image recognition

Neural networks training systems used for military equipment recognition on the images are considered in the article. The implementation, considered in the article, uses pretrained part of the model with freezing most of the trained parameters and fined tuning of some part of the model with using extra data set including artificially obtained images. Two widely used recognition networks was considered: ResNet50 and Xception. After these two networks analysis, we can say that the best approach for training the network is using data expansion strategy.

A method for recognizing contours of objects in a video data stream is proposed. Data will be uploaded using a video camera in real time and object recognition will be performed. We will use the YOLO network – a method of identifying and recognizing objects in real time. Recognized objects will be recorded in a video sequence showing the contours of the objects.

Phasor diagrams are a powerful tool for  visualizing and understanding the distribution of current, voltage, and power in electrical systems. During Russia's war against Ukraine, our energy industry has become very vulnerable to enemy attacks, and therefore needs a quick and effective recovery. Energy specialists lack software tools for working with the power system, and in the period of development of artificial intelligence, creating such tools is not so difficult.

It is acknowledged that each person's life, group of people and nation is formed depending on geographical, economic, political, cultural and religious conditions. Lifestyle is formed as a result of daily repetition and consists of the following factors: nutrition, exercise, the presence of bad habits, moral and spiritual development, and so on. In recent decades, lifestyle has been considered an integral part of well-being, leading to increased research. According to the scientist's study, more than half of health problems are related to diet.

Finding similar images on a visual sample is a difficult AI task, to solve which many works are devoted. The problem is to determine the essential properties of images of low and higher semantic level. Based on them, a vector of features is built, which will be used in the future to compare pairs of images. Each pair always includes an image from the collection and a sample image that the user is looking for. The result of the comparison is a quantity called the visual relativity of the images. Image properties are called features and are evaluated by calculation algorithms.

The problem of constructing a model of logical classification trees based on a limited method of selecting elementary features for geological data arrays is considered. A method for approximating an array of real data with a set of elementary features with a fixed criterion for stopping the branching procedure at the stage of constructing a classification tree is proposed. This approach allows to ensure the necessary accuracy of the model, reduce its structural complexity, and achieve the necessary performance indicators.