Levenshtein distance-based regularity measurement of circadian rhythm patterns

In this paper, we introduce an algorithm and an application for modeling user’s circadian rhythm with activity trackers, also known as smart bands (e.g., Misfit Shine or Fitbit). The proposed algorithm detects anomalies in the user 's circadian rhythm pattern (i.e., activity pattern of 24-hour cycle). Diurnal biorhythm data were collected using smart bands and the data were analyzed using Levenshtein distance. We evaluate the performance of the proposed algorithm to distinguish between ordinary days and abnormal days. During the experiment period, the users recorded the mood, fatigue, and event occurrence of the day, and evaluated the performance of the proposed algorithm through comparison with user’s recorded opinions. In the user study, the proposed method detected normal or abnormal patterns of life rhythm with 86% accuracy.