Scholarlink

Background <p>Ankle injuries represent a leading cause of long-term impairment for athletes. Wearable inertial sensors have emerged for continuous joint monitoring yet implementing accurate real-time injury detection remains a challenge due to the latency, energy, and computational limitations. Effective solutions must therefore support fast, adaptive, and energy-efficient inference without compromising clinical relevance.</p> Methods <p>We implemented an adaptive ankle injury detection framework using the Ankle Motion Kinematics Dataset (AMKD), which synchronized inertial sensor and video-labeled data from 87 athletes across 12 sports. The system integrates a quantized 1D convolutional neural network (1D-CNN) and a pruned long short-term memory (LSTM) model into a lightweight ensemble. A reinforcement learning (RL) agent dynamically adjusts model parameters based on motion context, informed by a Gaussian process predictor that anticipates future kinematic shifts.</p> Results <p>The core ensemble model achieved 94.3% classification accuracy on the test set. The full adaptive system, operating under real-time constraints, achieved 87.4% overall detection accuracy and a 12.1% false alarm rate (<i>p</i> &lt; 0.01). It predicted 76.3% of injury events at least 150 ms in advance and maintained a low latency of 17.2 ms 34.8% faster than the best-performing baseline while reducing energy consumption by 35.4% and memory usage by 27.7%. The adaptive controller proactively detected 82.6% of high-risk transitions, and real-world deployment yielded 98.7% uptime across 8-hour sessions, confirming practical viability.</p> Conclusion <p>These results validate the framework as a viable, low-latency solution for real-time ankle injury detection in sports medicine and rehabilitation settings. Its modularity and efficiency enable seamless integration into existing wearable pipelines while maintaining responsiveness in dynamic conditions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive ensemble sizing with reinforcement learning for real-time ankle injury detection in wearable sensor systems

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月24日

查看全文
  • Abdulmohsen S. Alanazi,
  • Abdulelah F. Alshehri,
  • Rayan A. Almutairi,
  • Emad N. Alzeanidi,
  • Abdullah N. Alzeanidi,
  • Saleh T. Alsuwaih,
  • Moath A. Albukairi,
  • Tariq S. Alotaibi,
  • Albandari M. Alajlan,
  • Moaath A. Alamir

摘要

Background

Ankle injuries represent a leading cause of long-term impairment for athletes. Wearable inertial sensors have emerged for continuous joint monitoring yet implementing accurate real-time injury detection remains a challenge due to the latency, energy, and computational limitations. Effective solutions must therefore support fast, adaptive, and energy-efficient inference without compromising clinical relevance.

Methods

We implemented an adaptive ankle injury detection framework using the Ankle Motion Kinematics Dataset (AMKD), which synchronized inertial sensor and video-labeled data from 87 athletes across 12 sports. The system integrates a quantized 1D convolutional neural network (1D-CNN) and a pruned long short-term memory (LSTM) model into a lightweight ensemble. A reinforcement learning (RL) agent dynamically adjusts model parameters based on motion context, informed by a Gaussian process predictor that anticipates future kinematic shifts.

Results

The core ensemble model achieved 94.3% classification accuracy on the test set. The full adaptive system, operating under real-time constraints, achieved 87.4% overall detection accuracy and a 12.1% false alarm rate (p < 0.01). It predicted 76.3% of injury events at least 150 ms in advance and maintained a low latency of 17.2 ms 34.8% faster than the best-performing baseline while reducing energy consumption by 35.4% and memory usage by 27.7%. The adaptive controller proactively detected 82.6% of high-risk transitions, and real-world deployment yielded 98.7% uptime across 8-hour sessions, confirming practical viability.

Conclusion

These results validate the framework as a viable, low-latency solution for real-time ankle injury detection in sports medicine and rehabilitation settings. Its modularity and efficiency enable seamless integration into existing wearable pipelines while maintaining responsiveness in dynamic conditions.