Statistically Speculating on the Source of Sneezes and Sniffles
summary
One year of self‑reported antihistamine usage plus sneeze counts and GPS traces feed a homemade iPhone logging app and HDF5/pandas pipeline; external features include London Air, weather, MyFitnessPal and commute logs. Logistic models (scikit‑learn, statsmodels) only predict use on time‑subsets (home vs air‑conditioned office), with humidity emerging as a driver and loratadine effective after ~2 hours; sample starts at one person, tools and code are open source and the methodology is reproducible.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 1:03Motivation and goals
- 3:31Allergic vs non-allergic rhinitis
- 6:45Ridim app data
- 8:30Sneeze and antihistamine logs
- 10:13Sneezing patterns
- 12:00Sneezes and antihistamines
- 13:30Antihistamine effectiveness
- 15:38Antihistamine usage model
- 16:41Weather and pollution data
- 19:29Logistic regression models
- 21:18First model findings
- 23:02Refining with controlled tests
- 24:23Data tools workflow
- 25:28Future experiments
- 26:54Sensors and future data
- 27:35Summary and next steps
- 28:24Q&A
related talks
06mPredicting Subjective Measures of Social Anxiety from Sparsely Collected Mobile Sensor Data
26mMachine Learning for Personalised Health
44mQuantified Self: Analyzing the Big Data of our Daily Life
06mOne More Bite? Inferring Food Consumption Level of College Students Using Smartphone Sensing and ...
27mHARSHA URLAM & SWETA SINGH at Cypher 2017
06mExamining the Social Context of Alcohol Drinking in Young Adults with Smartphone Sensing
33mCOVIDcast: An ecosystem for COVID-19 tracking and forecasting
06mBreathTrack: Detecting Regular Breathing Phases from Unannotated Acoustic Data Captured by a ...