Attention-Based Sequence Learning Model for Travel Time Estimation

Zhong, Wang; Fu, Hao; Liu, Guiquan; Meng, Xianwei

doi:10.1109/access.2020.3042673

Cited by 2 publications

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [31] has also incorporated intersection direction and driver behavior with other features in an attention-based GCN for TTP and demonstrated improved performance.…”

Section: Introductionmentioning

confidence: 99%

Travel Time Prediction Using Hybridized Deep Feature Space and Machine Learning Based Heterogeneous Ensemble

et al. 2022

View full text Add to dashboard Cite

Travel Time Prediction (TTP) has become an essential service that people use in daily commutes. With the precise TTP, individuals, logistic companies, and transport authorities can better manage their activities and operations. This paper presents a novel Hybridized Deep Feature Spacebased TTP ensemble model (HDFS-TTP) for accurate travel time prediction. In the first step, extensive endogenous and exogenous data sources are augmented with traffic data obtained using sensors. Next, we used Principal Component Analysis (PCA) and Deep Stacked Auto-Encoder (DSAE) for feature reduction. We generated feature spaces of deep learning models, namely Convolutional Neural Network (CNN), Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU), and fed them to a model based on Support Vector Regressor (SVR) for predicting travel times. Two best-performing models are selected, and their feature spaces are hybridized to boost feature space. On this boosted feature space, we employed SVR for final prediction. Our proposed HDFS-TTP ensemble can learn complex nonlinearities in traffic data with the varying architectural design. The performance of our proposed HDFS-TTP ensemble using hybridized and boosted feature spaces showed significant improvement in test data in terms of Root Mean Square Error (62.27 ± 1.58), Mean Absolute Error (13.38 ± 1.09), Maximum Absolute Error (104.66 ± 2.77), Mean Absolute Percentage Error (2.50 ± 0.03), and Coefficient of determination (0.99714 ± 0.00044).

show abstract

“…al. [31] has also incorporated intersection direction and driver behavior with other features in an attention-based GCN for TTP and demonstrated improved performance.…”

Section: Introductionmentioning

confidence: 99%