Short-term travel time prediction by deep learning: A comparison of different LSTM-DNN models

Liu, Yangdong; Wang, Yizhe; Yang, Xiaoguang; Zhang, Linan

doi:10.1109/itsc.2017.8317886

Cited by 84 publications

(48 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…17 For this model also the output is not only dependent on the current input but on the output of previous hidden layers. Although a previous study, for instance, stacked LSTM and DNN for sequential data, 10 this study was able to implement this model, and also LSTM-DNN on non-sequential datasets. The following sections will go over a structure of LSTM model and a methodological approach taken in this study for setting hyperparameters.…”

Section: Lstmmentioning

confidence: 89%

“…Another study conducted to demonstrate the use of different LSTM and deep neural network (DNN) techniques to predict travel time on one or several time steps in the future. 10 Autoregressive integrated moving average, linear regression models and LSTM models with different setting, were conducted and compared. The results indicated that a stacked of LSTM along with deep neural layers (LSTM-DNN) outperform the other models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of various machine learning architectures for crash prediction, considering different depths and processing layers

Rezapour

Ksaibati

2020

Engineering Reports

View full text Add to dashboard Cite

Over a million people die every year as a result of road crashes. A significant proportion of all road fatalities are related to vulnerable road users, including motorcyclist and pedestrian. Artificial intelligent can proactively act to identify those drivers as higher risk of crashes. However, an accurate predictive model is essential for the safety of the road users. High accuracy could be achieved by implementing a reliable method with an optimal architecture and structure being able to identify and flag the risky drivers before a crash occurs. Over the last decade, extensive research has been conducted to achieve a higher accuracy by adjusting the depth of various machine learning algorithms or staking different processing layers. The literature highlights that having a higher algorithm complexity or blindly stacking up layers would not necessarily enhance the model accuracy. Despite the extensive efforts being made about the impacts of depth and various processing layers in the literture, not much research has been conducted on transportation problems to investigate the importance of those factors on the accuracy of crash prediction. In this context, this study aims to implement and compare various deep learning architectures in predicting motorists' crash severity. Various processing layers and depths are considered and compared. Long short‐term memory (LSTM) models have extensively been used in the literature for different types of sequential datasets. However, a comprehensive application of this method for non‐sequential data is still missing. Different processing layers of LSTM and deep neural network (DNN)‐based models with various depths and combinations are here considered and compared. The results indicate that a simple LSTM outperforms an LSTM model with higher depths, and a model with DNN stacked on top of the LSTM model. This study discusses in detail the methodological approach to stacking various layers and hyperparameters tuning.

show abstract

Section: Lstmmentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Application of various machine learning architectures for crash prediction, considering different depths and processing layers

Rezapour

Ksaibati

2020

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…Liu et al [19] used a hybrid LSTM model to predict the vehicle flow of each road section and intersection in an actual traffic network. They successfully used the maximum relative error to compare the difference between the actual and predictive vehicle flows.…”

Section: Literature Reviewmentioning

confidence: 99%

Untitled

2020

CiVEJ

View full text Add to dashboard Cite

Land use and transportation planning are interdependent , as well as being important factors in forecasting urban development. In recent years, predicting traffic based on land use, along with several other variables, has become a worthwhile area of study. In this paper, it is proposed that Deep Neural Network Regression (DNN-Regression) and Recurrent Neural Network (DNN-RNN) methods could be used to predict traffic. These methods used three key variables: land use, demographic and temporal data. The proposed methods were evaluated with other methods, using datasets collected from the City of Calgary, Canada. The proposed DNN-Regression focused on demographic and land use variables for traffic prediction. The study also predicted traffic temporally in the same geographical area by using DNN-RNN. The DNN-RNN used long short-term memory to predict traffic. Comparative experiments revealed that the proposed DNN-Regression and DNN-RNN models outperformed other methods.

show abstract

“…LSTM networks are not affected by the exploding gradient problem that is common in regular RNN when trained to predict values at future steps. These characteristics have made LSTM networks popular for time-series forecasting ( Bao, Yue, & Rao, 2017;Bui, Le, & Cha, 2018;Liu, Wang, Yang, & Zhang, 2017 ). Most reported works in deep learning for time-series forecasting aim to predict the expected value rather than a prediction interval.…”

Section: Literature Review For Prediction Interval Modellingmentioning

confidence: 99%

Prediction interval methodology based on fuzzy numbers and its extension to fuzzy systems and neural networks

Marín

Cruz

Sáez

et al. 2019

Expert Systems with Applications

View full text Add to dashboard Cite

Prediction interval modelling has been proposed in the literature to characterize uncertain phenomena and provide useful information from a decision-making point of view. In most of the reported studies, assumptions about the data distribution are made and/or the models are trained at one step ahead, which can decrease the quality of the interval in terms of the information about the uncertainty modelled for a higher prediction horizon. In this paper, a new prediction interval modelling methodology based on fuzzy numbers is proposed to solve the abovementioned drawbacks. Fuzzy and neural network prediction interval models are developed based on this proposed methodology by minimizing a novel criterion that includes the coverage probability and normalized average width. The fuzzy number concept is considered because the affine combination of fuzzy numbers generates, by definition, prediction intervals that can handle uncertainty without requiring assumptions about the data distribution. The developed models are compared with a covariance-based prediction interval method, and high-quality intervals are obtained, as determined by the narrower interval width of the proposed method. Additionally, the proposed prediction intervals are tested by forecasting up to two days ahead of the load of the Huatacondo microgrid in the north of Chile and the consumption of the residential dwellings in the town of Loughborough, UK. The results show that the proposed models are suitable alternatives to electrical consumption forecasting because they obtain the minimum interval widths that characterize the uncertainty of this type of stochastic process. Furthermore, the information provided by the obtained prediction interval could be used to develop robust energy management systems that, for example, consider the worst-case scenario.

show abstract

Short-term travel time prediction by deep learning: A comparison of different LSTM-DNN models

Cited by 84 publications

References 15 publications

Application of various machine learning architectures for crash prediction, considering different depths and processing layers

Application of various machine learning architectures for crash prediction, considering different depths and processing layers

Untitled

Prediction interval methodology based on fuzzy numbers and its extension to fuzzy systems and neural networks

Contact Info

Product

Resources

About