Missing Value Imputation for Traffic-Related Time Series Data Based on a Multi-View Learning Method

Li, Linchao; Zhang, Jian; Wang, Yong Gang; Ran, Bin

doi:10.1109/tits.2018.2869768

Cited by 138 publications

(66 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…drivers would try to change the current lane for ensuring their efficiency. Since literature [47] has pointed out using simulation data for analyzing LCC has its limitation and it might not truly reflect the real-world situations, the impact of lane change still needs further examination from field test data [48]. 800.0k…”

Section: Journal Of Advanced Transportationmentioning

confidence: 99%

Safety Evaluation for Connected and Autonomous Vehicles’ Exclusive Lanes considering Penetrate Ratios and Impact of Trucks Using Surrogate Safety Measures

Zhang

Cheng

et al. 2020

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

Plenty of studies on exclusive lanes for Connected and Autonomous Vehicle (CAV) have been conducted recently about traffic efficiency and safety. However, most of the previous research studies neglected comprehensive consideration of the safety impact on different market penetration rates (MPRs) of CAVs, traffic demands, and proportion of trucks in mixture CAVs with human’s driven vehicle environment. On this basis, this study is to (1) identify the safety impact on exclusive lanes for CAVs under different MPRs with different traffic demands and (2) investigate the safety impact of trucks for CAV exclusive lanes on mixture environment. Based on the Intelligent Driver Model (IDM), a CAV platooning control algorithm is proposed for modeling the driving behaviors of CAVs. A calibrated 7-kilometer freeway section microscopic simulation environment is built by VISSIM. Four surrogate safety measures, including both longitudinal and lateral safety risk indexes, are employed to evaluate the overall safety impacts of setting exclusive lanes. Main results indicate that (1) setting one exclusive lane is capable to improve overall safety environment in low demand, and two exclusive lanes are more suitable for high-demand scenario; (2) existence of trucks worsens overall longitudinal safety environment, and improper setting of exclusive lanes in high trucks, low MPR scenario has adverse effect on longitudinal safety; and (3) setting exclusive lanes have better longitudinal and lateral safety improvement in high-truck proportion scenarios. Setting one or two exclusive lanes led to [+42.4% to −52.90%] and [+45.7% to −55.2%] of longitudinal risks while [−1.8% to −87.1%] and [−2.1% to −85.3%] of lateral conflicts compared with the base scenario, respectively. Results of this study provide useful insight for the setting of exclusive lanes for CAVs in a mixture environment.

show abstract

Section: Journal Of Advanced Transportationmentioning

confidence: 99%

Safety Evaluation for Connected and Autonomous Vehicles’ Exclusive Lanes considering Penetrate Ratios and Impact of Trucks Using Surrogate Safety Measures

Zhang

Cheng

et al. 2020

Journal of Advanced Transportation

Self Cite

View full text Add to dashboard Cite

show abstract

“…Parametric methods include auto aggressive integrated moving average method ARIMA [13], exponential smoothing (ES) [14], and seasonal auto aggressive integrated moving average method (SARIMA) [15,16]. In their study, Li et al suggested that a multi-view learning approach estimates the missing values in traffic-related time series data [17]. Parametric methods focus on pre-determining the structure of the model based on theoretical or physical assumptions, later tuning a set of parameters that represent the traffic conditions (i.e., a trend in the actual world) [10,11].…”

Section: Introductionmentioning

confidence: 99%

Short Term Traffic State Prediction via Hyperparameter Optimization Based Classifiers

Zahid

Chen

Jamal

et al. 2020

Sensors

View full text Add to dashboard Cite

Short-term traffic state prediction has become an integral component of an advanced traveler information system (ATIS) in intelligent transportation systems (ITS). Accurate modeling and short-term traffic prediction are quite challenging due to its intricate characteristics, stochastic, and dynamic traffic processes. Existing works in this area follow different modeling approaches that are focused to fit speed, density, or the volume data. However, the accuracy of such modeling approaches has been frequently questioned, thereby traffic state prediction over the short-term from such methods inflicts an overfitting issue. We address this issue to accurately model short-term future traffic state prediction using state-of-the-art models via hyperparameter optimization. To do so, we focused on different machine learning classifiers such as local deep support vector machine (LD-SVM), decision jungles, multi-layers perceptron (MLP), and CN2 rule induction. Moreover, traffic states are evaluated using traffic attributes such as level of service (LOS) horizons and simple if–then rules at different time intervals. Our findings show that hyperparameter optimization via random sweep yielded superior results. The overall prediction performances obtained an average improvement by over 95%, such that the decision jungle and LD-SVM achieved an accuracy of 0.982 and 0.975, respectively. The experimental results show the robustness and superior performances of decision jungles (DJ) over other methods.

show abstract

“…It has been widely recognized that the application of data fusion techniques which consider various correlated data sources can help to improve the accuracy of the estimation of OD trip matrix [26][27][28][29]. In such data fusion process, the following two issues have to be addressed: (1) the smart card data contains only transaction-related information, which is useful only when it can be matched with the vehicle's operational data while the boarding and alighting locations are not recorded [30]; (2) the information recorded by the smart card system might not be matched perfectly with that data of the GPS system.…”

Section: Introductionmentioning

confidence: 99%

A Method for Bus OD Matrix Estimation Using Multisource Data

Huang

Shen³

et al. 2020

Journal of Advanced Transportation

View full text Add to dashboard Cite

The automated fare collection (AFC) system has gained increasing popularity among transit systems worldwide. The AFC system is usually an entry-only system that only records the serial number of the smart card and the transaction time of each use. Neither the AFC data nor the bus global positioning system (GPS) could reveal the passenger’s alighting information, namely, alighting time and station. Hence, the station-to-station origin-destination (OD) trip information cannot be obtained directly from the available data sources. To address this problem, this paper proposes a methodology that estimates the OD matrix by using smart card and GPS data. In this paper, the characteristics of the basic data sources are first analyzed, based on which the bus arrival time is generated using the density-based clustering algorithm and a time correction strategy, based on which the passenger’s boarding station is identified. The alighting stations are inferred based on the characteristics of bus trip chaining, which could identify over 80% of the alighting stations on average. Finally, the proposed methodology is verified by a comprehensive field survey in Suzhou, China, with 100% sample rate.

show abstract

Missing Value Imputation for Traffic-Related Time Series Data Based on a Multi-View Learning Method

Cited by 138 publications

References 35 publications

Safety Evaluation for Connected and Autonomous Vehicles’ Exclusive Lanes considering Penetrate Ratios and Impact of Trucks Using Surrogate Safety Measures

Safety Evaluation for Connected and Autonomous Vehicles’ Exclusive Lanes considering Penetrate Ratios and Impact of Trucks Using Surrogate Safety Measures

Short Term Traffic State Prediction via Hyperparameter Optimization Based Classifiers

A Method for Bus OD Matrix Estimation Using Multisource Data

Contact Info

Product

Resources

About