IMPLEMENTING COMPREHENSIVE CLOUD-BASED PLATFORMS FOR NATURALISTIC DRIVING STUDIES
- 提供方法
- 本サイト上にてダウンロード・閲覧可
- 形態
- 価格
- 一般価格(税込):¥1,100 会員価格(税込):¥880
- 文献番号
- 20219010
- 文献・情報種別
- その他の国際会議
- 掲載ページ
- 1-6(Total 6 p)
- 発行年月
- 2021年 9月
- 出版社
- (公社)自動車技術会
- 言語
- 英語
書誌事項
著者(英) | 1) Archana Venkatachalapathy, 2) Aditya Raj, 3) Jennifer Merickel, 4) Anuj Sharma |
---|---|
勤務先(英) | 1) Iowa State University, 2) Iowa State University, 3) University of Nebraska Medical Center, 4) Iowa State University |
抄録(英) | Naturalistic driving studies are a sought-after method to research driving behavior. In a Naturalistic Driving Study, drivers are requested to drive as they typically would while sensors installed in their vehicle collect large amounts of detailed data on driving patterns (e.g., speed, acceleration, throttle, GPS) that can be merged with roadway, weather, lighting, and other databases. Given the large amount of complex data collected, there is a need for robust data systems for storing, mining, visualizing, and analyzing this big naturalistic data. We designed a comprehensive cloud-based AI platform (Deep Insight) for data management, modeling, and enhanced annotations for naturalistic driving data to address this need. The platform capitalizes on Amazon Web Services, hosting a repository of public and privately collected NDS datasets with tool integration for data annotation and machine learning modeling that permits data analysis and inference. This end-to-end framework provides effective and reliable tools for storing, processing, annotating, modeling, and visualizing NDS datasets. Critically, it permits a partially automated analysis pipeline that reduces the manual labor and time required to process and model large datasets. Integration with RocketML and dockers allows users to train and deploy machine learning models efficiently without dependency on the computing environment. This cloud-based platform offers a wide range of benefits in terms of cost, access, scalability, and security, aiming to create a one-stop destination for analyzing naturalistic driving data and studying driver behavior. 翻訳 |