Linguistic Variables Research Articles

Optimizing natural gas pipeline risk assessment using hybrid fuzzy bayesian networks and expert elicitation for effective decision-making strategies

Natural gas pipelines are susceptible to external and internal risk factors, such as corrosion, environmental conditions, external interferences, construction and design faults, and equipment failures. Bayesian Networks (BN) is a promising risk assessment approach widely used to evaluate these risk factors. One of BN's inherent limitations is its inability to accurately capture statistical dependencies and causal relationships, which can be overcome by incorporating expert elicitation into BN. To account for uncertainty and vagueness in assessing pipeline failure risks, fuzzy set theory (FST) can be combined with BN, commonly known as Fuzzy Bayesian Networks (FBN). This study developed an FBN framework that uses linguistic variables to calculate fuzzy probability (FPr) through domain expert elicitation, and crisp probabilities (CPr) are computed using historical incident data from the Pipeline and Hazardous Materials Safety Administration (PHMSA). Based on the findings from the case study of the Midwest region of the USA, external factors, i.e., third-party interference, outside force, and other incidents, significantly impact pipeline performance and reliability. Diagnosis inference indicates that in the Midwest region of the USA, pipeline material and age are critical factors leading to corrosion failure by threatening pipeline integrity. The findings from this study suggested that a targeted risk mitigation strategy is paramount for minimizing the risks associated with pipeline networks.

Spatial location does not consistently constrain perceptual learning in speech

Recent research showed selectivity of perceptual learning in speech to linguistic variables and non-linguistic variables. With regard to the latter Keetels et al. (2016) reported that perceptual learning for one spatial location does not fully generalize to another. This spatial selectivity has been suggested to indicate that learning may target non-linguistic representations. We test whether spatial selectivity is a general property of perceptual learning or whether it is related to specific design choices, such as using a single nonword throughout the study. Therefore, we aimed to replicate spatial selectivity with a paradigm that makes use of a larger set of word and nonword stimuli. However, in three experiments, one in-person and two web-based, no effect of spatial selectivity was observed. A Bayesian analysis suggests that the null hypothesis is better supported by the data than the alternative hypothesis based on the previously reported effect size. Repercussions for the debate about pre-lexical representations in speech processing are discussed.

A Q methodological study into pre-service Chinese as a foreign language (CFL) teachers’ mindsets about teaching competencies

Abstract A teacher’s mindset significantly affects their engagement, development, teaching quality, and well-being. This is crucial for pre-service teachers acquiring competencies for effective teaching. While research often focuses on English language teaching in Western contexts, little explores non-Western language teaching mindsets. Given the intersections of associated social, cultural, and linguistic variables with mindset, this study investigates Chinese as a foreign language (CFL) pre-service teachers’ mindsets on teaching competencies. The study utilized Q methodology, which is a philosophical and conceptual framework for examining subjectivity, and post-sort questionnaires with 39 pre-service teachers in China. The research findings provide important insights into the diverse and contradictory mindsets of pre-service CFL teachers, and the ideologies influencing beliefs as to what constitutes effective language teaching in the Chinese socio-cultural and socio-political context, providing insights into how teacher training programs need to be tailored to challenge and extend the complex mindsets held by pre-service language teachers.

Multiple-attribute group decision-making approach using power aggregation operators with CRITIC-WASPAS method under 2-dimensional linguistic intuitionistic fuzzy framework

The 2-dimensional linguistic intuitionistic fuzzy variables (2DLIFVs) provide an efficient tool to model the cognitive information of experts in practical circumstances while considering the reliability of the evaluation results. It is a hybrid model representing qualitative information, which derives from integrating the 2-dimensional linguistic variables (2DLVs) with linguistic intuitionistic fuzzy numbers (LIFNs). In this work, we first define a novel score function to establish a proper ranking order among the 2DLIFVs. Next, we define a new distance measure under a 2-dimensional linguistic intuitionistic fuzzy framework to determine the difference between 2DLIFVs. Some mathematical properties and special cases of the defined distance measure are also discussed. The power average (PA) operators provide aggregation tools, allowing aggregated arguments to support each other in the aggregation process. Motivated by the notion of power average (PA) and power geometric (PG), we define four new aggregation operators (AOs) to aggregate 2DLIFVs by considering information correlation in terms of support degree during the aggregation process. Several mathematical properties of the proposed AOs are also investigated. In addition, a new integrated 2DLIF-CRITIC-WASPAS methodology is developed in the 2-dimensional linguistic intuitionistic fuzzy environment to deal with complex decision issues. In this method, a “Criteria Importance Through Intercriteria Correlation (CRITIC)” approach is used to obtain the associate weights of the attributes, and the “Weighted Aggregated Sum Product Assessment (WASPAS)” method is executed to establish a valid ranking order among the alternatives.Moreover, a real problem of venture capital investment related to renewable energy projects is considered to demonstrate the applicability of the proposed methodology. The evaluation process considers four aspects: the management team, service or product, finance, and the market, which are related to 14 attributes. A sensitivity analysis is carried out to explain the reliability of the obtained results. Comparing the proposed method with some extant methods establishes the strength and robustness of the formulated method in real-world situations.

Development of a fuzzy logical model of Sugeno for the classification of grain varieties

Ambiguity and fuzziness are characteristic of many real-life situations, including the classification of objects based on their characteristics. In this context, fuzzy logic is a powerful tool for modeling uncertainty and making decisions under fuzzy conditions. The Sugeno model, a subset of fuzzy logic, offers a simple and effective approach to constructing rule-based control and classification systems based on linguistic variables. This paper explores the application of the Sugeno model to classify grain varieties based on their characteristics. For this purpose, a data set containing information about the parameters of grains from three different varieties of wheat is used. The study develops a fuzzy logic model that can effectively and accurately classify grain varieties based on their size and shape. To build the model, the scikit-fuzzy library is used, which provides tools for working with fuzzy logic in the Python programming language. Experiments are conducted with different variants of classification rules, optimizing the model to achieve the highest classification accuracy and reliability. The results obtained allow us to evaluate the effectiveness and applicability of the Sugeno model for the classification problems of grain varieties. The developed model can be useful for agronomists and agricultural specialists to automate the process of identifying wheat varieties based on their characteristics.

Profiling Social Sentiment in Times of Health Emergencies with Information from Social Networks and Official Statistics

Social networks and official statistics have become vital sources of information in times of health emergencies. The ability to monitor and profile social sentiment is essential for understanding public perception and response in the context of public health crises, such as the one resulting from the COVID-19 pandemic. This study will explore how social sentiment monitoring and profiling can be conducted using information from social networks and official statistics, and how this combination of data can offer a more complete picture of social dynamics in times of emergency, providing a valuable tool for understanding public perception and guiding a public health response. To this end, a three-layer architecture based on Big Data and Artificial Intelligence is presented: the first layer focuses mainly on collecting, storing, and governing the necessary data such as social media and official statistics; in the second layer, the representation models and machine learning necessary for knowledge generation are built, and in the third layer the previously generated knowledge is adapted for better understanding by crisis managers through visualization techniques among others. Based on this architecture, a KDD (Knowledge Discovery in Databases) framework is implemented using methodological tools such as sentiment analysis, fuzzy 2-tuple linguistic models and time series prediction with the Prophet model. As a practical demonstration of the proposed model, we use tweets as data source (from the social network X, formerly known as Twitter) generated during the COVID-19 pandemic lockdown period in Spain, which are processed to identify the overall sentiment using sentiment analysis techniques and fuzzy linguistic variables, and combined with official statistical indicators for prediction, visualizing the results through dashboards.

Use of fuzzy logic for analyzing the socio-economic well-being of the population

The article reveals a new approach to the analysis of population welfare using the theory of fuzzy sets. The purpose of the study is to develop and apply a methodology based on fuzzy logic to quantify and analyze the social and economic well-being of citizens. The main task includes the development of a methodological approach, the construction of a model for assessing well-being and the development of recommendations for planning socio-economic strategies. As a solution, the use of fuzzy logic is proposed, which allows better consideration of ambiguities and uncertainties in the data on the well-being of the population. The study presents a detailed description of the developed model, which includes the formation of lin-guistic variables, the definition of term sets, and the development of inference rules. These components allow the model to adapt to different conditions and types of data, providing flexibility and a wide field of application of the method. The study also emphasizes the impor-tance of analyzing factors that affect the well-being of the population, such as household in-come, expenditure on medicine and food, education level, housing conditions, the importance of personal economy and others. The authors indicate the dynamic influence of these factors and the need for their regular updating to increase the accuracy of forecasts. The results of the study demonstrate that the developed model provides more accurate and reasonable fore-casts of the level of socio-economic well-being compared to traditional methods. The ob-tained data can be used to plan socio-economic strategies at the micro and macro levels, con-tributing to the development of effective measures to improve the well-being of the population. The article makes a significant contribution to the development of socio-economic welfare analysis methods, showing the potential of fuzzy logic as a tool for increasing the accuracy of forecasting and developing sound socio-economic policies.

A novel approach to hazard evaluation for MASS operation based on a hesitant fuzzy linguistic term set

Expert judgment has been widely utilized in ship risk assessment. The traditional method is believed to be capable of processing only designated linguistic variables, which fails to capture the degree of expert hesitation in assessing a complex system. A novel model, the bi-independent hesitant fuzzy linguistic term set (BHFLTS), based on the hesitant fuzzy linguistic term set (HFLTS), is proposed to incorporate this hesitation. This paper also identifies ten navigational hazards to maritime autonomous surface ship (MASS) operation based on a literature review. In addition, the BHFLTS approach combined with the technique for order preference by similarity to an ideal solution (TOPSIS) is utilized for hazard assessment and ranking, and with this method, “Collision avoidance decision algorithm malfunction”, “Ship situation awareness system failure” and “Command transmission system failure” are rated as the top three navigational hazards that threaten MASS operation.

Sustainability evaluation of sports tourism using a linguistic neutrosophic multi-criteria decision-making method.

Sports tourism represents a novel industrial manifestation of the profound integration between the tourism and sports sectors. The objective of this research is to examine an innovative multi-criteria decision-making (MCDM) method for the sustainability evaluation of sports tourism. The largest innovations are the expression and treatment of ambiguous data and interdependent evaluation criteria in the sports tourism sustainability evaluation process. On the one hand, intricate assessment data is represented using linguistic neutrosophic numbers (LNNs), which employ three linguistic variables to convey uncertainty and imprecision. On the other hand, to effectively capture the interrelationships among inputs, two novel aggregation operators are proposed. They are devised based on the Einstein operations and Heronian mean operators of LNNs. Subsequently, a linguistic neutrosophic evaluation method utilizing the aforementioned operators is presented. Comparative and sensitivity analyses conclude that great interdependence exists among five different dimensions of sustainability evaluation in sports tourism, and the proposed method can reflect the interrelations among inputs without redundant calculations.

Bi-objective optimization of an EDM process with Cu-MWCNT composite tool using single-valued neutrosophic grey relational analysis

Purpose In many of today’s manufacturing industries, such as automobile, aerospace, defence, die and mould making, medical and electrical discharge machining (EDM) has emerged as an effective material removal process. In this process, a series of discontinuous electric discharges is used for removing material from the workpiece in the form of craters generating a replica of the tool into the workpiece in a dielectric environment. Appropriate selection of the tool electrode material and combination of input parameters is an important requirement for performance enhancement of an EDM process. This paper aims to optimize an EDM process using single-valued neutrosophic grey relational analysis using Cu-multi-walled carbon nanotube (Cu-MWCNT) composite tool electrode. Design/methodology/approach This paper proposes the application of grey relational analysis (GRA) in a single-valued neutrosophic fuzzy environment to identify the optimal parametric intermix of an EDM process while considering Cu-MWCNT composite as the tool electrode material. Based on Taguchi’s L9 orthogonal array, nine experiments are conducted at varying combinations of four EDM parameters, i.e. pulse-on time, duty factor, discharge current and gap voltage, with subsequent measurement of two responses, i.e. material removal rate (MRR) and tool wear rate (TWR). The electrodeposition process is used to fabricate the Cu-MWCNT composite tool. Findings It is noticed that both the responses would be simultaneously optimized at higher levels of pulse-on time (38 µs) and duty factor (8), moderate level of discharge current (5 A) and lower level of gap voltage (30 V). During bi-objective optimization (maximization of MRR and minimization of TWR) of the said EDM process, the achieved values of MRR and TWR are 243.74 mm3/min and 0.001034 g/min, respectively. Originality/value Keeping in mind the type of response under consideration, their measured values for each of the EDM experiments are expressed in terms of linguistic variables which are subsequently converted into single-valued neutrosophic numbers. Integration of GRA with single-valued neutrosophic sets would help in optimizing the said EDM process with the Cu-MWCNT composite tool while simultaneously considering truth-membership, indeterminacy membership and falsity-membership degrees in a human-centric uncertain decision-making environment.

Fuzzy time series dalam meramalkan jumlah produksi karet di Sumatra Utara

Rubber (Hevea brasiliensis) belongs to the genus Heveadari familia Euphorbiaceae which is a tropical woody tree native to the amazon jungle. Rubber is one of the plantation crops that is very important for the economy in Indonesia. Rubber production in North Sumatra has increased every year. To find out whether the amount of rubber production in North Sumatra increases or decreases next year by forecasting the amount of rubber production and getting better forecasting results in the future. This estimate can use the fuzzy time series forecasting method. The fuzzy time series uses the fuzzy set theory as the basis for calculations and a concept used to forecast actual data formed with linguistic variables. The method used in predicting the amount of rubber production in North Sumatra is the fuzzy time series method with data from 1997 to 2021. And the result of forecasting rubber production in 2022 is 261997 with MAPE of 0.54%.
 Keywords: Forecasting, rubber production, fuzzy time seriesMSC2020: 62M10, 62M20, 62M86, 03E72

EARTHQUAKE FREQUENCY DATA MODELING IN MENTAWAI USING FUZZY TIME SERIES LEE AND FUZZY TIME SERIES TSAUR

The Fuzzy Time Series (FTS) was first studied by Song and Chissom based on the theory of fuzzy sets and the concept of linguistic variables and their applications discovered by Zadeh. FTS has several models, namely FTS Lee, FTS Tsaur, and so on. In this study, we will model earthquake frequency data in Mentawai using FTS Lee and FTS Tsaur. The seismicity data used in this study is earthquake frequency data in the Mentawai which are calculated from 1960 to 2022. Additionally, the seismicity data source is taken from the U.S. Geological Survey catalog. Based on MAPE and MSE, the results obtained on the FTS Lee and FTS Tsaur models are MAPE values of 37,511% and 27,051%. And the MSE values obtained were 27,073 and 11,671. Thus, the best model used in modeling data on the frequency of earthquake occurrences in the Mentawai Islands is the Ruey Chyn Tsaur Fuzzy Time Series model.

Study of Linguistic Components of Pakistani English: An Indigenized English Variety

This study explores the linguistic components of Pakistani English (PakE) and how this English variety has been indigenized in linguistically diverse Pakistan. English is recognized as an official language in Pakistan, but it is often taught without appropriate socio-cultural context. The research aims to highlight the development of PakE through examining factors that influence its evolution, and analyze main linguistic features that draw its distinction from British English. The study uses a qualitative methodology, particularly thematic analysis of audio recorded interviews with two university students. Findings of the study reveal clausal, syntactic and lexical features of PakE that deviate from standard British English variety. The findings also demonstrate how PakE speakers code-mix Urdu and English, use unique sentence formations, and transform declarative sentences into interrogatives in casual talk. Moreover, the results imply the need for greater focus on linguistic diversity and importance of inclusion of native socio-cultural contexts in English language education across Pakistan. Additionally, understanding of common features of PakE can help informing language planning and policies focused on endorsing regional linguistic identity. Further research examining additional social, cultural and linguistic variables influencing ongoing development of Pakistani English as an indigenized variety is needed.

An innovative distance measure for quantifying the dissimilarity between Q-Rung orthopair fuzzy sets

Q-Rung orthopair fuzzy set (Q-ROFSs) is a generation of quartic fuzzy sets (QFSs), Fermatean fuzzy sets (FFSs), Pythagorean fuzzy sets (PFSs), Intuitionistic fuzzy sets (IFSs), and fuzzy sets (FSs). Fuzzy similarity measures find wide-ranging applications in several fields, such as pattern recognition (PR), classification, and multi-criteria decision-making (MCDM). The computation of criteria weights in MCDM heavily relies on the fuzzy environment. Therefore, this study focuses on developing a similarity measure for Q-ROFS based on Hausdorff distance, a valuable tool for establishing object similarities. We introduce an innovative distance measure designed to quantify the dissimilarity between Q-ROFSs. Our approach leverages this distance measure to establish a similarity measure between Q-ROFSs. Furthermore, we present a set of properties associated with the suggested similarity measures. To demonstrate the usefulness of these measures, we provide numerous numerical examples in the fields of PR and linguistic variable characterization. By leveraging our innovative techniques, we also develop a novel algorithm for orthopair fuzzy Tomada de Decisao Iterativa Multicriterio (TODIM), a highly interactive and effective MCDM approach. Moreover, we have successfully applied the newly devised orthopair fuzzy TODIM method to address MCDM challenges encountered in diverse real-life problems. The obtained algebraic outcomes affirm that the suggested similarity measures are appropriate, practical, and applicable for queries involving fuzzy linguistic variables in MCDM contexts.

Ensuring the relevance of enterprise business process knowledge based on an ontological model

The problem of ensuring the relevance of knowledge about the business process of an enterprise based on its ontological model is considered. The obsolescence of enterprise business process models leads to the need to redesign solutions for their automation. Approaches to solving the problem of maintaining the relevance of the business process model are presented. The regulatory basis of the business process of an enterprise was examined for its similarity to models developed to solve automation problems, and a conclusion was made that they have a common basis. This makes it possible to consider the regulatory basis as a metamodel and store data using linguistic variables. Ontological models built according to the IDEF5 standard for the most common regulatory documents of a business process are considered. It was been revealed that one of the most important elements of managing an industrial enterprise and its business processes is maintaining the relevance of all components, including the situational ontological model. A methodology is proposed for integrating an ontological model into the process of updating enterprise regulatory documents, preserving knowledge about the business process and retrieving it to generate changes to regulatory documents and models used to automate business processes. An example of using the technique for planning equipment repairs carried out outside the main work plan is considered.

Effects of exposure to dialect-specific allophonic variation on perceptual similarity ratings of vowels

Dialect exposure affects listeners’ lexical processing. In this study, we examined whether listeners’ exposure to dialect-specific allophonic variation in two linguistic variables in American English (nasal split /æ/ system and pre-voiceless /ɑɪ/ raising) affects their perceptual similarity ratings of matching versus mismatching allophones. Listeners from the U.S. North were assumed to have more exposure to pre-voiceless /ɑɪ/ raising and less exposure to a nasal split /æ/ system, while listeners from the U.S. Midland were assumed to have more exposure to a nasal split /æ/ system and less exposure to pre-voiceless /ɑɪ/ raising. We analyzed Northern and Midland listeners’ perceptual similarity ratings on a 1–5 scale for three types of auditory vowel pairs: match (e.g., ban-bang or bike-bite), allophonic mismatch (e.g., ban-bat or bike-bide), and phonemic mismatch (e.g., ban-bike). We predict that listeners with more exposure to dialect-specific allophonic variation should rate allophonic mismatches as more different than allophonic matches compared to listeners with less exposure. Preliminary results suggest that listeners rate allophonic matches as more similar than allophonic mismatches, and both of these types are rated as more similar than phonemic mismatches, consistent with existing literature. There was no effect of dialect exposure to allophonic variation on perceptual similarity ratings.

Analysis of inertia, damping, and synchronization characteristics in grid-connected photovoltaic systems with fuzzy logic control

The integration of renewable energy sources (RES) into DC-distributed power systems (DC-DPSS) is gaining traction as a sustainable energy solution. However, the inherent variability of RES output can introduce instability into the grid, posing challenges for maintaining system reliability and stability. Fuzzy logic controllers (FLCs) have emerged as a promising approach to mitigate these instability issues, offering a robust and adaptable control strategy that can effectively handle the complexities of DC-DPSS. This paper examines the application of FLCs in DC-DPSS, exploring their effectiveness in addressing instability caused by RES fluctuations. FLCs are a control system that leverages fuzzy logic, a form of logic that utilizes linguistic variables to represent uncertainty, make decisions, and improve the stability of DC-distributed power systems. The research analyzes various system parameters, including inertia, damping, and synchronization characteristics, using a static synchronous generator (SSG) model. The study builds upon prior findings by adding a fuzzy logic controller to the existing system. The results showed better performance which resulted in improved inertia, damping, and synchronization characteristics. The efficiency of the proposed controller is demonstrated using MATLAB/Simulink.

FUZZY CONTROL OF POWER CONSUMPTION OF ELECTROMECHANICAL EQUIPMENT OF THE MAIN DRAINAGE COMPLEX AT IRON ORE MINE

The paper presents a fuzzy control system for the consumption of electric power by pumps of the main drainage complex of a mine based on the Mamdani fuzzy inference algorithm. The proposed system has a structure with two inputs, such as water inflow and electricity cost, and one output, the power of pumping units. The choice of the Mamdani method for building a fuzzy system is due to the fact that all these inputs and outputs are subject to preliminary expert evaluation. All quantities are fuzzificated by smooth membership functions - Gaussian and sigmoid. The input values of the system are represented by linguistic variables, each of which includes five fuzzy sets that define the membership in the very low, low, medium, high, and very high levels of the corresponding input value. The output of the system contains ten fuzzy sets. During the fuzzification, it was assumed that in order to avoid overloading the pump motors, only one option is considered: their operation at maximum power when there is a very high level of mine water inflow during heavy rains or for other reasons. In all other cases, the operation of at least one of the pumps with the highest permissible power is excluded. A base of 25 fuzzy rules was formed. When defining the rules, it is assumed that in all cases when there is a high water inflow into the mine, all three pumps must be put into operation, regardless of the electricity cost in force in the current period of time. This set of rules is of the highest importance due to the need to prevent flooding of the mine. For other values of water inflow, the output power consumption of drainage pumping units depends on the current cost. This set of rules has a lower priority. We simulated the operation of the dewatering pumping system with and without a fuzzy power consumption control system. The test signal for the "water inflow" input was represented as a random variable with a normal distribution. The test signal for the "electricity cost" input was formed on the basis of real data on the price determined by the operator for the day ahead market for 12/24/2023. It was found that the use of a fuzzy system can reduce the cost of purchasing electricity by 1.24% per day. It should also be noted that the economic effect is achieved not by reducing the level of power consumption, but by rationalizing the operation of the drainage complex, which ensures maximum groundwater drainage performance when the cost of electricity is high, and minimum when it is low.

Risk assessment for the liquefied petroleum gas filling industry using fuzzy logic and hazard and operability

The object of this study is to integrate Hazard and Operability (HAZOP) analysis and Fuzzy Logic to improve risk assessment in the Liquefied Petroleum Gas (LPG) filling industry. the research introduces a new approach to resolve the uncertainties and imprecise information inherent in traditional risk evaluation methods. Using HAZOP, a qualitative analysis conducted by the experts of industry identifies potential process deviations and hazards, categorized by impact type such as fire, explosion, and environmental damage. Fuzzy Logic, quantifies these risks by evaluating the likelihood and consequences of accidents using linguistic variables like "high," "medium," and "low." The simulation of different parameters considers various scenarios, including the interplay of consequence severity, event frequency, and detection capability on overall risk using model fuzzy-Hazop. The results provide more precision and actionable risk assessments, showing the potential of the combination of Hazop and fuzzy logic for safety measurement in the LPG filling process. The study concludes HAZOP with fuzzy logic evaluates risks in uncertain conditions, offering an alternative for clearer, decision-making in risk-based design processes

Improving the technology for constructing a software tool to determine the similarity of raster graphic images

The object of research is the process of searching and analyzing images of raster graphics. In the context of this work, the problem of the lack of an effective and fast procedure for determining the similarity of images was solved. The technology for improving the construction of a software tool for determining the similarity of raster graphics images by devising a procedure for determining the similarity of images using a hash code that corresponds to all variants of the image, regardless of size and aspect ratio, is reported. The image features of raster graphics were systematized. A procedure for determining the similarity of images using a hash code is proposed. This procedure makes it possible to process all possible variants of the image, regardless of the size and aspect ratio. The resulting indicator of the proposed procedure is the value of the hash codes. It is proposed to use the mathematical apparatus of fuzzy logic by introducing linguistic variables to estimate the similarity index. A comparison of the numerical values of similarity, obtained on the basis of the use of information systems, and the linguistic values revealed in the survey process was carried out. Threshold values were obtained that make it possible to assess the degree of similarity of the images. Based on the proposed algorithm, a prototype of the information system for determining the similarity of images of raster graphics has been designed. As a result of the calculation of the numerical characteristics of the improvement of the technology of constructing a software tool for determining the similarity of images of raster graphics, the value of the precision indicators was approximately 0.89 and the completeness was 0.8. The advantage of the proposed technology for determining the similarity of images over known analog technologies is illustrated by the amount of RAM of the developed software, which is 210 MB