Probability Of Drinking Research Articles

Drinking event detection on a sensing wristband using machine learning

Adequate hydration is important for one’s health, but many people do not consume sufficient fluids. By constantly monitoring fluid intake, we gain information that can be extremely useful in dealing with unhealthy drinking habits. This paper deals with the problem of developing a machine learning method for drinking detection, intended for use on an edge device, with a specific focus on power consumption. The proposed approach is based on data from inertial sensors built into a practical, non-invasive wrist-worn device that monitors wrist movement throughout the day and automatically detects drinking events. It ensures low energy consumption by triggering the machine learning only when the probability of drinking is high, as well as by other energy saving measures. To develop and validate our methods, we collected data from 19 participants, which resulted in 135 hours of data, of which 2 hours and 30 minutes correspond to drinking activities. The algorithm was thoroughly assessed through both offline testing and by running the algorithm directly on the wristband in real life. During the offline evaluation, we obtained a precision of 94.5 %, a recall of 84.9 %, and an F1 score of 89.4 %. Testing in real life demonstrated a precision of 74.5 % and a recall of 89.9 %. Additionally, the energy efficiency analysis showed that our proposed technique for triggering the drinking detection method reduced the battery power consumption during the periods of inactivity by a factor of 5.8 compared to continuously monitoring for drinking events.

A Multiyear Daily Process Examination of Social Anxiety, Alcohol-Outcome Expectancies and Alcohol Use Among College Students

Background. Expectancies of the positive and negative effects of drinking have been posited to be important moderators of the association between social anxiety and alcohol use. However, investigations of these interactive effects have not examined the moderating role of within-person daily variation in such expectancies. Methods. We used a multi-year micro-longitudinal design to examine the interactive relationship between social anxiety and daily changes in alcohol-outcome expectancies in predicting later-day drinking among college students (N = 537; 51.7% female). In a baseline survey participants reported on their social anxiety, then approximately two weeks later, they reported daily for 30 days on their tension reduction and impairment alcohol-outcome expectancies and their drinking level. We repeated this procedure for up to three additional years. Results. The probability of drinking and the amount consumed were higher on days characterized by high levels of tension-reduction and impairment expect...

The impact of minimum legal drinking age laws on alcohol consumption, smoking, and marijuana use: Evidence from a regression discontinuity design using exact date of birth

This paper uses a regression discontinuity design to estimate the impact of the minimum legal drinking age laws on alcohol consumption, smoking, and marijuana use among young adults. Using data from the National Longitudinal Survey of Youth (1997 Cohort), we find that granting legal access to alcohol at age 21 leads to an increase in several measures of alcohol consumption, including an up to a 13 percentage point increase in the probability of drinking. Furthermore, this effect is robust under several different parametric and non-parametric models. We also find some evidence that the discrete jump in alcohol consumption at age 21 has negative spillover effects on marijuana use but does not affect the smoking habits of young adults. Our results indicate that although the change in alcohol consumption habits of young adults following their 21st birthday is less severe than previously known, policies that are designed to reduce drinking among young adults may have desirable impacts and can create public health benefits.

Adolescents, bush parties and drinking-driving.

We describe the prevalence of bush party (an outdoor gathering of youth) attendance and examine predictors of attendance and of driving after drinking at bush parties. The 1995 Ontario Student Drug Use Survey (OSDUS) data on students (n = 1,853) in schools across the province in grades 7, 9, 11 and 13 are employed to estimate prevalence of bush party attendance within the previous 12 months. The 1994 Graduated Licensing Study (GLS), a multi-community survey of drivers (n = 1,157, 53.6% male) in grades 11 and 12 in Ontario, data are employed to study predictors of attendance and of drinking-driving. Based on the OSDUS, the prevalence of bush party attendance is 37.6%. Based on the GLS, 38.4% attended bush parties, and among attenders 71.5% drank at bush parties, 63.5% observed drinking-driving, 16.1% rode with a drinking-driver and 16.6% drove after drinking at bush parties. Logistic regression reveals that attendance at bush parties is positively associated with number of other places alcohol was consumed, tobacco use, number of alcohol-related problems, number of kilometers ever driven, sensation seeking and northern residents. Among attenders who drank at bush parties, males were three and a half times more likely to drive after drinking at a bush party, and the probability of drinking and driving increased with the number of other drugs used. Despite important differences in the design and purpose of the two surveys, both indicate that bush party attendance is prevalent among adolescents. Driving after drinking at these events is common and warrants community action.

Drinking, Driving, and the Price of Automobile Insurance

This study describes premium penalties imposed by insurers for drunk driving and other chargeable accidents, assesses why variations in premiums for drivers with clean records and adverse records differ across states and insurers, and determines the effect of imposing penalties on persons convicted of drunk driving. There are significant differences among insurers in treatment of violators, both in underwriting and in premium setting-which are in part attributable to state policies, such as imposition of take-all-comer rules. Imposing premium surcharges for a charge of drunk driving has a significant deterrent effect on the probability of drinking and driving.

Drinking among rural youth: the dynamics of parental and peer influence.

The data reported here are from a study of all eighth and and twelfth grade students ih three counties of north central Idaho. Questions were administered in the classroom setting by the senior author and an assistant. At least 16% of eighth graders and 34% of twelfth graders in north central Idaho counties drink frequently. A much higher proportion drink occasionally. Drinking behavior of parents and closeness of relationship with parents are strongly related to drinking patterns. An even stronger relationship exists between drinking and peer relationships. A high degree of problem-related communication with parents is associated with lower probability of drinking, while low problem-related communication with peers is associated with less frequent drinking.

Effects of number of pellets per food delivery and pellet sucrose composition on schedule-induced drinking

Four groups of four rats were tested on a fixed-time (FT 60-sec) schedule in which one, three, or five pellets per food delivery and 0%, 8%, 16%, and 32% sucrose pellets were factorially combined. The results showed no statistically significant differences in water intake associated with sucrose content of the pellets, but did show a significant inverse relationship between water intake and number of pellets given per reinforcement. This latter finding was interpreted as a result of the direct relationship in the rat between total number of reinforcement opportunities and probability of drinking. This relationship was suggested to be an important dependent variable in studies that measure and attempt to account for collateral fluid ingestion.