A study using artificial intelligence to analyze smartphone data successfully identified behaviors indicating cannabis intoxication with up to 90% accuracy. The technology discreetly utilizes various smartphone sensors, capturing over 100 different behavioral and environmental factors, and could potentially aid cannabis users in making safer decisions while under the influence of cannabis.
The latest research using artificial intelligence to predict cannabis intoxication based on biometric data from smartphone sensors is astonishing in its precision.
For more news like this, download our free cannabis news app.
AI Research for Detecting Cannabis Use
Researchers from the Stevens Institute of Technology recently published a study in the journal Drug and Alcohol Dependence, which analyzed data from the phones of cannabis users and non-users. Cannabis users independently reported consumption times and intoxication levels, classifying it on a simple scale of 1 to 10.
Comparing over 100 different factors, such as time, location, noise level, and movement recorded by the phones of both groups, scientists argue that they noticed significant differences when cannabis users were under its influence. These differences would be difficult to capture with ordinary human senses. Similar technology has been used before to study the effects of alcohol and other substances.
The AI Utilizes Smartphone Sensors
“Smartphones with mobile sensors are ubiquitous and can discreetly monitor our behavior,” says Sang Won Bae, an assistant professor at the Stevens Institute of Technology, leading the study. “They are not distracting, there’s no need to wear them, and the data collected by them can help avoid mistaken decisions under the influence of substances.”
Potential in Detecting Psychoactive Effects of Cannabis
The observed differences in the data were used to train a machine learning model. It is possible that in the future, it will allow for the identification of people under the influence of cannabis in real-time based on information from phone sensors. Possible interventions include notifications suggesting the use of transportation services. Researchers found that their AI model could predict cannabis intoxication with 90% accuracy after training on phone data.
“The goal is to predict people’s behavior to support them in times of physical or mental impairment,” says Bae.
Although the study claimed that it could predict cannabis intoxication based only on phone data with 67% accuracy, after correlating with temporal data (day of the week, time of day), accuracy increased to 90%. A scale from 0 to 10 was used to determine the level of intoxication.
“We tested the importance of temporal features compared only to data from smartphone sensors,” says the report, indicating that the AI model could predict intoxication with 60% accuracy based solely on temporal factors.
Limitations of the Artificial Intelligence Study
Despite promising results, the study had certain limitations, such as a small sample of participants or potential errors in cannabis users’ self-reporting.
This is not the first attempt to detect real-time cannabis intoxication. Most blood, saliva, or urine tests cannot predict whether a person is under the influence of cannabis; they only detect recent consumption. Companies are working on eye movement analysis technology to detect intoxication, but they have not yet been introduced to the market.
“This artificial intelligence study showed that using data from smartphone sensors to detect subjective cannabis intoxication in a natural environment among young adults is possible,” says the report.
However, the results are preliminary, and further artificial intelligence research is needed. The findings of this study are still in the initial phase, and broader-scale research is required for machine learning models to better understand the mechanisms characterizing people under the influence of cannabis.
DISCLAIMER: This article was written by a third-party contributor and does not reflect the opinion of Hemp.im, its management, staff, or its associates. Please review our disclaimer for more information.
This article may include forward-looking statements. These forward-looking statements generally are identified by the words “believe,” “project,” “estimate,” “become,” “plan,” “will,” and similar expressions. These forward-looking statements involve known and unknown risks as well as uncertainties, including those discussed in the following cautionary statements and elsewhere in this article and on this site. Although the company may believe that its expectations are based on reasonable assumptions, the actual results that the company may achieve may differ materially from any forward-looking statements, which reflect the opinions of the management of the company only as of the date hereof. Additionally, please make sure to read these important disclosures.
First published in Fakty Konopne, a third-party contributor translated and adapted the article from the original. In case of discrepancy, the original will prevail.
Although we made reasonable efforts to provide accurate translations, some parts may be incorrect. Hemp.im assumes no responsibility for errors, omissions or ambiguities in the translations provided on this website. Any person or entity relying on translated content does so at their own risk. Hemp.im is not responsible for losses caused by such reliance on the accuracy or reliability of translated information. If you wish to report an error or inaccuracy in the translation, we encourage you to contact us.