A review of several metrics for solving the classification and data clustering problems is presented. Definitions and theorems are given. Questions of the optimization of initial cluster allocation are considered. Experiments on uniform cluster placement in the traveling-salesman problem are carried out.

This research addresses the problem of early detection of smoke and open fire on the observed territory by unmanned aerial vehicles. We solve the tasks of improving the quality of incoming video data by removing motion blur and stabilizing the video stream; detecting the horizon line in the frame; and identifying fires using semantic segmentation with Euclidean–Mahalanobis distance and the modified convolutional neural network YOLO. The proposed horizon line detection algorithm allows for cutting off unnecessary information such as cloud-covered areas in the frame by calculating local contrast, which is equivalent to the pixel informativeness indicator of the image. Proposed preprocessing methods give a delay of no more than 0.03 s due to the use of a pipeline method for data processing. Experimental results show that the horizon clipping algorithm improves fire and smoke detection accuracy by approximately 11%. The best results with the neural network were achieved with YOLO 5m, which yielded an F1 score of 76.75% combined with a processing speed of 45 frames per second. The obtained results differ from existing analogs by utilizing a comprehensive approach to early fire detection, which includes image enhancement and alternative real-time video processing methods.

The problem of the unmanned flight vehicle moving along the given route in a perturbed environment comes down to that of pursuing a target which simulates motion of the reference flight vehicle in compliance with its task. A scheme was proposed of a control system selecting the control strategy according to the current states of the flight vehicle and target. Consideration was given to the issues of the lead determination of the point of meeting of the flight vehicle with the target and rearrangement in the transfer functions of the equations of longitudinal and lateral motions of the flight vehicle in a restless tmosphere. The systems of automatic stabilization of the pitch and yaw angles with autopilot are used as the internal control loops. In the experimental part of the paper, the FV motion is modeled under the control constraints.

The results of solving collective pursuit problems that cover strategic and tactical levels of the behavior of players are generalized. The proposed approach is based on a combination of methods of...

Controlling the motion of a group of unmanned flight vehicles (FVs) in a perturbed environment is considered on the example of two similar problems: tracking of the dynamic target and moving along the given path. The problem of the target tracking implies that a randomly-arranged FV group approaches close to the target and flies near it during a specified time period. The low-velocity target seeks to evade from the pursuers as far as possible. In the path following problem, each FV needs to fly along the trajectory given by the motion of a corresponding reference target. In the process of problem solving, each FV implements behavioral strategies by following the proposed rules of orientation angles and velocity selection. Pontryagin's maximum principle and a geometric approach are applied to construct the control angles. The general simulation scheme of the pursuit process that takes into account the mathematical models of FVs and the wind disturbances is provided. In the experimental part of the paper, the solution of the specified problems is modeled in a perturbed environment.

The use of the parabola and its branches as a nonlinearity expanding the logical capabilities of artificial neurons is considered. In particular, the appli