College of General Aviation and Flight, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, People's Republic of China.
Sci Rep. 2024 Sep 4;14(1):20641. doi: 10.1038/s41598-024-71192-x.
Even though the capability of aircraft manufacturing has improved, human factors still play a pivotal role in flight accidents. For example, fatigue-related accidents are a common factor in human-led accidents. Hence, pilots' precise fatigue detections could help increase the flight safety of airplanes. The article suggests a model to recognize fatigue by implementing the convolutional neural network (CNN) by implementing flight trainees' face attributions. First, the flight trainees' face attributions are derived by a method called the land-air call process when the flight simulation is run. Then, sixty-eight points of face attributions are detected by employing the Dlib package. Fatigue attribution points were derived based on the face attribution points to construct a model called EMF to detect face fatigue. Finally, the proposed PSO-CNN algorithm is implemented to learn and train the dataset, and the network algorithm achieves a recognition ratio of 93.9% on the test set, which can efficiently pinpoint the flight trainees' fatigue level. Also, the reliability of the proposed algorithm is validated by comparing two machine learning models.
尽管飞机制造能力有所提高，但人为因素仍然在飞行事故中起着关键作用。例如，与疲劳相关的事故是人为事故的一个常见因素。因此，飞行员的精确疲劳检测有助于提高飞机的飞行安全性。本文提出了一种通过实施卷积神经网络（CNN）来识别疲劳的模型，该模型通过实施飞行学员的面部特征来实现。首先，当运行飞行模拟时，通过称为地空呼叫过程的方法得出飞行学员的面部特征。然后，通过使用 Dlib 包检测到 68 个面部特征点。根据面部特征点得出疲劳特征点，以构建一个称为 EMF 的模型来检测面部疲劳。最后，实施了所提出的 PSO-CNN 算法来学习和训练数据集，网络算法在测试集上的识别率达到 93.9%，可以有效地确定飞行学员的疲劳程度。此外，通过比较两种机器学习模型验证了所提出算法的可靠性。
