scholarly journals Injury prediction algorithm for rear‐seat occupants in advanced automatic crash notification systems

2021 ◽  
Author(s):  
Ying Lu ◽  
Yufa Liu ◽  
Yu Shu ◽  
Yuezhou Yin
Keyword(s):  
Rear Seat ◽  
Prediction Algorithm ◽  
Injury Prediction

Serious injury prediction algorithm based on large-scale data and under-triage control

2017 ◽  
Vol 98 ◽  
pp. 266-276 ◽  
Author(s):  
Tetsuya Nishimoto ◽  
Kosuke Mukaigawa ◽  
Shigeru Tominaga ◽  
Nils Lubbe ◽  
Toru Kiuchi ◽  
...  
Keyword(s):  
Large Scale ◽  
Prediction Algorithm ◽  
Injury Prediction ◽  
Large Scale Data ◽  
Serious Injury ◽  
Scale Data

Study on Australia Injury Prediction Algorithm using Machine Learning

2020 ◽  
Vol 2020 (0) ◽  
pp. J02206
Author(s):  
Syunsuke UEKI ◽  
Nishimoto TETHUYA ◽  
Giulio PONTE
Keyword(s):  
Machine Learning ◽  
Prediction Algorithm ◽  
Injury Prediction

Effect of Using Myopia Prediction Algorithm

2019 ◽  
Author(s):  
Keyword(s):  
Prediction Algorithm

Fast inter prediction algorithm in enhancement layer of quality scalable video coding

2011 ◽  
Vol 25 (2) ◽  
pp. 153-158 ◽  
Author(s):  
Yuanyuan Huang ◽  
Dayong Wang ◽  
Jianping Li
Keyword(s):  
Video Coding ◽  
Scalable Video Coding ◽  
Prediction Algorithm ◽  
Scalable Video ◽  
Inter Prediction ◽  
Enhancement Layer

PROCESS PREDICTION ALGORITHM BASED ON ALTERNATIVE MODELS

2020 ◽  
Vol 73 ◽  
pp. 97-104
Author(s):  
V. K. Klochko ◽  
Keyword(s):  
Prediction Algorithm ◽  
Alternative Models ◽  
Process Prediction

Is JUUL marketing to kids on social media? Analysis of JUUL Twitter Followers� Age (Preprint)

2018 ◽  
Author(s):  
Annice Kim ◽  
Robert Chew ◽  
Michael Wenger ◽  
Margaret Cress ◽  
Thomas Bukowski ◽  
...  
Keyword(s):  
Social Media ◽  
Application Programming Interface ◽  
Media Analysis ◽  
Prediction Algorithm ◽  
Social Media Networks ◽  
Verification Methods ◽  
Twitter Account ◽  
Application Programming ◽  
Age Verification ◽  
Age Category

BACKGROUND JUUL is an electronic nicotine delivery system (ENDS) resembling a USB device that has become rapidly popular among youth. Recent studies suggest that social media may be contributing to its popularity. JUUL company claims their products are targeted for adult current smokers but recent surveillance suggests youth may be exposed to JUUL products online. To date, there has been little attention on restricting youth exposure to age restricted products on social media. OBJECTIVE The objective of this study was to utilize a computational age prediction algorithm to determine the extent to which underage youth are being exposed to JUUL’s marketing practices on Twitter. METHODS We examined all of @JUULvapor’s Twitter followers in April 2018. For followers with a public account, we obtained their metadata and last 200 tweets using the Twitter application programming interface. We ran a series of classification models to predict whether the account following @JUULvapor was an underage youth or an adult. RESULTS Out of 9,077 individuals following @JUULvapor Twitter account, a three-age category model predicted that 44.9% are 13 to 17 years old (N=4,078), 43.6% are 18 to 24 years old (N=3,957), and 11.5% are 25 years old or older (N=1,042); and a two-age category model predicted that 80.6% (N=7,313) are under 21 years old. CONCLUSIONS Despite a disclaimer that followers must be of legal age to purchase tobacco products, the majority of JUUL followers on Twitter are under age. This suggests that ENDS brands and social media networks need to implement more stringent age-verification methods to protect youth from age-restricted content.

Decreased routing path based on a dynamic prediction algorithm for mobile sink in WSN

2007 ◽  
Author(s):  
Weiwei Jiao ◽  
Dongliang Xie ◽  
Wenbin Yu ◽  
Jian Ma ◽  
Shiduan Cheng
Keyword(s):  
Mobile Sink ◽  
Prediction Algorithm ◽  
Dynamic Prediction
Sign in / Sign up

Export Citation Format

Share Document