Vehicle node identity recognition method and device based on metric learning

Abstract

The invention provides a vehicle node identity recognition method and device based on metric learning. The method comprises the following steps: establishing a multi-target open individual representation calculation model based on a metric learning theory; obtaining and preprocessing wireless signals corresponding to different vehicle nodes to obtain wireless signals corresponding to different vehicle nodes with the data dimension being N; training the multi-target open individual representation calculation model according to the wireless signal to obtain a standard feature value with the datadimension being d after dimension reduction; inputting a wireless signal corresponding to a to-be-identified vehicle node into the trained multi-target open individual representation calculation model to obtain a test feature value with a data dimension d; calculating the minimum Euclidean distance between the test feature value and the standard feature value, and comparing the minimum Euclideandistance with a preset threshold to identify whether the identity of the to-be-identified vehicle node corresponding to the test feature value is legal or not; therefore, the resource waste is avoidedwhile the security authentication is ensured.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a vehicle node identification method of metric learning, a computer-readable storage medium, a computer device and a vehicle node identification device of metric learning. Background technique [0002] Among related technologies, air-space-ground integrated vehicle networking uses space network to provide effective data resource sharing and integration, improve the coordination ability of future vehicles-road-network, and provide important network infrastructure support for the full realization of the application of unmanned vehicles ; Although spatial information networks play a pivotal role in many major application scenarios, compared with traditional networks, air-space-ground integrated networks face more severe challenges due to their complexity, openness, and cross-domain characteristics; Therefore, the research on the security protection of air-space-ground...

AI Technical Summary

Problems solved by technology

[0002] Among related technologies, air-space-ground integrated vehicle networking uses space network to provide effective data resource sharing and integration, improve the coordination ability of future vehicles-road-network, and provide important network infrastructure support for the full realization of the application of unmanned vehicles ; Although spatial information networks play a pivotal role in many major application scenarios, compared with traditional networks, air-space-ground integrated networks face more severe challenges due to their complexity, openness, and cross-domain characteristics; Therefore, the research on the security protection of air-space-ground integrated Internet of Vehicles has become the key to the promotion of intelligent driving in the future, which has attracted extensive attention from domestic and foreign researchers.

[0003] At present, for its security, more protection technologies are focused on the link layer of the network and above, such as communication standard protocols and technologies based on cryptography encryption algorithms; Domain convergence requires additional computing and communication overhead at the link layer and above protocols, resulting in a large waste of resources

Images