Towards a Transfer Learning-Based Approach for Monitoring Fitness Levels

摘要: The mobile ecosystem is rife with applications that aim for individuals to persue a more active and healthier lifestyle. Applications vary from simple diaries track your weight, calorie intake or blood glucose values towards advanced ones offer health recommendations while monitoring fitness levels during workouts throughout the day. Leveraging machine learning techniques popular approach recognize non-trivial activities, such as different types of sports. However, face time consuming training phase before they become practical. In this work, we report on our feasibility analysis transfer way apply learned models one individual another, various feature variabilities may jeopardize applicability learning.