<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Fatigue is an important factor affecting modern flight safety. It can easily lead to a decline in the pilot's operational capabilities, misjudgments and flight illusions. Moreover, it may even cause serious flight accidents. In this paper, a wearable wireless physiological device is used to obtain pilot electrocardiogram data in simulated flight experiments. Bioelectric signals have higher reliability than image information, and are not easily affected by the external environment (such as shooting angle and light intensity). On the other hand, neural networks have been widely used in various classification and regression tasks. In this study, the EEG was collected in the driving flight simulator, and after simple filtering and preprocessing, the time domain data was sent directly to the convolutional neural network, eliminating the need for additional feature extraction operations. We found that the convolutional neural network can effectively amplify the fluctuation details of the time domain data and train the pilot fatigue state recognition model. The results show that the recognition accuracy of the convolutional neural network model reaches 98%, which is 26% and 12% higher than the traditional k-nearest neighbor classification algorithm (KNN) and support vector machine (SVM) model, respectively. The recognition model based on convolutional neural network established in this paper is suitable for the recognition of pilot fatigue status. This has important practical significance for reducing flight accidents caused by pilot fatigue, and provides a theoretical basis for pilot fatigue risk management and the development of intelligent aircraft autopilot systems.</p>
</abstract>

Fatigue is an important factor affecting modern flight safety. It can easily lead to a decline in the pilot's operational capabilities, misjudgments and flight illusions. Moreover, it may even cause serious flight accidents. In this paper, a wearable wireless physiological device is used to obtain pilot electrocardiogram data in simulated flight experiments. Bioelectric signals have higher reliability than image information, and are not easily affected by the external environment (such as shooting angle and light intensity). On the other hand, neural networks have been widely used in various classification and regression tasks. In this study, the EEG was collected in the driving flight simulator, and after simple filtering and preprocessing, the time domain data was sent directly to the convolutional neural network, eliminating the need for additional feature extraction operations. We found that the convolutional neural network can effectively amplify the fluctuation details of the time domain data and train the pilot fatigue state recognition model. The results show that the recognition accuracy of the convolutional neural network model reaches 98%, which is 26% and 12% higher than the traditional k-nearest neighbor classification algorithm (KNN) and support vector machine (SVM) model, respectively. The recognition model based on convolutional neural network established in this paper is suitable for the recognition of pilot fatigue status. This has important practical significance for reducing flight accidents caused by pilot fatigue, and provides a theoretical basis for pilot fatigue risk management and the development of intelligent aircraft autopilot systems.

Research on Fatigue Classification of Flight Simulation Training

School of Computer Science and Engineering

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Research on Fatigue Classification of Flight Simulation Training"}

Fatigue is an important factor affecting modern flight safety. It can easily lead to a decline in the pilot's operational capabilities, misjudgments and flight...

Participant ID	001	002	003
Experiment 101	9:00–9:30	10:00–10:30	11:00–11:30
Experiment 102	13:30–14:00	14:30–15:00	15:30–16:00

Participant ID	001	002	003
Experiment 101	9:00–9:30	10:00–10:30	11:00–11:30
Experiment 102	13:30–14:00	14:30–15:00	15:30–16:00

Research on Fatigue Classification of Flight Simulation Training

Publicado en línea: 28 may 2023

Páginas: 81 - 96

DOI: https://doi.org/10.2478/ijanmc-2022-0007

Palabras clave
Fatigue Classification, Eeg, Cnn, Neural Network

© 2022 Lien Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

图 1

图 2

图 3

图 4

Experiment schedule

实验计划表

Research on Fatigue Classification of Flight Simulation Training

Publicado en línea: 28 may 2023

Páginas: 81 - 96

DOI: https://doi.org/10.2478/ijanmc-2022-0007

Palabras claveFatigue Classification, Eeg, Cnn, Neural Network

© 2022 Lien Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

图 1

图 2

图 3

图 4

Experiment schedule

实验计划表

Palabras clave
Fatigue Classification, Eeg, Cnn, Neural Network