Abstract
Ensuring driver readiness poses challenges, yet driver monitoring systems can assist in determining the driver's state. By observing visual cues, such systems recognize various behaviors and associate them with specific conditions. For instance, yawning or eye blinking can indicate driver drowsiness. Consequently, an abundance of distributed data is generated for driver monitoring. Employing machine learning techniques, such as driver drowsiness detection, presents a potential solution. However, transmitting the data to a central machine for model training is impractical due to the large data size and privacy concerns. Conversely, training on a single vehicle would limit the available data and likely result in inferior performance. To address these issues, we propose a federated learning framework for drowsiness detection within a vehicular network, leveraging the YawDD dataset. Our approach achieves an accuracy of 99.2%, demonstrating its promise and comparability to conventional deep learning techniques. Lastly, we show how our model scales using various number of federated clients
Abstract (translated)
确保驾驶员准备就绪存在挑战,然而驾驶员监控系统可以帮助确定驾驶员的状态。通过观察视觉信号,这些系统识别出各种行为并将其与特定条件相关联。例如,打哈欠或眼睛眨动可能表明驾驶员疲劳。因此,为驾驶员监控生成大量分布式数据。采用机器学习技术,如驾驶员疲劳检测,提出了一个潜在解决方案。然而,将数据传输到集中的机器进行模型训练是不切实际的,因为数据量较大,存在隐私问题。相反,在单个车辆上训练会导致可用数据有限,很可能导致性能较差。为解决这些问题,我们提出了一个基于车辆网络的联邦学习框架来进行驾驶员疲劳检测,利用YawDD数据集。我们的方法实现了99.2%的准确率,证明了其潜力和与传统深度学习技术的可比性。最后,我们展示了我们的模型如何随着各种联邦客户端数量的不同而扩展。
URL
https://arxiv.org/abs/2405.03311