Filters








3,694 Hits in 11.3 sec

Long Short-Term Memory Networks for Traffic Flow Forecasting: Exploring Input Variables, Time Frames and Multi-Step Approaches

Bruno Fernandes, Fabio Silva, Hector Alaiz-Moreton, Paulo Novais, Jose Neves, Cesar Analide
2020 Informatica  
frames used by the model and the employed approach for multi-step forecasting.  ...  Recent times came, however, with promising results regarding the use of Recurrent Neural Networks (RNNs), such as Long Short-Term Memory networks (LSTMs), to accurately address time series problems.  ...  Long Short-Term Memory networks (LSTMs), a specific type of RNNs, are among those that have been showed to produce valid results on time series data Ma et al., 2015) .  ... 
doi:10.15388/20-infor431 fatcat:ineg5l5pi5gd7cogcoqfqxzqna

Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting

Bing Yu, Haoteng Yin, Zhanxing Zhu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Timely accurate traffic forecast is crucial for urban traffic control and guidance.  ...  Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy the requirements of mid-and-long term prediction tasks and often neglect spatial and temporal dependencies  ...  By combining long short-term memory (LSTM) network [Hochreiter and Schmidhuber, 1997 ] and 1-D CNN, Wu and Tan [2016] presented a feature-level fused architecture CLTFP for shortterm traffic forecast  ... 
doi:10.24963/ijcai.2018/505 dblp:conf/ijcai/YuYZ18 fatcat:du2tmnse6bawxersbwhvi63am4

A Comparison of ARIMAX, VAR and LSTM on Multivariate Short-Term Traffic Volume Forecasting

Bhanuka Dissanayake, Osanda Hemachandra, Nuwan Lakshitha, Dilantha Haputhanthri, Adeesha Wijayasiri
2021 Zenodo  
This paper proposes a comparison of statistical learning models, Vector Auto Regression, ARIMAX and a deep learning model, LSTM neural network, in the context of multivariate short-term (24 hours) time  ...  VAR model produced the best performance with an accuracy of 91.459% and proved to be used successfully in short term traffic forecasting in ITS applications.  ...  ACKNOWLEDGEMENT This research was supported by the Accelerating Higher Education Expansion and Development (AHEAD) Operation of the Ministry of Higher Education, Sri Lanka funded by the World Bank.  ... 
doi:10.5281/zenodo.4514955 fatcat:lbkucqzgzvau3cdl2xyag5none

Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion [article]

Dongxu Guo, Taylor Mordan, Alexandre Alahi
2022 arXiv   pre-print
Considering the lack of suitable existing datasets for it, we release TRANS, a benchmark for explicitly studying the stop and go behaviors of pedestrians in urban traffic.  ...  We evaluate our model and several baselines on TRANS, and set a new benchmark for the community to work on pedestrian stop and go forecasting.  ...  Long Short-Term Memory (LSTM) networks, as variations of RNNs, address the problem of vanishing gradients and long-term dependency in modeling long sequences [49] .  ... 
arXiv:2203.02489v1 fatcat:auat4itsmfg47oqg6lvdfeu27y

Deep learning for spatio-temporal forecasting – application to solar energy [article]

Vincent Le Guen
2022 arXiv   pre-print
The motivating application at Electricity de France (EDF) is short-term solar energy forecasting with fisheye images.  ...  Our second direction is to augment incomplete physical models with deep data-driven networks for accurate forecasting.  ...  Related work We review here related multi-step video prediction approaches dedicated to long-term forecasting.  ... 
arXiv:2205.03571v1 fatcat:dwkprkwf6ncgjcnvkpx3yrdfjm

Combining Deep Learning and Multiresolution Analysis for Stock Market Forecasting

Khaled A. Althelaya, Salahadin A. Mohammed, El-Sayed M. El-Alfy
2021 IEEE Access  
INDEX TERMS Deep learning, multiresolution analysis, long-short term memory, financial time series, forecasting.  ...  In this article, we propose a model based on deep neural networks that improves the forecasting of stock prices.  ...  ACKNOWLEDGMENT The authors would like to thank King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia, for support during this work.  ... 
doi:10.1109/access.2021.3051872 fatcat:vdlnsq66bzfxthrnsprds6bwgq

Sound Levels Forecasting in an Acoustic Sensor Network Using a Deep Neural Network

Juan M. Navarro, Raquel Martínez-España, Andrés Bueno-Crespo, Ramón Martínez, José M. Cecilia
2020 Sensors  
., vehicles flow or street geometry, and predict equivalent levels for a temporal long-term.  ...  Therefore, forecasting of temporal short-term sound levels could be a helpful tool for urban planners and managers.  ...  These problems are solved by the Long Short-Term Memory neural networks (LSTM), for which it incorporates a series of steps to decide which information will be stored and which erased.  ... 
doi:10.3390/s20030903 pmid:32046231 pmcid:PMC7038967 fatcat:t55wzounrjdqzdfiltiy2mkt4y

ADST: Forecasting Metro Flow using Attention-Based Deep Spatial-Temporal Networks with Multi-Task Learning

Hongwei Jia, Haiyong Luo, Hao Wang, Fang Zhao, Qixue Ke, Mingyao Wu, Yunyun Zhao
2020 Sensors  
In this paper, we identify the unique spatiotemporal correlation of urban metro flow, and propose an attention-based deep spatiotemporal network with multi-task learning (ADST-Net) at a citywide level  ...  Furthermore, we enforce multi-task learning to utilize transition passenger flow volume prediction as an auxiliary task during the training process for generalization.  ...  Acknowledgments: Our sincere thankfulness be tendered to all the reviewers for their valuable comments and helpful suggestions. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s20164574 pmid:32824074 pmcid:PMC7472615 fatcat:ynrvnnerabby5hpnqrcqesv4qa

Multistep traffic forecasting by dynamic graph convolution: Interpretations of real-time spatial correlations

Guopeng Li, Victor L. Knoop, Hans van Lint
2021 Transportation Research Part C: Emerging Technologies  
A B S T R A C T Accurate and explainable short-term traffic forecasting is pivotal for making trustworthy decisions in advanced traffic control and guidance systems.  ...  We believe that this research paves a path to more transparent deep learning models applied for short-term traffic forecasting.  ...  We thank them for supporting this study.  ... 
doi:10.1016/j.trc.2021.103185 fatcat:nfn2igym7bao3nl6nro4t64upq

Spatial-Temporal Graph Attention Networks: A Deep Learning Approach for Traffic Forecasting

Chenhan Zhang, James J. Q. Yu, Yi Liu
2019 IEEE Access  
Compared with previous related research, the proposed approach is able to capture dynamic spatial dependencies of traffic networks.  ...  For more information, see  ...  [19] have shown a good result by combining CNN with Long Short-term Memory (LSTM) network for TSP.  ... 
doi:10.1109/access.2019.2953888 fatcat:h3mjwe3765bophjanjexw6gs24

SA-JSTN: Self-Attention Joint Spatiotemporal Network for Temperature Forecasting

Lukui Shi, Nanying Liang, Xia Xu, Tao Li, Zhou Zhang
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
performance especially in short-term prediction.  ...  propose a new deep learning model for temperature forecasting, Self-Attention Joint Spatiotemporal Network (SA-JSTN), which simultaneously captures the spatiotemporal interdependency information.  ...  ACKNOWLEDGMENTS The authors would like to thank Rafaela Castro of the Federal Center for Technological Education of Rio de Janeiro, Brazil, and the Hebei Meteorological Bureau of China, for providing the  ... 
doi:10.1109/jstars.2021.3112131 fatcat:qfjhuxv5ibffdk7p35c57b6eky

DESIGN AND RESULTS OF AN AI-BASED FORECASTING OF AIR POLLUTANTS FOR SMART CITIES

L. Petry, T. Meiers, D. Reuschenberg, S. Mirzavand Borujeni, J. Arndt, L. Odenthal, T. Erbertseder, H. Taubenböck, I. Müller, E. Kalusche, B. Weber, J. Käflein (+4 others)
2021 ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
To forecast these air pollutants for the next 48 hours, a sequence-to-sequence encoder-decoder model with a recurrent neural network (RNN) was implemented.  ...  of air pollutants in urban environments by including real time weather forecast data.  ...  ACKNOWLEDGEMENTS The research is supported by the German Federal Ministry of Transport and Digital Infrastructure (BMVI) under the frame of mFUND, a research initiative funding R & D projects related to  ... 
doi:10.5194/isprs-annals-viii-4-w1-2021-89-2021 doaj:f0c949b1e85841d2b817a4608f26cbef fatcat:2p5f5uw2arepfgzzclnw3u55ge

Deep learning for spatio‐temporal supply and demand forecasting in natural gas transmission networks

Milena Petkovic, Thorsten Koch, Janina Zittel
2021 Energy Science & Engineering  
The results demonstrate that the proposed model can deal with complex nonlinear gas network flow forecasting with high accuracy and effectiveness.  ...  Since the average velocity of gas in a pipeline is only 25 km/h, an adequate high-precision, high-frequency forecasting of supply and demand is crucial for efficient control and operation of such a transmission  ...  Bogaerts at al. 37 combined graph convolutions and Long Short Term Memory network (LSTM) for making short-term and long-term prediction of traffic flows while similar method was proposed by Wu et al  ... 
doi:10.1002/ese3.932 fatcat:xrxkgump5nhm3ds6iy7mme6z74

Long Short Term Memory Networks for Bandwidth Forecasting in Mobile Broadband Networks under Mobility [article]

Konstantinos Kousias, Apostolos Pappas, Ozgu Alay, Antonios Argyriou, Michael Riegler
2020 arXiv   pre-print
In this work, we introduce HINDSIGHT++, an open-source R-based framework for bandwidth forecasting experimentation in MBB networks with Long Short Term Memory (LSTM) networks.  ...  We primarily focus on bandwidth forecasting for Fifth Generation (5G) networks.  ...  ACKNOWLEDGMENTS This work is partially funded by the EU H2020 5GENESIS (815178), and by the Norwegian Research Council project MEMBRANE (250679).  ... 
arXiv:2011.10563v1 fatcat:3h3teaszyzc3lcokupyz3pptya

Multi-Horizon Air Pollution Forecasting with Deep Neural Networks

Mirche Arsov, Eftim Zdravevski, Petre Lameski, Roberto Corizzo, Nikola Koteli, Sasho Gramatikov, Kosta Mitreski, Vladimir Trajkovik
2021 Sensors  
In this work, we propose using Recurrent Neural Network (RNN) models with long short-term memory units to predict the level of PM10 particles at 6, 12, and 24 h in the future.  ...  The obtained results show that the proposed models consistently outperform the baseline model and can be successfully employed for air pollution prediction.  ...  Cyril and Methodius University in Skopje, Faculty of Computer Science and Engineering. We also acknowledge the support of NVIDIA through the donation of a Titan V GPU.  ... 
doi:10.3390/s21041235 pmid:33578633 fatcat:zwi5gxfkmjbyrdzxcsh2veyzlu
« Previous Showing results 1 — 15 out of 3,694 results