Detecting aggressive and abnormal driver behavior, which depends on a multitude of external and internal factors, is critically important for enhancing road safety. This article provides a comprehensive review of machine learning methods applied for driver behavior classification. An extensive analysis is conducted to assess the pros and cons of existing machine learning algorithms. Various approaches to problem formulation and solution are discussed, including supervised and unsupervised learning techniques. Furthermore, the review examines the diverse range of data sources utilized in driver behavior classification and the corresponding technical tools employed for data collection and processing. Special emphasis is placed on the analysis of Microelectromechanical Systems sensors and their significant contribution to the accuracy and effectiveness of driver behavior classification models. By synthesizing existing research, this review not only presents the current state of the field but also identifies potential directions for future research, aiming to advance the development of more robust and accurate driver behavior classification systems.

Keywords: machine learning, driver classification, driver behavior, data source, microelectromechanical system, driver monitoring, driving style, behavior analysis

This paper considers existing classical and neural network methods for combating noise in computer vision systems. Despite the fact that neural network classifiers demonstrate high accuracy, it is not possible to achieve stability on noisy data. Methods for improving an image based on a bilateral filter, a histogram of oriented gradients, integration of filters with Retinex, a gamma-normal model, a combination of a dark channel with various tools, as well as changes in the architecture of convolutional neural networks by modifying or replacing its components and the applicability of ensembles of neural networks are considered.

Keywords: image processing, image filtering, machine vision, pattern recognition

In this work, we studied the effect of fog on machine vision systems, in particular, on the correctness of the pattern recognition algorithm. As part of this work, a filter is implemented that eliminates distortions caused by fog. A corrective filter has been developed, an analysis of the operation of a neural network with images of various definitions has been carried out, on the basis of which recommendations have been made to improve the accuracy of pattern recognition.

Keywords: image processing, image filtering, machine vision systems, pattern recognition

The paper considers the development of a system for executing machine learning models. The developed system is a set of micro-services that can be used in various areas of production. Technologists for the implementation and prospects of the product being developed are considered. The work uses modern technologies for segmentation and recognition of objects on frames, as well as technologies that allow you to build an infrastructure for this system, and software development technologies.

Keywords: machine learning, computer vision, microservice architecture, pattern recognition