INFORMATION AND WEB TECHNOLOGIES

. The problem of developing an intellectual decision support system for the identification of cultural values (on the basis of works of art), the issue of choosing and justifying methods and tools for its construction is considered. Methods of research and construction of complex objects, prospects of using similar systems based on modern artificial neural networks as a tool for developing an intelligent decision support system are considered. Considerable attention is paid to the issues of methods of automatic identification and classification of works of art, as the main elements of an intelligent decision support system. Prospects and ways of further research and use of this subject area are also defined.

Proceedings of the 7th International Scientific and Practical Conference «Current Issues and Prospects for The Development of Scientific Research» (April 19-20, 2023).

No 151
The state policy and normative legal foundations of Ukraine in the field of expertise of cultural values (CV) are reflected in such documents [1][2][3][4]. The need to carry out an examination arises in various circumstances: assessment of receipts of items to the library, archive or museum in order to determine their cultural and historical significance when admitted to the museum, archive or library collection. There is also a strong demand for expertise when it is necessary to export CV abroad [5].
The desire to check the results of stylistic analysis, to confirm or reject conclusions about the belonging of a given work to one or another author, to develop the most effective method of conservation and restoration prompted researchers, restorers, and art historians to turn to objective data of material analysis more and more often. In practice, the following methods of material analysis are most often performed [6]:  Identification, examination, and registration of cultural values are important links in the system of accounting and control over the preservation of monuments of national culture, their movement across the customs border of Ukraine, as well as in the field of regulation of legal relations of management, related property complexes of all forms of ownership. Expert activity actively contributes to the scientific study of cultural values -artifacts of national history, material carriers of people's ideals, as well as specific goods on the world market [7].
It should be noted that part of the tasks and problems related to the development of systems for the identification of CV are either in the stage of partial solution or are only being formulated.
In addition, systems of this type can solve a wider range of problems, for example: searching and saving information about CV, and can also be used to popularize this issue in society.
At the same time, it should be noted that one of the tasks set in the work is to improve the quality and efficiency of the solution to the practical problem of identification of  No 151 the CV due to the implementation and use of the intelligent decision support system (IDSS) created on the basis of modern methods/models/technologies/tools. In the future, this tool can be used not only by experts in specialized laboratories, but also by a wider range of users [8,9]: − Experts in the field of cultural values and objects of art. The author determined that part of the issues that arose during the analysis of the state of the issue and the setting of the research objectives depend to a large extent on factors and third parties that will not have a direct relationship to the processes of development and implementation of the IDSS [10].
During the solution of the set tasks, additional questions arise, not so much of an engineering and technical nature, but of an organizational, methodical and normative-legal nature, which must be taken into account for the effective and high-quality development of the IDSS.
So, for example, when analyzing and solving organizational issues, developers should decide on the types of objects of cultural values for their further analysis, since CVs are diverse and characterized by different features, therefore the approach to solving the given task should take this factor into account. When setting the task and analyzing the relevant subject area, the requirements of potential users should be taken into account and relevant experts should be consulted.

No 151
Regarding the solution of methodical and methodological issues, the following aspects can be noted: − Analysis of methods of identification of objects of cultural value according to their types.
− Consultations with experts according to the type of objects of CV.
− Determination of sources of information about objects of CV, with the help of which the content of the data warehouse of the IDSS system is filled and updated.
− Additional reference sources of information, with the help of which experts substantiate and reinforce their conclusions.
After analyzing relevant issues and consulting with experts, we can come to the conclusion that, unfortunately, there are no clear algorithms and methods for the initial identification of objects of cultural value at the initial stage, and most experts rely on their experience and visual inspection. For their more detailed analysis, CV objects are transferred to specialized laboratories, where various methods of analysis are used [6].
When solving regulatory and legal issues, it was determined that some of these issues are regulated by relevant laws, resolutions and orders of relevant bodies and services. For example, the following issues were considered: − Analysis of the normative legal framework on work with objects of CV, such as documents such as [1][2][3][4] and others.
− Legal legitimacy of certain types of research on identification.
− Legal consequences of decisions taken on the identification of CV.
It should be noted that the intelligent decision-making support system for the identification of cultural values is implemented as an additional tool, and the decision to recognize this or that object remains with the user (inspector). Thus, the development and use of systems of this type does not contradict the current legislation.
In addition, the author considered: − the issue of developing a conceptual model of an intelligent decision-making support system for the − the issue of choosing and justifying methods and tools for its construction, methods of research and construction of complex objects, prospects of using modern artificial neural networks as a tool for developing an intelligent decision support system [12]; − the working algorithm of the IDSS for the identification of CV and the user with it, the question of determining the main work scenarios and limitations, and the question of the expediency of dividing the software implementation of the system into separate modules, which will make the system scaling process less time-consuming and more effective [13]; − problems of practical implementation of data storage and DBMS as the main component of an IDSS for the identification of cultural values [14,15].
Where the complexity and complexity of the approach to the solution of the task is noted, the prospects and ways of further research and use of this subject area are determined.
But the main scientific achievements, according to the author, are the solutions proposed in [16-18]: − Considered the task of establishing the authenticity of paintings during customs inspection. A two-stage procedure is proposed, which involves a quick check based on the analysis of photographs of the works of painting and a longer museum examination. To implement photo analysis, it is proposed to use an intelligent decision-making system, the action of which is based on a classifier that implements the k-nearest neighbors algorithm. A set of features describing the properties of paintings has been formed, metrics have been proposed for calculating the degree of similarity of objects during classification. For training the algorithm, a data set is offered, which includes paintings by world, European artists, and Ukrainian masters of different centuries.
− A method of automatically determining the age of a picture from a digital photograph using classification performed by an intelligent decision-making system is proposed. It is proposed to use the attribute of the year of creation of the painting as the main criterion for making a decision during the customs verification of the legitimacy of  No 151 the export. Instead of a long and expensive museum examination, photography of works of art is used under customs conditions and photo processing using a set of descriptors. The set of descriptors is proposed to include local binary patterns, their color modification, Haralik textural features, the first four moments, Tamura textural features, SIFT descriptor. The data obtained as a result of the action of the descriptors form the values of several dozen separate attributes. They form data vectors, which are then concatenated into a generalized description of the object vector. In the feature space created in this way, automatic classification is performed using the method of weighted knearest neighbors. The proposed algorithm calculates the distance between objects in the multidimensional space of attribute values, and assigns new objects to the formed classes. The criterion for creating classes is the age of the picture from the existing database. As a measure of object proximity, it is proposed to use Euclid and Minkowski metrics. It is proposed to calculate the weights for the classification algorithm using the Fisher method. The effectiveness of the proposed method was investigated during experiments with an image database containing photos of paintings by world, European, and Ukrainian artists. Algorithm configuration parameters ensuring high accuracy of classification were found. The conducted experiments showed the effectiveness of the selected descriptors for the formation of vectorsdescriptions of picture images. The highest accuracy is provided by the combination of descriptors, which reveals significant differences in the structural properties of the images. This approach to the description of objects in combination with the proposed classification algorithm and the chosen main criterion ensures high accuracy of the obtained solutions. The direction of further research may include the use of convolutional neural networks to improve classification accuracy under the condition of a static database.
− Considered the problem of automatic image classification using an intelligent decision-making system based on the knowledge graph and accurate image analysis. The task of automatic multi-task classification of paintings A system architecture is proposed that verifies provenance, implements detailed analysis (FGIA) of visual features of an image, and performs automatic classification of a picture by authorship, genre, and time of creation. The provenance is contained in the knowledge graph, for vectorization of which it is proposed to use a graph2vec type encoder with an attention mechanism, and detailed analysis is proposed to be performed using search distinctive regions (SDR) and learning distinctive regions (LDR) extracted by convolutional neural networks. A generalized loss function is proposed for training the classifier, as well as a data set that includes the provenance and images of paintings by European and Ukrainian artists.