Physiological data analysis -- alcohol drinking prediction using statistical and deep learning methods
Metadata[+] Show full item record
Alcohol craving can cause many problems for people's life. However, there are very few related works doing alcohol prediction based on physiological data, except some from our lab. The goal of this research is to predict whether people have alcohol drinking or not from real physiological data in order to help them with drinking problems. The raw physiological data in this work include skin temperature, heart rate, galvanic skin response (GSR), steps, and calories. The data was collected from 29 users with basic watch and the reading frequency is one record per minute. In this thesis, three data analysis pipelines, drinking record prediction pipeline, drinking episode statistical pipeline, and drinking episode deep learning pipeline, are implemented. The drinking record prediction pipeline is doing prediction based on oneminute record. The drinking episode pipeline is doing prediction based on thirty-minute episode. Statistical features are extracted from the thirty-minute data blocks. The drinking episode deep learning pipeline is doing prediction based on thirty-minute episode as well. In this deep learning pipeline, one dimensional signal is converted to spectrum graph. Then use Cifar 10 model to extract deep learning features from the spectrum graph. After that apply machine learning methods on the deep learning features to do the classification. Within-user and cross user experiments are conducted in this thesis because different users may have different reaction to alcohol. Different models are found for different users and general model is discovered for cross-users. Balanced data is used for training and testing, so the baseline accuracy is 50 percent. The accuracy for within-user is up to 88.89 Percent and the accuracy for cross-user is 75.68 Percent, which indicates that the withinuser result is much better than cross-user result. In order to find the most significant feature in alcohol drinking prediction, experiments are also conducted on skin temperature only features, heart rate only features, and GSR only features. The results show that heart rate contributes most in the alcohol drinking prediction.