Now showing 1 - 2 of 2
  • Publication
    Providing Explainable Race-Time Predictions and Training Plan Recommendations to Marathon Runners
    Millions of people participate in marathon events every year, typically devoting at least 12-16 weeks to building their endurance and fitness so that they can safely complete these gruelling 42.2km races. Most runners follow a training plan that is tailored to their expected finish-time (e.g. sub-4 hours or 4-5 hours), and these plans will prescribe a complex mixture of training sessions to help them achieve these times. However, such plans cannot adapt to the individual needs (fitness levels, changing goals, personal preferences) of runners, providing only broad training guidance rather than more personalised support. The development of wearable sensors and mobile fitness applications facilitates the collection of a large amount of training data from runners. In this paper, we propose a recommender system that utilizes such training data to deliver more personalised training advice to runners, using ideas from case-based reasoning to reuse and adapt the training habits of similar runners. Explainability plays a significant role in this type of system, and we also describe how the predictions and recommendation advice can be presented to runners. An initial off-line evaluation is presented based on a large-scale, real-world dataset.
      32Scopus© Citations 14
  • Publication
    Using Case-Based Reasoning to Predict Marathon Performance and Recommend Tailored Training Plans
    Training for the marathon, especially a first marathon, is always a challenge. Many runners struggle to find the right balance between their workouts and their recovery, often leading to sub-optimal performance on race-day or even injury during training. We describe and evaluate a novel case-based reasoning system to help marathon runners as they train in two ways. First, it uses a case-base of training/workouts and race histories to predict future marathon times for a target runner, throughout their training program, helping runners to calibrate their progress and, ultimately, plan their race-day pacing. Second, the system recommends tailored training plans to runners, adapted for their current goal-time target, and based on the training plans of similar runners who have achieved this time. We evaluate the system using a dataset of more than 21,000 unique runners and 1.5 million training/workout sessions.
      241Scopus© Citations 19