Physics-inspired techniques for segmenting human self-reported weight loss time series

Using techniques from statistical physics, physicists have modeled and analyzed human phenoma varying from academic citation rates to disease spreading to vehicular traffic jams. The last decade's explosion of digital information and the growing ubiquity of smartphones has led to a wealth of human self-reported data. Unfortunately, the medical community has traditionally eschewed self-reported data due to concerns about dishonesty and the complexities of analyzing data that exhibits non-uniform sampling and statistically significant but physically insignificant correlations. How do we move beyond summary statistics? In this talk I present our physically motivated techniques for segmenting and characterizing individual human weight loss time series and contrast them with more traditional statistically and algorithmically motivated techniques.