Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account

Shulou

Stanford University study: smartphone recording can tell whether a person is drunk or not, with an accuracy of 98%

2025-04-03 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >

Share

Shulou(Shulou.com)11/24 Report--

CTOnews.com, Nov. 9 (Xinhua) A recent study by Stanford University found that smartphones have a 98% chance of accurately identifying when a person is drunk through voice patterns.

The study tested 18 participants (72% of men, aged 21-62), whose voice patterns were analyzed by sensors to see if they were drunk. The study is published in the journal Journal of Studies on Alcohol and Drugs.

Brian Suffoletto, an associate professor of emergency medicine at Stanford University, said he was surprised by the accuracy of the results, adding that further research was needed to confirm the validity of the findings.

He said the findings could help reduce future road injuries and deaths caused by drunk driving, adding: "although we are not the first team to study changes in language characteristics during drunkenness, I firmly believe that our accuracy stems from our application of cutting-edge technologies in signal processing, acoustic analysis and machine learning."

Tuyuan PixabayCTOnews.com learned from the study that in this study, participants took a certain dose of alcohol according to their body weight and had to drink it within an hour. They then underwent a series of tongue twister tests. Participants were required to repeat the content loudly every hour for up to seven hours, while their voices were recorded by their smartphones.

Before drinking, the researchers also measured the participants' breath alcohol levels and recorded tongue twisters. After that, the breath alcohol content was tested every 30 minutes for 7 hours.

After that, the researchers analyzed the speaker's voice by software, checked the frequency and tone parameters at one-second intervals, constructed a support vector machine model to detect drunkenness (defined as respiratory alcohol concentration > 0.08%), compared the baseline speech spectrum features with each subsequent time point, and checked the accuracy of 95% confidence interval (CI).

Professor Suffoletto says a combination of steps and texting can be used to determine how drunk a person is. He added that the results of the study can be used to determine whether a person is drunk or not through mobile phone recording, thus providing timely intervention.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information

Wechat

© 2024 shulou.com SLNews company. All rights reserved.

12
Report