Digitalization Challenges:

A Decision-Making Model for SCADA Systems Staff Selection

DANIELA BORISSOVA1, ZORNITSA DIMITROVA1, NAIDEN NAIDENOV1,

MAGDALENA GARVANOVA2, IVAN GARVANOV2, IVAN BLAGOEV1

1Information Processes and Decision Support Systems,

Institute of Information and Communication Technologies at the Bulgarian Academy of Sciences,

Acad. G. Bonchev Str. Bl. 2, Sofia 1113

BULGARIA

2Information Systems and Technologies

University of Library Studies and Information Technologies

Tsarigradsko shose Boul. 119, Sofia 1784

BULGARIA

Abstract: - The article examines the issues related to industrialization and more precisely the main driver of

digital transformation namely people. Industry 5.0 through digitization focuses on promoting sustainability and

the need for social and individual well-being. The most important factor in digital transformation is people, not

technology. And here is the main problem – there are not enough people with skills to support high-tech

systems such as SCADA. For this goal, a decision-making model in the selection of staff for SCADA systems

support is proposed. The applicability of the model is used in the selection of staff to support a SCADA system

of a small airport with the primary goal of detection and recognition of moving objects. The obtained results are

encouraging and give confidence about the applicability of the proposed model.

Key-Words: digitalization challenges; decision making; mathematical model; SCADA; staff selection;

evaluation criteria.

Received: February 16, 2024. Revised: July 17, 2024. Accepted: August 11, 2024. Published: September 26, 2024.

1 Introduction

With the emergence of Industry 4 and Industry 5 in

recent years, ongoing digital industrial

transformation can be identified in various

applications in industrial areas, [1], [2]. Industry 5.0

through digitization and technology emphasizes the

promotion of sustainability and foregrounds the

need for both social and individual well-being.

Therefore, digital transformation is directly related

to the adoption of disruptive technologies that

increase not only productivity but also lead to

improved social welfare, [3]. The most important

factor in digital transformation is not technology,

but people. And here is the main problem: there are

not enough people with the skills to engage with the

challenges that new digital technologies pose.

Ones of the most important systems

contributing to industrial digitalization are the

SCADA (Supervisory, Control and Data

Acquisition) systems, designed for remote

supervision, control and optimization of industrial

processes, with the ability to integrate data collected

from various industrial processes and automata.

Control and data collection systems aim to improve

the efficiency of industrial control systems while

also providing better protection of the equipment

used, [4], [5]. SCADA and industrial control

systems play an essential role in managing and

controlling critical infrastructures. The list of critical

infrastructures varies in different countries and

could include nuclear reactors, transportation

including airports, chemical/civil engineering, water

plants, wind and photovoltaic farms, agriculture,

healthcare, research, etc. SCADA contributes to

facilitating the seamless flow of data essential for

monitoring, control, decision-making, and more.

Along with Industries 4.0 and the Industrial

Internet of Things (IIoT) evolution, contemporary

SCADA systems rely on different technologies

including cloud technology [6], big data analytics

[7], [8], artificial intelligence [9], [10], and machine

learning, [11], [12], [13].

Some of the opportunities, challenges, and

potential solutions to the challenges of integrating

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1869

Volume 21, 2024

IIoT into existing SCADA systems are discussed in

[14]. The use of these technologies contributes to

improving interoperability, easing maintenance, and

thus decreasing the infrastructure cost, [15]. In a

review paper, the authors analyze SCADA system

architectures and implemented communication

protocols to understand and highlight the need for

the security of SCADA systems, [16].

In addition, the need for technological resilience

of cyber assets should be mentioned, which can only

be achieved in the presence of well-trained and

motivated specialists, [17]. It should also be noted

that the weakest link in the security chain is the

human being, which can be either a user, a

customer, an administrator, or even a manager, [18].

Therefore, technological progress needs competent

users/operators with the necessary skills to perform

not only routine procedures but also decision-

making in critical situations, [19].

Personnel recruitment refers to a systematic

process of evaluating and selecting the most

qualified candidates from a given number for a

particular position, [20], [21]. In this regard, the

current article proposed a model to support

decision-making in selecting of staff to support

SCADA systems. The recent investigation describes

the most common uses of machine learning in

personnel selection, along with some challenges to

adopting machine learning in personnel selection,

[22]. In contrast to the variety of approaches for the

selection of personnel, [23], [24], [25], the proposed

model is formulated to be easy and flexible to cope

with the problem of selection of staff to support

SCADA systems.

The rest of the paper follows the following

structure: Section 2 provides basic information

about key indicators important in the staff selection

considering SCADA systems, Section 3 describes

the proposed model for evaluation and selection of

the most reliable candidates to support SCADA

systems; Section 4 contain the data for numerical

testing; Section 5 describes the obtained results and

discussion and the conclusion is drawn in Section 6.

2 Groups of Criteria to Evaluate

Candidates to Support SCADA

Systems

SCADA systems differ for different specific

industries and applications but it is easy to identify

some commonly supported functionalities such as:

 Data collection is a basic functionality of

SCADA systems because thanks to the

sensors it becomes possible to collect the data

transmitted to the field controllers, which in

turn transmit them to the SCADA computers.

 Another basic functionality is remote control,

which is achieved by controlling field

actuators and the data received from field

sensors via sensor networks. The sensors and

actuators have to work in sync in collecting

and sending data and this should be properly

reflected in all sensed data.

 Through network communication, it is

possible to implement all SCADA

functionalities. The data collected from the

sensors through the SCADA field controllers

is transmitted to the SCADA monitoring

computers. In the opposite direction – remote

control instructions are transmitted from the

SCADA monitoring computers to the

actuators.

 Data presentation, which is the process of

visualizing both current and historical data to

the operators controlling the SCADA system,

is implemented through appropriately

designed human-machine interfaces.

 Real-time processing and visualization

combined with historical data are important

for SCADA systems. This is because based on

this data, operators can track and make

decisions based on current state trends versus

historical ones.

 Alert alarms in SCADA systems are designed

to promptly inform operators of potential

anomalies in the system. These alarms are

configured to notify operators of stalled

processes, malfunctions, or situations where

SCADA processes need to be stopped, started,

or corrected.

 Reporting in SCADA systems. This

functionality refers to the generation and

distribution of reports based on collected data.

These reports can be customized for various

specific uses and could include various

information, such as operational status,

alarms, performance metrics, and trends.

SCADA systems work with a real-time

operational database that presents both current and

past values used to monitor and control the

operation. Databases play a crucial role in the

storage and management of historical data, as they

enable the retrieval of historical data used to analyze

trends, optimize processes, and make strategic

decisions. Therefore, security is vital for SCADA

systems, as in most cases access to databases is

remote. The use of firewalls, encryption,

authentication, and appropriate access controls is

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1870

Volume 21, 2024

mandatory to protect data and infrastructure. This

means that operational staff must be aware of

security measures against data breaches and cyber-

attacks.

To be efficient and effective, the most reliable

candidate has to be able to handle various

technologies related to sensors and signal

processing, communication protocols, data mining,

and decision-making and specifics of the application

area as shown in Figure 1.

Fig. 1: Knowledge of various technologies for

SCADA

Knowledge related to the sensors networks and

actuators is required as the SCADA systems collect

data from multiple units to measure temperature,

pressure, flow rate, voltage, and other characteristics

and then send it to a central computer system. The

collected data is transmitted securely via a remote

terminal unit to a dedicated server or cloud. Next,

the data needs to be properly processed and

interpreted to retrieve the trends by a suitable

method such as statistics, machine learning, big data

analytics, etc. to get the information. This

information needs to be analyzed additionally with

the help of suitable decision-making models that

decisions will contribute to determining the final

decision. The connection between field instruments

that collect sensor data, controllers, and central

SCADA computers is made through the

communication infrastructure, allowing operators to

visualize current and historical data in the human-

machine interface. This process must necessarily be

in accordance with the subject area in which

SCADA is implemented. This theoretical

knowledge would not be useful if the candidate

failed to demonstrate its application in practice.

Along with the required knowledge, the

preferred candidate should also possess additional

skills such as good verbal and written

communication, active listening; teamwork which is

a critical factor for the success of any business;

awareness; ability, and readinеss to devеlop,

organizе, and run a businеss processes/project;

ability to conflict and stress management;

motivation; time management; confidence building;

decision making, etc.

All this means that the indicators for evaluation

and selection of the most preferred candidate for

managing the SCADA system can be grouped into

the following three groups of criteria:

 Theoretical knowledge: sensor networks,

controllers, signal processing techniques,

database, data analysis, big data mining

algorithms, machine learning techniques and

algorithms, programming language/s, human-

machine interface, models for decision-

making, etc.

 Soft skills: verbal and written communication,

active listening, working in a team, conflict

management, strategic thinking, creativity,

ability to manage stress, initiative, curiosity

planning, flexibility discipline, deductive

reasoning and synthesis, confidence building,

problem-solving, empathy, social skills, etc.

 Problem-solving – solving specific practical

cases.

It should be noted, that hard skills and practical

problem-solving can be much easier to identify

because they could be assessed using appropriate

tests, [26]. Soft skills are highly subjective and

require interviews through which it is possible to

ascertain some of these skills.

These three types of criteria sets appear to be

useful as evaluation criteria in the selection of

personnel to maintain SCADA systems.

3 Mathematical Model for Assessment

and Selection of the Most Reliable

Candidate for Support SCADA

Systems

To assess candidates for supporting the SCADA

systems it is necessary to consider three separate

groups of criteria concerning theoretical knowledge,

soft skills, and practical problem-solving. This is

realized through the proposed mathematical model

for the assessment of the performance of candidates

(), formulated as follows:

 



   



 

 



  



       



 



  







   

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1871

Volume 21, 2024







   

where   󰇝   󰇞 is used to denote the set of

candidates, coefficient α is used to denote the

importance of theoretical knowledge, coefficient β

is used to denote the soft skills, while the coefficient

 expresses the practical problem-solving.

The coefficients , , and  are used to

denote the importance of criteria related to

theoretical knowledge, soft skills, and practical

problem-solving. The evaluation score of i-th

candidate about the t-th criterion is denoted by ,

 expresses scores of i-th candidate about the s-th

criterion regarding soft skills, while  expresses

scores of i-th candidate about the p-th criterion

regarding practical problem-solving.

The allowable interval of the evaluation scores

 a , and  should be identical to the variation

interval of the other variables in the proposed model

(1) – (5). Therefore, the interval between 0 and 1

can ensure that comparable values are obtained, and

is therefore considered an acceptable variation

interval. Using the relation (2) it is possible to

aggregate the separated three parts of evaluation

regarding theoretical knowledge, soft skills, and

practical problem-solving in the final generalized

assessment. According to relation (1), the ranking of

the candidates could be done by considering three

types of criteria with different importance. Thus the

model becomes more flexible to defined groups of

criteria that can be considered with different

importance in determining the final candidates’

ranking.

The formulated mathematical model (1) – (5)

could be easily simplified if necessary by imposing

a value equal to zero for one or two of the

coefficients in relation (2). In this situation, the

proposed model (1) – (5) will rely only on one or

two of the groups of criteria. These scenarios can be

useful in the selection of personnel for the

implementation of a specific task and in the

selection of personnel for the formation of a team

for the implementation of a specific project.

4 Numerical Application

The applicability of the proposed mathematical

model (1) – (5) was applied to the selection of staff

to support a SCADA system of a small airport with

the primary goal of detection and recognition of

moving objects.

Ten candidates have submitted their documents

for the position to support the SCADA system. For

the evaluation, 5 indicators from the group of

theoretical knowledge are considered 1) sensors (t-

1); 2) signals processing (t-2); 3) protocols for

communications (t-3); 4) database (t-4); 5) decision-

making models (t-5). The second group of criteria

related to soft skills considers 1) conflict

management (s-1); 2) motivation (s-2); 3) planning

(s-3) and from the third direction, the candidates

need to solve a practical problem (p-1). The

normalized evaluations toward all of the described

indicators are shown in Table 1.

In addition to the normalized scores about

theoretical knowledge (,), soft skills (), and

practical problem solving (), according to the

proposed mathematical model (1) – (5), the

importance weights between theoretical knowledge,

soft skills and practical problem solving should be

determined by the coefficients (), () and 󰇛󰇜,

together with the importance coefficients for the

groups of criteria ,  and .

Three different scenarios are investigated and

the corresponding coefficients and weights for their

importance are shown in Table 2.

Table 1. Normalized evaluation score of candidates toward the groups of criteria

Theoretical knowledge

Soft skills

Practical problem

solving

t-1

t-2

t-3

t-4

t-5

s-1

s-2

s-3

p-1

0.94

0.78

0.81

0.94

0.86

0.78

0.98

0.86

0.88

0.95

0.91

0.79

0.87

0.88

0.92

0.75

0.81

0.85

0.88

0.96

0.79

0.83

0.89

0.95

0.77

0.89

0.84

0.87

0.93

0.8

0.82

0.89

0.83

0.85

0.81

0.93

0.91

0.87

0.79

0.86

0.81

0.82

0.92

0.79

0.9

0.89

0.93

0.78

0.86

0.79

0.89

0.85

0.77

0.88

0.90

0.93

0.72

0.81

0.79

0.88

0.94

0.86

0.81

0.80

0.97

0.82

0.78

0.9

0.82

0.9

0.81

0.93

0.86

0.94

0.86

0.8

0.79

0.85

0.82

0.81

0.88

0.87

0.86

0.88

0.76

0.88

0.83

0.8

0.79

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1872

Volume 21, 2024

Table 2. Coefficients for the importance of groups of criteria and weights for the importance of indicators

Group of criteria

Case-1

Case-2

Case-3

Theoretical knowledge

0.33

0.60

0.50

t-1

0.20

t-2

0.20

t-3

0.20

t-4

0.20

t-5

0.20

Soft skills

0.33

0.20

0.00

s-1

0.33

s-2

0.33

s-3

0.34

Problem-solving

0.34

0.20

0.50

p-1

1.0

Case-1 expresses the scenario in which

theoretical knowledge, soft skills, and practical

problem-solving have equal importance (α = β =

0.33,  = 0.34) and the distribution of weighted

coefficients between indicators takes equal

importance too.

Case-2 expresses the scenario where the

theoretical knowledge is predominant (α = 0.60)

regarding soft skills (β = 0.20) and practical

problem solving ( = 0.20) and the distribution of

weighted coefficients between indicators remains

the same.

Case-3 expresses the scenario, where theoretical

knowledge and practical problem solving have equal

importance (α = 0.50) and the group of

indicators toward soft skills has no importance

while the distribution of weighted coefficients

between indicators remains the same.

5 Results and Discussion

Based on the proposed model (1) – (5) and the input

data from the previous section, several optimization

problems determining the overall performance of

each candidate are formulated and solved. The

ranked list of candidates based on preferences in

Case-1 is shown in Figure 2.

Fig. 2: Candidates ranked according to preferences

from Case-1

From this ranking, it can be seen that the first

place is occupied by candidate #8 with an overall

performance score of .

If the strategy for ranking needs to be changed

using the preferences expressed by Case-2 are used,

then the ranking of candidates acquires a different

appearance, as shown in Figure 3.

Fig. 3: Candidates ranked according to preferences

from Case-2

In this situation, the first in ranking is candidate

#1 with a total score of .

According to the expressed preferences through

Case-3, the corresponding ranking list of the

candidates is shown in Figure 4.

Fig. 4: Candidates ranked according to preferences

from Case-3

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1873

Volume 21, 2024

In this ranking list, the best candidate is under #

4 with a score of .

The comparison between ranked lists of

candidates according to the different preferences

and using the same evaluations (Table 1) is shown

in Figure 5.

Fig. 5: Comparison between ranked candidates

using different preferences

The comparison of the three simulated scenarios

shows that depending on the preferences of the

expert authorized for the selection of personnel, the

most suitable candidate for the maintenance of

SCADA systems can be determined. If all three

groups of indicators are considered equally

important, then the ideal candidate should be #8 as

its overall performance score is the highest. If it is

needed to identify a candidate with the highest

theoretical knowledge less soft skills and practical

problem-solving, then candidate #1 is the solution.

When it is necessary to determine a candidate with

theoretical knowledge and practical problem-

solving, ignoring soft skills, the decision indicates

that the choice is for candidate #4.

It should be noted that all of these three

rankings according to the three different cases

(Table 2) do not elect the same candidate.

Depending on the specific situation and the required

qualities of the candidate for supporting SCADA

systems, it is possible to determine the appropriate

candidate. For example, the ranking may give more

preference to candidates with more theoretical

knowledge if a candidate with development skills is

sought. In situations where, for some reason, it is

imperative to quickly find a candidate, then it would

be inappropriate for the ranking to give preference

to candidates with practical experience in solving

problems.

Irrespective of the situation for choosing a

suitable candidate, it is necessary to take into

account some soft skills that will contribute to

building a better and responsible team. All this

means that the availability of various recruitment

tools is a step in the right direction and can be seen

as a prerequisite for increasing the quality of the

staff employed.

In cases where the job description allows for

working independently or working in small teams,

soft skills may be overlooked in comparison to

theoretical knowledge and practical problem-

solving. The larger team will always require skills

related to soft skills and some appropriate activities

should be carefully considered to overcome such

circumstances.

The use of such mathematical models

contributes to achieving not only high security in the

communications of complex systems such as

SCADA through the selection of suitable and

reliable staff for support but also to achieving better

economic sustainability.

6 Conclusion

The article examines the problems of assessment

and ranking with subsequent personnel selection.

For this purpose, a mathematical model is proposed,

which considers three separate groups of criteria

regarding theoretical knowledge, soft skills, and

practical problem-solving. The advantage of the

proposed model is the fact that these groups of

criteria can be taken into account in the final

decision with different importance. The tricky

element in the proposed modeling approach is the

determination of the type of indicators in the criteria

groups. Therefore, it is important when defining the

direct duties in the job description that the qualities

that the candidate must have for the specific position

are formulated. This would facilitate the

determination of the relevant indicators used in the

proposed model for ranking the applicants. The

relatively simple structure of the proposed model

makes it suitable for implementation in Excel

spreadsheets or it could be realized as a decision-

support tool.

The proposed decision-making model for staff

evaluation, ranking, and selection can be applied in

various areas where some kind of assessment and

subsequent choice needs to be made, for which

heterogeneous data are used. The limitations of the

proposed model consist in the fact that the ranking

of the candidates is realized taking into account the

preferences of only one authorized decision-maker.

Therefore, improvements in this work and future

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1874

Volume 21, 2024

development will be sought in formulating an

appropriate model for group decision-making to

consider more than one point of view in the process

of assessment and choice.

Acknowledgement:

This work is supported by the Bulgarian National

Science Fund by the project “Mathematical models,

methods and algorithms for solving hard

optimization problems to achieve high security in

communications and better economic

sustainability”, KP-06-H52/7/19-11-2021 and is

supported also by the Bulgarian National Science

Fund by the project “Innovative Methods and

Algorithms for Detection and Recognition of

Moving Objects by Integration of Heterogeneous

Data”, KP-06-N 72/4/05.12.2023.

References:

[1] Ghobakhloo, M., Mahdiraji, H.A.,

Iranmanesh, M., & Jafari-Sadeghi, V., From

industry 4.0 digital manufacturing to Industry

5.0 digital society: a roadmap toward human-

centric, sustainable, and resilient production,

Information Systems Frontiers, 2024,

https://doi.org/10.1007/s10796-024-10476-z.

[2] Kraus, K., Kraus, N., Manzhura, O.,

Ishchenko, I., & Radzikhovska, Y., Digital

transformation of business processes of

enterprises on the way to becoming Industry

5.0 in the Gig economy, WSEAS Transactions

on Business and Economics, Vol. 20, 2023,

pp. 1008–1029,

https://doi.org/10.37394/23207.2023.20.93.

[3] Nouria, K., The role of digital transformation

in achieving economic well-being the case of

Algeria, WSEAS Transactions on Business

and Economics, Vol. 21, 2024, pp. 1698–

1712,

https://doi.org/10.37394/23207.2024.21.139.

[4] Borissova, D., & Mustakerov, I., A concept of

intelligent e-maintenance decision making

system, In IEEE INISTA, Albena, Bulgaria,

2013, pp. 1–6,

https://doi.org/10.1109/INISTA.2013.657766

[5] Borissova, D., & Mustakerov, I., An

integrated framework of designing a decision

support system for engineering predictive

maintenance, Int. Journal Information

Technologies & Knowledge, Vol. 6, No. 4,

2012, pp. 366–376.

[6] Shahzad, A., Musa, S., Aborujilah, A. & Irfan,

M., A Performance Approach: SCADA

System Implementation within Cloud

Computing Environment, In 2013 Int. Conf.

on Advanced Computer Science Applications

and Technologies, Kuching, Malaysia, 2013,

pp. 274–277,

https://doi.org/10.1109/ACSAT.2013.61.

[7] Nie, X., Fan, T., Wang, B., Li, Z., Shankar,

A., & Manickam, A., Big Data analytics and

IoT in operation safety management in under

water management, Computer

Communications, Vol. 154, 2020, pp. 188–

196,

https://doi.org/10.1016/j.comcom.2020.02.052

[8] Ikegwu, A.C., Nweke, H.F., Anikwe, C.V.,

Alo, U.R., & Okonkwo, O.R., Big data

analytics for data-driven industry: a review of

data sources, tools, challenges, solutions, and

research directions, Cluster Computing, Vol.

25, 2022, pp. 3343–3387,

https://doi.org/10.1007/s10586-022-03568-5.

[9] Aldossary, L.A., Ali, M., & Alasaadi, A.,

Securing SCADA systems against cyber-

attacks using artificial intelligence, In 2021

Int. Conf. on Innovation and Intelligence for

Informatics, Computing, and Technologies

(3ICT), Zallaq, Bahrain, 2021, pp. 739–745,

https://doi.org/10.1109/3ICT53449.2021.9581

394.

[10] Alzahrani, A., & Aldhyani, T.H.H., Design of

efficient based artificial intelligence

approaches for sustainable of cyber security in

smart industrial control system, Sustainability,

Vol. 15, No. 10, 2023, 8076,

https://doi.org/10.3390/su15108076.

[11] Timken, M., Gungor, O., Rosing, T. &

Aksanli, B., Analysis of machine learning

algorithms for cyber attack detection in

SCADA power systems, In 2023 Int. Conf. on

Smart Applications, Communications and

Networking (SmartNets), Istanbul, Turkiye,

2023, pp. 1–6,

https://doi.org/10.1109/SmartNets58706.2023.

10216147.

[12] Balla, A., Habaebi, M.H., Islam, MD. R., &

Mubarak, S., Applications of deep learning

algorithms for supervisory control and data

acquisition intrusion detection system,

Cleaner Engineering and Technology, Vol. 9,

2022, 100532,

https://doi.org/10.1016/j.clet.2022.100532.

[13] Diaba, S.Y., Anafo, T., Tetteh, L.A., Oyibo,

M.A., Alola, A.A., Shafiekhah, M., &

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1875

Volume 21, 2024

Elmusrati, M., SCADA securing system using

deep learning to prevent cyber infiltration,

Neural Networks, Vol. 165, 2023, pp. 321–

332,

https://doi.org/10.1016/j.neunet.2023.05.047.

[14] Nechibvute, A., & Mafukidze, H.D.,

Integration of SCADA and industrial IoT:

Opportunities and challenges, IETE Technical

Review, Vol. 41, No. 3, 2023, pp. 312–325,

https://doi.org/10.1080/02564602.2023.22464

26.

[15] Lin, C.-Y., & Nadjm-Tehrani, S., Protocol

study and anomaly detection for server-driven

traffic in SCADA networks, International

Journal of Critical Infrastructure Protection,

Vol. 42, 2023, 100612,

https://doi.org/10.1016/j.ijcip.2023.100612.

[16] Yadav, G., & Paul, K., Architecture and

security of SCADA systems: A review,

International Journal of Critical

Infrastructure Protection, Vol. 34, 2021,

100433,

https://doi.org/10.1016/j.ijcip.2021.100433.

[17] Blagoev, I., & Shalamanov, V., Development

of cyber ranges as a reference environment for

digital transformation, In: 2023 4th

International Conference on Communications,

Information, Electronic and Energy Systems

(CIEES), Plovdiv, Bulgaria, 2023, pp. 1–5,

https://doi.org/10.1109/CIEES58940.2023.10

378806.

[18] Giacomello, G., & Pescaroli, G., Managing

human factors, In: Kott, A., Linkov, I. (eds)

Cyber Resilience of Systems and Networks.

Risk, Systems and Decisions, 2019,

https://doi.org/10.1007/978-3-319-77492-

3_11.

[19] Stoyanova, K., & Guliashki, V., MOEAs for

portfolio optimization applications, Lambert

Academic Publishing, 2018.

[20] Nalbant, K.G., A methodology for personnel

selection in business development: An

interval type 2-based fuzzy DEMATEL-ANP

approach, Heliyon, Vol. 10, No. 1, 2024,

e23698,

https://doi.org/10.1016/j.heliyon.2023.e23698.

[21] Kazancoglu, Y., & Ozkan-Ozen, Y.D.,

Analyzing Workforce 4.0 in the Fourth

Industrial Revolution and proposing a road

map from operations management perspective

with fuzzy DEMATEL, Journal of Enterprise

Information Management, Vol. 31, No. 6,

2018, pp. 891–907,

https://doi.org/10.1108/JEIM-01-2017-0015.

[22] Campion, E.D., & Campion, M.A., Impact of

machine learning on personnel selection,

Organizational Dynamics, Vol. 53, No. 1,

2024, 101035,

https://doi.org/10.1016/j.orgdyn.2024.101035.

[23] Li, J., He, R., & Wang, T., A data-driven

decision-making framework for personnel

selection based on LGBWM and IFNs,

Applied Soft Computing, Vol. 126, 2022,

109227,

https://doi.org/10.1016/j.asoc.2022.109227.

[24] Van Iddekinge, C.H., Lievens, F., & Sackett,

P.R., Personnel selection: A review of ways to

maximize validity, diversity, and the applicant

experience, Personnel Psychology, Vol. 76,

No. 2, 2023, pp. 651–686,

https://doi.org/10.1111/peps.12578.

[25] Kanakaris, N., Giarelis, N., Siachos, I., &

Karacapilidis, N., Making personnel selection

smarter through word embeddings: A graph-

based approach, Machine Learning with

Applications, Vol. 7, 2022, 100214,

https://doi.org/10.1016/j.mlwa.2021.100214.

[26] Zhou, Y.-F., Yang, H.-L., Li, J.-J., Lin, & Yi-

D., Automata for knowledge assessment

based on the structure of observed learning

outcome taxonomy, Information Sciences,

Vol. 659, 2024, 120058,

https://doi.org/10.1016/j.ins.2023.120058.

Contribution of Individual Authors to the

Creation of a Scientific Article (Ghostwriting

Policy)

The authors equally contributed to the present

research, at all stages from the formulation of the

problem to the final findings and solution.

Sources of Funding for Research Presented in a

Scientific Article or Scientific Article Itself

No funding was received for conducting this study.

Conflict of Interest

The authors have no conflicts of interest to declare.

Creative Commons Attribution License 4.0

(Attribution 4.0 International, CC BY 4.0)

This article is published under the terms of the

Creative Commons Attribution License 4.0

https://creativecommons.org/licenses/by/4.0/deed.en

_US

WSEAS TRANSACTIONS on BUSINESS and ECONOMICS

DOI: 10.37394/23207.2024.21.152

Daniela Borissova, Zornitsa Dimitrova,

Naiden Naidenov, Magdalena Garvanova,

Ivan Garvanov, Ivan Blagoev

E-ISSN: 2224-2899

1876

Volume 21, 2024