Earticle

초록

영어

Recently, cloud computing technology is rapidly growing at a faster rate offering cloud-based driver profiling applications with lower latency. In this study, we have proposed a computational efficient cloud-based architecture for the deployment of driver profiling deep learning algorithms. In order to validate the efficacy of the proposed architecture, we have evaluated the performance of the proposed deep learning architecture for the recent driver behavior identification using time series sensor data. We have utilized an Amazon web service-based cloud computing solution for the deployment of the proposed architecture. The experimental results show that the proposed architecture improves end-to-end latency by 3.1 times compared to the traditional method.

목차

Abstract
1. Introduction
2. Related Works
3. Proposed Method
4. Preliminary Experimental Result
5. Conclusion
Acknowledgement
References

키워드

저자

• 메디 피라한데 [ Mehdi Pirahandeh | Department of Electrical and Computer Engineering, Inha University, South Korea ]
• 김덕환 [ Deok-Hwan Kim | Department of Electrical and Computer Engineering, Inha University, South Korea ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  한국차세대컴퓨팅학회 학술대회

• 간기

  반년간

• 수록기간

  2021~2025

• 십진분류

  KDC 566 DDC 004