Predictive Cruise Control with Private Vehicle-to-Vehicle Communication for Improving Fuel Consumption and Emissions

Zhang, Xueru; Huang, Chunan; Liu, Mingyan; Stefanopoulou, Anna G.; Ersal, Tulga

doi:10.1109/mcom.001.1900146

Cited by 11 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In cruise control and platooning services, provide privacy guarantees for users while maintaining the utility of a predictive controller is critical. Zhang et al designed a privacy preserving scheme to protect the platoon header's privacy for the application of predictive speed planning scenario [128]. To achieve differential privacy of the broadcast data from the platoon header, the convex combination of the previous broadcast data and the fresh true date will be generated as the first step.…”

Section: Security In Cellular Based V2x Communicationsmentioning

confidence: 99%

Recent Advances and Challenges in Security and Privacy for V2X Communications

Huang

Fang

Qian

et al. 2020

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

In recent studies, vehicular networks have been considered as a promising solution to achieve better traffic management and to improve the driving experience of drivers. In vehicular networks, vehicle-to-everything (V2X) services, e.g. onroad traffic information exchange and location-based services, are provided to facilitate road safety for vehicles and traffic management for the relevant authorities. Dedicated Short Range Communications is specifically designed for V2X communications, and recently the cellular network has shown great potential to support V2X with better performance and more applications. Due to the wireless nature of V2X communications, how to secure V2X communications and guarantee the privacy of users are great challenges that have hampered the implementation of vehicular services. Many solutions have been proposed by researchers in last two decades. In this paper, we present a comprehensive survey on the state-of-the-art solutions concerning security and privacy for V2X communications. For security, detailed discussions on cryptography based schemes and trust based schemes are provided. For privacy, we summarize and compare general solutions in preserving identity privacy and location privacy. Cellular based V2X communications have shown many advantages over DSRC, and the oncoming fifth-generation cellular technology is going to provide more possibilities to V2X. Thus, security architectures and solutions for cellular based communications are also illustrated and discussed. Finally, we summarize the remaining challenges and point out future research directions.

show abstract

Section: Security In Cellular Based V2x Communicationsmentioning

confidence: 99%

Recent Advances and Challenges in Security and Privacy for V2X Communications

Huang

Fang

Qian

et al. 2020

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…The information exchanged over the iterative process gives rise to privacy concerns if the local training data contains sensitive information such as medical or financial records, web search history, and so on [2]- [5]. It is therefore highly desirable to ensure such iterative processes are privacy-preserving.…”

Section: Introductionmentioning

confidence: 99%

Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms

Zhang

Khalili

Liu

2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

View full text Add to dashboard Cite

Alternating direction method of multiplier (ADMM) is a powerful method to solve decentralized convex optimization problems. In distributed settings, each node performs computation with its local data and the local results are exchanged among neighboring nodes in an iterative fashion. During this iterative process the leakage of data privacy arises and can accumulate significantly over many iterations, making it difficult to balance the privacy-accuracy tradeoff. We propose Recycled ADMM (R-ADMM), where a linear approximation is applied to every even iteration, its solution directly calculated using only results from the previous, odd iteration. It turns out that under such a scheme, half of the updates incur no privacy loss and require much less computation compared to the conventional ADMM. Moreover, R-ADMM can be further modified (MR-ADMM) such that each node independently determines its own penalty parameter over iterations. We obtain a sufficient condition for the convergence of both algorithms and provide the privacy analysis based on objective perturbation. It can be shown that the privacyaccuracy tradeoff can be improved significantly compared with conventional ADMM.

show abstract

“…Identify the accuracy A 0 of the locally best feature candidate F 00 ; 6 if A 0 > A then 7 Update A and F 0 with A 0 and F 00 , then start a new search from F 0 ; 8 else 9…”

Section: Warm Startmentioning

confidence: 99%

“…As another example, in smart city travel demand applications, a large number of different vehicle records, weather conditions, and geographic metrics are taken as features in the prediction models with feature dimensions greater than 200 million [4,5] . Moreover, the data generated in the smart city context are usually gathered in a heterogeneous and streaming fashion [6][7][8] . A majority of these applications are timesensitive (e.g., smart and connected vehicles) which need real-time or near-real-time data analysis [9] .…”

Section: Introductionmentioning

confidence: 99%

Novel and efficient randomized algorithms for feature selection

Wang

Xiao

Rajasekaran

2020

Big Data Min. Anal.

View full text Add to dashboard Cite

Feature selection is a crucial problem in efficient machine learning, and it also greatly contributes to the explainability of machine-driven decisions. Methods, like decision trees and Least Absolute Shrinkage and Selection Operator (LASSO), can select features during training. However, these embedded approaches can only be applied to a small subset of machine learning models. Wrapper based methods can select features independently from machine learning models but they often suffer from a high computational cost. To enhance their efficiency, many randomized algorithms have been designed. In this paper, we propose automatic breadth searching and attention searching adjustment approaches to further speedup randomized wrapper based feature selection. We conduct theoretical computational complexity analysis and further explain our algorithms' generic parallelizability. We conduct experiments on both synthetic and real datasets with different machine learning base models. Results show that, compared with existing approaches, our proposed techniques can locate a more meaningful set of features with a high efficiency.

show abstract

Predictive Cruise Control with Private Vehicle-to-Vehicle Communication for Improving Fuel Consumption and Emissions

Cited by 11 publications

References 10 publications

Recent Advances and Challenges in Security and Privacy for V2X Communications

Recent Advances and Challenges in Security and Privacy for V2X Communications

Recycled ADMM: Improving the Privacy and Accuracy of Distributed Algorithms

Novel and efficient randomized algorithms for feature selection

Contact Info

Product

Resources

About