Filters








17,495 Hits in 5.7 sec

Few-Shot Traffic Prediction with Graph Networks using Locale as Relational Inductive Biases [article]

Mingxi Li, Yihong Tang, Wei Ma
2022 arXiv   pre-print
It is also demonstrated that the learned knowledge from LocaleGn can be transferred across cities.  ...  The research outcomes can help to develop light-weighted traffic prediction systems, especially for cities lacking in historically archived traffic data.  ...  In traffic prediction tasks, region-based transfer learning across cities is applied by matching similar sub-regions among different cities [46] .  ... 
arXiv:2203.03965v1 fatcat:vrr73yqsondvxmpkrh6c7q6lbu

Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities [article]

Yihong Tang, Ao Qu, Andy H.F. Chow, William H.K. Lam, S.C. Wong, Wei Ma
2022 arXiv   pre-print
Instead, we envision that the improvement can be achieved by transferring the "forecasting-related knowledge" across cities with different data distributions and network topologies.  ...  Accurate real-time traffic forecast is critical for intelligent transportation systems (ITS) and it serves as the cornerstone of various smart mobility applications.  ...  The authors thank the Transport Department of the Government of the Hong Kong Special Administrative Region for providing the relevant traffic data and suggestions for the experimental deployment in Hong  ... 
arXiv:2202.03630v1 fatcat:wao6svsnyzfnlijzraphy62rie

Deep Neural Mobile Networking [article]

Chaoyun Zhang
2020 arXiv   pre-print
In particular, deep learning based solutions can automatically extract features from raw data, without human expertise.  ...  This makes monitoring and managing the multitude of network elements intractable with existing tools and impractical for traditional machine learning algorithms that rely on hand-crafted feature engineering  ...  For each prediction instance, most approaches forecast traffic consumption at all locations across the city for over 60 time steps Figure 3 . 7 : 37 Snapshots of network-wide predictions made after 10  ... 
arXiv:2011.05267v1 fatcat:yz2zp5hplzfy7h5kptmho7mbhe

Spider: Deep Learning-driven Sparse Mobile Traffic Measurement Collection and Reconstruction

Yini Fang, Alec F. Diallo, Chaoyun Zhang, Paul Patras
2021 2021 IEEE Global Communications Conference (GLOBECOM)  
Data-driven mobile network management hinges on accurate traffic measurements, which routinely require expensive specialized equipment and substantial local storage capabilities, and bear high data transfer  ...  To overcome these challenges, in this paper we propose Spider, a deep-learningdriven mobile traffic measurement collection and reconstruction framework, which reduces the cost of data collection while  ...  In this paper, we propose Spider, a deep learning-driven mobile traffic measurement collection and reconstruction framework for infrastructure-level data.  ... 
doi:10.1109/globecom46510.2021.9685804 fatcat:fqkghupeejc6rktdybw43l3h44

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks [article]

Chaoyun Zhang, Paul Patras
2017 arXiv   pre-print
To overcome these challenges, in this paper we harness the exceptional feature extraction abilities of deep learning and propose a Spatio-Temporal neural Network (STN) architecture purposely designed for  ...  of mobile traffic due to user mobility.  ...  For each prediction instance, most approaches forecast traffic consumption at all locations across the city for over 60 time steps for all instances.  ... 
arXiv:1712.08083v1 fatcat:mueo5gutxzgclczzcmodurspj4

Long-Term Mobile Traffic Forecasting Using Deep Spatio-Temporal Neural Networks

Chaoyun Zhang, Paul Patras
2018 Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing - Mobihoc '18  
To overcome these challenges, in this paper we harness the exceptional feature extraction abilities of deep learning and propose a Spatio-Temporal neural Network (STN) architecture purposely designed for  ...  of mobile traffic due to user mobility.  ...  For each prediction instance, most approaches forecast traffic consumption at all locations across the city for over 60 time steps for all instances.  ... 
doi:10.1145/3209582.3209606 dblp:conf/mobihoc/ZhangP18 fatcat:e77ogifuenffjiwsampkwwcnzu

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.  ...  We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems.  ...  employing deep learning to urban traffic prediction with mobility data.  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde

Deep Learning in Mobile and Wireless Networking: A Survey

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 IEEE Communications Surveys and Tutorials  
Drawing from our experience, we discuss how to tailor deep learning to mobile environments. We complete this survey by pinpointing current challenges and open future directions for research.  ...  We then discuss several techniques and platforms that facilitate the efficient deployment of deep learning onto mobile systems.  ...  employing deep learning to urban traffic prediction with mobility data.  ... 
doi:10.1109/comst.2019.2904897 fatcat:xmmrndjbsfdetpa5ef5e3v4xda

Transfer learning for cross-modal demand prediction of bike-share and public transit [article]

Mingzhuang Hua, Francisco Camara Pereira, Yu Jiang, Xuewu Chen
2022 arXiv   pre-print
To this end, this study explores various machine learning models and transfer learning strategies for cross-modal demand prediction.  ...  These results verify our combined method's forecasting improvement over existing benchmarks and demonstrate the good transferability for cross-modal demand prediction in multiple cities.  ...  [10] combined transfer learning and deep learning to predict road traffic flow and found that the fine-tuning strategy is suitable in their study.  ... 
arXiv:2203.09279v1 fatcat:yqtp7hiknrcxlcyqcrjjtjtco4

TransMUSE: Transferable Traffic Prediction in MUlti-Service EdgeNetworks [article]

Luyang Xu, Haoyu Liu, Junping Song, Rui Li, Yahui Hu, Xu Zhou, Paul Patras
2022 arXiv   pre-print
In this context, network traffic prediction is crucial for operators to provide reliable connectivity across large geographic regions.  ...  Therefore, in this paper we propose TransMUSE, a novel deep learning framework that clusters similar services, groups edge-nodes into cohorts by traffic feature similarity, and employs a Transformer-based  ...  of a graph attention spatio-temporal network (GASTN) for city-wide mobile traffic prediction [6] .  ... 
arXiv:2203.02083v1 fatcat:qkjwuid2z5dlzexgozeowtnmtq

Editorial Special Issue on AI Innovations in Intelligent Transportation Systems

Tai-Hoon Kim
2022 IEEE transactions on intelligent transportation systems (Print)  
propose a traffic-light scheduling framework utilizing the deep reinforcement learning technique to balance the traffic flow and prevent congestion in dense regions of the city via a software-defined control  ...  For intelligent traffic light control signals, a deep reinforcement learning model is proposed to switch traffic light control signals in different phases, i.e., red, green, and yellow.  ... 
doi:10.1109/tits.2022.3152067 fatcat:w5qyxfyp7zfzjckdkhsmddvzwm

AI and Deep Learning for Urban Computing [chapter]

Senzhang Wang, Jiannong Cao
2021 The Urban Book Series  
, deep learning, and reinforcement learning.  ...  Thus, we briefly introduce the deep-learning models that are widely used in various urban-computing tasks.  ...  prediction AI and Deep Learning for Urban Computing AI and Deep Learning for Urban Computing  ... 
doi:10.1007/978-981-15-8983-6_43 fatcat:uq7j3hvsvzfl5lq33omx64un3i

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.  ...  Then a framework is introduced to show a general pipeline of the utilization of deep learning models for STDM.  ...  [142] proposed a novel cross-city transfer learning method for deep spatio-temporal prediction, called RegionTrans.  ... 
arXiv:1906.04928v2 fatcat:4zrdtgkvirfuniq3rb2gl7ohpy

Short-Term Forecast of Bicycle Usage in Bike Sharing Systems: A Spatial-Temporal Memory Network

Xinyu Li, Yang Xu, Qi Chen, Lei Wang, Xiaohu Zhang, Wenzhong Shi
2021 IEEE transactions on intelligent transportation systems (Print)  
Although many deep learning algorithms have been developed in recent years to support travel demand forecast, they have mainly been used to predict traffic volume or speed on roadways.  ...  Bike-sharing systems have made notable contributions to cities by providing green and sustainable mobility service to users.  ...  Several existing deep learning methods originally used for other tasks are transferred to predict traffic flow/demand through the reconstruction of traffic data structures, such as CNN, RNN, and Stacked  ... 
doi:10.1109/tits.2021.3097240 fatcat:4tdism2d7ne4ra25sama75mb4y

Predicting Short-term Mobile Internet Traffic from Internet Activity using Recurrent Neural Networks [article]

Guto Leoni Santos, Pierangelo Rosati, Theo Lynn, Judith Kelner, Djamel Sadok, Patricia Takako Endo
2020 arXiv   pre-print
We compare the performance of two deep learning architectures - Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) - for predicting mobile Internet traffic using two months of Telecom Italia  ...  Both Deep Learning algorithms were effective in modeling Internet activity and seasonality, both within days and across two months. We find variations in performance across clusters within the city.  ...  mobile Internet traffic across a city comprising multiple cells.  ... 
arXiv:2010.05741v1 fatcat:ynl4ujltjbdxrhawc62v4erx6m
« Previous Showing results 1 — 15 out of 17,495 results