Towards a Computational Framework for Automated Discovery and Modeling of Biological Rhythms from Wearable Data Streams

  title={Towards a Computational Framework for Automated Discovery and Modeling of Biological Rhythms from Wearable Data Streams},
  author={Runze Yan and Afsaneh Doryab},
  • Runze Yan, A. Doryab
  • Published in IntelliSys 7 August 2021
  • Biology, Computer Science
Modeling biological rhythms helps understand the complex principles behind the physical and psychological abnormalities of human bodies, to plan life schedules, and avoid persisting fatigue and mood and sleep alterations due to the desynchronization of those rhythms. The first step in modeling biological rhythms is to identify their characteristics, such as cyclic periods, phase, and amplitude. However, human rhythms are susceptible to external events, which cause irregular fluctuations in… Expand
1 Citations

Tables from this paper

From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
This work presents a novel taxonomy system with two major components that can specify and classify apps/systems from aspects of the life-cycle of mHealth Sensing: (1) Sensing Task Creation & Participation, (2) Health Surveillance & Data Collection, and (3) Data Analysis & Knowledge Discovery. Expand


Modeling Individual Cyclic Variation in Human Behavior
Applying Cyclic Hidden Markov Models for detecting and modeling cycles in a collection of multidimensional heterogeneous time series data to two real-world health-tracking datasets yields important insights including which symptoms to expect at each point during the cycle. Expand
Concepts in human biological rhythms
This review presents phenomena thai, mainly characteristic of and unique to - human chronobiology, and which cannot be fully explained by concepts and models drawn from laboratory experiments, and presents a genetic model to explain interindividual differences in the period of biological rhythms in certain conditions. Expand
Analysis of Nonstationary Time Series for Biological Rhythms Research
  • T. Leise
  • Computer Science, Medicine
  • Journal of biological rhythms
  • 2017
Some methods for assessing the rhythmic properties of time series, including tests of whether a time series is indeed rhythmic are described, using simulated and real time series. Expand
Automatic detection of social rhythms in bipolar disorder
Automatic smartphone sensing is a feasible approach for inferring rhythmicity, a key marker of wellbeing for individuals with bipolar disorder. Expand
Social (media) jet lag: how usage of social technology can modulate and reflect circadian rhythms
Examining the interplay between biological rhythms and technology-mediated social interactions, it is found that technology may both modulate and reflect circadian rhythms. Expand
A new method for change-point detection developed for on-line analysis of the heart beat variability during sleep
We present a novel scaling-dependent measure for times series analysis, the progressive detrended fluctuation analysis (PDFA). Since this method progressively includes and analyzes all data points ofExpand
The search for rhythmicity in biological time-series.
  • J. T. Enright
  • Mathematics, Medicine
  • Journal of theoretical biology
  • 1965
The periodogram has been used for a re-examination of some of the original biological data which led to the hypothesis of an extrinsic origin for persistent rhythmicity, and re-analyses indicate that none of 17 examined data sets provides convincing evidence for accurate tidal components, and that the presence of accurate diurnal components represents a reasonable interpretation for only 3 data sets out of 17. Expand
Strengths and Limitations of Period Estimation Methods for Circadian Data
Six techniques for determining period in the BioDare system are reviewed, the principles behind each are explained, and guidelines on which algorithms are most appropriate for which data types are provided, and recommendations on experimental design to extract optimal data for analysis are provided. Expand
Cosinor-based rhythmometry
  • G. Cornelissen
  • Computer Science, Medicine
  • Theoretical Biology and Medical Modelling
  • 2014
The extended cosinor has been further developed for the analysis of long time series, focusing both on rhythm detection and parameter estimation, and ways of dealing with non-stationary data are presented. Expand
Modeling Biobehavioral Rhythms with Passive Sensing in the Wild
This study studies the feasibility of detecting rhythms in data that is passively collected from Fitbit devices and using the obtained model parameters to predict readmission risk after pancreatic surgery, producing a model of individual patients' rhythms for each stage of treatment that is predictive of readmission. Expand