Using periodicity intensity to detect long term behaviour change

ABSTRACT

This paper introduces a new way to analyse and visualize quantified-self or lifelog data captured from any lifelogging device over an extended period of time. The mechanism works on the raw, unstructured lifelog data by detecting periodicities, those repeating patters that occur within our lifestyles at different frequencies including daily, weekly, seasonal, etc. Focusing on the 24 hour cycle, we calculate the strength of the 24-hour periodicity at 24-hour intervals over an extended period of a lifelog. Changes in this strength of the 24-hour cycle can illustrate changes or shifts in underlying human behavior. We have performed this analysis on several lifelog datasets of durations from several weeks to almost a decade, from recordings of training distances to sleep data. In this paper we use 24 hour accelerometer data to illustrate the technique, showing how changes in human behavior can be identified.

References

1. Aiden R. Doherty, Alan F. Smeaton. 2008. Automatically segmenting lifelog data into events. In Proceedings of the Ninth International Workshop on Image Analysis for Multimedia Interactive Services, (WIAMIS'08). 20--23. IEEE.
2. Aiden R. Doherty, Niamh Caprani, Ciarán O'Conaire, Vaiva Kalnikaite, Cathal Gurrin, Noel E. O'Connor and Alan F. Smeaton. 2011. Passively recognising human activities through lifelogging. Computers in Human Behavior, 27, 5:1948--1958.
3. Changgui Gu, Claudia P. Coomans, Kun Hu, Frank A. J. L. Scheer, H. Eugene Stanley, Johanna H. Meijer. 2015. Lack of exercise leads to significant and reversible loss of scale invariance in both aged and young mice. In Proceedings of the National Academy of Sciences 02/2015; 112, 8: 2320--2324. http://dx.doi.org/10.1073/pnas.1424706112
4. Cathal Gurrin, Alan F. Smeaton, and Aiden R. Doherty. 2014. LifeLogging: Personal Big Data. Found. Trends Inf. Retr. 8, 1: 1--125. http://dx.doi.org/10.1561/1500000033
5. Feiyan Hu, Alan F. Smeaton and Eamonn Newman. 2014. Periodicity detection in lifelog data with missing and irregularly sampled data. In Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 16--23, Belfast, N. Ireland, November 2--5.
6. Kun Hu, Eus J. W. Van Someren, Steven A. Shea, and Frank A. J. L. Scheer. 2009. Reduction of scale invariance of activity fluctuations with aging and Alzheimer's disease: Involvement of the circadian pacemaker. Proceedings of the National Academy of Sciences 106, 8: 2490--2494. http://dx.doi.org/10.1073/pnas.0806087106
7. Pil Ho Kim and Fausto Giunchiglia. 2012. Life logging practice for human behavior modeling. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2873--2878. http://dx.doi.org/10.1109/ICSMC.2012.6378185
8. J. D. Scargle. 1982. Studies in astronomical time series analysis. II - Statistical aspects of spectral analysis of unevenly spaced data. Astrophysical Journal, 263: 835--853.
9. Peng Wang and Alan F. Smeaton. 2013. Using visual lifelogs to automatically characterise everyday activities. Information Sciences 230: 147--161.

Index Terms

• Information systems

  • Information systems applications

    • Multimedia information systems