Currently, the problem of automated data analysis and statistics collection from stock quotation charts has not been fully resolved. Most of the analysis of visual data falls on the physical work of the analyst, or on obsolete software solutions. The process of summarizing the information received from financial markets still requires physical attention and labor, which increases the risks associated primarily with the human factor and corresponding errors. An algorithm has been developed and tested for the automated collection of statistics from graphs of stock quotes, including data on the development and context of various figures (patterns) of technical analysis, as well as an improved adaptation and tracking system for the trend. The modeling process, analysis and the results of applying the analysis algorithm and statistics collection are presented. The developed algorithm works in conjunction with the previously created neural network pattern detector, which allows to automatically search for the exact boundaries of technical analysis figures of various sizes, analyze the context in front of them and play the patterns. This makes it possible to obtain important statistics that allow one to determine the degree of confidence in emerging patterns, taking into account their type, context, and other factors. In terms of accuracy and efficiency, the developed algorithm meets the existing challenges in the financial markets and can significantly increase the efficiency of the trader or investor through the automated processing of graphic and visual data. The created solution is universal in nature and can be applied to any capital market, regardless of the location and nature of the assets placed. The results can be used both to improve the accuracy of existing trading strategies, and for the analytical work of financial market participants. The use of new technologies for statistical processing of information can significantly improve the accuracy of investment and trade decisions

Today, there is a serious need to improve the performance of algorithms for detecting objects in images. This process can be accelerated with the help of preliminary processing, having found areas of interest on the images where the probability of object detection is high. To this end, it is proposed to use the algorithm for distinguishing the boundaries of objects using the Sobel operator and Kohonen self-organizing maps, described in this paper and shown by the example of determining zones of interest when searching and recognizing objects in satellite images. The presented algorithm allows 15–100 times reduction in the amount of data arriving at the convolutional neural network, which provides the final recognition. Also, the algorithm can significantly reduce the number of training images, since the size of the parts of the input image supplied to the convolution network is tied to the image scale and equal to the size of the largest recognizable object, and the object is centered in the frame. This allows to accelerate network learning by more than 5 times and increase recognition accuracy by at least 10 %, as well as halve the required minimum number of layers and neurons of the convolutional network, thereby increasing its speed.

Application of kohonen neural networks to search for regions of interest in the detection and recognition of objects

One of the most effective ways to improve the accuracy and speed of algorithms for searching and recognizing objects in images is to pre-select areas of interest in which it is likely to detect objects of interest. To determine areas of interest in a pre-processed radar or satellite image of the underlying surface, the Kohonen network was used. The found areas of interest are sent to the convolutional neural network, which provides the final detection and recognition of objects. The combination of the above methods allows to speed up the process of searching and recognizing objects in images, which is becoming more expedient due to the constantly growing volume of data for analysis. The process of preliminary processing of input data is described, the process of searching and recognizing patterns of aircraft against the underlying surface is presented, and the analysis of the results is carried out. The use of the Kohonen neural network makes it possible to reduce the amount of data analyzed by the convolutional network by 18–125 times, which accordingly accelerates the process of detection and recognition of the object of interest. The size of the parts of the input image fed into the convolutional network, into which the zones of interest are divided, is tied to the image scale and is equal to the size of the largest detectable object, which can significantly reduce the training sample. Application of the presented methods and centering of the object on training images allows accelerating the convolutional network training by more than 5 times and increasing the recognition accuracy by at least 10%, as well as minimizing the required minimum number of layers and neurons of the network by at least halving, respectively increasing its speed