Non-invasive fitness assessment in horses: Integrating wearables and machine learning

The field of human sports has advanced significantly with the integration of machine learning and sensors for performance analysis. However, sport horses have not benefited equally from technological advancements due to their inability to provide feedback, such as verbal expressions of fatigue or difficulty.

Veterinarians and researchers traditionally interpret equine well-being through methods like verbal encouragement, facial expressions, and blood sample analysis. These methods are either subjective or invasive, causing stress and disruption during training. Accurate and reliable fitness parameter values are essential to avoid overtraining and injuries, necessitating a more effective and less intrusive approach.

This PhD thesis aims to revolutionize sport horse training by using wearable inertial sensors and state-of-the-art machine learning to enhance performance and prevent injuries. The study is divided into nine chapters, each contributing to the overall goal of improving equine fitness and well-being.

Each chapter begins with a literature review to identify gaps and challenges in equine fitness and performance. Inertial sensors were chosen for their ability to capture a wide range of real-time motion data. The sensors were placed on various parts of the horse’s body, including the head, neck, shoulders, back, and legs. Data were collected during various training and competition scenarios to evaluate the system's effectiveness.

The results demonstrated that the system could accurately capture and analyze a broad spectrum of motion data, providing valuable insights for trainers and riders. This technology can improve fitness and prevent injuries in sport horses by offering practical tools for assessing equine fitness outside of laboratory settings.

This thesis makes significant contributions to equine research by leveraging wearable sensor technology and machine learning to enhance our understanding of equine fitness, performance, and well-being. The findings are valuable not only to the scientific community but also to the broader equestrian world, promoting the welfare of sport horses and the sustainability of the equestrian industry.