IntoxiGait Deep Learning: Investigating deep learning to predict intoxication levels using smartphones and smartwatches
PúblicoAlcohol abuse has been a pervasive problem worldwide, causing 88,000 annual deaths. Recently, several projects have attempted to estimate a users level of intoxication by measuring gait using mobile sensors. The goal of this project was to compare a deep learning approach to previous methods to predict the blood alcohol concentration of a user by training a convolutional neural network and creating a mobile app which could accurately determine intoxication level. We gathered data from 38 participants over the course of 12 weeks, collecting accelerometer and gyroscope data simultaneously from both a smartwatch and smartphone. Our neural networks accuracy is roughly 64% on the test set and 69% on the training set into 5 BAC ranges for an input containing two seconds of data.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Creator
- Publisher
- Identifier
- E-project-032318-145400
- Advisor
- Year
- 2018
- Date created
- 2018-03-23
- Resource type
- Major
- Rights statement
Las relaciones
- En Collection:
Elementos
Elementos
Miniatura | Título | Visibilidad | Embargo Release Date | Acciones |
---|---|---|---|---|
|
IntoxiGait_Deep_Learning_Final_Report.pdf | Público | Descargar |
Permanent link to this page: https://digital.wpi.edu/show/1544bq57j