LSTM network: a deep learning approach for short‐term traffic forecast

Zhao, Zheng; Chen, Weihai; Wu, Xiaofeng; Chen, Peter C. Y.; Liu, Jingmeng

doi:10.1049/iet-its.2016.0208

Cited by 1,433 publications

(654 citation statements)

References 39 publications

Supporting

Mentioning

634

Contrasting

Unclassified

Order By: Relevance

“…However, RNNs are not capable of preserving long-term dependencies on historical traffic data, as their performance would deteriorate with longer input. As a result, Long Short-Term Memory (LSTM) networks are further adopted by many research studies [37], [38] to perform long-term prediction tasks. Inspired by the human's ability to capture a focus in certain visions, attention mechanisms have been integrated into the neural networks for sequence-to-sequence learning [39].…”

Section: Related Workmentioning

confidence: 99%

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

Fan

Xiang

Chen

et al. 2021

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperforms all baseline methods with up to 65.3% accuracy improvement (e.g., 2.2% MAPE) in predicting nearby traffic volume. We believe that this work can open a new gate of reusing building sensing data for urban traffic sensing, thus establishing connections between smart buildings and intelligent transportation.

show abstract

Section: Related Workmentioning

confidence: 99%

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

Fan

Xiang

Chen

et al. 2021

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…In general, a LSTM network [19] has been gradually applied to the time-series analysis [20][21][22] by profiting from some advantages. In particular, it is a special type of recurrent neural network (RNN), which skillfully solved the problem of gradient vanishing of RNN.…”

Section: Statistics Prediction With Lstmmentioning

confidence: 99%

Re‐ADP: Real‐Time Data Aggregation with Adaptive ω‐Event Differential Privacy for Fog Computing

Huo

Yong

2018

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In the Internet of Things (IoT), aggregation and release of real-time data can often be used for mining more useful information so as to make humans lives more convenient and efficient. However, privacy disclosure is one of the most concerning issues because sensitive information usually comes with users in aggregated data. Thus, various data encryption technologies have emerged to achieve privacy preserving. These technologies may not only introduce complicated computing and high communication overhead but also do not work on the protection of endless data streams. Considering these challenges, we propose a real-time stream data aggregation framework with adaptive -event differential privacy (Re-ADP). Based on adaptive -event differential privacy, the framework can protect any data collected by sensors over any dynamic time stamp successively over infinite stream. It is designed for the fog computing architecture that dramatically extends the cloud computing to the edge of networks. In our proposed framework, fog servers will only send aggregated secure data to cloud servers, which can relieve the computing overhead of cloud servers, improve communication efficiency, and protect data privacy. Finally, experimental results demonstrate that our framework outperforms the existing methods and improves data availability with stronger privacy preserving.

show abstract

“…The success of LSTM relies on the ability to learn the time series characteristics and to determine several hyperparameters automatically from data [33][34][35]. The LSTM model is composed of one input layer, one hidden layer, and one output layer.…”

Section: Long Short-term Memorymentioning

confidence: 99%

“…One of the most famous RNN is the long shortterm memory (LSTM) model, which can automatically adjust some hyperparameters and can capture the long temporal features of the input data [33]. The LSTM has been introduced into the traffic information prediction field and experiments have shown some promising results [34,35]. The DBN and LSTM will be introduced in detail to represent the basic deep learning method and the advanced recurrent NN, respectively.…”

Section: Introductionmentioning

confidence: 99%

Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method

Jia

2017

Journal of Advanced Transportation

137

View full text Add to dashboard Cite

Accurate traffic flow prediction is increasingly essential for successful traffic modeling, operation, and management. Traditional data driven traffic flow prediction approaches have largely assumed restrictive (shallow) model architectures and do not leverage the large amount of environmental data available. Inspired by deep learning methods with more complex model architectures and effective data mining capabilities, this paper introduces the deep belief network (DBN) and long short-term memory (LSTM) to predict urban traffic flow considering the impact of rainfall. The rainfall-integrated DBN and LSTM can learn the features of traffic flow under various rainfall scenarios. Experimental results indicate that, with the consideration of additional rainfall factor, the deep learning predictors have better accuracy than existing predictors and also yield improvements over the original deep learning models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time series characteristics of traffic flow data.

show abstract

LSTM network: a deep learning approach for short‐term traffic forecast

Cited by 1,433 publications

References 39 publications

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

BuildSenSys: Reusing Building Sensing Data for Traffic Prediction With Cross-Domain Learning

Re‐ADP: Real‐Time Data Aggregation with Adaptive ω‐Event Differential Privacy for Fog Computing

Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method

Contact Info

Product

Resources

About