楽 WALK : スマートフォンを用いた歩行時心拍数推定システム RAKUWALK : heart rate prediction system during walking with smartphone

Walking is effective exercise for maintaing and promoting healthy life, but high perceived exertion during walking may be counterproductive. For effective and continuous walking, it is necessary to select a walking route suitable for individual physical ability. Though perceived exertion during walking can be estimated by heart rate, it is costly for a user to equip with a special device such as a heart rate monitor. In this paper, aiming to realize a health-conscious walking navigation system that recommends a walking route with minimal perceived exertion satisfying constraints of calorie consumption and walking hours, we propose a system called RAKUWALK which estimates perceived exertion during walking with only available functions of a smartphone. For this purpose, we build a perceived exertion model which predicts the heart rate from walking data including acceleration and walking speed based on machine learning. We applied the proposed method to actual walking data and confirmed that the method estimates the heart rate within 11bpm.