Vehicle sending information authenticity real-time detection method based on width learning

Abstract

The invention discloses a vehicle sending information authenticity real-time detection method based on width learning. The vehicle sending information authenticity real-time detection method comprisesthe following steps: (1) collecting and sharing vehicle data information; (2) performing feature extraction on the acquired information, standardizing the proposed features, and standardizing the authenticity label of the message by using a two-dimensional vector; (3) establishing a false message detection model; (4) training a false message detection model; (5) detecting the authenticity of themessage sent by the vehicle; and (6) updating the model: when new data collected in the system is accumulated to a certain quantity, triggering the model to automatically utilize the newly added datato update by using an incremental learning algorithm. According to the method disclosed by the invention, the requirements on real-time performance and expandability of improper behavior detection ofthe vehicle can be well met. Meanwhile, the resource consumption is reduced, a more reliable basis is provided for traffic safety analysis, and potential safety hazards in traffic are reduced.

Description

technical field [0001] The invention relates to an information detection method, in particular to a real-time detection method for authenticity of information sent by a vehicle based on breadth learning. Background technique [0002] The Internet of Vehicles is a huge interactive network composed of the vehicle's own environment and status information. Through the Internet and computer technology, the aggregation, analysis and processing of vehicle information can be realized, and then the coordination and cooperation among various participating elements of transportation can be strengthened to achieve traffic optimization. The communication forms of the Internet of Vehicles are mainly divided into V2V communication between vehicles (Vehicle-to-Vehicle) and V2I communication (Vehicle-to-Infrastructure) between vehicles and roadside infrastructure. V2V is mainly based on on-board sensors and communication units. The status information of adjacent vehicles is shared, and accid...

AI Technical Summary

Problems solved by technology

However, the deep neural network has a complex structure, involves multiple layers and a large number of hyperparameters, and the training is extremely time-consuming. It often takes hours or even days to complete the training of a high-precision model, and the time cost is huge.

[0006] 2. The Internet of Vehicles is a highly dynamic network. Data is continuously generated and arrived in the form of streams. Therefore, as time goes by, the previous model is not enough to reflect the authenticity and integrity of the system, and is gradually no longer applicable. Therefore, the model is required to have Good scalability, can use new data streams to supplement and update the trained model

However, most of the currently proposed deep learning schemes for misbehavior detection do not have this capability and end up having to train new models from scratch at great cost.

[0007] 3. Vehicles are also limited by resources such as processing and storage

However, due to the complex structure of the deep learning network, the storage of a large number of hyperparameters, and the need to train a new model from scratch on massive data to complete the update, it poses a huge challenge to storage, computing and other resources.

[0008] Obviously, the existing deep learning models for vehicle bad behavior detection are almost always constrained by the characteristics and requirements of the Internet of Vehicles

Although the method based on deep learning can achieve high precision, it cannot effectively detect vehicle bad behavior due to time-consuming, poor scalability, and high resource overhead.

Images