Today one of the topical issues is the practical application of the theory of pattern recognition, face recognition, including the definition of a person in the image and its subsequent identification. Such tasks include the extraction of indirect signs of interaction between users of social networks. By identifying the user's face and further searching it in photographs and video files in other profiles, an expansion of the list of basic data available to the analyst is achieved. It is known that the system of computer vision, which is able to recognize faces in a natural and artificial environment under any conditions, has not been implemented to date. One of the obstacles is the variation of the scene - the area where the face is being identified. The article proposes a model of an intelligent information system using bion-spirited methods for preprocessing images in order to expand the range of allowable scene variations.

Keywords: pattern recognition, object identification, photometry, intellectual system, social networks, analysis

Forecasting is required for effective control of the processes of electric power transmission and consumption, load estimation, and reduction of technical and commercial losses. The methods based on artificial neural networks are the most universal. However, practical application of those methods is limited by the complexity and the cost of software and by high requirements to the personnel who create and operate such systems. We propose two ways of the interaction between providers and consumers of forecasts of electric power consumption that solve those problems. The first way implements "model as a service" conception and the second way implements "forecast as a service" conception.

Keywords: electricity demand forecasting, information system, artificial neural network, forecast provider, forecast consumer, way of interaction

The paper issues a technique for constructing effective data insertion procedures in structure-independent databases that uses the activity approach. The essence of this technique is to present the procedure in the form of an action mechanism that allows its semantics to be opened, thereby minimizing the number of identical same meaning characteristics. The use of the technique for data insertion procedures constructing into structure-independent databases, as well as the use of a NoSQL DBMS that is homogeneous in structure to structure-independent databases made it possible to significantly improve performance. You can judge it from the computational experiment which is performed in the work.

Keywords: data insertion procedure, structure-independent database, activity approach, technique, action mechanism, semantics, experiment, performance

We consider the method of texts comparison in Russian in the subtask of semantic proximity determination. It is performed a review of existing methods of comparison. It is proposed a method of determination of similarity degree between textual passages within a semantic class. Existing methods are compared with the proposed method and a comparison made by people, in an experiment, which shows the suitability of the proposed method.

Keywords: textual similarity, semantics classes, comparison of texts, semantic schemes representation, textual passages

This paper examines the effectiveness of the software framework developed by the authors for the task of  sonar information systems software design. This is done by a theoretical estimate based on the data obtained during the actual production process, as well as practical by rebuilding the software using the skeleton. Fixed a set of indicators on which to judge the complexity and evaluated there . Finally, an assessment of the results of the experiment and draw conclusions about the direction of further research.

Keywords: software design, sonar information systems framework, performance evaluation