用深度学习监测疲劳，动态调整可穿戴设备界面。
Fatigue-Aware Adaptive Interfaces for Wearable Devices Using Deep Learning
- 融合生理信号与上下文信息，用深度学习识别用户疲劳状态。
- 界面元素自动优化后，认知负荷降低18%，满意度提升22%。
- 适合长时间使用智能手表、头显等设备的用户群体。
智能手表和头戴显示等可穿戴设备在远程学习与工作等长时间任务中日益普及，但持续交互常导致用户疲劳，降低效率与参与度。本研究提出一种基于深度学习的疲劳感知自适应界面系统，通过分析心率、眼动等生理数据，动态调整文本大小、通知频率和视觉对比度等界面元素以减轻认知负荷。系统采用多模态学习处理生理与上下文输入，并运用强化学习优化界面配置。实验表明，在长期任务中，该系统相较静态界面实现18%的认知负荷下降与22%的用户满意度提升，显著增强可穿戴计算环境的可用性与可访问性。
原文摘要 · Abstract (English)
Wearable devices, such as smartwatches and head-mounted displays, are increasingly used for prolonged tasks like remote learning and work, but sustained interaction often leads to user fatigue, reducing efficiency and engagement. This study proposes a fatigue-aware adaptive interface system for wearable devices that leverages deep learning to analyze physiological data (e.g., heart rate, eye movement) and dynamically adjust interface elements to mitigate cognitive load. The system employs multimodal learning to process physiological and contextual inputs and reinforcement learning to optimize interface features like text size, notification frequency, and visual contrast. Experimental results show a 18% reduction in cognitive load and a 22% improvement in user satisfaction compared to static interfaces, particularly for users engaged in prolonged tasks. This approach enhances accessibility and usability in wearable computing environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。