Estimating the Vigilance of High-Speed Rail Drivers Using a Stacking Ensemble Learning Method

Zhai, Donghai; Pan, Yufan; Li, Peige; Li, Guofa

doi:10.1109/jsen.2021.3077021

Cited by 9 publications

(3 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a wireless EEG acquisition device, Zhou et al [ 62 ] collected EEG data from 10 train drivers and tested them on EEG, achieving a 99.4% correct classification rate within a 9-second time window. Zhai et al [ 61 ] proposed a two-layer superimposed ensemble learning model based on EEG signals to estimate the alertness of highway drivers. The mean absolute error (MAE), root mean square error (RMSE), and goodness of fit (R-squared) are 70.14 (± 13.02) ms, 102.19 (± 22.18) ms, and 0.74 (± 0.09) for the estimated reaction time, respectively.…”

Section: Detection Methods Of Train Driver Fatigue and Distractionmentioning

confidence: 99%

Types, Risk Factors, Consequences, and Detection Methods of Train Driver Fatigue and Distraction

Fan

Huang

Lin

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Train drivers’ inattention, including fatigue and distraction, impairs their ability to drive and is the major risk factor for human-caused train accidents. Many experts have undertaken numerous studies on train driver exhaustion and distraction, but a systematic study is still missing. Through a systematic review, this work aims to outline the types, risk factors, consequences, and detection methods of train driver fatigue and distraction. The effects of central nervous fatigue and cognitive distraction in train drivers during driving are caused by rest and sleep schedules, workload, automation levels, and mobile phones. Furthermore, train drivers’ fatigue and distraction can cause loss of concentration and slow reaction, resulting in dangerous driving behaviour such as speeding and SPAD. Researchers have combined subjective reporting, physiological parameters, and physical factors to construct detection algorithms with good results to detect train driver fatigue and distraction. This review offers recommendations for researchers looking into train driver fatigue and distraction. And it can also make valuable recommendations for future studies about railway traffic safety.

show abstract

Section: Detection Methods Of Train Driver Fatigue and Distractionmentioning

confidence: 99%

Types, Risk Factors, Consequences, and Detection Methods of Train Driver Fatigue and Distraction

Fan

Huang

Lin

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…In order to break through the bottleneck of the existing single-classification algorithm or fusion algorithm, when the accuracy of electricity theft behavior detection reaches a certain level, even if it continues to optimize, it still cannot be improved [29,30]. For their optimization algorithms, such as the stacking strong model ensemble learning method, the selection of base classifiers does not have a good selection strategy, resulting in poor detection results or unable to explain the rationality of its selection.…”

Section: Motivationmentioning

confidence: 99%

An Efficient Method Combined Data-Driven for Detecting Electricity Theft with Stacking Structure Based on Grey Relation Analysis

et al. 2022

View full text Add to dashboard Cite

Nowadays, electricity theft has been a major problem worldwide. Although many single-classification algorithms or an ensemble of single learners (i.e., homogeneous ensemble learning) have proven able to automatically identify suspicious customers in recent years, after the accuracy of these methods reaches a certain level, it still cannot be improved even if it continues to be optimized. To break through this bottleneck, a heterogeneous ensemble learning method with stacking integrated structure of different strong individual learners for detection of electricity theft is presented in this paper. Firstly, we use the grey relation analysis (GRA) method to select the heterogeneous strong classifier combination of LG + LSTM + KNN as the base model layer of stacking structure based on the principle of the highest comprehensive evaluation index value. Secondly, the support vector machine (SVM) model with relatively good results of the stacking overall structure experiment is selected as the model of the meta-model layer. In this way, a heterogeneous integrated learning model for electricity theft detection of the stacking structure is constructed. Finally, the experiments of this model are conducted on electricity consumption data from State Grid Corporation of China, and the results show that the detection performance of the proposed method is better than that of the existing state-of-the-art detection method (where the area under receiver operating characteristic curve (AUC) value is 0.98675).

show abstract

“…Shi et al [6] developed a method combining DE features with SVR to estimate the vigilance state in driving tasks, and then introduced extreme learning machine (ELM) methods to estimate the vigilance state of drivers using the PSD features of EEG [8]. Zhai et al [9] proposed an ensemble learning model to estimate drivers' vigilance state based on the PSD of EEG, which stacked SVR and random forest (RF) regression methods. Recently, some deep learning methods have been proposed.…”

Section: Introductionmentioning

confidence: 99%

Investigating EEG-based cross-session and cross-task vigilance estimation in BCI systems

Wang,

Qiu,

Wei

et al. 2023

J. Neural Eng.

View full text Add to dashboard Cite

Objective. The state of vigilance is crucial for effective performance in brain-computer interface (BCI) tasks, and therefore, it is essential to investigate vigilance levels in BCI tasks. Despite this, most studies have focused on vigilance levels in driving tasks rather than on BCI tasks, and the electroencephalogram (EEG) patterns of vigilance states in different BCI tasks remain unclear. This study aimed to identify similarities and differences in EEG patterns and performances of vigilance estimation in different BCI tasks and sessions. Approach. To achieve this, we built a steady-state visual evoked potential (SSVEP)-based BCI system and a rapid serial visual presentation (RSVP)-based BCI system and recruited 18 participants to carry out four BCI experimental sessions over four days. Main results. Our findings demonstrate that specific neural patterns for high and low vigilance levels are relatively stable across sessions. Differential entropy (DE) features significantly differ between different vigilance levels in all frequency bands and between BCI tasks in the delta and theta frequency bands, with the theta frequency band features playing a critical role in vigilance estimation. Additionally, prefrontal, temporal, and occipital regions are more relevant to the vigilance state in BCI tasks. Our results suggest that cross-session vigilance estimation is more accurate than cross-task estimation. Significance. Our study clarifies the underlying mechanisms of vigilance state in two BCI tasks and provides a foundation for further research in vigilance estimation in BCI applications.

show abstract

Estimating the Vigilance of High-Speed Rail Drivers Using a Stacking Ensemble Learning Method

Cited by 9 publications

References 70 publications

Types, Risk Factors, Consequences, and Detection Methods of Train Driver Fatigue and Distraction

Types, Risk Factors, Consequences, and Detection Methods of Train Driver Fatigue and Distraction

An Efficient Method Combined Data-Driven for Detecting Electricity Theft with Stacking Structure Based on Grey Relation Analysis

Investigating EEG-based cross-session and cross-task vigilance estimation in BCI systems

Contact Info

Product

Resources

About