Distracted driving recognition method based on federated learning

Abstract

The invention discloses a distracted driving recognition method based on federated learning. Two machine learning technologies of federated learning and a shallow convolutional neural network are adopted, the federated learning mainly utilizes distributed data, a global statistical model is constructed through a deep neural network (DNN), and the recognition accuracy is improved, meanwhile, key parameters are uploaded under the homomorphic encryption condition, and data generated locally is not leaked; a convolutional neural network (CNN) mainly utilizes the advantages of image feature extraction and is responsible for extracting differentiated features of a user side, namely personalization of a local model; through federated learning and homomorphic encryption technologies, the problem of personal privacy protection in a cloud environment is solved, the problem of data islands is effectively solved, and the recognition efficiency is improved, so that the requirements of practical application are met.

Description

technical field [0001] The invention belongs to the field of computer technology, and relates to an image-based object detection technology, in particular to a federated learning-based distracted driving recognition method. Background technique [0002] With the rapid development of the economy, the frequency of traffic accidents is also increasing year by year. Driver distraction is one of the main reasons for traffic accidents. The identification based on distracted driving is an urgent problem to be solved. Distracted driving is another activity performed during driving, such as editing text messages, answering calls, etc., which seriously threatens driving safety on the road. Due to the high speed of the car, when the driver edits a WeChat message while driving, his eyes will leave the road for about 4 seconds, which almost covers the length of the football field at a speed of 60 mph. [0003] With the in-depth research of machine learning, many experts and scholars at ...

AI Technical Summary

Problems solved by technology

[0004] 1. In real life, driving behavior data involves personal privacy issues, often exists in the form of isolated islands, and a large number of users are unwilling to share

[0005] 2. The large amount of data generated every day is limited by the environment of mobile driving, resulting in poor interaction and poor communication between data owners and data analysts

[0006] 3. Low hardware performance

[0008] In summary, the current research mainly considers the accuracy of distracted driving recognition, and basically does not consider the issue of privacy protection, especially when personal privacy is uploaded to the cloud, which also brings serious security problems: the data stored in the cloud may Can be stolen by cloud providers and other cloud clients

[0009] With the introduction of the GDPR Act in 2018, the original privacy data sharing method is prohibited, and a large number of isolated data cannot fully enjoy the dividends brought by big data and cloud computing, resulting in a huge waste of resources

Images