Unlock instant, AI-driven research and patent intelligence for your innovation.

Self-adaptive federated learning method for Internet of Vehicles

An adaptive, car networking technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve problems such as user privacy issues, and achieve the effect of good models and privacy protection

Pending Publication Date: 2022-01-28
HUNAN UNIV OF SCI & ENG
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Collection and analysis of data can help transportation departments make better decisions, but may create privacy concerns for users

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Self-adaptive federated learning method for Internet of Vehicles
  • Self-adaptive federated learning method for Internet of Vehicles
  • Self-adaptive federated learning method for Internet of Vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0076] The invention will be further described below with reference to the accompanying drawings and embodiments.

[0077] like figure 1 As shown, an adaptive federal learning model for the Internet access, including the following steps.

[0078] Step 1: Build a federal learning pool. A adaptive federal learning module mounted on the server cluster, which can choose the most appropriate federal learning algorithm based on the characteristics of the data source.

[0079] At the same time, for horizontal federal learning, longitudinal federal learning, federal migration learning, according to the actual application scenario, the most suitable learning method is selected, and the distribution characteristics of the data source are analyzed.

[0080] Step 2: Build a horizontal federal learning model. The vehicle is used as the client, the server in the block chain as the server node; the vehicle downloads the parameters from the block chain, and local model training is performed by lo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a self-adaptive federated learning method for the Internet of Vehicles, and provides a self-adaptive federated learning model for the Internet of Vehicles on the research basis of cryptography. According to the method, the model can be trained under the condition that original data are not shared, and the most suitable federal learning algorithm can be selected according to an actual application scene. On the other hand, the problems of data islands, insufficient privacy protection and the like are also generated while the Internet of Vehicles brings convenience, the invention provides a solution, the solution provides a federated learning pool module training model, the most suitable federated learning algorithm can be selected according to a real-time application scene, while the user privacy is protected, better model improvement can be obtained.

Description

Technical field [0001] The present invention relates to an adaptive federal learning method for a vehicle. Background technique [0002] The network (IOV) is a new type of industry in depth fusion such as automobile, electronic, information communication, traffic, management. As a necessary technical means for intelligent transportation systems and automatic driving, the car is a core technology that solves the current traffic problem. In IOV, data exchange between the vehicle unit (OBU), the roadside unit (RSU), and the mobile network realizes the information sharing between the vehicle and all systems. For example, in the vehicle (V2V) communication in one of the Internet applications, the function running on the sensor node can be part of each vehicle in-vehicle system, while the function running on the base station can run on the roadside unit device. In this way, the local transportation department can accurately and comprehensively grasp the real-time traffic conditions and...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F21/60G06F21/62G06N3/08
CPCG06F21/602G06F21/6245G06N3/08
Inventor 程文志欧嵬刘志壮张文昭王林慧袁明潘晴云
Owner HUNAN UNIV OF SCI & ENG