期刊
IEEE NETWORK
卷 34, 期 3, 页码 178-185出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MNET.011.1900338
关键词
Neurons; Predictive models; Support vector machines; Real-time systems; Biological system modeling
类别
资金
- NSERC-SPG
- Canada Research Chairs Program
- NSERC-CREATE TRANSIT Funds
- NSERC-DISCOVERY
In recent years, ML-based models are gaining enormous attention from both the automotive industry and academia to support IoVs. Through the accurate prediction of traffic/road conditions, various safety and infotainment applications can efficiently utilize the network entities and enhance the quality of service. Topology control and mobility management protocols in IoVs, among others, would achieve higher efficiency through the support of real-time traffic flow forecasting. However, the current research trend on improving prediction accuracy refrains from answering the essential question of whether ML-based prediction schemes are suitable for real-time traffic prediction. To answer this question, a thorough extensive study to evaluate the efficiency of prediction- based traffic flow schemes is required. In this article, we investigate the effectiveness of various ML-based prediction models by considering both the prediction accuracy and computational time cost. Accordingly, we present rigorous quantitative analysis to identify the important factors that may restrict the use of ML-based prediction models to support real-time services in the IoV environment.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据