , No. 1, Article . Publication date: December 2020. Deep Learning for Human Mobility: a Survey on Data and Models • 25  ... 
arXiv:2012.02825v2 fatcat:r7navzojwnaojncfsx3sbnfsze

How Data Mining and Machine Learning Evolved from Relational Data Base to Data Science [chapter]

G. Amato, L. Candela, D. Castelli, A. Esuli, F. Falchi, C. Gennaro, F. Giannotti, A. Monreale, M. Nanni, P. Pagano, L. Pappalardo, D. Pedreschi (+7 others)
2017 Studies in Big Data  
By assuming that positivity and negativity "flow" along the links connecting the definiendum with the words contained in the definiens, random walks on the word graph can be used for performing fine-grained  ...  In [21] , as an example, the authors presented a deep learning based method for searching in a visual feature space, by learning to translate a textual query into a visual representation allowing text  ... 
doi:10.1007/978-3-319-61893-7_17 fatcat:wzk6jc6ounenrexcvmo4aw72ja

Benchmarks for reinforcement learning in mixed-autonomy traffic

Eugene Vinitsky, Aboudy Kreidieh, Luc Le Flem, Nishant Kheterpal, Kathy Jang, Fangyu Wu, Richard Liaw, Eric Liang, Alexandre M. Bayen
2018 Conference on Robot Learning  
To promote similar advances in traffic control via RL, we propose four benchmarks, based on three new traffic scenarios, illustrating distinct reinforcement learning problems with applications to mixed-autonomy  ...  We release new benchmarks in the use of deep reinforcement learning (RL) to create controllers for mixed-autonomy traffic, where connected and autonomous vehicles (CAVs) interact with human drivers and  ...  In Sec. 4 we detail the results of the application of three deep-RL algorithms to learning neural network-based policies and another deep-RL algorithm to learn purely linear policies.  ... 
dblp:conf/corl/VinitskyKFKJWLL18 fatcat:4fgjbfoczzd7dj2dtdwtw6w7ze

Modeling Taxi Drivers' Behaviour for the Next Destination Prediction [article]

Alberto Rossi, Gianni Barlacchi, Monica Bianchini, Bruno Lepri
2019 arXiv   pre-print
The proposed approach was tested on the ECML/PKDD Discovery Challenge 2015 dataset - based on the city of Porto -, obtaining better results with respect to the competition winner, whilst using less information  ...  , and on Manhattan and San Francisco datasets.  ...  Previous approaches for predicting the next taxi destination were mainly focused on fine-grained single trajectories, meaning that they were based on the whole GPS trace of each ride [3] , showing some  ... 
arXiv:1807.08173v2 fatcat:4rpwx777kzhtjcbz3gn3zrqlfq
« Previous Showing results 1 — 15 out of 1,045 results