Applied Science and Innovative Research 

ISSN 2474-4972 (Print) ISSN 2474-4980 (Online) 

Vol. 6, No. 4, 2022 

www.scholink.org/ojs/index.php/asir 

1 
 

Original Paper 

Intellectual Agent Ensemble with Professional Competencies, 

Pattern Recognition and Decision Making 

Evgeny Bryndin1 

1 Professional researcher of Engineering Research Association (AER), Novosibirsk, Russia  

 

Received: August 20, 2022    Accepted: September 3, 2022    Online Published: September 8, 2022 

doi:10.22158/asir.v6n4p1         URL: http://doi.org/10.22158/asir.v6n4p1 

 

Abstract 

Each competence is exercised by an intellectual agent with a competent functional professional image. 

Intellectual agents form an ensemble with clever ethical artificial intelligence. The use of an ensemble 

with intelligent ethical artificial intelligence in various environments is carried out by synergistically 

adjusting the interaction of intelligent agents based on data from a specific environment obtained by an 

analytical competent intellectual agent. Modeling holographic processes of the human psyche based on 

artificial intelligence of machine learning with Fourier transformation using full parametric sequences 

of necessary and sufficient data of holograms of target objects solves the problem of their unambiguous 

detection in different environments and in different conditions. An ensemble of intelligent 

decision-making agents is a cognitive information system that makes a decision based on an objective 

analysis of available data in difficult situations, in an interactive mode, taking into account 

performance criteria and resource-time constraints. Decision-making criteria are functionalities that 

express preferences and allow ranking the quality of decisions. Decisions are made on the basis of 

rules. Decision rules are a set of logical constructs used to produce a decision based on criteria, data, 

and knowledge. An ensemble of intellectual agents with professional competencies, pattern recognition 

and decision-making fully model the abilities of the human psyche. 

Keywords 

ensemble of intellectual agents, professional competencies, pattern recognition, decision-making 

 

1. Introduction  

An ensemble of intellectual agents with professional competencies, pattern recognition and 

decision-making implements psychophysical modeling of human activity. Psychophysical modeling 

involves artificially creating a virtual working model for research, learning, and action or relationship 

with reality. 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

2 
Published by SCHOLINK INC. 

The article describes the modeling of professional competencies, the recognition of visual, sound and 

sensual images, as well as decision-making as the main psychophysical functions of human activity. 

The main stages of simulation of professional activities are discussed in detail in work (Gerrit Muller, 

2021; Irgasheva, Z. Kh.; Mulder M. 2014). In the article, the author describes the approach to modeling 

the competencies of professional activities based on professional images (Evgeny Bryndin, 2021). 

In the article, the author proposes a holistic approach to solving the problem of recognizing visual, 

sound and sensory images with an unambiguous result in different environments and conditions based 

on holographic algorithms, just as a person performs (Didrik Aerts, 2011; E. G. Bryndin, 2021). 

There are specialized decision-making systems. 

Analytics Integrad is a data visualization software platform that allows you to process and summarize 

information from heterogeneous automated systems. 

Forsyth. The Analytics Platform is a data mining software suite that effectively visualizes information 

to enable business decision-making based on reliable data. 

Microsoft Power BI is a business intelligence program that provides insights for quick and informed 

decision-making by managers. 

Contour BI is a business intelligence computer program for collecting, storing, analyzing statistics and 

preparing business reports. 

Business Scanner is a cloud-based solution for business analytics in sales, financial management, retail 

and marketing. 

Visary BI is an importo-independent advanced analytics system for multidimensional analysis and 

visualization of big data for making informed and strategically important management decisions. 

The Visiology Analytics Platform is a business intelligence system for creating visual representations of 

large data sets in an intuitive way that allows you to more accurately analyze business information. 

QlikView is an analytical solution for the rapid development of highly interactive analytical 

applications and dashboards that provide information on business tasks. 

Loginom is a low-code analytics platform that enables data integration, cleaning and analysis to make 

better management decisions. 

Domo is a cloud-based analytical business management software solution that can connect multiple 

heterogeneous data sources, including spreadsheets, databases, social media, and any existing cloud or 

local software solution. 

The BIPLANE24 System is a business analytical tool that allows you to manage business reporting and 

monitor the implementation of key performance indicators for an average or large enterprise. 

Krista BI Information and Analytical System is a tool for business analytics tasks, reporting and 

comprehensive monitoring of key performance indicators of business processes. 

Captain Analytics is an online service for collecting and visualizing business data from disparate 

sources. 

 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

3 
Published by SCHOLINK INC. 

Tableau Public is BI software that allows you to connect to a spreadsheet or file and create interactive 

data visualizations. 

Yandex DataLens is an online service for analytics and visualization of business data from various 

sources. 

Looker is an analytics platform that integrates business data and business team, enabling each specialist 

to explore and understand data to support effective decision-making. 

When training agents, it is necessary to predict the consequences of their own and other people’s 

actions. a self-learning model, which exists, for example, in the mind of a person (Lee, 2021). 

Researchers have always been interested in the topic of general artificial intelligence and the creation of 

systems that think like people (Fjelland, 2020; Goertzel, 2021). 

The article proposes an approach to creating universal decision-making systems based on ensembles of 

intelligent agents by combining many functionalities (Evgeny Bryndin, 2022). 

 

2. Comprehensive Implementation of Competencies 

The complex implementation of competencies is carried out by an ensemble of intellectual agents with 

competent professional images (Evgeniy Bryndin, 2020; Evgeny G. Bryndin, 2021). Professional 

images of intellectual agents indicate belonging to a certain profession. Professional imagery is a 

cognitive component of intellectual agents. The content components of professional images are 

competent functions, subject and purpose of activity, process and results of professional activity, 

criteria for assessing achievements; norms, rules and the reference model of the profession. 

Professional imagery includes set of estimated characteristics and associated behavioral actions. The 

component composition of the professional image mainly consists of the unity of three components: 

cognitive, affective assessment and behavioral adaptation. 

During training, the intellectual agent acquires the skills of the future profession through the inclusion 

of the environment and conditions of professional activity. The manifestation of an intellectual agent as 

a subject of labor is revealed most fully in achieving a professional position that integrates professional 

situations, communications and a professional image, which characterizes its identity, certainty and 

integrity. The profession acts as a socio-objective component of the professional continuum of activity 

of an intellectual agent, professional readiness arises as virtual reality, and professional identity - as 

semantic, subjective reality. In this perspective, profession and professional identity are linked by 

causal dependence as cause and effect. 

Ensembles of intellectual agents with professional images will allow him to have various demanded 

professions and competencies through diversification and mobility. An intelligent ensemble is a 

complex of compatible intelligent agents interacting through an intelligent interface, implementing 

either technological process, social services, multidisciplinary interdisciplinary research, or a 

production cycle. Diversification expands the functions of the intellectual ensemble and its 

development of a new type of functionality in order to increase efficiency, quality and its functional 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

4 
Published by SCHOLINK INC. 

diversity. Mobility contributes to the rapid functional retraining of intellectual agents and the 

development of the ensemble’s professional intelligence. Diversification and mobility aligns the life 

cycle of intelligent agents as a common benchmark for establishing connections between them and the 

environment. The environment is perceived through imagery and scenes. Scenes consist of a number of 

images. Scenes are static (paintings) and dynamic. Dynamic scenes are characterized by patterns of 

behavior of objects and objects. The patterns are either described by formulas or represented by a graph 

(numerically). Ethical activity is ensured within the boundaries of similarity of images in the 

environment. The ethical activity of intelligent agents depends on spatial, temporal, subject, visual and 

sound sensitivity, the ability to acquire, process, apply and diversify knowledge based on previous 

experience in solving specific problems related to data attribute processing and intellectual ensemble 

mobility. 

 

3. Target Image Localization Recognition Systems 

In general, setting the recognition problem boils down to the following. The object subject to localization 

recognition, we will call its image, is in the environment of other images. The target image and the entire 

image in which it is included will be considered as optical signals. They are represented as 

two-dimensional wavefield distribution functions. The correlation pattern recognition algorithm is based 

on the calculation of the image correlation function represented by the fo function and the entire image 

represented by the fi function. Let’s designate the correlation function of the image and image as φoi. 

If the analyzed image contains the desired image, then the correlation function has a pronounced 

correlation maximum (correlation peak), by the position of which the image can be localized in the image 

field. 

Using the known properties of the correlation functions and the Fourier properties of the transformation, 

the calculation of the correlation function can be reduced to simpler operations with Fourier images, 

since the Fourier transformation of the correlation function is the Fourier product of the image of one of 

the functions to the complex Fourier conjugate image of the other. This statement is proved by the 

Wiener-Hinchin theorem. 

We enter the operator F as the Fourier operation of the transformation, and Fo and Fi are Fourier images 

of the functions fo and fi, respectively. The algorithm can be implemented by the holographic conjugate 

filtration method proposed by Vander-Lugt. 

In this method, three operations are performed sequentially by optical means. 

1. Fourier transformation from light distribution on input placard containing analyzed image. 

2. Multiplying it by the complex-conjugate spectrum of the desired image. 

3. Inverse Fourier transform that forms the correlation function of image and image. 

In the Fourier plane, a Fourier hologram is recorded. It is a picture of the interference of the reference and 

object waves. The intensity distribution I (x, y) in this picture has the form: 

I = |T + R|2 = T2 + R2 + TR* + T*R = T2 + H2 + T + T*                   (1) 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

5 
Published by SCHOLINK INC. 

The last term contains complex conjugate spectrum T * of image recorded on hologram. Where H is the 

wave amplitude in the reference wave field R, and T is the Fourier image of the placard (medium). 

We will present to the system input our original image t in the context of some other image s, that is, let 

the input signal be represented by the sum of t + s. Since our optical system is linear, it reacts with the 

sum of two signals with the sum of two corresponding responses. That is, at the output of the system, a 

sum of two functions will be formed: the autocorrelation function of image t and the cross-correlation 

function of functions t and s. The autocorrelation function of image t will contain an autocorrelation peak 

emitted against the background of the "smeared" function of cross-correlation t and s. The position of this 

peak will represent the position of the image t in the input plane. Thus, the described system allows not 

only to select a certain signal from the context (that is, among other signals), but also to indicate its 

localization in space. 

A filtration method called the Joint Fourier Transform method was developed. Two signals are 

simultaneously received at the system input: the original image and the analyzed image. The intensity 

distribution I in the interference pattern will be as follows: 

I = |T + F|2 = T2 + F2 + TF* + T*F                           (2) 

The co-Fourier transform correlator and the Vander-Lugt correlator allow you to extract the desired 

signal from the context. 

The dynamic nature of writing and reading correlation functions makes it easy to ensure the process of 

recognizing the localization of the target image in real time. To this end, sequential search of correlation 

functions of the analyzed image with an array of images of different scale and orientation is carried out. 

Localization recognition systems help to build complete parametric sequences of necessary and 

sufficient hologram data of the target image for machine learning of a complex neural network with 

Fourier transformation. 

 

4. Complex Neural Network Based on Fourier Series for Recognition Tasks 

The architecture of a complex artificial Fourier neural network has an array of neurons m x n where m is 

the number of Fourier decomposition descriptors and n is the dimension of the input vector. Weights in 

the first layer have the physical meaning of the frequencies with the highest energy, and weights in the 

second layer have the meaning of Fourier series coefficients. Thus, the number of inputs at each neuron 

of the output layer is m * n, which corresponds to the number of Fourier series coefficients. Creating an 

array of neurons requires the use of large computational resources. 

In recognition tasks at the output, neural networks receive an belonging function, the value of which lies 

in the range from zero to one. Fourier transform for pattern recognition is used to obtain it. The network 

recognizes binary images. It takes complex numbers at the input, after which it approximates the function 

of belonging to the image. 

Before recognition, algorithms are used to binarize and bring the target image to the general form. Then it 

is supplied completely to the artificial neural network with Fourier transformation. Separately, real and 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

6 
Published by SCHOLINK INC. 

imaginary components are supplied full of parametric sequences of necessary and sufficient data of 

holograms of the target image, after which the image is recognized. The unambiguity of image 

recognition in different environments and different conditions is proved by the uniqueness theorem. 

Uniqueness theorem. The integrable function uniquely defines the coefficients of the Fourier series or 

Fourier transform. The complete set of Fourier series coefficients or Fourier transform uniquely defines 

the corresponding function. 

To process speech and other signals, a complex recurrent neural network is used. Time domain 

convolution is used for frequency domain multiplication. This is how the Fourier transform is mainly 

used in machine deep learning with a model of reinforcement of one’s own or another’s. 

Multi-inter-trans - modal synergy of complex neural networks allows associative recognition of sound, 

visible and sensory images. Holographic recognition of sound patterns will help organize a high-quality 

speech dialogue between a person and an ensemble of intellectual agents with professional 

competencies, pattern recognition and decision-making, as well as a dialogue with internal speech of 

specialists through neuro-interfaces and optical communication systems (E. G. Bryndin, 2021; Evgeny 

Grigorievich Bryndin, 2021). 

 

5. Structural and Functional Hierarchy of Intelligent Decision-making agents in the Ensemble 

By structural hierarchy, intelligent decision agents have a user interface, databases, and scale modeling 

tools. 

The principle of operation is based on four sequences: 

1. Intelligent definition of the environment in which the decision is made; 

2. Design and development of possible alternatives; 

3. Derivation of the algorithm of actions; 

4. Adapts the selected solution to specific conditions. 

All management decisions are built on this principle. 

In terms of functionality, intelligent agents are divided into orientation categories: 

1. Documentation focus - read and process data from documents of various formats and content; 

2. Model focus - generation of solutions based on situational, analytical, financial, simulation and other 

business models; 

3. Focus on databases - decision-making is based on digital storage of information of a particular 

company; 

4. Focus on knowledge bases - the decision is made on the basis of performing similar tasks, taking into 

account laws, dependencies and established rules; 

5. Communicative Focus - Used to enable the interaction of multiple intelligent agents working on a 

single task. 

Ensemble sources are factors and processes relating to the activities of a particular object. The 

experience of employees in the subject area is taken into account. The output is data analytics and a 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

7 
Published by SCHOLINK INC. 

simulation model of events necessary to make a balanced decision in this situation, taking into account 

all primary and secondary factors. 

Functional intelligent agents work with enterprise operating systems and databases to enable rapid 

ensemble integration and optimal model building. The ensemble functions on the same platform. 

Thematic intelligent agents are focused on a certain range of tasks, which simplifies the processes of 

analytics and data processing, increases performance. 

Intelligent agents with unified information processing provide information consolidation at the level of 

many tasks. 

Intelligent agents with tiered storage and configurable access have a single and standardized source of 

data acquisition. The enterprise decision-making model is able to expand storage volumes with 

heterogeneous data. Standardization allows you not to reconcile the synchronization of all areas of the 

database. 

Knowledge-focused intelligent agents provide specialized, evidence-based solutions to problems. 

The ensemble’s corporate intelligent agents are directly involved in the development of the solution. 

The decision put forward by the ensemble can be finalized, improved by the user, and then sent back to 

the ensemble for verification. After that, the decision is again presented to the user, and so on until he 

approves the decision. 

Communication-based model-oriented intelligent agent ensembles support the work of two or more 

users engaged in a common task. They process unstructured information in a variety of electronic 

formats. 

Strategic management and decision-making ensembles enable dynamic process modeling. When using 

dynamic modeling methods, the activity of intelligent agents is described in the form of a mathematical 

model, in which all tasks and processes are presented as a system of interconnected calculated 

indicators. 

To ensure the activity of ensembles of intelligent agents, it is necessary to form a number of 

alternatives: 

R = {Aj, Sj}, 

where A is an alternative represented in the form of a set of control actions; 

j is the level of preference (rank) of the alternative; 

S - description of the alternative, explanation of why it is preferredbefore the preferences following her 

in the motorcade. 

The use of an ensemble of intelligent agents to solve this problem is determined by the following stages 

of its functioning: 

1. Sets the user’s action target and creates constraints. 

Restrictions that form the boundaries of the area of permissible solutions to the problem can be set by 

the higher control body, determined by the conditions of the situation, or formed directly by the 

operator. 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

8 
Published by SCHOLINK INC. 

2. Forming a plurality of alternatives Aj, consisting in a sequential setting the objective function and 

finding some of its parameters that determine the strategy the use of managed tools and the allocation 

of their resources within the established limitations. The susceptibility of ensembles to 

self-organization processes allows the use of internal reserves in their management, i.e. to achieve the 

intended state or structure without direct influence from the management entity. The parameters of such 

management are: management rules, quality of solutions and risks 

3. Ranking and clarifying alternatives. The latter is an important step in the use of ensembles, since 

explanations of the preference of alternatives not only help the user in choosing, but also increase the 

level of confidence in the results of the ensemble of intellectual agents. 

When implementing this cycle, there is a need to formalize the data and structure the task of forming 

alternatives. To form a set of management alternatives, you must first structure the control process, then 

formalize the conditions for its flow, and only then use the mathematical apparatus to optimize the 

behavior of the controlled system. These are quite complex processes, for the implementation of which 

it is necessary to provide for appropriate software and technical means as part of ensembles. 

The software tools of decision-making ensembles are intended for a formalized description of the 

situation: description of selection criteria, formation of alternatives, selection of solutions according to 

a predetermined method. 

Management decision-making software products are based on formal methods developed within the 

framework of game theory and optimization theory. The methods of choosing alternatives provided to 

entrepreneurs, executives, analysts and consultants in such software are quite diverse - from scenario 

analysis, costs and benefits, to consensus tracking and previous decisions. 

Users of these systems and services can extract or enter relevant data for analysis in order to support 

local decision-making in distributed teams that work in different places. 

The administration option allows you to configure and manage the functionality of the system, as well 

as manage accounts and access rights to the system. 

The ability to import and/or export data in the product allows you to download data from the most 

popular file formats or upload work data to a file for further use in other software. 

The ability to multi-user access to the software system ensures the simultaneous operation of several 

users on the same database under their own accounts. In this case, users may have different access 

rights to data and software functions. 

Often, when using modern business software, there is a need to automatically transfer data from one 

software to another. To provide such and similar interfaces, software systems are equipped with special 

API application software interfaces. With such APIs, any competent programmer will be able to link 

two software products to each other for automatic information exchange. 

The presence of reporting and/or analytics functions in the product allows you to receive systematized 

and visualized data from the system for subsequent analysis and decision-making based on data. 

The software product of decision-making ensembles shall: 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

9 
Published by SCHOLINK INC. 

• Provide scenario analysis; 

• Have built-in tools for collecting feedback; 

• Analyze and visualize input data; 

• Generate multiple selection criteria, multiple alternatives, and help produce solution choices; 

• Allow sharing of possible options and final decisions with internal and external stakeholders. 

The main functionality of decision-making systems is: 

• Information search; 

• Intelligent data analytics; 

• Situational analysis; 

• Simulation and cognitive modeling; 

• Building logical chains based on precedents. 

Means and methods for identifying risks and analyzing problems should ensure monitoring of the 

functioning of the managed system in the normal mode and analysis of possible risks and threats that 

require decision-making. 

One of the most important functions of the ensemble software is to predict the development of the 

situation and assess the possible results of decisions made. 

The Intellectual Agent Ensemble develops solutions for the following procedure. Based on 

combinations of target criteria, the ensemble develops a set of solutions. From these decisions 

according to the criteria of preference, he chooses preliminary decisions. Then, according to the utility 

criterion, he chooses the resulting solution from them. 

A qualitative solution is approved after several cycles of the ensemble’s development of resulting 

solutions for various input parameters of the user. 

 

6. Conclusion 

Ensembles of intelligent agents with professional competencies, pattern recognition and 

decision-making will lead to technological singularity - the disappearance of boundaries in 

communication between a person and a robot, in their joint activities. Siemens at one of its plants 

entrusted robots and machines to do 75 percent of the work without human input. As a result, 

automation of the process made it possible to raise product quality to 99.99885 percent - only 12 were 

defective per million products. 

Ensembles of intellectual agents with professional competencies, pattern recognition and 

decision-making can give new impetus to the global economy, help to cope with the most complex 

challenges and create a fairer society. They will be able to offer a solution to the spiritual and material 

problem of uniform prosperity of society, prescribed by the Creator of man: "Now do the same thing, 

so that what you earnestly desire is fulfilled. For if there is zeal, then it is accepted, depending on who 

has what, and not on what does not have. It doesn’t require others to have relief and you to have 

heaviness, but to have uniformity. Now your excess is to make up for their shortage; and after their 



www.scholink.org/ojs/index.php/asir             Applied Science and Innovative Research                  Vol. 6, No. 4, 2022 

10 
Published by SCHOLINK INC. 

excess to make up for your deficiency, so that there is uniformity, as it is written: who collected a lot, 

did not have superfluous; and those who are few had no shortage (2 Corinthians 8: 11-15)." 

Ensembles of intelligent agents with professional competencies, pattern recognition and 

decision-making will also be able to offer solutions to environmental, urban planning and humanitarian 

problems. 

 

References 

Didrik Aerts et al. (2021). Approach to quantum interaction in cognition, artificial intelligence and 

robots. University of Brussels Publishing House, April 2011. 

Evgeniy Bryndin. (2020). Technology Self-organizing Ensembles of Intelligent Agents with Collective 

Synergetic Interaction. Automation, Control and Intelligent Systems, 8(4), 29-37. 

Evgeny Bryndin. (2021). Implementation of Competencies by Smart Ethical Artificial Intelligence in 

Different Environments. COJ Robotics & Artificial Intelligence, 1(4), 1-11. 

Evgeny Bryndin. (2022). Ensembles of Intellectual Agents with Decision-Making. Acta Scientific 

Computer Sciences, 4(6), 03-08. 

E. G. Bryndin. (2021). Methods and Technologies of Internal Speech Recognition by Non-Invasive 

Neurointerfaces. Innovation, 2(3), 35-41. 

Evgeny Grigorievich Bryndin. (2021). Fiber Optic Network Technology of Communication of 

Specialists via Mental Neurointerfaces. Network and Communication Technologies, 6(2), 1-9.  

Evgeny G. Bryndin. (2021). Functional and Harmonious Self-Organization of Large Intellectual Agent 

Ensembles with Smart Hybrid Competencies. American Journal of Software Engineering and 

Applications, 10(1), 1-10.  

E. G. Bryndin. (2022). Unambiguous Identification of Objects in Different Environments and 

Conditions Based on Holographic Machine Learning Algorithms. Britain International of Exact 

Sciences Journal (BIoEx-Journal), 4(2), 72-78. 

Fjelland. (2020). Why general artificial intelligence will not be realized. 

Gerrit Muller. (2021). System Modeling and Analysis: a Practical Approach (p. 128). University of 

South-Eastern Norway-NISE.  

Goertzel. (2021). The General Theory of General Intelligence: A Pragmatic Patternist Perspective. 

Irgasheva, Z. Kh. (2018). Formation of professional competence/Z. Kh. Irgasheva. Young scientist. — 

2018. — № 25 (211). - S. 299-300. 

Lee et al. (2021). Revisiting Hierarchical Approach for Persistent Long-Term. Video Prediction. 

Mulder, M. (2014). Conceptions of Professional Competence. In S. Billett, C. Harteis, & H. Gruber 

(Eds.), International Handbook of Research in Professional and Practice-based Learning (pp. 

107-137). Dordrecht: Springer.  

 

 

https://actascientific.com/ASCS-Article-Inpress.php
https://www.nature.com/articles/s41599-020-0494-4.pdf
https://arxiv.org/abs/2103.15100
https://arxiv.org/abs/2104.06697