1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
Adoption of artificial intelligence in 
operations management 
Oluseyi Afolabi Adeyemi1, Idowu Adetona Ayoade2, Esther Onoge Adeyemi3, 
Oladeji Oluniyi Olanrele4, Ibukun O. Eweoya5, Joel Matthew6 
1,6School of Physics, Engineering, and Computer Science. University of Hertfordshire, 
Hatfield, UK. 
3Logistics and IT Department, MyBnK, London. UK. 
2,4Faculty of Engineering, First Technical University, Ibadan. 
5Mathematics and Computer Science Department, Elizade University, Ilara-Mokin. 
 
Abstract: This is a review conducted in relation to the application of Artificial 
Intelligence (AI) in Operations Management between the years 2010 – 2021. The 
purpose of this paper is to provide a survey of the usage of AI in operations 
management aimed at presenting the themes, trends, direction of research and its 
practical impacts. Artificial Intelligence (AI) is playing a major role in the fourth 
industrial revolution, and a lot of evolution in various machine learning 
methodologies. AI techniques are widely used by the practicing engineers to solve 
a whole range of intractable problems. This study provides a forum for rapid 
evaluation of the works describing the theoretical and practical application of AI 
methods in operations management. The study reports some novel aspects of AI 
used for a real-world engineering application towards solving problems, increased 
productivity, and improved customer satisfaction. 
Keywords. Artificial Intelligence, Operations Management, Review, Survey 
1. Introduction and Methodology 
Organisations are becoming more competitive due to new regulations, global challenges, 
and focus on net zero energy. The adoption of AI has helped organizations to deal with 
these challenges by providing solutions to uncertainties and achieving optimized results 
through reduced costs, speed, agility, efficiency, and flexibility. There have been an 
increased number of studies and publications for AI adoption in operations management. 
The number of papers published per year has not slowed down in the recent decade. With 
over 120,000 articles published between 2010-2021 and over 17,000 in operations 
management. The result of having so many publications is the associated complexity of 
understanding what else needs to be addressed. Other known issues linked with the use 
of repetitive publications, lack of substantial useful information hence not making 
significant contribution to knowledge.  
 
The design and methodology adopted is like that used by authors of previous surveys. 
That is to seek for literal replication of the review process and to build on the wealth of 
knowledge of authors, their experience(s) and expertise. 
To keep in line with the previous surveys that have been conducted on this topic, the 
same areas of operations management was used which includes process planning and 
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
control and quality, maintenance and fault diagnosis and areas of design and scheduling. 
The areas from the previous survey have been maintained to represent the categories that 
will be researched.  
➢ Case-based reasoning (CBR). 
➢ Genetic algorithms (GAs). 
➢ Neural Networks (NN). 
➢ Knowledge-based Systems (KBS).  
➢ Fuzzy logic (FL); and 
➢ Data Mining (DM).  
 
The Science Direct database was used to search for references using only the keywords 
that have been categorised in this paper. Review articles and research articles were 
identified while unrelated papers were abandoned. Further filtering was conducted to 
remove other forms of irrelevant papers to avoid double counting the same paper, 
however in most cases the title, abstract and conclusion sections were clear indicators to 
categorize the papers.  
 
This paper is arranged in three parts namely, introduction and methodology, survey and 
categories giving insights into the papers published in each section and conclusion 
presenting the quantitative data in this paper. 
2. Survey and Categories 
2.1 Design  
2.1.1 FL in Design  
FL is employed in controllers for example, Youssef et al., (2018) reveal how to use 
FL for maximum power point tracking (MPPT) in photovoltaic systems, enabling it to 
function with different irradiance and temperature conditions. The proposed MPPT 
controller provides high flexibility and re-configurability, low cost of implementation 
and power usage. Costo Branco and Dente (2010) design and evaluate a fuzzy logic 
pressure controller for the braking system on an Airbus to achieve pressure control with 
high fit for hydraulic load fluctuations. Another paper presented by Tzafestas et al., 
(2010) propose the design of a FL in the control of autonomous non-holonomic mobile 
robots to discover a fuzzy path tracking algorithm. Cheng et al., (2010) investigated the 
design of a variable-voltage DC source using a fuzzy logic controller to handle load 
changes and input voltage fluctuations. 
Furthermore, there are uses of FL in hybrid sectors; Tahmasebi and Hezarkhani 
(2012) adopted fuzzy logic in grade estimations which is important in mine projects to 
overcome challenges due to difficulties of mineral ore deposits structural complications. 
Anifowose and Abdulraheem (2011) demonstrate functional networks, fuzzy logic 
driven and support vector machines to predict oil and gas reservoir attributes. Menghal 
and Laxmi (2016) discuss the control of an induction motor drive using fuzzy logic 
knowledge which was developed using MATLAB/Simulink to clarify the usefulness of 
PI and fuzzy control and to present an improved control performance of FLs algorithm 
over conventional PI controllers. Garcia-Diaz et al., (2013) argue for the use of FL 
models in software development effort estimation as an alternative to linear regression 
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
methods. The paper argues further by comparing two types of FL systems: Mamdani and 
Takagi-Sugeno and proving the outcome from the results of Takagi-Sugeno FL system 
to be more accurate than the other FL system as well as the linear regression model. 
Mehbodniya et al., (2013) established an innovative multi-criteria vertical handoff 
algorithm for heterogeneous wireless networks that achieves seamless mobility with 
maximal end-users’ satisfaction using Fuzzy VIKOR (FVIKOR). 
2.1.2 KBS in Design  
Publications on knowledge-based systems are quite few and dispersed, Naranje and 
Kumar (2014) establish that KBS is used for the design of deep drawing die for 
axisymmetric parts yielding an interactive user-friendly, flexible, and economic 
implementation system. Mayr et al., (2018) shows that KBS are mostly relevant for 
supporting the planning of electric drives production systems, but ML-based methods 
are principally for optimizing single production processes. Khan et al., (2021) developed 
an integrated KBS useful for the transformation of traditional supply chain to digital 
supply chain. Rocca (2012) discuss knowledge-based engineering (KBE) as a budding 
technology with great potential for engineering design applications and its 
distinctiveness based on programming method to portray its validity in capturing and re-
using engineering knowledge to automate large portions of the design process. Bing et 
al., (2017) provides a language-independent framework to implement slot-filling 
assignments by searching the web with accurate inquiries and originating lightweight 
extraction patterns. A pseudo-testing approach is adopted to approve the patterns derived 
from various sentences and highly encouraging outcomes are achieved. 
2.1.3 CBR in Design  
Case-based reasoning is for adopted problem solving based on previously successful 
incidents, therefore it uses experiences to deal with and resolve situations. Hu et al., 
(2015) proposed the acceptability of grey relational analysis and weighted mean (GRA-
WM) adaptation in application of CBR for mechanical design over classical methods as 
that helps to decide valuable specifications of new mechanical product by adapting 
earlier favourable solutions to current problems. The authors in year 2016 further 
propose the hybrid weighted mean (HWM) approach by capitalising on improved 
adaptation performance in relation to adaptation precision of other comparative methods. 
Guo et al., (2012) shows the application of intelligent CBR system to fulfil the design 
support for injection mould design with outstanding performance than current CBR. 
Peng et al., (2011) argues for the use of a rule-based reasoning (RBR) and CBR to 
develop a virtual reality (VR) based integrated system for machining fixture design, 
which could help designers to refer to earlier design cases to make abstract fixturing 
solutions quickly. Goh and Guo (2018) developed an intelligent online knowledge-based 
system, FPSWizard, which is a hybrid of CBR and RBR to improve recovery 
performance and to deliver complete solutions to fall from heights. FPSWizard is useful 
as a decision support system for professional engineers and safety professionals in 
choosing and plotting solutions to the work-at-height challenges in the construction 
industry. Perez et al., (2021) present a solution to the challenge of administering risks 
during a surgical procedure using an integration of Multi-Agent System (MAS) with 
Case-Based Reasoning (CBR). The solution method demonstrates its ability to manage 
alert thresholds during erratic and inimical events in an environment that coordinates 
data as dissimilar as infectious agents, patient's vitals, and human tiredness. The 
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
outcomes show that the thresholds predicted by the system are more efficient than the 
existing ones. Herrero-Reder et al., (2017) assessed the conceptual similarity between a 
memory storage and prediction framework and CBR. The authors displayed how robots 
can achieve complex behaviours by demonstration and enhance their knowledge base 
without guidance. They confirmed that active learning enables us to gain knowledge that 
are analytically difficult to model but easy to demonstrate in practical ways. The 
suitability of case base recovery process to handle scalable tasks is suggested.  
2.1.4 GAs in Design 
Genetic algorithm is a process of natural selection used to generate high quality 
optimised solutions to problems by depending on selection, crossover and/or mutation. 
Pan (2010) used Canonic Signed Digit (CSD) coded GA to develop chromosomes by 
decreasing the time emaciated by trials and errors in the evolution process and to increase 
the training speed. An efficient hybrid code for the filter coefficients is suggested to 
enhance the precision of the coefficient of finite impulse response digital filter 
(FIR).  Nagarajan et al., (2016) proposed the retrieval of any kind of medical image such 
as breast cancer, brain tumour, lung cancer, and thyroid cancer adopted to decrease the 
existing system dimensionality problems. The experiment proved that the GA directed 
image retrieval system chooses optimal subset of feature to recognize the right set of 
images using a machine learning based feature selection method.  Luan et al (2019) used 
the hybridization algorithm of GA and ant colony optimization (ACO) to provide a 
decision support tool that helps in solving the challenges associated with multicriteria 
decision making of supplier association. The unified algorithm has shown improved 
quality and efficiency with a methodological contribution to the optimization of 
algorithm research. Lee (2018) conducted a review of the applications of GA in 
operations management (OM) over a ten-year period ranging from year 2007 to 2017. 
The study encouraged the use of heuristic search methods for improved OM decisions as 
against non-deterministic polynomial hard problems algorithms.  
2.1.5 NN in Design  
Neural networks fundamentally reflect the behaviour of the human brain, which 
allows computers to recognise patterns and solve problems.  
Kamrunnahar and Urquidi-Macdonald (2010) utilized supervised neural network 
(NN) method as a data mining tool to forecast corrosion behavior of metal alloys. The 
NN model learned the basic laws that outline the alloy’s composition and environment 
to the corrosion rate. Both DC and AC corrosion experiments were conducted with 
existing corrosion data on corrosion allowable and corrosion resistive alloys. The data 
mining outcomes recognized the categorization and prioritization of certain parameters 
for example, pH, temperature, time of exposure, electrolyte composition, metal 
composition to establish the synergetic impact of the parameters and variables on 
electrochemical potentials and corrosion rates. Chen (2011) employed a Takagi–Sugeno 
(T–S) fuzzy model and parallel-distributed compensation (PDC) plan to design a 
nonlinear fuzzy controller for the stability of nonlinear systems. The neural-network 
model is used to submerge the modelling error challenges associated with nonlinear 
systems. A new stability NN-based controller design is utilized to secure the stability of 
the nonlinear system. The control problem is now presented as a linear matrix inequality 
(LMI) difficulty and a simulation is provided to explore the practicability of the proposed 
fuzzy controller design method.  
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
Hassan et al., (2013) presented a review of major studies adopting the ANN method 
to solve major problems related to power system control due to the constraint of 
conventional control theory, modern control theory, and adaptive control theory. It was 
discovered that fast-acting, accurate controllers based on ANN technique are the 
preferred choice to shun system collapse, sustain system transient stability, damp 
oscillations, stabilize voltage, and to provide high-quality service to consumers. Though, 
all NN has some benefits and disadvantages, it was proposed that the recurrent neural 
network (RNN) is appropriate for monitoring and control. And, power systems should 
be taken as a supplementary tool, rather than a substitute for conventional or other AI 
based power system methods. In transiting from power system monitoring to forecasting 
stream flow, Sahoo et al., (2019) established the application of NN in simulating river 
flow for forecasting the development of water resources. Traditional radial basis function 
network (RBFN) and RNN were utilized for model development and RNN model 
provides optimized performance as against RBFN. For RNN, Tan-sig, Log-sig, Purelin 
transfer function are adopted for evaluating model performance, and Tan-sig provides 
best value of model performance among them. 
3. Results 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0
1000
2000
2
0
1
0
2
0
1
1
2
0
1
2
2
0
1
3
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
2
0
1
8
2
0
1
9
2
0
2
0
2
0
2
1
Design
0
500
1000
2
0
1
0
2
0
1
1
2
0
1
2
2
0
1
3
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
2
0
1
8
2
0
1
9
2
0
2
0
2
0
2
1
Scheduling 
0
1000
2000
2
0
1
0
2
0
1
1
2
0
1
2
2
0
1
3
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
2
0
1
8
2
0
1
9
2
0
2
0
2
0
2
1
Process Planning 
0
100
200
2
0
1
0
2
0
1
1
2
0
1
2
2
0
1
3
2
0
1
4
2
0
1
5
2
0
1
6
2
0
1
7
2
0
1
8
2
0
1
9
2
0
2
0
2
0
2
1
Quality, Maintenance and Fault Diagnosis
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
 
 
Figure 1: A selection of charts to represent the Number of publications of 
AI in OM over the review period the top four charts are from 2010-2021 
and the bottom four are from 2005-2009. 
 
 
4. Conclusions  
This chapter will compare the results obtained from my review period and the review 
period conducted by the previous paper. A total of 2266 papers have been published 
between the previous survey, this in comparison to the current survey proves to be only 
13% of what has been done between the years of 2010-2021. The number of papers 
released on average have increased by 37% per year.  The results described in this chapter 
has been visually represented in figure 14, to ensure ease in comparison between the 
statistical overview of the two surveys.  
0
2000
4000
6000
2008 2010 2012 2014 2016 2018 2020 2022
N
u
m
b
e
r 
o
f 
P
u
b
lic
at
io
n
s
Year
Papers Published for AI in Operations Management (2010-
2021) 
0
200
400
600
2004 2005 2006 2007 2008 2009 2010
N
u
m
b
er
 o
f 
P
u
b
lic
at
io
n
s
Years 
Number of Publication for AI in OM (2005-2009)
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
 
The previous survey states that there were trends for design and scheduling which 
showed an increase in the use of GA. Based on the graph that they provide it does show 
that scheduling and design have a huge interest from the use of GAs. With 210 papers 
for design and 309 for scheduling, the highest number of papers released for any of the 
categories over the 2005-2009 period. The paper then goes on to reveal that a steady 
number of publications around 20-35 papers have been published for NN for design 
during the course period. Again, the second highest use is NN as statistics show that a 
total of 386 paper have been published which is just over half the number of GA’s that 
have been published. The use of NN within process planning and control seem to control 
more than 70% of all publications in the process planning category. This compared to 
the study conducted between 2010-2021 shows that GA and NN have remained to be 
areas of great interest after hybrid as GA has had a total of 4554 papers released in total 
and NN came third with 2232 papers. This shows that interest has not decreased in these 
areas rather steadied over the course of the 11-year period. Many understand the impact 
of research within GA can have on evolving designs due to their flexibility and potential 
for optimizing tasks. Both the surveys found that there is a decline in the use of KBS as 
all its benefits have been studied thoroughly and now it is no longer considered 
innovative and newer and more advanced systems have been developed. A total of 29 
studies have been conducted for the years 2005-2009 and between 2010-2021 a 
combined total of 72 more papers have been added. The previous survey iterates that 
KBS research has been on-going since 1980s which helps us to understand why so little 
is now researched after it being 40 years.  
 
The four graphs displayed in the previous are quite different from the ones that have been 
produced for the period in this survey. Where in the current survey all four graphs; figure 
1-4, show hybrid models increasing exponentially, in the previous survey GA seems to 
be increasing exponentially for Design and Scheduling. Whereas quality, maintenance 
and fault diagnosis, and process planning and control show NN being the dominating 
research factor. All other methods seem to fluctuate between 0-40 papers. Finally, the 
previous survey states that with the limited time frame researched hybrid systems are 
gaining popularity, which can be carried over to the current survey as hybrid systems are 
currently the most interested aspect of AI.  
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
 
 
What are the trends in use of AI in operations management? 
To conclude, this research has shown that the interest in KBS has declined drastically 
during the period of this paper. In contrast, the interest in hybrid 
systems has seen a surge in the number of total papers released 
per year. The results show that the interest in hybrid systems in 
only increasing and there are still more iterations of systems to 
be found and used effectively for various result purposes. With 
more and more companies adopting AI within the supply chain, 
it is increasingly more attractive to find the most effective 
solution to provide a compelling solution to their users.  Design 
is the most appealing and logical solution to research for hybrid 
and therefore I believe that will only grow over the years as design to be the most 
researched area of operational management.  Looking into the future years research has 
shown that hybrid is still a major research focus with 36% of the total papers published 
referencing hybrid systems. A total of 4319 papers have been published within 
operations management. A key statistic to look at is data mining which has gained 
interest with a further 25% papers being related to that. KBS has almost 0 papers in this 
year, and it is believed that this trajectory will stay the same as most of the research is 
this field has been conducted thoroughly with no new innovations. 
 
 
 
References 
[1] Kobbacy, K.A.H. and Vadera, S. (2011), "A survey of AI in operations management from 2005 to 
2009", Journal of Manufacturing Technology Management, Vol. 22 No. 6, pp. 706-733 
[2] Youssef, A., Telbany, M. and Zekry, A., 2018. Reconfigurable generic FPGA implementation of fuzzy 
logic controller for MPPT of PV systems. Renewable and Sustainable Energy Reviews, 82, pp.1313-1319. 
[3] Costa Branco, P. and Dente, J., 2010. Design and experimental evaluation of a fuzzy logic pressure 
controller for the Airbus 310/320 braking control system. Engineering Applications of Artificial 
Intelligence, 23(6), pp.989-999. 
[4] Tzafestas, S., Deliparaschos, K. and Moustris, G., 2010. Fuzzy logic path tracking control for autonomous 
non-holonomic mobile robots: Design of System on a Chip. Robotics and Autonomous Systems, 58(8), 
pp.1017-1027. 
[5] Cheng, C., Cheng, P. and Wu, M., 2010. Fuzzy logic design of self-tuning switching power supply. Expert 
Systems with Applications, 37(4), pp.2929-2936. 
[6] Tahmasebi, P. and Hezarkhani, A., 2012. A hybrid neural networks-fuzzy logic-genetic algorithm for grade 
estimation. Computers & Geosciences, 42, pp.18-27. 
[7] Anifowose, F. and Abdulraheem, A., 2011. Fuzzy logic-driven and SVM-driven hybrid computational 
intelligence models applied to oil and gas reservoir characterization. Journal of Natural Gas Science and 
Engineering, 3(3), pp.505-517. 
[8] Menghal, P. and Laxmi, A., 2016. Fuzzy Based Real Time Control of Induction Motor Drive. Procedia 
Computer Science, 85, pp.228-235. 
Hybrid
36%
CBR
1%
GA
18%
KBS
0%
NN
9%
DM
25%
FL
11%
Number of papers published per system for 
2022
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
[9] Garcia-Diaz, N., Lopez-Martin, C. and Chavoya, A., 2013. A Comparative Study of Two Fuzzy Logic 
Models for Software Development Effort Estimation. Procedia Technology, 7, pp.305-314. 
[10] Mehbodniya, A., Kaleem, F., Yen, K. and Adachi, F., 2013. A fuzzy extension of VIKOR for target 
network selection in heterogeneous wireless environments. Physical Communication, 7, pp.145-155. 
[11] Naranje, V. and Kumar, S., 2014. A knowledge-based system for automated design of deep drawing die 
for axisymmetric parts. Expert Systems with Applications, 41(4), pp.1419-1431. 
[12] Mayr, A., Weigelt, M., Masuch, M., Meiners, M., Hüttel, F. and Franke, J., 2018. Application Scenarios 
of Artificial Intelligence in Electric Drives Production. Procedia Manufacturing, 24, pp.40-47. 
[13] Khan, S., Naim, I., Kusi-Sarpong, S., Gupta, H. and Idrisi, A., 2021. A knowledge-based experts’ system 
for evaluation of digital supply chain readiness. Knowledge-Based Systems, 228, p.107262. 
[14] Rocca, G., 2012. Knowledge based engineering: Between AI and CAD. Review of a language-based 
technology to support engineering design. Advanced Engineering Informatics, 26(2), pp.159-179. 
[15] Bing, L., Zhang, Z., Lam, W. and Cohen, W., 2017. Towards a language-independent solution: 
Knowledge base completion by searching the Web and deriving language pattern. Knowledge-Based 
Systems, 115, pp.80-86. 
[16] Hu, J., Qi, J. and Peng, Y., 2015. New CBR adaptation method combining with problem–solution 
relational analysis for mechanical design. Computers in Industry, 66, pp.41-51. 
[17] Qi, J., Hu, J., & Peng, Y. (2016). Hybrid weighted mean for CBR adaptation in mechanical design by 
exploring effective, correlative and adaptative values. Computers in Industry, 75, 58-66. 
[18] Guo, Y., Hu, J. and Peng, Y., 2012. A CBR system for injection mould design based on ontology: A case 
study. Computer-Aided Design, 44(6), pp.496-508. 
[19] Peng, G., Chen, G., Wu, C., Xin, H. and Jiang, Y., 2011. Applying RBR and CBR to develop a VR based 
integrated system for machining fixture design. Expert Systems with Applications, 38(1), pp.26-38. 
[20] Goh, Y. and Guo, B., 2018. FPSWizard: A web-based CBR-RBR system for supporting the design of 
active fall protection systems. Automation in Construction, 85, pp.40-50. 
[21] Perez, B., Lang, C., Henriet, J., Philippe, L. and Auber, F., 2021. A cluster-based approach to predict 
serious adverse events in surgery. Expert Systems with Applications, 184, p.115506. 
[22] Herrero-Reder, I., Urdiales, C., Peula, J. and Sandoval, F., 2017. CBR based reactive behavior learning 
for the memory-prediction framework. Neurocomputing, 250, pp.18-27. 
[23] Pan, S., 2010. A canonic-signed-digit coded genetic algorithm for designing finite impulse response 
digital filter. Digital Signal Processing, 20(2), pp.314-327. 
[24] Nagarajan, G., Minu, R., Muthukumar, B., Vedanarayanan, V. and Sundarsingh, S., 2016. Hybrid Genetic 
Algorithm for Medical Image Feature Extraction and Selection. Procedia Computer Science, 85, pp.455-
462. 
[25] Luan, J., Yao, Z., Zhao, F. and Song, X., 2019. A novel method to solve supplier selection problem: 
Hybrid algorithm of genetic algorithm and ant colony optimization. Mathematics and Computers in 
Simulation, 156, pp.294-309. 
[26] Lee, C., 2018. A review of applications of genetic algorithms in operations management. Engineering 
Applications of Artificial Intelligence, 76, pp.1-12. 
[27] Kamrunnahar, M. and Urquidi-Macdonald, M., 2010. Prediction of corrosion behavior using neural 
network as a data mining tool. Corrosion Science, 52(3), pp.669-677. 
[28] Chen, C., 2011. Stability analysis and robustness design of nonlinear systems: An NN-based 
approach. Applied Soft Computing, 11(2), pp.2735-2742. 
[29] Hassan, L., Moghavvemi, M., Almurib, H. and Steinmayer, O., 2013. Current state of neural networks 
applications in power system monitoring and control. International Journal of Electrical Power & 
Energy Systems, 51, pp.134-144. 
[30] Sahoo, A., Samantaray, S. and Ghose, D., 2019. Stream Flow Forecasting in Mahanadi River Basin using 
Artificial Neural Networks. Procedia Computer Science, 157, pp.168-174. 
[31] Yang, T., Zhang, L., Kim, T., Hong, Y., Zhang, D. and Peng, Q., 2021. A large-scale comparison of 
Artificial Intelligence and Data Mining (AI&DM) techniques in simulating reservoir releases over 
the Upper Colorado Region. Journal of Hydrology, 602, p.126723. 
[32] Zaragozí, B., Rabasa, A., Rodríguez-Sala, J., Navarro, J., Belda, A. and Ramón, A., 2012. Modelling 
farmland abandonment: A study combining GIS and data mining techniques. Agriculture, Ecosystems 
& Environment, 155, pp.124-132. 
[33] Fan, C. and Xiao, F., 2017. Assessment of Building Operational Performance Using Data Mining 
Techniques: A Case Study. Energy Procedia, 111, pp.1070-1078. 
[34] Ostheimer, J., Chowdhury, S. and Iqbal, S., 2021. An alliance of humans and machines for machine 
learning: Hybrid intelligent systems and their design principles. Technology in Society, 66, p.101647. 
[35] Han, S., Wang, W. and Liu, X., 2021. A new type-2 fuzzy multi-criteria hybrid method for rail transit 
operation safety assessment. Applied Soft Computing, 113, p.107927. 
1 Corresponding Author. o.adeyemi5@herts.ac.uk 
 
 
Sensitivity: Internal 
[36] Butdee, S. and Kunhirunbawon, S., 2020. Multi-criteria decision for machining process plan evaluation 
using fuzzy logic modeling and feature based method. Materials Today: Proceedings, 26, pp.1982-1987. 
[37] Uzoka, F., Obot, O., Barker, K. and Osuji, J., 2011. An experimental comparison of fuzzy logic and 
analytic hierarchy process for medical decision support systems. Computer Methods and Programs in 
Biomedicine, 103(1), pp.10-27. 
[38] Son, M. and Kim, T., 2012. Torpedo evasion simulation of underwater vehicle using fuzzy-logic-based 
tactical decision making in script tactics manager. Expert Systems with Applications, 39(9), pp.7995-
8012. 
[39] Leo Kumar, S., 2017. State of The Art-Intense Review on Artificial Intelligence Systems Application in 
Process Planning and Manufacturing. Engineering Applications of Artificial Intelligence, 65, pp.294-329. 
[40] Naranje, V., Kumar, S. and Hussein, H., 2014. A Knowledge Based System for Cost Estimation of Deep 
Drawn Parts. Procedia Engineering, 97, pp.2313-2322. 
[41] Wei, H., Xu, Q. and Tang, X., 2011. A knowledge-based problem solving method in GIS 
application. Knowledge-Based Systems, 24(4), pp.542-553. 
[42] Zhang, B., Li, X., Lin, B. and Zhu, Y., 2021. A CBR-based decision-making model for supporting the 
intelligent energy-efficient design of the exterior envelope of public and commercial buildings. Energy 
and Buildings, 231, p.110625. 
[43] Popa, A. and Wood, W., 2011. Application of case-based reasoning for well fracturing planning and 
execution. Journal of Natural Gas Science and Engineering, 3(6), pp.687-696. 
[44] El-Fakdi, A., Gamero, F., Meléndez, J., Auffret, V. and Haigron, P., 2014. eXiTCDSS: A framework for 
a workflow-based CBR for interventional Clinical Decision Support Systems and its application to 
TAVI. Expert Systems with Applications, 41(2), pp.284-294. 
[45] Zhang, Z., Tang, R., Peng, T., Tao, L. and Jia, S., 2016. A method for minimizing the energy consumption 
of machining system: integration of process planning and scheduling. Journal of Cleaner Production, 
137, pp.1647-1662. 
[46] Li, X., Gao, L., Wang, W., Wang, C. and Wen, L., 2019. Particle swarm optimization hybridized with 
genetic algorithm for uncertain integrated process planning and scheduling with interval processing 
time. Computers & Industrial Engineering, 135, pp.1036-1046. 
[47] Kölker, K. and Lütjens, K., 2015. Using Genetic Algorithms to Solve Large-scale Airline Network 
Planning Problems. Transportation Research Procedia, 10, pp.900-909 
[48] A.N. Author, Article title, Journal Title 66 (1993), 856–890.