=Paper=
{{Paper
|id=Vol-3101/Paper31
|storemode=property
|title=Cognitive and information decision-making technologies and risk assessment in technogenic systems
|pdfUrl=https://ceur-ws.org/Vol-3101/Paper31.pdf
|volume=Vol-3101
|authors=Lubomir Sikora,Natalia Lysa,Jan Krejčí,Rostislav Tkachuk,Olga Fedevych
|dblpUrl=https://dblp.org/rec/conf/citrisk/SikoraLKTF21
}}
==Cognitive and information decision-making technologies and risk assessment in technogenic systems==
https://ceur-ws.org/Vol-3101/Paper31.pdf
Cognitive and Information Decision-Making Technologies
and Risk Assessment in Technogenic Systems
Lubomir Sikora1, Natalia Lysa1, Jan Krejčí2, Rostislav Tkachuk3 and Olga Fedevych1
1
Lviv Polytechnic National University, 12, Bandera str., Lviv, 79013, Ukraine
2
Jan Evangelisty Purkynė University, Ceske mladeze, 8, Usti nad Labem, 40096, Czech Republic
3Lviv State University of Life Safety, 35, Kleparivska str., Lviv, 79007, Ukraine
Abstract
The article considers information technology of formation and decision – making, in the conditions of
risk construction methods, for technogenic systems management with use of cognitive model of
operator activity as a basis of decision – making processes intellectualization. It is substantiated, on
the basis of system analysis, the decomposition of the management problem on the problem of
solving which is necessary for decision making. The structural interaction scheme of intellectual ACS
with the management (team) person is constructed and the information technology of dialogue in
technogenic system management structure is developed. The interaction scheme of conflicting active
systems in the conditions of resources redistribution is substantiated. The classification of
management tasks, using system analysis and information technology, to assess the situation in the
system is presented. The structure of the cognitive-logical formation of management tasks procedure
in risk conditions on the basis of the intellectual agent model and the generator of procedures for
their solution, situational tasks is developed.
Keywords 1
System, information, situation, knowledge, risks, decisions, cognitive procedures, conflicts, logical
rules, management.
1. Introduction
Integrated human-machine systems, control structures, automated personnel training systems are
hierarchical systems characterized by uncertainty in the structure and dynamics of control objects.
Therefore, decision-making in such systems with incomplete data on the problem and functional
structure of technological processes and under the influence of disturbing influences with a priori
unknown statistical characteristics, is a complex intellectual procedure that includes the selection of
adequate object models, algorithms for data selection and processing, and accordingly, the formation
of approaches to the synthesis of decision-making procedures using the theory of possibility and the
theory of fuzzy sets in the assessment of situations based on the object state images recognition
CITRisk’2021: 2nd International Workshop on Computational & Information Technologies for Risk-Informed Systems, September
16–17, 2021, Kherson, Ukraine
EMAIL: lssikora@gmail.com (L.Sikora); lysa.nataly@gmail.com (N.Lysa); jan.krejci@ujep.cz (J.Krejčí); rlvtk@ukr.net
(R.Tkachuk); olha.y.fedevych@lpnu.ua (O.Fedevych)
ORCID: 0000-0002-7446-1980 (L.Sikora); 0000-0001-5513-9614 (N.Lysa); 0000-0003-4365-5413 (J.Krejčí); 0000-0001-9137-1891
(R.Tkachuk); 0000-0002-8170-3001 (O.Fedevych)
© 2021 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)
[1, 2, 4–7].
Purpose. Substantiation of information technologies methods, system analysis, logical-
cognitive models for control systems of technogenic structures in the conditions of threats
creation.
2. References analysis
In the fundamental work [1] the principles of complex control structures of automated human-
machine systems creation are considered and large systems development forecast is given. In [2,
3] the hierarchical systems construction methods using manager operator cognitive models are
analyzed. Problems of operator activity on management in ACS and operative thinking at
decision-making are considered in monographs [4, 5]. Management problems in the conditions
of a situation change at action of disturbances on process of decision-making are shown in [6, 8].
The monograph [7] highlights the logical problems of artificial intelligence for use in control
systems. The monograph [16] is devoted to the study of mathematical modeling methods of data
processing processes by a human operator in human-machine systems and the detection of errors
due to factors influencing its activities. Monographs [15, 17] are devoted to data processing
methods for decision making, artificial intelligence, theory of knowledge and learning, modern
technologies of process analysis and technical logic.
In [11, 12] the analysis of risks models which arise in hierarchical technogenic systems is
carried out.
In [9] construction methods of information technology of formation and decision-making
under risk conditions are considered for management of technogenic systems with use of
cognitive model of operator activity. In [10] the problem of decision-making in the risk
conditions and conflict situations in the presence of terminal restrictions is considered at the time
of resolving the crisis in the complex system management structure.
The results of research used in the [13, 14, 19–21] are devoted to the analysis of information
technologies, the concept of their development, platforms and standards, software and expert
systems, fuzzy logic.
In [22] the use of data mining to improve energy efficiency in complex systems is
substantiated.
The paper [23] is devoted to developing the Multi-hazard Risk Assessment Framework
containing models, scenarios, and methods for analyzing the risk related to multi-hazards. The
multi-layered spatial model and the model of the Human-Infrastructure System based on
hierarchies and having great scalability in time and space are proposed. These models take into
account all possible relations between people, objects of infrastructure, natural environment, and
corresponding spatial areas [24]. The proposed event-based scenario representation model
provides sufficient detailization in space and time and can properly represent multi-hazards,
including compound events, cascading effects, and risk-related processes driven by
environmental and societal changes.
3. Presentation of the main research material
Decision-making under active threats in hierarchical organizational and production systems is a
complex problem and is characterized by both a game component and clear decision-making
procedures in the management of technological processes (TP) and organizational and
administrative structures (OAS), both in normal and in extreme conditions that arise due to
information-type attacks and cognitive failures of managers.
Decomposition of making managerial decisions problem in terms of threats risks can be
divided into a set of tasks:
– creation of new intelligent control systems for the processes of autonomous control systems
functioning (ACS) of TP and SCA;
– existing ACS operating modes diagnostics, their optimization and adaptation to the effects
of disturbances and threats and changes in their target orientation.
3.1. Classification of intelligent control information systems
Here is the classification of intelligent information systems (IIS) [2, 3], which are components of
automated control systems (human-machine complexes):
– problem-oriented expert systems using artificial intelligence for data processing and
classification;
– intelligent information systems of man-made and organizational structures situational
management that operate in the face of threats and attacks to change strategies and goals;
– сomputational and logical modeling systems of dynamics of potentially dangerous objects
(PВO) – design objects;
– intelligent educational systems in the structure of universities;
– intelligent simulators for special training of personnel working in conditions of threats and
cognitive disruptions;
– intelligent agents, as goal-oriented structures in hierarchical control systems of technogenic
systems.
3.2. Consideration the classes of problems, the solution of which
ensures the reliable operation of man-made (technogenic)
systems in the face of active threats
Problem area and types of tasks that can be performed by the information-intellectual system (IIS)
[16, 17] in the development of management strategies and ensuring resilience to active threats,
information attacks on the ACS system and technogenic structures:
– ault diagnosis of complex systems and software products;
– planning a targeted actions sequence for the strategies implementation;
– observation of situations, recognition and classification of images;
– object management in accordance with the setted strategies and goals.
Here is a block diagram of the interaction of intelligent systems (IS) – Figure 1.
Figure 1: Block diagram of the intelligent systems interaction (ACS-LPR)
Such a complex intellectual structure performs the function of object management with a certain
type of technological process {ТПj ← Fi}, which is affected by disturbing factors from the
external environment and the dynamics of market environment changes in the parameters. The
task of the system is to keep the object in the target operation area in case of resource type
failures and interferences. To effectively solve management problems, it is necessary that the
structure of decision-making procedures and data structure have a conjugate, consistent,
formalized, logical-mathematical and informational representation Figure 2 and appropriate
meaning in the perception of the situation content by the operator cognitive system.
The task, in the general case, is a situation with uncertainty that motivates purposeful actions
of the intelligent system to achieve a certain goal at a given time interval and its effective
solution based on proven strategies, methods, algorithms, procedures and cognitive methods.
The target in such a system is encoded in the solving system (IPS – intelligent problem
solver). Then it acts as requirements description for the state of the system in which the target is
formed. An intelligent system (IPS) is characterized by an algorithm and a procedure for finding
a strategy for problem task and situation solving, based on a given goal orientation.
V. Glushkov pointed out the important role of information technologies for the creation of
problems solving methods and procedures that arise in the design of systems (man-made,
publishing and organizational) in his research [8].
Substantiating their automation based on the use of information models of dialog mode,
inference, generating hypotheses and decision making methods, it was first identified the role of
management intellectualization in schemes for constructing procedures for the algorithms
synthesis for solving constructive problems. This did not take into account the cognitive, but
only the energy aspects of the operator's behavior when assessing the situation in the system
under the influence of active type interference and threats – Figure 2.
Figure 2: Information technology and interaction scheme of the agent with artificial intelligence
with the expert and the coordinating managing agent (IACS-TP) of the control system
4. Models of data perception in the ACS-TP operator field of attention
in the limit modes of energy-active object operation
The operator's perception of analog and digital data from the control devices of the control object
state has its own features in assessing their content in the field of attention, which are that when
analyzing the situation in the object:
– digital data is stored in memory but not visible from previous trajectory history ( Fn trak ) ;
– fuzzy orientation, according to the data on the distance to the modes boundary lines
( FΔαr ) ;
– the tendencies change trajectory dynamics at control actions performance on a short
( )
terminal time interval is not traced FΔ∗trakX ( t ) ;
– the input of the system usually has border loads of the technological structure at maximum
power, it is impossible to clearly determine the allowable distance to the limit mode and the time
of transition to the emergency state in a short time interval (t02-t04) of energy-intensive object,
( )
FΔ0 (L A − Lg ) ;
– indication of maximum values changes the perception of the data content by the operator
and puts him in a stress state due to the alarm of the system transition to an uncontrolled
emergency state (t04, t05) F (HL( L A )) .
At perception of analog signals in the graphic form there are some lacks, and possibility of
the trajectory forecast the operator in terminal time is complexed at the expense of associative
figurative display of data in the attention field and scenario interpretation of events. (Ті) by
classifier of the situation – Figure 3. Only the trajectory interpretation leads to distortion of the
display scale values in different intervals of numerical values of measurement and when the
trajectory enters the mode boundary areas, causing stress in decision-making on management
(t04, t05), of ACS operator cognitive system.
Figure 3: Situation classifier block diagram
Designation to the structural scheme: {Si} – system state, DSit (θ (ti )) – dynamic in the time
moment t i by parameter Q , ( ALARM ) , ( AVAR ) – state of alarm and accident, IMS –
information measuring system, ACS – automated control system, TS (EICO) – technological
system with energy-intensive control object, RS – source of resources.
Based on the analysis of real load modes and standards, critical parameters are determined
and a permissible states regime map of the energy-active control object is formed, which is the
basis for developing a situations system classifiers based on the choice of power scale
class Sh (P ) .
With the target task of increasing the power of the energy-active object, the operator performs
complex (tracking) control according to on a given trajectory – Figure 4.
On a certain control cycle to the maximum load, the operator (Zi ) , depending on the value of
power load, perceives the situation on the basis of data with different levels of mental stress,
which can lead his neurocognitive system, from fear of an accident, to systemic-cognitive
failure.
Data perception distortion scheme (Fig. 4) by a person operator of ACS-TP reflects the
influence of many factors and interpretation of the situation content depending on the uncertainty
in the description of dynamic objects and units according to the confidence degree in the
readings of devices (correct), which are the part of IMS-ASU structure using current state change
trajectory images and assessment of membership functions {Mi}.
The reason for the existence of uncertainties should be considered incompleteness and
inconsistency of data from different devices that control the unit, incompleteness of the selected
information base of the IMS, aging of devices during long service life, measurement errors from
the type of control and management problem (which is being solved) according to the event
development scenario – Figure 3.
Shp N1xO N2xO N3xO N4xO
O N5xO
O max L+A
1.0
L+g
Ln
0.5
O 01
O min
0
t
t01 t02 t03 t04 t05 Ті 1
Shp Nx
N0 L+k
O max L+A
1.1
L+g
Ln
0.5
0.25
O01
Omin
?s1 ?s2 ?s3 ?s4
2
Figure 4: Data perception distortion scheme in the field of view of the ACS-TP operator in the
conditions of loading traffic growth
According to the type of tasks to be solved by the operator, uncertainties are formed in the
generated situations under the influence of obstacles:
– Uncertainty due to the ambiguity of existing knowledge about the object in the database and
knowledge base and blurring and ambiguity, incomplete professional knowledge of the operator
and his ability to make decisions in stressful situations;
– Uncertainty caused by incomplete knowledge about the object for different subject-oriented
area hierarchy levels of control object units and blocks description, which have a physical or
linguistic nature.
According to the situation, the uncertainties are divided into:
Linguistic uncertainty – is caused by the vagueness and ambiguity of individual words of
grammatical constructions, which have syntactic, semantic and pragmatic components and
represent a description of the situation.
Cognitive uncertainty – is generated by the perception peculiarity of different types of data
devices in the field of operators attention and their interpretation.
Physical uncertainty – is caused by a low level of knowledge about physico-chemical energy
processes in the management object and misunderstanding of their essence, which leads to
incorrect management decisions, increased risk of accidents, technological process instability.
Physical uncertainty is associated with the stochasticity of events, phenomena, processes,
their causal relationships, the error in the data selection at different times when changing the
technological process dynamic modes in the object units and blocks.
When approaching the limit modes, the operator on the basis of information from the data
stream from the multimedia board and analog and digital devices that are in his field of vision
forms situation image in the system target space according to the mode specified by the manager.
According to the load, the operator decides to correct the situation in the event of resource
disturbances, information threats, system attacks, malfunctions appearances, that can cause
accidents and risks in the system. The modes dependence on the load level, leads to cognitive
stress when making decisions on the correction of state control and the anxiety growth when
approaching the allowable normative values.
In such a situation, the operator as a cognitive intellectual agent must have a certain
intellectual potential that ensures effective management decisions. Intellectual potential depends
on the knowledge of professional training, the ability to make decisions in unusual situations.
Accordingly, this approach is the basis for the separation of activity factors.
Selected factors of ability to manage, in terms of risk and extreme situations, are formed in the
tables:
Table 1 – factors of operator disorientation while decision making;
Table 2 – uncertainties factors in the data selection on the object state to assess the situation
by the operator;
Table 3 – cognitive factors in assessing the reliability of data and management decisions;
Table 4 – knowledge required to perform the management decisions by the operator.
The values of factors (coefficients) are obtained in the process of testing according to the
logical-cognitive approach of their construction [2, 3].
Table 1
Factors of operator disorientation in decision makingce
№ Facts Factor content kF
1 Fn (trak X i ) When digitally represented N Xi the state change F (N X )
trajectory is not traced
2 Fn (Δαr ) Loss of orientation by the operator when the FGr
trajectory approaches to the boundary mode line
3 FΔU (trak X ) There are no tendencies to change the trajectory FΔU
x (t , u ) under the action of management U in
conditions of noise
4 FΔU (LΔ − LG ) Disorientation of the operator when approaching the FΔ (LA )
emergency state of systems under the control and
interference action
5 F (HL(LA )) Occurrence of stress in the operator when F (max N
max N X approaching the emergency line and when estimating
the maximum devices readings
6 F (N X ± Δ i ) Distortion of data perception by the operator at F (sen D
disturbances action
7 ( )
FD N̂ X The operators confidence degree in the devices ( )
FD N̂ X
readings on the reliability level
8 FN (sit ПG ) The situation uncertainty factor in the operator FN X̂( )
imagination under the interference influence
Table 2
Uncertainties factors in selecting object status data for operator for event assessment
№ Facts Factor content kF
1 (
Fnd V pi |iU=1 ) Data incompleteness and inconsistency from Fnd
different devices
2 FIB (N X ) Incomplete information base of various devices F (Sh )
scales
3 Fsni (N X ) Contradictory data from different devices values F sn
4 FT ∈ (N X ) Changing readings due to aging devices FΔ N X
5 F (NT ) Devices terminal reliability during system operation FT
6 F (ΔX (ξ )) Device errors under interference action FΔX
7 FRS Errors dependence on the type of control tasks FR
importance
8 FUS Dependence on the type of management tasks FU
(need)
9 FV ( A lg VD ) Data reliability factor for selected measurement ( )
FV D̂
algorithms
10 (
FD A lg N̂ X ) Data reliability factor for selected data processing F (D̂ )
n
algorithms
11 FnZ (Di (ξ )) Uncertainty factor due to incomplete knowledge of FUZ
system functions
12 Fμ (Ndi ) Data blur Fμ
Table 3
Cognitive factors in assessing the data reliability and management decisions
№ Facts Factor content kF
1 FnZ 0 Low, disordered professional knowledge of a K nZ 0
professional operator about the object
2 FnR Low level of training K nR
3 FVR Ability and ability to make operational decisions KUR
4 FS (sit ) Ability to make decisions in a stressful situation K SS
5 Fnf Misunderstanding of physical processes in units and K nf
blocks
6 FL (sit ) Ability to linguistically meaningful description of the K LS
situation
7 FKZ (PRU ) The impact of interference on cognitive failure in K KZ
decision-making on management
8 Fμ (sit → Iconsit ) The ability to imagine the image of the situation K PU
9 FПС (Iconsit ) Ability to correctly assess the situation in the space K ПС
of goals
10 FKI (Di / Tm ) Ability to detect constructive information from the K Ki
data stream
11 Fnr (URi ) Indecision in making management decisions FnrU
Table 4
Knowledge that needed to make management decisions by the operator
№ Facts Factor content kF
1 Z sd Knowledge of the object’s structure and dynamics Fsd
2 Z ps Knowledge of how to represent the spaces of goals F ps
and states of the object
3 ( R
Z M F → sit ) Model of the object's reaction to the influencing Fm , f
factor
4 P
Z SU ((U , F ) → sit ) Ability to use knowledge to predict changes in the P
FSU
state under the action of management and threats
5 ZV (strat (U Ci )) Ability to build optimal strategies for achieving goals FCU
in the face of threats
6 K
Z pn (F → U d ) Ability to evaluate cause-and-effect diagrams of the F pnK
threat factors influence on the cognitive agent
management actions
7 K
Z PR (KsitU i ) Ability to make decisions in crisis and emergency K
FPR
situations based on system knowledge and experience
8 Z μ (Ді ) Ability to process fuzzy data Fμd ( Д і )
9 Z ЛІ (ПД і ) Ability to interpret blurred data Fμ ( Д і )
Based on the testing and the results obtained, it is possible to assess the level of operational staff
training at existing enterprises and optimize them to minimize incorrect decisions that lead to
emergencies due to incorrect assessment of measurement data about objects state and their
interpretation under threats and information attacks.
According to the situation that occurs in the system, table 5 and table 6 are constructed, which
characterize the ability of the operator to make management decisions.
Expert assessments of cognitive components (CFi , PRі ) for decision making by the manager.
Table 5
Cognitive operations for management
Kd Kr
Factor Cognitive acts
intervals value
CF1 goal realization 0,8-10 0,6-0,9
CF2 goal orientation 0,8-1,0 0,5-,8
CF3 generation of strategies 0,7-1,0 0,5-0,8
CF4 control logic 0,6-1,0 0,4-0,7
CF5 assessment of actions taken 0,5-1,0 0,5-0,7
PR1 action planning 0,6-1,0 0,5-0,8
PR2 choice of alternatives 0,6-1,0 0,5-0,8
PR3 wrong choice Ωі 0,5-1,0 0,3-0,7
PR4 creativity 0,7-1,0 0,6-0,9
PR5 goal generation 0,8-1,0 0,6-0,8
PR6 assessment of situations 0,5-1,0 0,5-0,9
PR7 logic procedure RZ 0,7-1,0 0,7-0,9
PR8 coordination procedures 0,8-1,0 0,7-0,9
Expert evaluation (ІІ) logic of thinking
Table 6
IT-technology cognitive components (КСі)
Components Information operations Intervals Kd, Kr
KCm whole oriented thinking cognitive models 0,6-0,95 0,50-0,95
KCd analytical data analysis 0,5-0,95 0,50-0,95
KCe logic of thinking, CІА 0,15-0,95 0,4-0,95
KCa cognitive processes algorithmization 0,10-0,95 0,25-0,90
situational tasks and problems essence cognitive
KCz 0,15-0,85 0,40-0,55
analysis
cognitive procedures for forming problem-solving
KCp 0,14-0,90 0,4-0,85
schemes
KCi identification of the problem tasks information essence 0,25-0,90 0,60-0,95
KCr use of information technology to solve problems 0,30-0,90 0,60-0,95
cognitive processing of CIA data streams received from
KCdv 0,30-0,85 0,40-0,90
the object
cognitive models of decision-making logic by an
KCl 0,4-0,90 0,40-0,90
intelligent agent
Cognitive coefficients of intellectual abilities expert assessment are determined on the basis of
{ } { }
test data processing PRi in=1 , {∀PRі ∈ [0,5 − 1,0]}, KCi ьі=1 , {∀KCi ∈ [0,7 − 1,0]}, and determine
the quality of decision-making by the operator in the face of threats.
Accordingly, there are assessments of the decision-making quality for the intelligent agent
management
→ [0,5 − 0,7] → [Rick → n ]
ІАn ∧{PRі і = 1,n} → [0,7 − 0,8] → [Alarm] .
і
→ [0,8 − 1,0] → [Norma ]
The assessment of the risk level is based on the following models that characterize the
processes of management decisions by the IA operator:
1. Probabilistic model of risk at the moment (t ∈ Tnk )
Risk (tі ∈ Tnk ) = L pi {Рі / Сі }ti → {Рі +1 / Сin }ti +1 → Alarm
where Pi – the probability of wrong decisions that lead to consequences {Сi } – failure of the
target task in the emergency area.
2. Unprofitable risk assessment model [22] when assessing an emergency situation:
H : С ∈ СV → (αr → 0)
Risk (Р / Сui ) → ∅ → ij і .
H i 2 : Сі ∉ Сv → (αr → 1)
Determines the maximum loss when exiting the target control area (CV ) .
3. Risk assessment based on the decision tree in the threats management of the maximum
load of man-made system energy-intensive units – Figure 5.
4. Methods of payment functions for the loss of structure, resources, products.
5. To assess the risk level in the face of threats and management failures, hypothesis testing
procedures were used in the form:
H 1 : ∀x[P ( x ) ⇒ Q ( x )] , P ( x ) = Z j ∈ Bi ;
H 2 : ∀x[Q ( x ) ⇒ R ( x )] , Q ( x ) = Z j +1 ∈ B j +1 .
Then the condition of reaching the target state is set
Ci : ∀x[P ( x ) ⇒ R ( x )] , traR ( x ) ≡ (Z j → Z j +1 → Z j + 2 ) , R ( x ) ≡ Z j + 2 ∈ Bc .
Str1 Alarm Avar
PVi
sit X
Str2 Risk 0.5 Norma
Str3 Gmish
Figure 5: Block diagram of risk assessment, where PVi – selection procedure, {Strі } – strategies
for choosing control actions
These chains can be blocked under stress, which leads to the failure of management actions and
emergencies.
5. Conclusion
The logical substantiation problem of decision-making rules in intellectual systems is
considered, the dialogue scheme and the decision – making scheme are substantiated as bases of
persons admissible behavior strategies synthesis (active agent). It is shown that in stupor state,
the deployment circuits in the process of logical goal-oriented output inference and event
scenario evaluation can be blocked, which leads to the IACS loss of control for a certain terminal
time.
The problem of forming target decision-making strategies for managing complex objects on
the basis of an active intelligent agent as a target-made system in the integrated automated
control systems structure is considered. The expert assessments construction methods for
checking the operators-intelligent agents cognitive abilities are substantiated.
References
[1] V. Hlushkov, Introduction to ACS, Kyiv, Technics, 1974
[2] B. Durniak, L. Sikora, M. Antonyk, R. Tkachuk, Automated human-machine control systems
of integrated hierarchical organizational and production structures in risk and conflicts
conditions, Lviv, Ukraine Academy of printing, 2013
[3] B. Durniak, L. Sikora, M. Antonyk, R. Tkachuk, Cognitive models of strategies formation of
integrated hierarchical structures operative management in the risks and conflicts
conditions, Lviv, Ukraine Academy of printing, 2013
[4] V. Zaitsev, System analysis of operator activity, Moscow, USSR Radio, 1990
[5] N. Machina, Economical risk and its measurement methods, Kyiv, TSNL, 2003
[6] H. Pospielov, Situational management, Moscow, Science, 1986
[7] L. Sikora, Cognitive models and logic of operational management in hierarchical integrated
systems in risk conditions, Lviv, TSSD EBTETS, 2009
[8] V. Hlushkov, Man and computer technology, Kyiv, Science thought, 1971
[9] L. Sikora, N. Lysa, O. Fedevych, M. Navytka, R. Tkachuk, I. Dronyuk, Information
technologies of formation of intellectual decision-making strategies under conditions of
cognitive failures, in: Proceedings of Computational & Information Technologies for Risk-
Informed Systems, CITRisk-2020, Kherson, Ukraine, 2020, pр. 233–254
[10] L. Sikora, R. Tkachuk, N. Lysa, I. Dronyuk, O. Fedevych, Information and logic cognitive
technologies of decision-making in risk conditions, in: Proceedings of the 1st International
Workshop on Intelligent Information Technologies & Systems of Information Security,
IntellTSIS 2020, Khmelnytskyi, Vol. 2623, Ukraine, pp. 340–356
[11] S. Orel, M. Malʹovanyy, Risk, Lviv, LPNU, 2008
[12] Complete works of V. Hlushkov, Cybernetics institute, Investigation models and methods
for risks and reliablility theory operations, Kyiv, Cybernetics institute, 1992
[13] M. Barankevych, Expert methods in decision making, Lviv, Ivan Franko LNU PC, 2008
[14] National Aerospace University Kharkiv Aviation Institute, CASE – evaluation of critical
software systems, vol.1, Khmelnytsk-Kharkiv, NAU, 2012
[15] A. Barsyegian, Data and process analysis, Sankt-Petersburg, BHV-Peterburg, 2009
[16] V. Prisnyakov, L. Prisniakova, Information processing mathematical modeling conducted
by the human-machine systems operator, Moscow, Machinebuilding, 1990
[17] I. Chubukova, Data Mining, Moscow, IUIH Binom, 2008
[18] O. Larichev, Theory and methods of decision making, Moscow, LOGOS, 2000
[19] V. Sukhomlyn, Introduction to information technology analysis, Moscow, Hotline Telekom,
2003
[20] A. Vendrov, Software design of economic information systems, Moscow, Finance and
Statistics, 2000
[21] O. Belz, Fundamentals of economic expert systems, Lviv, Ivan Franko LNU PC, 2009
[22] M. Medykovskvi, O. Pavliuk, R. Sydorenko, Use of Machine Learning Technologies for the
Electric Consumption Forecast, Proceedings of the13th International Scientific and
Technical Conference on Computer Sciences and Information Technologies CSIT-2018,
Lviv, Ukraine, 2018, pp. 432-435. doi: 10.1109/STC-CSIT.2018.8526617
[23] V. Sherstjuk, M. Zharikova: Risk assessment framework based on the model of human-
infrastructure system. CEUR Workshop Proceedings, 2020, 2740, pp. 37–52 http://ceur-
ws.org/Vol-2740/20200037.pdf
[24] V.Peredery, M.Voronenko, E.Borchik, J.Krejci, Information technology of operative
formation and evaluation of relevant alternatives of decision-making in human-machine
systems of critical application, International Scientific and Technical Conference on
Computer Sciences and Information Technologies, 2018, 1, pp. 33–36, 8526750