Levenshtein distance-based regularity measurement of circadian rhythm patterns

Taek Lee, Hoh Peter In

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


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.

Original languageEnglish
Pages (from-to)4358-4366
Number of pages9
JournalJournal of Theoretical and Applied Information Technology
Issue number18
Publication statusPublished - 2017 Sept 30

Bibliographical note

Funding Information:
The corresponding author of this paper is Hoh Peter In (hoh_in@korea.ac.kr), and we declare that this paper is an improved version of our preliminary study [14] that had been previously introduced in a conference. This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (grant number : HI14C3212).


  • Activity tracker
  • Anomaly detection
  • Circadian rhythm
  • Pattern modeling
  • Wearable device

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'Levenshtein distance-based regularity measurement of circadian rhythm patterns'. Together they form a unique fingerprint.

Cite this