An integrated methodology for real-time driving risk status prediction using naturalistic driving data

Shangguan, Qiangqiang; Fu, Ting; Wang, Junhua; Luo, Tianyang

doi:10.1016/j.aap.2021.106122

Cited by 49 publications

(26 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the sliding interval was set to 1 s for real-time performance. The length of the time window was referred to previous studies [ 16 , 38 ]:

, and the optimal length would be explored through subsequent experiments. Each time window was labeled using Algorithm 1 [ 23 ].…”

Section: Methodology Descriptionmentioning

confidence: 99%

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Xie

Chen

et al. 2021

IJERPH

View full text Add to dashboard Cite

Real-time driving behavior identification has a wide range of applications in monitoring driver states and predicting driving risks. In contrast to the traditional approaches that were mostly based on a single data source with poor identification capabilities, this paper innovatively integrates driver expression into driving behavior identification. First, 12-day online car-hailing driving data were collected in a non-intrusive manner. Then, with vehicle kinematic data and driver expression data as inputs, a stacked Long Short-Term Memory (S-LSTM) network was constructed to identify five kinds of driving behaviors, namely, lane keeping, acceleration, deceleration, turning, and lane changing. The Artificial Neural Network (ANN) and XGBoost algorithms were also employed as a comparison. Additionally, ten sliding time windows of different lengths were introduced to generate driving behavior identification samples. The results show that, using all sources of data yields better results than using the kinematic data only, with the average F1 value improved by 0.041, while the S-LSTM algorithm is better than the ANN and XGBoost algorithms. Furthermore, the optimal time window length is 3.5 s, with an average F1 of 0.877. This study provides an effective method for real-time driving behavior identification, and thereby supports the driving pattern analysis and Advanced Driving Assistance System.

show abstract

“…In this study, the sliding interval was set to 1 s for real-time performance. The length of the time window was referred to previous studies [ 16 , 38 ]:

, and the optimal length would be explored through subsequent experiments. Each time window was labeled using Algorithm 1 [ 23 ].…”

Section: Methodology Descriptionmentioning

confidence: 99%

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Xie

Chen

et al. 2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…In a more anthropocentric approach, studies have developed models to evaluate dangerous driving behavior based on the driver’s state [ 14 ] and based on certain characteristics of the driver, such as demographics [ 15 ]. Other studies have developed models of recognizing dangerous driving based on driving behavior parameters such as speed, time to collision, and time to headway [ 13 , 16 , 17 ].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Risky driving behavior prediction models based on machine learning algorithms have become extremely popular, due to their high scoring accuracy. In relevant studies, the most utilized models with high performances were Random Forest (RFs; [ 15 ]), Multilayer Perceptron (MLP; [ 16 ]), Support Vector Machines (SVMs; [ 13 ]) and eXtreme Gradient boosting (XGBoost; [ 17 ]). For instance, [ 16 ] proposed a methodology to predict and evaluate the risk of the driver in real-time, based on four safety levels of driving behavior.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In relevant studies, the most utilized models with high performances were Random Forest (RFs; [ 15 ]), Multilayer Perceptron (MLP; [ 16 ]), Support Vector Machines (SVMs; [ 13 ]) and eXtreme Gradient boosting (XGBoost; [ 17 ]). For instance, [ 16 ] proposed a methodology to predict and evaluate the risk of the driver in real-time, based on four safety levels of driving behavior. In this study, the proposed methodology includes feature extraction, clustering techniques, feature importance, and the development and evaluation of four machine learning algorithms (i.e., RF, XGBoost, SVM, and MLP) where accuracy is higher than 85%.…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Data-Driven Estimation of a Driving Safety Tolerance Zone Using Imbalanced Machine Learning

Garefalakis

Katrakazas

Yannis

2022

Sensors

View full text Add to dashboard Cite

Predicting driving behavior and crash risk in real-time is a problem that has been heavily researched in the past years. Although in-vehicle interventions and gamification features in post-trip dashboards have emerged, the connection between real-time driving behavior prediction and the triggering of such interventions is yet to be realized. This is the focus of the European Horizon2020 project “i-DREAMS”, which aims at defining, developing, testing and validating a ‘Safety Tolerance Zone’ (STZ) in order to prevent drivers from risky driving behaviors using interventions both in real-time and post-trip. However, the data-driven conceptualization of STZ levels is a challenging task, and data class imbalance might hinder this process. Following the project principles and taking the aforementioned challenges into consideration, this paper proposes a framework to identify the level of risky driving behavior as well as the duration of the time spent in each risk level by private car drivers. This aim is accomplished by four classification algorithms, namely Support Vector Machines (SVMs), Random Forest (RFs), AdaBoost, and Multilayer Perceptron (MLP) Neural Networks and imbalanced learning using the Adaptive Synthetic technique (ADASYN) in order to deal with the unbalanced distribution of the dataset in the STZ levels. Moreover, as an alternative approach of risk prediction, three regression algorithms, namely Ridge, Lasso, and Elastic Net are used to predict time duration. The results showed that RF and MLP outperformed the rest of the classifiers with 84% and 82% overall accuracy, respectively, and that the maximum speed of the vehicle during a 30 s interval, is the most crucial predictor for identifying the driving time at each safety level.

show abstract

“…Considering the future state of charge (SOC) is important for ESSs to make decisions, especially after being integrated with devices that introduce uncertainties (Tang et al, 2020(Tang et al, , 2021Li et al, 2021). The length of the prediction time window and the time granularity could respectively affect the prediction accuracy (Shangguan et al, 2021) and the corresponding computational burden. A longer prediction time window can cover the uncertainty for a longer period, but takes more time to solve.…”

Section: Introductionmentioning

confidence: 99%

Two-Stage Energy Management for Energy Storage System by Using Stochastic Model Predictive Control Approach

2021

View full text Add to dashboard Cite

There is a growing tendency for industrial consumers to invest in both photovoltaic (PV) and energy storage systems (ESSs) to meet their electricity requirements. However, the uncertainty of load demand and PV output brings great challenges for ESS operation. In this paper, a stochastic model predictive control (MPC) approach-based energy management strategy for ESSs is proposed. A non-parametric probabilistic prediction method embedded in time series correlation is adopted to describe the uncertainty of load demand and PV output. Then, a two-stage energy management model is proposed aiming at minimizing the total operation cost. The upper stage can generate an hourly operation strategy for ESSs, while the lower stage focuses on a more detailed minute-level operation strategy. The hourly operation strategy is also used as a basis to guide the ESS operation in the lower stage. Besides, a chance constraint was introduced to achieve a win–win solution between PV power consumption and electricity tariff, while the terminal value constraint of the capacity of ESSs to better cope with the uncertainty beyond the prediction time window. Finally, the numerical results showed that the proposed method can achieve an effective ESS energy management strategy.

show abstract

An integrated methodology for real-time driving risk status prediction using naturalistic driving data

Cited by 49 publications

References 41 publications

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Real-Time Driving Behavior Identification Based on Multi-Source Data Fusion

Data-Driven Estimation of a Driving Safety Tolerance Zone Using Imbalanced Machine Learning

Two-Stage Energy Management for Energy Storage System by Using Stochastic Model Predictive Control Approach

Contact Info

Product

Resources

About