An Improved Traffic Congestion Monitoring System Based on Federated Learning

Xu, Chenming; Mao, Yunlong

doi:10.3390/info11070365

Cited by 19 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A similar approach is proposed by Xu and Mao [28] who introduce a software-based traffic congestion monitoring system. In their study, federated learning is especially used to identify vehicle targets in remote sensing images.…”

Section: Literature Review Resultsmentioning

confidence: 99%

Study on the Technical Evaluation of De-Identification Procedures for Personal Data in the Automotive Sector

Rannenberg¹,

Pape²,

Tronnier³

et al. 2021

View full text Add to dashboard Cite

The aim of this study was to identify and evaluate different de-identification techniques that may be used in several mobility-related use cases. To do so, four use cases have been defined in accordance with a project partner that focused on the legal aspects of this project, as well as with the VDA/FAT working group. Each use case aims to create different legal and technical issues with regards to the data and information that are to be gathered, used and transferred in the specific scenario. Use cases should therefore differ in the type and frequency of data that is gathered as well as the level of privacy and the speed of computation that is needed for the data. Upon identifying use cases, a systematic literature review has been performed to identify suitable de-identification techniques to provide data privacy. Additionally, external databases have been considered as data that is expected to be anonymous might be reidentified through the combination of existing data with such external data. For each case, requirements and possible attack scenarios were created to illustrate where exactly privacy-related issues could occur and how exactly such issues could impact data subjects, data processors or data controllers. Suitable de-identification techniques should be able to withstand these attack scenarios. Based on a series of additional criteria, de-identification techniques are then analyzed for each use case. Possible solutions are then discussed individually in chapters 6.1 - 6.2. It is evident that no one-size-fits-all approach to protect privacy in the mobility domain exists. While all techniques that are analyzed in detail in this report, e.g., homomorphic encryption, differential privacy, secure multiparty computation and federated learning, are able to successfully protect user privacy in certain instances, their overall effectiveness differs depending on the specifics of each use case.

show abstract

Section: Literature Review Resultsmentioning

confidence: 99%

Study on the Technical Evaluation of De-Identification Procedures for Personal Data in the Automotive Sector

Rannenberg¹,

Pape²,

Tronnier³

et al. 2021

View full text Add to dashboard Cite

show abstract

“…However, existing studies pay less attention to the spatiotemporal patterns of traffic congestion for regional expressway networks. Instead, they mainly focus on the traffic congestion of urban roads and have developed various methods to identify [10][11][12][13][14][15][16], predict [17][18][19][20][21], and analyze [22][23][24][25][26][27][28][29] urban traffic congestion. Compared with urban traffic congestion, there are fewer studies that focus on traffic congestion in expressways.…”

Section: Introductionmentioning

confidence: 99%

“…Dates of peak congestion and their descriptions. The first day of the New Year's Day Holiday 13. February 2015 The last working day before the Chinese New Year Holiday.…”

mentioning

confidence: 99%

A Method for Exploring and Analyzing Spatiotemporal Patterns of Traffic Congestion in Expressway Networks Based on Origin–Destination Data

Gao

Yan

et al. 2021

IJGI

View full text Add to dashboard Cite

Traffic congestion in expressway networks has a strong negative influence on regional development. Understanding the spatiotemporal patterns of traffic congestion in expressway networks is critical for improving the exchange of products in regional production and promoting regional economic development. Nevertheless, existing studies pay less attention to these spatiotemporal patterns of traffic congestion. Considering that Origin–Destination (OD) data are available for the recorded spatial movements of vehicles in expressways, this study proposes a method with which to explore traffic congestion at the level of road segments in the regional expressway network, the mainstream of driving behaviors, and traffic regulations. Methods for analyzing spatial disparity and temporal changes in traffic congestion in expressway networks are also put forward in this paper. The empirical results show that the proposed methods could detect road segments where traffic congestion happens, and then uncover temporal patterns of several congested locations and spatial patterns of road segments with frequent congestion. These spatiotemporal patterns of traffic congestion could be in accord with the actual situation. This study provides a new approach to investigating traffic congestion in expressway networks based on low-cost data, which might be helpful for optimizing expressway network planning and promoting balanced regional development.

show abstract

“…How to efficiently extract useful knowledge from such an amount of raw data has become a problem. Thanks to recent advances in deep learning, state-of-the-art deep learning models achieved significant performance improvements in a broad spectrum of areas with enough data, including computer vision [1], speech analysis [2], smart sensing [3], etc. However, to achieve better results, deep learning models usually have to go wider and deeper, which incurs high computational costs in terms of storage, memory, latency, and energy.…”

Section: Introductionmentioning

confidence: 99%

“…(2) Many works [5,8] set the pruning rate empirically with no guidance on how to determine a proper pruning rate to make the pruning process non-trivial. (3) The retraining process used in structured pruning is usually highly time-consuming.…”

Section: Introductionmentioning

confidence: 99%

Combine-Net: An Improved Filter Pruning Algorithm

Wang

Zhang

2021

Information

View full text Add to dashboard Cite

The powerful performance of deep learning is evident to all. With the deepening of research, neural networks have become more complex and not easily generalized to resource-constrained devices. The emergence of a series of model compression algorithms makes artificial intelligence on edge possible. Among them, structured model pruning is widely utilized because of its versatility. Structured pruning prunes the neural network itself and discards some relatively unimportant structures to compress the model’s size. However, in the previous pruning work, problems such as evaluation errors of networks, empirical determination of pruning rate, and low retraining efficiency remain. Therefore, we propose an accurate, objective, and efficient pruning algorithm—Combine-Net, introducing Adaptive BN to eliminate evaluation errors, the Kneedle algorithm to determine the pruning rate objectively, and knowledge distillation to improve the efficiency of retraining. Results show that, without precision loss, Combine-Net achieves 95% parameter compression and 83% computation compression on VGG16 on CIFAR10, 71% of parameter compression and 41% computation compression on ResNet50 on CIFAR100. Experiments on different datasets and models have proved that Combine-Net can efficiently compress the neural network’s parameters and computation.

show abstract

An Improved Traffic Congestion Monitoring System Based on Federated Learning

Cited by 19 publications

References 22 publications

Study on the Technical Evaluation of De-Identification Procedures for Personal Data in the Automotive Sector

Study on the Technical Evaluation of De-Identification Procedures for Personal Data in the Automotive Sector

A Method for Exploring and Analyzing Spatiotemporal Patterns of Traffic Congestion in Expressway Networks Based on Origin–Destination Data

Combine-Net: An Improved Filter Pruning Algorithm

Contact Info

Product

Resources

About