Adopting Artiﬁcial Intelligence in Danish SMEs: Barriers to Become a

Data Driven Company, Its Solutions and Beneﬁts

Nadeem Iftikhar

and Finn Ebertsen Nordbjerg

University College of Northern Denmark, Aalborg 9200, Denmark

Keywords:

Industry 4.0, Artiﬁcial Intelligence, SMEs, Smart Manufacturing.

Abstract:

Artiﬁcial intelligence allows small and medium-sized enterprises (SMEs) in the manufacturing sector to im-

prove performance, reduce downtime and increase productivity. SMEs in Denmark are still struggling to

implement artiﬁcial intelligence based strategies since they face a range of challenges, such as business ap-

plications, data availability, organizational culture towards the acceptance of new technologies, investment in

new technologies, skills gap, development process and effective strategy. In the beginning, the paper describes

the challenges faced by SMEs in adopting artiﬁcial intelligence. Then, the paper suggests solutions to over-

come these challenges and discusses the importance of artiﬁcial intelligence as well as the opportunities it

offers to SMEs.

1 INTRODUCTION

Industry 4.0, also called fourth industrial revolution,

is the integration of IT and production systems. The

IT systems compromise of artiﬁcial intelligence, in-

dustrial robots, sensors, alarms, IoT, cloud com-

puting, image analysis, inventory management, data

analysis and mood/behaviour analysis. The produc-

tion systems include but not limited to enterprise re-

source planning (ERP), manufacturing execution sys-

tem (MES), control and hardware. The integration of

IT systems with production systems provides new in-

sights from previously hidden information and allows

for better decision making. Further, since 5G reduces

response times from minutes to milliseconds, artiﬁ-

cial intelligence (AI) has become the main driving

force behind this industrial revolution in order to help

enterprises to improve yield, quality, performance, ef-

ﬁciency and to decrease product waste, downtime,

production and maintenance cost. AI is an broader

term that covers a wide range of concepts and tech-

nologies, including machine learning (ML) and deep

learning (DL). A survey of more than 500 Danish

companies (Colotla et al., 2016) concluded that most

of the companies are willing to change their business

models to adopt AI in order to become more produc-

tive and to improve customer as well as product ser-

vices. In spite of that most of the SMEs are left be-

https://orcid.org/0000-0003-4872-8546

hind in this race of embracing AI due to numerous

obstacles, just as, lack of expert knowledge, capabil-

ities and funds. Aiming to be a front-runner in the

use of AI, Denmark has formulated a National Strat-

egy for Artiﬁcial Intelligence

to boost research and

development in AI. The main aims of this strategy is

to establish better collaboration between researchers

and businesses, start new education programmes on

AI and raise an investment pool of DKK 1.5 (C 0.2)

billion based on public-private partnership to help en-

terprises adopt AI (O’Dwyer, 2019).

To summarize, the main contributions of this pa-

per are as follow:

• Discussing the main barriers for adopting AI.

• Suggesting the activities to be performed before

adopting AI and investigating what needs to be

done to prepare SMEs for AI adoption.

• Presenting the values of AI for SMEs.

The paper is structured as follows. Section 2

explains the motivation behind this paper. Sec-

tion 3 introduces the research methodology. Section 4

presents the challenges for successfully implementing

AI in SMEs. Section 5 suggests the solutions to deal

with these challenges. Section 6 presents the beneﬁts

of AI for SMEs. Section 7 concludes the paper and

points to the future directions.

https://en.digst.dk/policy-and-strategy/denmark-s-

national-strategy-for-artiﬁcial-intelligence

Iftikhar, N. and Nordbjerg, F.

Adopting Artiﬁcial Intelligence in Danish SMEs: Barriers to Become a Data Driven Company, Its Solutions and Beneﬁts.

DOI: 10.5220/0010691800003062

In Proceedings of the 2nd International Conference on Innovative Intelligent Industrial Production and Logistics (IN4PL 2021), pages 131-136

ISBN: 978-989-758-535-7

131

2 MOTIVATION

The European Commission deﬁnes SMEs as those en-

terprises employing fewer than 250 employees (Matt

et al., 2020), have an annual turnover of less than

DKK 375 (C 50) million and/or a total balance sheet

of less than DKK 320 ( C 43 million). According

to a survey conducted of European enterprises (J

ager

et al., 2015), only one-third of SMEs have adopted

the fourth industrial revolution compared to more than

two-thirds of large enterprises. The main challenges

for the European SMEs to adopt AI appear to be lim-

ited funding, changing business models, data acces-

sibility, legal and intellectual property issues, lack

of industrial standards and shortage of skilled work-

ers (Matt et al., 2020). Denmark’s industry structure

is centered around SMEs – there are currently more

than 300,000 SMEs in Denmark, corresponding to

more than 98% of Danish companies. Out of the to-

tal SMEs, just 5% SMEs in Denmark currently work

with AI (Lindberg et al., 2019). Further, only 20%

large enterprises have included AI in the core part

of their corporate strategy (Wagner, 2018). Denmark

ranks globally 25

on investment in AI and 65

as an

AI eco-system, total (% of GDP). Similarly like Euro-

pean SMEs, most of Danish enterprises also agree that

lack of skills and talent, access to funding, clear strat-

egy, data availability, ownership and commitment are

the biggest challenges to AI adoption. Adoption of AI

in Denmark will have a huge impact on Danish enter-

prises and economy. It will be a game changer for the

enterprises in order to help them to increase produc-

tivity and open the doors for new as well as innovative

products and business models. It is estimated that AI

may offers Danish enterprises between DKK 100 (C

13.5) to DKK 160 (C 21) billion of value potential.

Similarly, the impact potential of AI may bring up to

additional DKK 35 ( C 4.7) billion annually by 2030,

total (% of GDP).

Nonetheless, adopting AI will be costly, however,

its overall impact on the Danish economy will be pos-

itive. AI will make a positive difference to the Danish

job market by creating jobs up to 80,000 people with

AI skills by 2030 (Lindberg et al., 2019).

3 METHODOLOGICAL

APPROACH

The methodological approach used in this paper is

known as the systematic literature review (Kitchen-

ham et al., 2009). This approach deals with collect-

ing, checking and analysing data from the existing lit-

erature based on information found in journals, con-

ferences, books, academic dissertations, reports and

news articles with speciﬁc search questions in mind.

Some of the questions are as follow:

• What are the challenges of adopting AI in manu-

facturing SMEs in Denmark/Nordic countries?

• What solutions are most commonly associated

with AI adoption in SMEs?

• Does AI produce beneﬁcial outcomes for SMEs?

4 CHALLENGES FOR

ADOPTING AI IN SMEs

4.1 Overview

Small and medium-sized enterprises are far behind

in deploying AI-based technologies when compared

with large enterprises. The common challenges faced

by SMEs in Denmark as well as SMEs in neighbour-

ing Nordic countries and in Germany are: lack of sup-

port and commitment for AI within organization, high

degree of restraint over return on investment (ROI),

shortfall of right skills/competences, absence of dig-

ital standards, data security/privacy issues, inade-

quate funding and shortage of right tools/technologies

(Colotla et al., 2016), (Wuest et al., 2016), (Stentoft

et al., 2019), (El-Jawhari et al., 2020), (Bauer et al.,

2020), (Sjøberg, 2019), (Yu and Schweisfurth, 2020),

(Schr

oder, 2016), (Rauch et al., 2019), (Bianchini

and Michalkova, 2019), (Truv

e et al., 2019), (Aarstad

and Saidl, 2019), (Kim et al., 2018). Furthermore,

it can be observed in the radar chart (Fig. 1) with

number of quantitative variables that lack of organi-

zational readiness for change, skilled labour shortages

and shortage of funds are the three main obstacles to

AI adoption. As, the focus of this paper is to suggest

the activities that must be considered before imple-

menting AI in SMEs. Thus, in addition to these three

above mentioned challenges some of the other SME

speciﬁc challenges posed by AI adoption that must be

addressed are also discussed further in Section 5.

5 WAYS OF OVERCOMING THE

CHALLENGES

5.1 Overview

In order to overcome some of the challenges asso-

ciated with the adoption of AI, AI Denmark

has

https://aidenmark.dk

IN4PL 2021 - 2nd International Conference on Innovative Intelligent Industrial Production and Logistics

132

Shortage of workforce skilled in AI

Lack of clear business case

Lack of advice from experts

Lack of knowledge about the role of AI in Industry 4.0

Lack of access to good quality data

Shortage of funds

Lack of standards

Data security issues

Technologies not yet fully mature

Uncertain returns from investment

Lack of organizational readiness for change

Insufficient tailor-made AI solutions for SMEs

Manufacturing SMEs in

Denmark, Germany and

other Nordic countries

Figure 1: Barriers to AI adoption for SMEs.

launched an innovative project to help Danish SMEs

to increase their competitiveness with AI. The project

is ﬁnanced by The Danish Industry Foundation

. The

total project budget is DKK 34.5 (C 4.6) million and

the project will run for the next three years from 2021

to 2023. About 120 Danish SMEs will participate in

the project for a period of next six months in order

to gain competitive advantage. The main goals of the

project is to launch tailor-made/company-speciﬁc AI-

based pilot projects, provide training to its workforce

on the utilization of AI-based tools/technologies and

support successful process of organizational change.

In addition, the following initiatives will strengthen

the adoption of AI in Manufacturing SMEs in Den-

mark.

5.2 Business Strategy

5.2.1 Involvement of Top Management

The involvement of senior leadership in the imple-

mentation of Industry 4.0 and AI is one the most

critical success factors even more important than the

technical ability and AI technology (Dhasarathy et al.,

2020). Those SMEs, whose senior management has

basic understanding of AI-related technologies/tools,

their applications in SMEs and associated beneﬁts,

are more likely to succeed in adopting AI (Iftikhar

and Nordbjerg, 2021). Hence, it is recommended that

the top management should have a clear strategy of

how to generate most value with AI by investing in

AI skill development, good quality data and organiza-

tional cultural enhancement. Moreover, the AI strat-

egy should be an integral part of their overall business

strategy.

https://www.industriensfond.dk

5.2.2 Organizational Change Process and

Cultural Enhancement

Top management needs to enable a data and AI-

driven culture with in the organization (J

ohnk et al.,

2021). In order to meet this challenge, it is rec-

ommended that the top management must create AI

knowledge/awareness among its employees and edu-

cate the employees about the capabilities and value

of AI, in addition to the risks and limitations associ-

ated with AI. At the same time, they need to address

the ethical and moral implication of AI by generat-

ing trust between human-robot interaction tasks and

countering the fears of AI replacing their jobs.

5.2.3 Returns from AI Investment

To measure returns from AI investment, it is neces-

sary to calculate all possible costs such as, chang-

ing the overall business process and mindset, training

employees, data collection, technology investment as

well as forecast the business value that AI will bring

to the enterprise. In this way, the enterprise’s top man-

agement can make the decision on returns from AI

investment.

5.2.4 Crash Courses in AI for Everyone

The lack of AI knowledge within SMEs can prevent

them from adopting AI. Enterprise employees might

not know how to start/use or even which AI tech-

nology exists and how it can be used for their ben-

eﬁt (Hansen and Bøgh, 2021). To tackle this issue,

it is suggested that Denmark might also follow Fin-

land’s model to launch free online crash courses in

Elements of AI

with the aim of educating not only

the enterprise employees but also the general popula-

tion about this new technology. Similarly, enterprises

should commit and invest in the skill development

https://www.elementsofai.com

Adopting Artiﬁcial Intelligence in Danish SMEs: Barriers to Become a Data Driven Company, Its Solutions and Beneﬁts

133

programs of their work force. In addition, AI aware-

ness should be generated by establishing partnership

with other non-competing enterprises as well as edu-

cational institutions, especially the university colleges

for the reason that Danish university colleges have al-

ready close ties with SMEs. Basic to advanced level

AI courses should be offered with public-private part-

nerships for enterprises that are thinking about adopt-

ing AI as well as the enterprises that are already work-

ing with AI.

5.2.5 Business Case

Clearly deﬁning the ultimate project/business goals is

very crucial for the success of any AI-driven project.

It is suggested that the AI-driven project should start

with the identiﬁcation of a problem. The project

should have a speciﬁc and a clear business case. In

this regard, some of the most common questions that

should be answered are:

• What is this project going to achieve with respect

to business value?

• What is the problem that needs a solution?

• Why is the problem important?

• Are there any hypotheses?

• What is the preferred outcome?

• What are the expected beneﬁts for the business?

• Will the solution be actually implemented?

• What are the constraints with relation to the im-

plementation?

Further, once the scope of the to-do-list to achieve

the goals has been ﬁnalized. Assembling the right

project team, selecting the core functionalities and

preparing a prototype as early as possible, can form

the basis for a clear business case.

5.3 SME Collaborations

For Denmark to accelerate in AI adoption, a

joint alliance among SMEs, non-proﬁt organiza-

tions/associations, universities and startup companies

is necessary (Lindberg et al., 2019).

In this regard, an experimental learning facility

“small Industry 4.0 factory” has been established at

Aalborg University, Denmark. The main aim of

the learning factory is to create a platform for de-

veloping Industry 4.0 technologies to satisfy future

manufacturing requirements as well as demonstrat-

ing their value to SMEs in a production-like envi-

ronment (Nardello et al., 2017). Similarly, Manu-

facturing Academy of Denmark

and Norwegian Ar-

tiﬁcial Intelligence Research Consortium

has also

taken initiatives for the development of strategic part-

nerships between universities/university colleges, re-

search and technology organisations, start-up compa-

nies and SMEs.

Moreover, alliances among non-competing SMEs,

universities/university colleges and start-up compa-

nies are highly recommended. Through these al-

liances, partners can not only share their experiences

but also help in narrowing the talent gap by offering

expert help and contributing to the fund by sharing the

budget, for example due to similar business/use cases.

5.3.1 Narrow the Talent Gap in AI

The number of graduates in AI-related ﬁelds must be

increased by providing more AI-related educational

programs at Danish universities and university col-

leges as well as by attracting international talent. In

addition, to meet industry’s increasing need for AI

skills Denmark sets out to overcome the AI talent

shortage

by launching a large initiative called the

Danish Technology Pact (TP) to increase the number

of Science, Technology, Engineering and Mathemat-

ics (STEM) professionals with 20% by 2025.

5.3.2 AI Project Funding

SMEs should take proactive approach, partner with

other non-competing enterprises, start-up companies

as well as universities/university colleges in Den-

mark and internationally, and look for expert help,

for example, Manufacturing Academy of Denmark

(MADE) for funding their projects. Further, SMEs

can get funding help from Innobooster, which is a

funding programme within Innovation Fund Den-

mark

. Innobooster invests in promising ideas from

SMEs and start-ups. Innobooster covers 33% of

project expenses and invests up to DKK 5 ( C 0.65)

million in projects that demonstrate innovative think-

ing and signiﬁcant market potential.

Furthermore, it is recommended that ﬂexible loans

and tax incentives/credits should be offered to SMEs

carrying out AI-related projects. Cash awards should

be given for AI solutions that demonstrates best busi-

ness values. Similarly, SMEs should be offered

grants for private consultations, participation in train-

ing workshops and any opportunities to strengthen AI

skills of their work force.

https://www.made.dk

https://www.nora.ai

https://investindk.com/insights/denmark-sets-out-to-

overcome-the-ai-talent-shortage

https://innovationsfonden.dk

IN4PL 2021 - 2nd International Conference on Innovative Intelligent Industrial Production and Logistics

134

6 BENEFITS OF ADOPTING AI IN

SMES

6.1 Overview

The introduction of AI comes with many beneﬁts that

can help SMEs to gain valuable insight into their

usual operations and maintenance strategies, thus re-

ducing maintenance cost. SMEs can perform their

tasks in more efﬁcient way by improving operational

efﬁciency, production process and Overall Equipment

Effectiveness (OEE)

. Further, AI can assist SMEs in

raising human-robot collaboration, enhancing prod-

uct quality, minimizing downtime, increasing produc-

tivity, boosting revenue and exploring new business

opportunities (Colotla et al., 2016), (Lindberg et al.,

2019).

Furthermore, one of the direct beneﬁts of AI

in manufacturing SMEs is fault detection, predic-

tion/predictive maintenance and prevention, which is

described below.

6.1.1 Fault Detection, Prediction and Prevention

Fault detection or diagnosis identiﬁes a fault after

it occurred as well as the cause or location of the

fault and/or what needs to be adjusted in order to

ﬁx the fault. Fault diagnosis based systems monitor

data in real-time and provide an alert or alarm when

an anomaly has occurred (Iftikhar et al., 2020). On

the other hand, fault prediction or prognosis helps to

predict when and where a fault might occur, so that

necessary corrective actions can be taken. It is use-

ful to identify the remaining useful life of a machine

or when a equipment will fail (Angelopoulos et al.,

2020). Moreover, fault prevention takes fault predic-

tion a step further. In addition to predict the threats

of potential equipment failure, it also suggests what

actions should be taken in order to avoid the failure.

Additionally, a concrete example of the bene-

ﬁts of AI in a real-world medium-sized manufactur-

ing company in Denmark is presented in (Iftikhar

et al., 2019). One of the main goals of the exam-

ple “is to ﬁnd patterns at real-time in sensor data us-

ing AI that can help to predict and ultimately prevent

equipment/production line sudden failure”. Equip-

ment/production line failure is one of the most com-

mon causes of unplanned downtime that costs global

manufacturing sector an estimated DKK 315 ( C 42)

billion annually. Analyzing sensor data from a pro-

duction environment is complicated because the data

is often high dimensional and it is nearly impossible

https://www.oee.com

to ﬁnd patterns across dozens or even hundreds of sen-

sors, manually. AI has the ability to analyze the com-

plex relationships of the sensor data in real-time in

order to predict any upcoming errors in advance by

raising a warning ﬂag to keep production operations

running smoothly.

7 CONCLUSIONS

This paper underlines the importance of Industry

4.0 for SMEs that provides the opportunity to improve

their productivity and competitiveness by optimizing

their production processes. The paper also highlights

the Danish national strategies aim to reduce obstacles

for SMEs in order to adopt industry 4.0 and AI-related

technologies. Further, motivated by the impact of AI

on Danish economy in future, this paper aims at em-

phasizing the beneﬁts of AI that can help SMEs to

gain valuable insights from operational/process data

for better decision making.

Future research should validate and examine the

impact as well as measure the success of solu-

tions/activities suggested on AI adoption for SMEs.

REFERENCES

Aarstad, A. and Saidl, M. (2019). Barriers to adopting ai

technology in smes. Master’s Thesis, Copenhagen

Business School, Denmark.

Angelopoulos, A., Michailidis, E. T., Nomikos, N.,

Trakadas, P., Hatziefremidis, A., Voliotis, S., and Za-

hariadis, T. (2020). Tackling faults in the industry 4.0

era—a survey of machine-learning solutions and key

aspects. Sensors, 20(1):109.

Bauer, M., van Dinther, C., and Kiefer, D. (2020). Machine

learning in sme: An empirical study on enablers and

success factors. In Americas Conference on Informa-

tion Systems. AIS eLibrary.

Bianchini, M. and Michalkova, V. (2019). Data analytics

in smes: Trends and policies. OECD SME and En-

trepreneurship Papers, 14.

Colotla, I., Fæste, A., Heidemann, A., Winther, A.,

Andersen, P. H., Duvold, T., and Hansen, M.

(2016). Winning the industry 4.0 race: How ready

are danish manufacturers? Available online at:

https://innovationsfonden.dk/sites/default/ﬁles/2018-

07/bcg-winning-the-industry-40-race-dec-2016.pdf.

Dhasarathy, A., Gill, I., and Khan, N. (2020). The CIO

Challenge: Modern Business Needs a New Kind of

Tech Leader. McKinsey Digital.

El-Jawhari, B., Halbe, S., Whyte, M., Cobbaert, K.,

and Odenkirchen, A. (2020). An introduction

to implementing ai in manufacturing. Available

Adopting Artiﬁcial Intelligence in Danish SMEs: Barriers to Become a Data Driven Company, Its Solutions and Beneﬁts

135

online at: https://www.pwc.com/gx/en/industrial-

manufacturing/pdf/intro-implementing-ai-

manufacturing.pdf.

Hansen, E. B. and Bøgh, S. (2021). Artiﬁcial intelligence

and internet of things in small and medium-sized en-

terprises: A survey. Journal of Manufacturing Sys-

tems, 58:362–372.

Iftikhar, N., Lachowicz, B. P., Madarasz, A., Nordbjerg,

F. E., Baattrup-Andersen, T., and Jeppesen, K. (2020).

Real-time visualization of sensor data in smart man-

ufacturing using lambda architecture. In 9th Interna-

tional Conference on Data Science, Technology and

Applications, pages 215–222. Scitepress.

Iftikhar, N. and Nordbjerg, F. E. (2021). Implementing ma-

chine learning in small and medium-sized manufac-

turing enterprises. In 8th International Conference on

Changeable, Agile, Reconﬁgurable and Virtual Pro-

duction (forthcoming). Springer.

Iftikhar, N., Nordbjerg, F. E., Baattrup-Andersen, T., and

Jeppesen, K. (2019). Industry 4.0: Sensor data anal-

ysis using machine learning. In International Confer-

ence on Data Management Technologies and Applica-

tions, pages 37–58. Springer.

ager, A., Moll, C., Som, O., Zanker, C., Kinkel, S., and

Lichtner, R. (2015). Analysis of the Impact of Robotic

Systems on Employment in the European Union. Final

Report. Publications Ofﬁce of the European Union,

Luxembourg.

ohnk, J., Weißbert, M., and Wyrtki, K. (2021). Ready or

not, ai comes—an interview study of organizational

ai readiness factors. Business & Information Systems

Engineering, 63(1):5–20.

Kim, A. S., DiPlacido, M. P., Kerns, M. C., and

Darnley, R. E. (2018). Industry 4.0: Digiti-

zation in danish industry. Available online at:

https://core.ac.uk/download/pdf/212982545.pdf.

Kitchenham, B., Brereton, O. P., Budgen, D., Turner, M.,

Bailey, J., and Linkman, S. (2009). Systematic litera-

ture reviews in software engineering–a systematic lit-

erature review. Information and Software Technology,

51(1):7–15.

Lindberg, B., Andersen, J. R., Hansen, M. A. E., Frand-

sen, S., Krause, S., and Duvold, T. (2019). An

ai nation? harnessing the opportunity of artiﬁ-

cial intelligence in denmark. Available online at:

https://innovationsfonden.dk/sites/default/ﬁles/2019-

09/an-ai-nation-harnessing-the-opportunity-of-ai-in-

denmark.pdf.

Matt, D. T., Modr

ak, V., and Zsifkovits, H. (2020). Indus-

try 4.0 for SMEs: Challenges, Opportunities and Re-

quirements. Springer Nature, Cham.

Nardello, M., Madsen, O., and Møller, C. (2017). The smart

production laboratory: A learning factory for industry

4.0 concepts. In CEUR Workshop Proceedings (Vol.

1898).

O’Dwyer, G. (2019). Danish government injects 200

million euro into ai r&d. Available online at:

https://www.computerweekly.com/news/252466718/-

Danish-government-injects-200m-into-AI-RD.

Rauch, E., Dallasega, P., and Unterhofer, M. (2019). Re-

quirements and barriers for introducing smart man-

ufacturing in small and medium-sized enterprises.

IEEE Engineering Management Review, 47(3):87–94.

Schr

oder, C. (2016). The challenges of industry 4.0 for

small and medium-sized enterprises. Available online

at: https://library.fes.de/pdf-ﬁles/wiso/12683.pdf.

Sjøberg, M. (2019). Artiﬁcial intelligence in norwegian or-

ganizations: An exploratory study of challenges in ai

adoption. Master’s Thesis, University of Agder, Nor-

way.

Stentoft, J., Rajkumar, C., and Madsen, E. S. (2019).

Drivers and barriers for industry 4.0 readiness and

practice: a sme perspective with empirical evidence.

In 52nd Hawaii International Conference on System

Sciences. HICSS - University of Hawaii.

Truv

e, T., Wallin, W., and Ryfors, D. (2019). Swedish man-

ufacturing smes readiness for industry 4.0: what fac-

tors inﬂuence an implementation of artiﬁcial intelli-

gence and how ready are manufacturing smes in swe-

den? Bachelor’s Thesis, J

onk

oping University, Swe-

den.

Wagner, B. (2018). Get started with the iiot

& industry 4.0. Available online at:

https://forcetechnology.com/en/articles/industry-

4-0-iot-iiot-servitization.

Wuest, T., Weimer, D., Irgens, C., and Thoben, K. D.

(2016). Machine learning in manufacturing: advan-

tages, challenges, and applications. Production &

Manufacturing Research, 4(1):23–45.

Yu, F. and Schweisfurth, T. (2020). Industry 4.0 technol-

ogy implementation in smes–a survey in the danish-

german border region. International Journal of Inno-

vation Studies, 4(3):76–84.

IN4PL 2021 - 2nd International Conference on Innovative Intelligent Industrial Production and Logistics

136