![Evolution of AI in project management [100].](https://www.researchgate.net/profile/Ruben-Gonzalez-Crespo/publication/347514098/figure/fig1/AS:970949843222528@1608503890125/Evolution-of-AI-in-project-management-100_Q320.jpg)
![Neural Network of high order [135].](https://www.researchgate.net/profile/Ruben-Gonzalez-Crespo/publication/347514098/figure/fig2/AS:970949843251200@1608503890162/Neural-Network-of-high-order-135_Q320.jpg)
![Bagnet diagram [166].](https://www.researchgate.net/profile/Ruben-Gonzalez-Crespo/publication/347514098/figure/fig3/AS:970949843243008@1608503890188/Bagnet-diagram-166_Q320.jpg)
![FRBS Structure [71].](https://www.researchgate.net/profile/Ruben-Gonzalez-Crespo/publication/347514098/figure/fig4/AS:970949843238913@1608503890213/FRBS-Structure-71_Q320.jpg)
![EFHNN Architecture [29].](https://www.researchgate.net/profile/Ruben-Gonzalez-Crespo/publication/347514098/figure/fig5/AS:970949843234816@1608503890247/EFHNN-Architecture-29_Q320.jpg)
Content uploaded by Ruben Gonzalez Crespo
Author content
All content in this area was uploaded by Ruben Gonzalez Crespo on Dec 20, 2020
Content may be subject to copyright.
- 1 -
Please cite this article in press as:
J. Gil Ruiz, J. Martínez Torres, R. González Crespo. The Application of Articial Intelligence in Project Management Research: A review, International
Journal of Interactive Multimedia and Articial Intelligence, (2020), http://dx.doi.org/10.9781/ijimai.2020.12.003
The Application of Articial Intelligence in Project
Management Research: A Review
Jesús Gil Ruiz1*, Javier Martínez Torres2, Rubén González Crespo3
1 School of Doctorate Programs, Universidad Internacional de La Rioja, Logroño, La Rioja (Spain)
2 Department of Applied Mathematics I, Universidad de Vigo, Vigo (Spain)
3 School of Engineering and Technology, Universidad Internacional de La Rioja, Logroño, La Rioja
(Spain)
Received 11 May 2020 | Accepted 7 October 2020 | Published 18 December 2020
Keywords
Artiicial Intelligence,
Decision Support
Systems, Evolutionary
Diffuse Hybrid Neuronal
Network, Project
Management, Project
Success, Critical.
Abstract
The ield of artiicial intelligence is currently experiencing relentless growth, with innumerable models emerging
in the research and development phases across various ields, including science, inance, and engineering. In
this work, the authors review a large number of learning techniques aimed at project management. The analysis
is largely focused on hybrid systems, which present computational models of blended learning techniques. At
present, these models are at a very early stage and major efforts in terms of development is required within
the scientiic community. In addition, we provide a classiication of all the areas within project management
and the learning techniques that are used in each, presenting a brief study of the different artiicial intelligence
techniques used today and the areas of project management in which agents are being applied. This work
should serve as a starting point for researchers who wish to work in the exciting world of artiicial intelligence
in relation to project leadership and management.
* Corresponding author.
E-mail address: jesus.gil@unir.net
DOI:10.9781/ijimai.2020.12.003
I. I
IN recent decades, projects have tended to increase in complexity
to the point where they have become mega projects such as, for
example, the particle accelerator (CERN) or the photovoltaic plants
(BEN BAN solar) with the power of almost two nuclear reactors (1.8
GW). Meanwhile, the attendant industrial growth has resulted in a
greater degree of competence when addressing these projects in terms
of their control and development, which has become a necessity since
the projects often involve extremely tight proit margins. Adopting
certain project management methodologies (e.g., PMI, [130], IPMA,
and PRINCE) allows us to manage the start and the evolution of a
project in the most optimal way possible, controlling and responding
to any problems that arise during the project, facilitating their
completion and approval before any further risks arise. However, these
methodologies are arguably not suficient since the processes must be
clearly structured with complete and clear control of the project in
all the relevant areas. The aim must be to improve the experience of
the project manager when dealing with the various adverse situations
that will likely be encountered in the development of the project
while simultaneously preventing errors due to a lack of planning or
management, such as in portfolio management [41]. While the desired
project management methodology (PMP) practices are currently being
implemented – which allow for the best possible management of a
project – as noted above, the processes must be clearly structured
[142] and all areas of the project must be tightly controlled, including
in terms of the information systems [66].
In fact, the current methodologies are largely insuficient since the
project manager is generally left to deal with the decision making,
who, based on his or her professional experience, must make “intuitive”
decisions based on previous cases when facing a problem with ininite
variables and possibilities. Here, it is virtually impossible to face all
the issues and challenges that today’s projects entail. In fact, there are
a number of diverse reasons why projects tend to fail. However, after
more than ten years working on projects and learning about other
professionals’ experiences, we would highlight the following:
• Unassembled objectives or objectives that are not clearly deined.
• There is no communication protocol.
• Lack of deinition of roles and responsibilities.
• Expectation management.
• Scope Corruption.
• Ignore Project Risks.
• Lack of involvement of participants.
• Absence of formal planning.
• Estimated errors / unrealistic.
• Absence of methodologies, templates and documentation.
• Lack of resources.
• Absence of evidence or little focus on quality.
• Little formalized modiication process.
• Lack of training.
• Little or no address support.
- 2 -
International Journal of Interactive Multimedia and Artificial Intelligence
While all these points can be improved with a clear PMP, they will
always depend on the human factor, and many of them are dificult
to deal with, even for an experienced project manager. In view of this,
artiicial intelligence (AI) can play an important role in a variety of areas.
Integration
& Automation
Chatbots
Assistant
Machine Learning-
Bases Project
Management
Autonomus Artificial
Intelligence Project
Management
1983 2016 2023-2035 2035-2050
Fig. 1.Evolution of AI in project management [100].
Fig. 1 shows the evolution that has taken place in the last 37 years,
and what is expected in the future.
Integration, Automation, and Chatbot Assistants
The irst phase involved the integration of task automation software
such as Microsoft Project and Primavera (Oracle), which irst appeared
in 1983. In recent years, chatbot assistants are being used for meetings
and management equipment recaps and reminders, etc. While in
everyday life, we have been surrounded by chatbots for several years,
the area is still in its infancy in the world of project management.
Project Management Based on Machine Learning
The third stage began with the purest concept of AI. In the area of
project management, machine learning [132] has been implemented
to allow for predictive and corrective analysis aimed at providing
the project manager with data for decision making in terms of, for
example, how to plan and manage project resources within certain
parameters and restrictions or how to deal with problems and risks in
order to achieve project success based on the history of past projects.
In less than ten years, AI could work with the lessons learned from
the project history and could suggest new project schedules, adapting
[87] to the real time according to the performance of the resources
and the progress of the project. An AI system could even alert the
project manager about any possible risks and opportunities through
the use of real-time project data analysis. A new vision will be created
when it comes to directing projects by minimizing the risks involved
in decision making. An AI system may be capable of making decisions
for itself, which will herald the new era of AI [19], one that will mark
the fourth phase of the evolution of project management.
The objective of this work is to review the new proposals emerging
in the ield of AI in the various areas, and to ascertain which
techniques could be the most effective for ensuring the success of
the projects. We also look at all the applications and uses [112] of
AI in the broad ield of project management, from the commercial
development phase to the construction and commissioning phase,
including its application in the areas of operation and maintenance.
Numerous international studies have recently emerged in relation to
optimization techniques such as neural networks [27], support vector
machines [8], evolutionary algorithms [61], and hybrid systems [32]
[2]. Given their relevance to PMP, these techniques will improve the
experience of the project manager when facing the various adverse
situations that will be encountered in the development of the project,
and will help to prevent the errors resulting from a lack of planning
or management.
II. S M L T
A project has traditionally been classiied as successful if it has
complied with the following restrictions: scope, budget, and schedule.
The objective of this document is to review the new proposals
related to AI to improve the success of the project and to ascertain
the applications and uses that AI has in the broad ield of project
management, from the development phase of the business [91] to its
start-up [154] and onto its operation [125] [165] and maintenance [95]
[106] [156].
A. Individual Techniques
We begin by outlining each of the techniques used in the eld of
project management.
1. Artiicial Neural Networks ANN)
Neural networks attempt to simulate [162] the way the human brain
works as closely as possible, and are currently used in a number of
ields, including medicine, engineering, and construction management
[120]. The neural network conforms to data patterns and offers better
results. This is achieved through learning the network [165] and
comparing the results of the neural network with the data of other
projects until the performance of the neural network is optimized.
Neural networks have the following advantages [109]:
• The storage of information throughout the network.
• The ability to work with incomplete knowledge.
• Fault tolerance.
• The ability to carry out machine learning.
• A parallel-processing capacity.
These advantages make its implementation in computational
models highly interesting in all ields of research, text analytics [119],
and project management [76].
2. Neural Networks of High Order HONNS)
HONNs were originally proposed in the 1960s to perform nonlinear
discrimination but were discarded due to the enormous amount
of higher-order terms [43]. Beginning in the mid-1990s, several
researchers relied on HONNs rather than ONNs to resolve speciic
classiication problems [79]. In a high-order neuronal, the neuron
outputs are fed back to the same neuron or to neurons in the previous
layers, as shown in Fig. 2. The signals are transmitted in forward and
backward directions. High-order artiicial neural networks are mainly
based on the Hopield model.
u
1
xixi
-a
Πtanh(*)
un
z1
zn
Z(x)
Σ
wi1
win
wi1
∫
wiN
Fig. 2. Neural Network of high order [135].
3. Hopield Neural Network HNN)
The HNN [146] is a form of high-order artiicial neural network
with a single layer of fully connected neurons (i.e., all neurons are also
connected to each other, as shown in Fig. 3) and provides a method to
resolve combinatorial optimization problems. A HNN is guaranteed
to converge to a local minimum if a problem can be described as
an energy function with a minimum corresponding to the optimal
solution [60] [122].
- 3 -
Article in Press
u1
u2
u3
w1
w11
w2
w3
x1
x1
w12x2
w13x3
uixi
xi
Neurona 1
redi
x2
x3
Σ
Fig. 3. Topology of Hopeld networks, here with 3 neurons as an example [102].
4. Fuzzy Logic FL)
FL was initially proposed as a tool to describe uncertainty and
inaccuracy [163]. Since it mimics the higher-order mode in which the
human brain makes decisions in the face of uncertainty or vagueness,
FL provides an effective way for automated systems to describe highly
complex [48], poorly deined, or dificult to analyze subjects. In general,
FL is composed of a fuzziier, a rule base, an inference engine, and a
defuzziier [145] as shown in Fig. 4. The FL approach involves a number
of issues that have yet to be overcome [57], such as the coniguration
of the membership function, the determination of the composition
operator, and the acquisition of fuzzy rules that are speciic [152] to
the application. While FL parameters can be determined using the
experience and knowledge of experts, determining these parameters
in the absence of such experts remains dificult, especially in terms of
complex issues.
OutputInput
Fuzziier Defuzziier
Rules
Intelligence
Fig. 4. Architecture of fuzzy logic systems [153].
5. Fuzzy Cognitive Maps DCMs)
DCMs present an extension of cognitive maps and constitute
a fuzzy graphical structure (as shown in Fig. 5) used to represent
causal reasoning [96]. Their application is recommended for domains
where the concepts and relationships are fundamentally fuzzy, such
as politics, history, and strategic planning (projects) [51]. In the
diagram shown in Fig. 5, each node represents a fuzzy set or an event
that occurs to some degree. Here, it should be clariied that nodes are
causal concepts and can model events, actions, values, objectives, or
processes. Using this technique also provides the beneits of visual
modelling, simulation, and prediction. Scenario analysis contributes to
the identiication of different alternatives to reach a future state [124].
This presents a lexible strategic planning method that is frequently
used in technology management. While DCMs have been used for
scenario analysis, there is a lack of methodologies and tools that allow
for a fully effective quantitative analysis of the generated scenarios. In
the area of information technology management [104], the simulation
of software development projects and risk analysis in ERP maintenance
stand out. While the use of DCMs has been proposed for the integration
of strategic planning in relation to information systems and processes
[136], the possible project options are neither represented nor analyzed.
Furthermore, despite the DCM applications for the selection of
information technology projects, the technique has not been linked to
the organizational models that are obtained by describing the business
architecture through business modelling activities.
C1
w12
w12 w31
w34
w23
w41
w45
w54
C5
C4
C2
C3
Fig. 5. Diuse cognitive map topology [143].
6. Genetic Algorithms GAs)
GAs present adaptive methods that can be used to resolve search
and optimization problems and are based on the genetic process of
living organisms. Over the generations, populations evolve in nature
according to the principles of natural selection and the survival of the
ittest, as postulated by Darwin (1859). The power of GAs lies in the
fact that they present a robust technique and can successfully handle
a wide variety of problems in different areas, including those where
other methods encounter dificulties. While a GA is not guaranteed
to ind the optimal solution for a speciic problem, empirical evidence
suggests that solutions of an acceptable level can be identiied in a
timely manner when compared with other combinatorial optimization
algorithms. The wide application of GAs is related to the problems for
which there are no specialized techniques. In fact, these algorithms are
used in countless applications, including in the ields of engineering
[13], planning, games, and image processing [97]. Fig. 6 shows the
working architecture of GAs.
Initial
population
Fitness
Selection
Crossover
Mutation
Final
Generation?
No Yes
Children
Parents
Gene Chromosome
Chromosome
Evaluation
Fitness
Function
Design RMSE
Bit Inversion
Final Solution
111 111 110101
110 101 111000
111 111 110101
111 111 111100
111 111 111101
111 111 111101
Fig. 6. Genetic Algorithms Diagram [70].
In general, the application of GAs to the planning of multiple
projects that are to be executed simultaneously has yielded good
results. In certain studies, a method based on penalties has been
adopted [58] since it is dificult to obtain wholly correct solutions due
to the complexity of the problem of optimization. While the identiied
solutions have, on the whole, been good, it is important to highlight
- 4 -
International Journal of Interactive Multimedia and Artificial Intelligence
that, in some cases, the solutions lay outside of the algorithms, since the
best solutions do not always meet all the restrictions of the problem.
7. Fast-Messy Genetic Algorithm FmGA)
The fmGA [64] can eficiently identify optimal solutions to
problems with a large number of permutations. This type of algorithm
is known for its lexibility due to its capacity for being combined with
other methodologies to obtain better results [160]. The difference
between this and other genetic algorithms is based on the possibility
of modifying building blocks [86] to identify the best partial solutions,
which help us to focus on a faster global solution [65]. Fig. 7 shows the
working architecture of Messy GA.
EndStart
Messy GA
Tournament selection
without shuling
Tournament selection with shuling
Juxtapositional
phase
Population size
does not change
Population
size halved
at every
other
generation
Population
size halved
at every
generation
Population
size does
not change
Fig. 7. Messy GA Architecture [99].
The algorithm is used in many applications, especially in relation
to the resource management area of project management and civil
engineering [45].
8. Support Vector Machine SVM)
SVM presents a new form of learning, one that is more powerful than
that using traditional learning tools. The technique can also be used to
resolve data regression and categorization problems. Much like neural
networks, SVM requires training and testing using a training dataset.
The SVM functions allow for the better handling of unknown data and
the technique generally has certain advantages over neural networks,
often successfully applied to cost [10] and project management [158].
Within the area of classiication, SVM belongs to the category of linear
classiiers since it induces linear or hyperplane separators (as shown
in Fig. 8), either in the original space of the input examples [20] –
either separable or quasi-separable (noise) – or in a transformed space
(characteristic space).
(a) (b)
Fig. 8. Separation hyperplanes in a two-dimensional space of a set of separable
examples from two classes: (a) example of separation hyperplane, (b) other
examples of separation hyperplanes among the possible innities [18].
9. Bootstrap Technique BT)
The bootstrap method is a statistical technique used to estimate
quantities across a speciic population by averaging estimates from
multiple small data samples [50]. Importantly, the samples are
constructed by drawing observations from a large data sample one
at a time before returning them to the data sample after they have
been chosen. This allows a given observation to be included in a
small sample more than once. This sampling approach is known
as “replacement sampling.” The bootstrap method can be used to
estimate the size of a given population. This is achieved by repeatedly
taking small samples, calculating the statistics, and then extracting
the average. The bootstrap technique is a widely applicable and
extremely powerful [159] statistical tool that can be used to quantify
the uncertainty associated with a given estimator or statistical
learning method (e.g., ascertaining the probability that a project will
be successful). This is achieved by training the model with a sample
and evaluating the capacity of the model in relation to the samples not
included in the main sample. A useful feature of the bootstrap method
[17] is that the sample resulting from the estimates often forms a
Gaussian distribution. This technique is used in a wide variety of
sectors, including the ields of medicine, inancial management [154]
[111][142], and project management [68]. An example for risk analysis
is shown in Fig. 9.
Calculate interval
risk score
Determine the
inal risk ranking
Phase 3:
Interval Risk
Phase 1: Risk
Data Collection
Risk Observation
data (original
samples)
Phase 2: Non.parametric
Bootstrap technique
Start
End
Apply non-parametric
Bootstrap technique
(B=mi)
Calculate conidence
interval for the
criterio of risk analysis
Interval numbers
stabilized?
Yes
No
i=i+1
Fig. 9. Proposed approach for risk analysis [67].
10. K-Grouping Means
K-means presents an easy approach to creating groups of data
from random datasets [84]. K-means grouping that incorporates
heuristics such as Lloyd’s algorithm is easy to implement, even
in terms of large datasets, and has thus been widely used in many
areas, such as market segmentation, computer vision, geostatistics,
astronomy, and data mining in agriculture. The method is also used
for the pre-processing in other algorithms, including in terms of
identifying an initial coniguration. While the main problem is that
it cannot guarantee optimal convergence, it remains widely used
due to its simplicity. Many algorithms can identify speciic domains.
K-means generally converges in practical applications [55], especially
in pattern recognition problems. K-means clustering is also widely
and commonly used due to its simplicity, while it does have certain
inherent drawbacks, including having a ixed coniguration for the
optimal solution and being fairly time consuming.
11. Other Relevant Optimization Techniques
In the broad area of AI techniques, a number of well-known
techniques are used, including the artiicial bee colony algorithm [5],
particle swarm optimization (PSO), and differential evolution (DE)
[81]. There also exist various simple [128] or multi-objective Bayesian
optimization algorithms [101].
- 5 -
Article in Press
B. Hybrid Techniques
Here, we describe each of the hybrid techniques used in project
management. These hybrid systems are the future of AI and automated
project management.
1. Neuro-Fuzzy FNN)
The various logic and neural networks have special computational
properties [4] that make them suitable for certain cases. For example,
while neural networks offer advantages such as learning, adaptation,
fault tolerance, parallelism, and generalization, they are not good
at explaining how they have reached their decisions. In contrast,
fuzzy systems – which reason using inaccurate information through
an inference mechanism under linguistic uncertainty – are good
at explaining their decisions but cannot automatically acquire the
rules they use to make them. Meanwhile, neuro-diffuse systems
[53] combine the learning capacity of RNAs with the linguistic
interpretation power of diffuse inference systems. They are used in a
multitude of applications and ields [137] [85], including mechanical
engineering [155], image processing [74], electrical and electronic
systems [129], forecasting and prediction [49], and risk identiication
in project management.
2. Neural-Network-Adding Bootstrap
A bootstrap that adds neural networks presents a combination
of multiple artiicial neural network classiiers [151]. This method
uses more than one ANN-based classiier, meaning the inal decision
is made from each classiier through a voting system. The model
output is obtained as a linear combination of the experts’ output and
the combined weights are calculated based on the input. Bierman
proposed a new method to aggregate multiple models using boot
replicas of training data, which is known as “packaging”. It has been
shown that the generalizability of the model can be signiicantly
improved through this approach. The “bagging” idea is used to build
robust neural network models, or BAGNET models.
Rather than select a single neural network model, a BAGNET model
combines several neural network models to improve the precision and
robustness, as shown in Fig. 10 . The overall output of a BAGNET
model presents a weighted combination of the outputs of individual
neural networks. This approach has demonstrated a comparatively
good performance.
Σ
Fig. 10. Bagnet diagram [166].
3. Neural Networks of Adaptive Reinforcement
The main difference between this method and the above method
is that adaptive reinforcement neural networks [147] use weights
that are readjusted in each iteration, affording less importance to
the solutions that have not been correctly classiied. As a result, the
classiiers focus on more complex samples to obtain an increasingly
faster solution. A number of interesting studies on this technique are
currently available [126] [103].
4. Fuzzy Rule-Based Systems FRBS) and Genetic Fuzzy Systems
GFS)
FRBSspresent an extension of classical rule-based systems (hybrid
systems, as shown in Fig. 11) [75] given that they deal with “IF-THEN”
rules, the antecedents and consequents of which are made up of fuzzy
logical statements, rather than classical ones. They have demonstrated
their capacity for modelling, classiication, and data mining problems
in a large number of applications, which makes them highly useful for
project management and control. A GFS is essentially a fuzzy system
driven by a learning process based on evolutionary algorithms, which
includes FL + GA, genetic programming, and evolution strategies,
among other evolutionary algorithms [42].
Output InterfaceInput Interface
Environment Computation with Fuzzy Rule-Based Systems Environment
DESIGN PROCESS
Genetic Algorithm based
Learning Process
Knowledge Base
Data Base + Rule Base
Fuzzy Rule-
based system
Fig. 11. FRBS Structure [71].
The central aspect of using a GA [40] for the machine learning
of an FRBS is that the process can be analyzed as an optimization
problem. This technique is frequently used in weather forecasts [46],
the forecasting of renewable energy resources [144] (solar [90], wind
[108]), military projects [52], and project management [12].
5. Evolutionary Fuzzy Support Vector Machines Inference Model
EFSIM).
The inference model of evolutionary diffuse support vector
machines (EFSIM) presents a hybrid technique [35] that incorporates
three different AI techniques: FL, SVM, and fmGA, as shown in
Fig. 12. In this hybrid system, the FL deals with any vagueness and
approximate reasoning, the SVM acts as a supervisory learning tool
to handle diffuse input–output mapping, and the fmGA functions to
optimize the FL and SVM parameters. Interesting research on this
technique has been conducted in relation to project management [33].
6. Evolutionary Fuzzy Neural Inference Model EFNIM)
EFNIM presents a resolution technique for hybrid systems [27]
(composed of GA, FL, and NN, as shown in Fig. 13) that is used to
resolve all types of problems. The complementary combination of its
three elements maximizes the positive merits of each and helps to
compensate for their inherent individual weaknesses. The GA is used
for global optimization, the FL deals with uncertainties and handles
approximate inferences, and the NN is used in the input–output
mapping. Traditionally, the system has been used to resolve civil
engineering problems [30] and presents a hybrid system that has great
potential for assisting managers in implementing eficient long-term
strategies and in taking the correct action for achieving the ultimate
success of the project [94].
- 6 -
International Journal of Interactive Multimedia and Artificial Intelligence
GA Optimization
Input
Paerns Fuzziication Defuzziication
Inference
Engine (NNs)
Output
Paerns
(Control Flow)
Membership
Functions
Parameters
and topology of NNs
Defuzziication
parameter
Fig. 13. EFNIM Architecture [26].
7. Evolutionary Diffuse Hybrid Neuronal Network EFHNN)
The EFHNN mechanism is a fusion of HNN, FL, GA, and HNN. The
advantage this system has over EFNIM is that the former is capable of
handling deeper problems due to the large number of HNN models.
Global
Optimization
(GA)
Input
Paerns
Desired Outputs
Predited Outputs
Fuzziier
Inference Engine
Hybrid Neural Network
Defuzziier
(Control Flow)
Membership
Functions of FL
Fuzzy Hybrid
Neural Network
(FHNN)
Parameters
and topology of HNN
Defuzziication
parameter
Fig. 14. EFHNN Architecture [29].
As noted, the proposed EFHNN for project management
incorporates four AI approaches: NN, HONN, FL, and GA, as shown in
Fig. 14. Here, the NN and HONN are composed of the inference engine,
that is, the proposed HNN, the FL masters the fuzziier and defuzziier
layers, and the GA optimizes the HNN and FL. Currently, there exist a
small number of works that focus on this system in relation to project
management in the ield of civil engineering [32].
8. Other Relevant Optimization Techniques
Within the broad area of hybrid optimization techniques, there
are a number that are worth mentioning. This includes irely colony
algorithm-based support vector regression (SAFCASVR) [37] and
the fuzzy AHP and regression-based model [38]. Within the category
of hybrid systems based on neural networks, there are a number
of interesting examples, including multi-layer perceptron (MLP)
combined with radial basis function network (RBFN) [77], diffuse
object-oriented neural systems (OO-EFNIS) [92], wavelet-bootstrap-
ANN (WBANN) [150], and neural networks combined with GA [113].
III. A A I P
M
In the next section, we provide a brief description of the main
studies that are being carried out in the ield of AI in relation to project
management. The table 1 is also provided, which presents the main
authors working in each ield along with the optimization techniques
used in each study.
A. Tenders
Tenders and technical offers that comprise the irst phase of the
project, wherein the initial estimates and designs are proposed in
order to ascertain how much the project will cost as well as its scope.
While the area is perhaps underexplored, there exist a number of
interesting studies [38] on bidding strategies to support the decision
making or AI models optimized to predict the project award price.
In one study, the proposed model was used to analyze the data on
bridge construction projects taken from the database of the Taiwan
Public Construction Commission. The bid evaluation model and the
cost probability curve model can be used as a strategic tool to quantify
the project risks and to calculate the bids and tenders for construction
projects. Another study [148] focused on machine learning and AI in
terms of their impact on personal selling and sales management, with
the impact discussed in relation to a small area of sales and research
practice based on the seven steps of the sales process. From this, the
implications for theory and practice can be derived.
B. Project Health
A number of studies exist that focus on project management in
relation to health. The studies are fairly diverse and include research
[73] on achieving strategic control over the project’s cash lows in order
to develop appropriate strategies that apply factors such as the task
execution time, the construction rate, and the demand for resources
for cash-low control. There are also a number of studies that analyze
the project risks, with a model proposed [94] for risk analysis using
the unrestricted automatic causality of data from various software
projects. Here, it was demonstrated that the proposed model discovers
the causalities according to expert knowledge. For the prediction
of the timeframes in the management of construction projects [82],
researchers have proposed the application of AI instruments within
the construction schedule [14]. In this study, an original optimization
dispersion search algorithm was presented, which takes into account
both the technological and the organizational constraints.
C. Human Resources
Within the ield of project management, human resource
management is crucial since the projects depend on having the best
possible human capital. One study [116] provided a new approach to
the evaluation and classiication of candidates during the recruitment
process, which involves estimating their emotional intelligence using
the data from social networks. Elsewhere, in [82], the focus was on
eficient classiication algorithms to predict employee performance
fmGA parameters
Search
Training
Data Fuzziication Defuzziication
SVM training
model
Fitness
Evaluation
Optimal
Predition
model
Termination
criteria
(Control Flow)
Control Flow
MFs SVM parameters
(C, y) Defuzziication
parameter Yes
No
Fig. 12. Architecture of EFSIM [31].
- 7 -
Article in Press
and on the mining that is commonly used in many areas and has been
carried out by applying decision tree and classiication algorithms for
predicting employee performance.
D. Information Technology
Information technology is a new area within project management
but is one that is as important as all the other processes. A study was
carried out [149] in relation to an implementation model for computer
and network security purposes. Here, the aim was to use the model
to combat malicious user activity. A smart hybrid system based on
Bayesian learning networks and self-organizing maps was created
and used to classify the networks and the host-based data collected
within a local area network. Elsewhere, a study on cybersecurity and
the optimization in smart “autonomous” buildings [124] explored the
opportunities and challenges related to cybersecurity in Internet of
Things (EIoT) environments in terms of the energy in smart buildings.
Here, the proposed model can make decisions based on the data from
neural networks that are designed with a circuit feedback loop with
the ability to learn over time, which allows for learning from deined
datasets and making smart decisions.
E. Engineering and Design
AI methods have been used for the optimization of hybrid energy
systems [164] and models (evolutionary diffuse SVM) for estimating
TABLE I. M S R A
Category Investigation Optimization Techniques
Used
Tenders
Predicting project award
price [36] (NN)+(CBR)
Sales Prediction [148] (SVM), (NN)
Project
Project data analytics [28]
[7]
(EFNIM)
(Bootstrap)
Project risk modeling,
mitigation and management
[72]
[34]
(BN), (BNCC)
(GA)+(SVM)
Project mitigation and
recovery plans [93] (ANN)+(CBR)
Project execution discovery
and modeling
[11]
[94]
(GA)+(CPM)
(GA)+(FL)+(NN)=(EFNIM)
Real time predictive
analytics
[69]
[32]
(GA)
(EFHNN)
Agile Project Management [44] (CNN)
Automated report
generation [45] (GA)
Human Resources
Candidate identiication and
screening [116] (DT), (SVM) and (BN).
Performance management [82] (DT)
Retention management [78] (DT)
HR analytics [140] (ANN)
Information Technology
Cybersecurity prediction
and analytics
[149]
[133]
(ANN)+(BLN)+(SOM)
(ANN), (FL), (DT), (KNN),
(SVM)
Knowledge management [21] (ANN)+(FL)+(GA)
Design recognition library [114] (GA)
Innovation support and
prioritization [141] (ANN)+(FL)+(GA)
Logistics
Automated Logistical Truck
Services [3] (RNN), (CNN)
Object Detection and
Classiication Avoidance and
Navigation
[15] (ACO), (AG) (ANN), (AS).
(AIS)- (FNN)
Category Investigation Optimization Techniques
Used
Engineering & Design
Planning
[6]
[105]
[118]
(ANN)
(GA)+(TS)
(GA)
Stakeholder Management [33] (EFSIM)
Estimating [80]
[107]
(MA)
(ANN)+(FL)
Design automation and
optimization
[134]
[164]
[9]
[83]
[115]
[131]
(ANN)+(GA)
(GA), (PSO), (SA), (AIS),
(HS)
(ANN)
(ANN)
(ANN)+(GA)
(PNN)
Generative design [110] (ANN), (GA), (BN), (SVM),
(HS)
Continuous improvement [117] (WOA)
Evolving skills [25] (wSVM)+(FL) +(fmGA)
Operations
Back ofice/ automation/
Facilities management [157] (MLR), (ANN), (SVM), (HS)
Predictive maintenance [156]
[106]
(ANN)+(FL)+(GA)
(ANN)+(FL)+(GA)+(CBR)
Operating project analytics [16] (ANN)+(FL)+(GA)
Autonomous systems [121] (ANN)+(FL)+(GA)+(PSO)
Supply Chain
Supply Chain [161] (ANN)
Construction
Construction management [76] (ANN)
Construction cost estimation
[89]
[88]
[139]
(CBR)+(GA)
(ANN)+(CBR)+(MRA)
(MLP)+(GPA)
Construction risk
management [68] (Bootstrap)
Construction contract
management [39] (CBR)
Construction safety [127] (ANN)
Project portfolio selection [1]
[138]
(CBR)+(FL)
(HNN)+(PSO)
Onsite supervisory
manpower/
Management
[23]
[22]
(ANN)+(CBR)
(ANN)+(CBR)
- 8 -
International Journal of Interactive Multimedia and Artificial Intelligence
the construction costs. It is essential to monitor the project costs and
to identify any potential problems.
F. Operations
Operation and maintenance are also important aspects of industrial
projects, and numerous studies show how AI affects future predictive
maintenance. Here, one study [156] discusses the impact of AI on
predictive maintenance, which is an important aspect of advanced
production systems.
G. Supply Chain
A two-stage methodology has been applied to an industrial survey
dataset to investigate the relationships between key factors in a supply
chain model [161]. The advantage of this model is that it frees the
researcher from making subjective decisions during the analysis in
terms of, for example, specifying the acceptable initial route models
required for standard analysis.
H. Logistics
Researchers have conducted a general analysis of the AI
techniques applied throughout the world to address transportation
issues, primarily in terms of trafic management, trafic safety,
public transportation, and urban mobility [3]. Further studies on the
management of warehouses using AI have also been conducted [15],
while DHL also proposed an interesting approach in [62].
I. Construction
Neural networks are regarded as a promising management tool that
can enhance the current automation efforts in project management [76],
the construction phase, and the engineering phase [63]. Studies on AI
have also been carried out to identify the security risks in construction,
with a focus on the management of the portfolio of projects using AI
while taking into account the factors that generate risk in industrial
projects and the historical records of the company [1].
IV. C
The possibility of project success is a ield of research in which
researchers are working intensively. Here, the initial approaches were
based on statistical models that have not responded to the needs of
project management. In the ield of AI, researchers have identiied
the algorithms and tools that can best deal with the various project
variables and complex environments, with speciic algorithms devised
to address speciic problems in the project. The main conclusions
drawn from the reviewed works include that AI tools are more precise
than traditional tools, while, at present, they remain somewhat
complementary to the traditional approaches.
AI tools are highly useful to the project manager in terms of
controlling and monitoring the project; however, many of the
reviewed models involve weaknesses and limitations, which indicates
that project managers should continue to use their experience when
making evaluations according to the results. The trend of merging
different AI tools continues to hold sway, wherein the strengths of
one tool can compensate for the weaknesses of another. Indeed, this
approach is returning the best results, and this is where the future lies.
In this work, we studied the available AI techniques and the possible
applications in the ield of project management. In future work, a
hybrid computational model that could fully ascertain the potential
of AI in the ield of project management will be proposed. The hope
is that the management of autonomous projects will only require the
partial supervision of a human project manager.
However, an autonomous project management system will also
need to consider and fully control the project environment, including
in terms of the status of the customers or the project stakeholders.
Such a system can be used to apply AI algorithms for psychological
and emotional analysis to evaluate both team performance and
customer satisfaction. Looking to the future of 25 years from now, it
is likely that there will exist an AI capable of managing the entire
project, albeit with some form of human supervision.
The slow progress of AI in the ield of project management is
largely due to the lack of investment from private companies, which
means progress is only been made in the universities and the public
research organizations. In the future, AI will make all the decisions
and will manage the resources in an optimal and timely manner, while
the project manager will take the role of data scientist, working as part
of a team with the AI to interpret the data and the decision making.
Overall then, project managers will continue to play a crucial role
when the AI is fully developed.
A
I wish to thank my thesis tutors for the great help they provided.
I also thank my family, especially my father, Francisco Gil Moreno, a
successful businessman, without whom I could not have got where I
am today, may he rest in peace.
R
[1] H. R. Abbasianjahromi and H. Rajaie, “Application of fuzzy cbr and
modm approaches in the project portfolio selection in construction
companies,” Iranian Journal of Science and Technology - Transactions of
Civil Engineering, vol. 37, no. C1, pp. 143–155, 2013.
[2] A. Y. Abdelaziz, M. Z. Kamh, S. F. Mekhamer, and M. A. L. Badr, “A
hybrid HNN-QP approach for dynamic economic dispatch problem,”
Electric Power Systems Research., vol. 78, no. 10, pp. 1784–1788, 2008,
doi: 10.1016/j.epsr.2008.03.011.
[3] R. Abduljabbar, H. Dia, S. Liyanage, and S. A. Bagloee, “Applications
of artiicial intelligence in transport: An overview,” Sustainability
(Switzerland), vol. 11, no. 1. 2019, doi: 10.3390/su11010189.
[4] A. Abraham, “Adaptation of Fuzzy Inference System Using Neural
Learning, in Fuzzy Systems Engineering: Theory and Practice, Studies in
Fuzziness and Soft Computing,” Studies in Fuzziness and Soft Computing,
vol. 181, no. 3, 2005.
[5] B. Akay and D. Karaboga, “Artiicial bee colony algorithm for large-scale
problems and engineering design optimization,” Journal of Intelligent
Manufacturing, vol. 23, pp. 1001–1014, 2012, doi: 10.1007/s10845-010-
0393-4.
[6] F. Amer and M. Golparvar-Fard, “Formalizing Construction Sequencing
Knowledge and Mining Company-Speciic Best Practices from Past
Project Schedules,” in Computing in Civil Engineering 2019: Visualization,
Information Modeling, and Simulation - Selected Papers from the ASCE
International Conference on Computing in Civil Engineering 2019, 2019,
pp. 215–223, doi: 10.1061/9780784482421.028.
[7] L. Angelis and I. Stamelos, “A simulation tool for eficient analogy based
cost estimation,” Empirical Software Engineering, vol. 5, no. 1, pp. 35–68,
2000, doi: 10.1023/A:1009897800559.
[8] D. Anguita, A. Ghio, N. Greco, L. Oneto, and S. Ridella, “Model selection
for support vector machines: Advantages and disadvantages of the
Machine Learning Theory,” in Proceedings of the International Joint
Conference on Neural Networks, 2010, doi: 10.1109/IJCNN.2010.5596450.
[9] O. Arslan and O. Yetik, “ANN based optimization of supercritical ORC-
Binary geothermal power plant: Simav case study,” in Applied Thermal
Engineering, 2011, vol. 31, no. 17–18, pp. 3922–3928, doi: 10.1016/j.
applthermaleng.2011.07.041.
[10] L. Auria and R. A. Moro, “support vector machine as a Technique of
Solvency analysis,” DIW Berlin, vol. 811, 2008. doi: 10.2139/ssrn.1424949.
[11] R. F. Aziz, S. M. Hafez, and Y. R. Abuel-Magd, “Smart optimization for
mega construction projects using artiicial intelligence,” Alexandria Eng.
J., vol. 53, no. 3, pp. 591–606, 2014, doi: 10.1016/j.aej.2014.05.003.
[12] R. Bhattacharyya, P. Kumar, and S. Kar, “Fuzzy R&D portfolio selection of
- 9 -
Article in Press
interdependent projects,” Computers and Mathematics with Applications,
vol. 62, no. 10, pp. 3857–3870, 2011, doi: 10.1016/j.camwa.2011.09.036.T.
[13] Bhoskar, O. K. Kulkarni, N. K. Kulkarni, S. L. Patekar, G. M. Kakandikar,
and V. M. Nandedkar, “Genetic Algorithm and its Applications to
Mechanical Engineering: A Review,” in Materials Today: Proceedings,
2015, vol. 2, no. 4–5, pp. 2624–2630, doi: 10.1016/j.matpr.2015.07.219.
[14] W. Boejko, Z. Hejducki, and M. Wodecki, “Applying metaheuristic
strategies in construction projects management,” Journal of Civil
Engineering and Management, vol. 18, no. 5, pp. 621–630, Oct. 2012, doi:
10.3846/13923730.2012.719837.
[15] E. Bottani, R. Montanari, M. Rinaldi, and G. Vignali, “Intelligent
algorithms for warehouse management,” Intelligent Systems Reference
Library, vol. 87, pp. 645–667, 2015, doi: 10.1007/978-3-319-17906-3_25.
[16] G. Braswell, “Artiicial Intelligence Comes of Age in Oil and Gas,”
Journal of Petroleum Technology, vol. 65, no. 01, pp. 50–57, 2013, doi:
10.2118/0113-0050-jpt.
[17] S. T. Buckland, A. C. Davison, and D. V. Hinkley, “Bootstrap Methods
and Their Application,” Biometrics, vol. 52, no. 2, p. 795, 1998, doi:
10.2307/3109789.
[18] E. Carmona, “Tutorial sobre Maquinas de Vectores Soporte (SVM).”
2016. UNED, Consultada en http://www. ia. uned. es/~ ejcarmona/
publicaciones/[2013-Carmona]%20SVM.pdf (fecha de consulta 01-07-
2017).
[19] A. Castillo, J.M, Cortes, C, Gonzalez, J., & Benito, “Prospecting The Future
with AI,” Internacional Journal of Artiicial Intelligence and Interactive
Multimedia, vol. 1, no. 2, pp. 1–53, 2009.
[20] C. Chapell and V. Vapnik, “Model selection for Support Vector Machines,”
in Advances in Neural Information Processing Systems, 2000, pp. 230–
236, doi:10.5555/3009657.3009690
[21] [1] S. S. Chaudhry, M. W. Varano, and L. Xu, “Systems research, genetic
algorithms and information systems,” Systems Research and Behavioral
Science, 2000, doi: 10.1002/(sici)1099-1743(200003/04)17:2<149::aid-
sres290>3.3.co;2-h.
[22] J. H. Chen and S. C. Hsu, “Hybrid ANN-CBR model for disputed change
orders in construction projects,” Automation in Construction, 2007, doi:
10.1016/j.autcon.2007.03.003.
[23] J. H. Chen, L. R. Yang, W. H. Chen, and C. K. Chang, “Case-based allocation
of onsite supervisory manpower for construction projects,” Construction
Management and Economics, 2008, doi: 10.1080/01446190802014778.
[24] M. Y. Cheng, J. S. Chou, A. F. V. Roy, and Y. W. Wu, “High-performance
Concrete Compressive Strength Prediction using Time-Weighted
Evolutionary Fuzzy Support Vector Machines Inference Model,”
Automation in Construction, 2012, doi: 10.1016/j.autcon.2012.07.004..
[25] M. Y. Cheng, N. D. Hoang, A. F. V. Roy, and Y. W. Wu, “A novel time-
depended evolutionary fuzzy SVM inference model for estimating
construction project at completion,” Engineering Applications of
Artiicial Intelligence, vol. 25, no. 4, pp. 744–752, 2012, doi: 10.1016/j.
engappai.2011.09.022.
[26] M. Y. Cheng, L. C. Lien, H. C. Tsai, and P. H. Chen, “Artiicial intelligence
approaches to dynamic project success assessment taxonomic,” Life
Science Journal, vol. 9, pp. 5156–5163, 2012.
[27] M. Y. Cheng, H. C. Tsai, and W. S. Hsieh, “Web-based conceptual cost
estimates for construction projects using Evolutionary Fuzzy Neural
Inference Model,” Automation in Construction, vol. 18, no. 2, pp. 164–172,
2009, doi: 10.1016/j.autcon.2008.07.001.
[28] M. Y. Cheng, H. C. Tsai, and C. L. Liu, “Artiicial intelligence approaches
to achieve strategic control over project cash lows,” Automation
in Construction, vol. 18, no. 4, pp. 386–393, 2009, doi: 10.1016/j.
autcon.2008.10.005.
[29] M. Y. Cheng, H. C. Tsai, and E. Sudjono, “Evaluating subcontractor
performance using evolutionary fuzzy hybrid neural network,”
International Journal of Project Management, vol. 29, no. 3, pp. 349–356,
2011, doi: 10.1016/j.ijproman.2010.03.005.
[30] M. Y. Cheng, H. C. Tsai, and E. Sudjono, “Evolutionary fuzzy hybrid
neural network for conceptual cost estimates in construction projects,”
in 2009 26th International Symposium on Automation and Robotics
in Construction, ISARC 2009, 2009, pp. 512–519, doi: 10.22260/
isarc2009/0040.
[31] M. Y. Cheng, D. K. Wibowo, D. Prayogo, and A. F. V. Roy, “Predicting
productivity loss caused by change orders using the evolutionary
fuzzy support vector machine inference model,” Journal of Civil
Engineering and Management, vol. 21, no. 7, pp. 881–892, Oct. 2015, doi:
10.3846/13923730.2014.893922.
[32] T. M. Cheng and R. Z. Yan, “Integrating messy genetic algorithms and
simulation to optimize resource utilization,” Computer-Aided Civil
and Infrastructure Engineering, vol. 24, no. 6, pp. 401–415, 2009, doi:
10.1111/j.1467-8667.2008.00588.x..
[33] J. S. Chou, M. Y. Cheng, and Y. W. Wu, “Improving classiication accuracy
of project dispute resolution using hybrid artiicial intelligence and
support vector machine models,” Expert Systems with Applications, vol.
40, no. 6, pp. 2263–2274, 2013, doi: 10.1016/j.eswa.2012.10.036.
[34] J. S. Chou, M. Y. Cheng, Y. W. Wu, and A. D. Pham, “Optimizing parameters
of support vector machine using fast messy genetic algorithm for dispute
classiication,” Expert Syst. Appl., 2014, doi: 10.1016/j.eswa.2013.12.035.
[35] J. S. Chou, M. Y. Cheng, Y. W. Wu, and A. D. Pham, “Optimizing
parameters of support vector machine using fast messy genetic algorithm
for dispute classiication,” Expert Systems with Applications, vol. 41, no.
8, pp. 3955–3964, 2014, doi: 10.1016/j.eswa.2013.12.035.
[36] J. S. Chou and A. D. Pham, “Smart Artiicial Firely Colony Algorithm-
Based Support Vector Regression for Enhanced Forecasting in Civil
Engineering,” Computer-Aided Civil and Infrastructure Engineering, vol.
30, no. 9, pp. 715–732, 2015, doi: 10.1111/mice.12121.
[37] J. S. Chou and A. D. Pham, “Smart Artiicial Firely Colony Algorithm-
Based Support Vector Regression for Enhanced Forecasting in Civil
Engineering,” Comput. Civ. Infrastruct. Eng., 2015, doi: 10.1111/
mice.12121.
[38] J. S. Chou, A. D. Pham, and H. Wang, “Bidding strategy to support
decision-making by integrating fuzzy AHP and regression-based
simulation,” Automation in Construction, vol. 35, pp. 517–527, 2013, doi:
10.1016/j.autcon.2013.06.007.
[39] D. K. Chua and P. K. Loh, “CB-Contract: Case-Based Reasoning Approach
to Construction Contract Strategy Formulation,” Journal of Computing
in Civil Engineering, vol. 20, no. 5, pp. 339–350, 2006, doi: 10.1061/
(asce)0887-3801(2006)20:5(339).
[40] O. Cordón, “A historical review of evolutionary learning methods for
Mamdani-type fuzzy rule-based systems: Designing interpretable genetic
fuzzy systems,” International Journal of Approximate Reasoning, vol. 52,
no. 6. pp. 894–913, 2011, doi: 10.1016/j.ijar.2011.03.004.
[41] F. Costantino, G. Di Gravio, and F. Nonino, “Project selection in project
portfolio management: An artiicial neural network model based on
critical success factors,” International Journal of Project Management,
vol. 33, no. 8, pp. 1744–1754, 2015, doi: 10.1016/j.ijproman.2015.07.003.
[42] E. Cox, Fuzzy Modeling and Genetic Algorithms for Data Mining and
Exploration. 2005. Doi: 10.1016/B978-0-12-194275-5.X5000-2.
[43] A. L. A. Dalhoum and M. Al-Rawi, “High-Order Neural Networks are
Equivalent to Ordinary Neural Networks,” Modern Applied Science, vol.
13, no. 2, p. 228, Jan. 2019, doi: 10.5539/mas.v13n2p228.
[44] H. K. Dam, T. Tran, J. Grundy, A. Ghose, and Y. Kamei, “Towards effective
AI-powered agile project management,” in Proceedings - 2019 IEEE/ACM
41st International Conference on Software Engineering: New Ideas and
Emerging Results, ICSE-NIER 2019, 2019, pp. 41–44, doi: 10.1109/ICSE-
NIER.2019.00019.
[45] R. Day, J. Zydallis, G. Lamont, and R. Pachter, “Analysis of ine granularity
and building block sizes in the parallel fast messy GA,” in Proceedings of
the 2002 Congress on Evolutionary Computation, CEC 2002, 2002, vol. 1,
pp. 127–132, doi: 10.1109/CEC.2002.1006221.
[46] J. J. G. De la Rosa, A. A. Pérez, J. C. Palomares Salas, J. G. Ramiro Leo, and
A. M. Muñoz, “A novel inference method for local wind conditions using
genetic fuzzy systems,” Renewable Energy, vol. 36, no. 6, pp. 1747–1753,
2011, doi: 10.1016/j.renene.2010.12.017.
[47] N. Dong, M. Fischer, D. Ge, and R. E. Levitt, “Automated look-ahead
schedule generation and optimization for the inishing phase of complex
construction projects,” CIFE Technical Report, Stanford University, no.
June, p. 1 online resource., 2012.
[48] S. Ebrahimnejad, S. M. Mousavi, and H. Seyraianpour, “Risk identiication
and assessment for build-operate-transfer projects: A fuzzy multi
attribute decision making model,” Expert Systems with Applications, vol.
37, no. 1, pp. 575–586, Jan. 2010, doi: 10.1016/j.eswa.2009.05.037.
[49] T. Efendigil, S. Önüt, and C. Kahraman, “A decision support system for
demand forecasting with artiicial neural networks and neuro-fuzzy
- 10 -
International Journal of Interactive Multimedia and Artificial Intelligence
models: A comparative analysis,” Expert Systems with Applications, vol.
36, no. 3 PART 2, pp. 6697–6707, 2009, doi: 10.1016/j.eswa.2008.08.058.
[50] B. Efron and R. Tibshirani, “Bootstrap methods for standard errors,
conidence intervals, and other measures of statistical accuracy,” Statistical
Science, vol. 1, no. 1, pp. 54–75, 1986, doi: 10.1214/ss/1177013815.
[51] C. Egbu and S. Suresh, “Knowledge Mapping Techniques Within The
Construction Industry:An Exploratory Study,” CIB W102-Information
Knowl. Manag. Build., pp. 48–57, 2008.
[52] C. Egbu and S. Suresh, “Knowledge Mapping Techniques Within The
Construction Industry:An Exploratory Study,” CIB W102-Information
and knowledge management in Buildings, pp. 48–57, 2008.
[53] A. O. Esogbue and J. A. Murrell, “Fuzzy adaptive controller using
reinforcement learning neural networks,” in 1993 IEEE International
Conference on Fuzzy Systems, 1993, pp. 178–183, doi: 10.1109/
fuzzy.1993.327494.
[54] W. H. Estler H.C, “Heuristic Search-Based Planning for Graph
Transformation Systems,” ICAPS Workshop on Knowledge Engineering
for Planning and Scheduling, p. 54, 2011.
[55] A. M. Fahim, A. M. Salem, F. A. Torkey, and M. A. Ramadan, “Eficient
enhanced k-means clustering algorithm,” Journal of Zhejiang University:
Science, vol. 7, no. 10, pp. 1626–1633, 2006, doi: 10.1631/jzus.2006.A1626.
[56] E. Faliagka et al., “On-line consistent ranking on e-recruitment: Seeking
the truth behind a well-formed CV,” Artiicial Intelligence Review, vol. 42,
no. 3, pp. 515–528, 2014, doi: 10.1007/s10462-013-9414-y.
[57] M. Fazzolari, R. Alcala, Y. Nojima, H. Ishibuchi, and F. Herrera, “A review
of the application of multiobjective evolutionary fuzzy systems: Current
status and further directions,” IEEE Transactions on Fuzzy Systems, vol.
21, no. 1, pp. 45–65, 2013, doi: 10.1109/TFUZZ.2012.2201338.
[58] C. M. Fonseca and P. J. Fleming, “Genetic Algorithms for Multiobjective
Optimization: Formulation, Discussion and Generalization,” Icga, vol. 93,
no. July, pp. 416–423, 1993, doi: citeulike-article-id:2361311.
[59] A. Fukunaga, G. Rabideau, S. Chien, and D. Yan, “Towards an application
framework for automated planning and scheduling,” in IEEE Aerospace
Applications Conference Proceedings, 1997, vol. 1, pp. 375–386, doi:
10.1109/aero.1997.574426.
[60] T. Ganesan, P. Vasant, and I. Elamvazuthi, “Hopield neural networks
approach for design optimization of hybrid power systems with multiple
renewable energy sources in a fuzzy environment,” Journal of Intelligent
and Fuzzy Systems, vol. 26, no. 5, pp. 2143–2154, 2014, doi: 10.3233/IFS-
130889.
[61] B. S. Garcia, R., Perez, I., Villavicencio, N., Piñero, P., “Experiences by
using genetic algorithms in project scheduling,” Revista Cubana de
Ciencias Informáticas, vol. 10, pp. 71–86, 2016.
[62] L. Kota, “Artiicial Intelligence in Logistics,” Advanced Logistic Systems
- Theory and Practice, vol. 12, no. 1, pp. 47–60, 2019, doi: 10.32971/
als.2019.004.
[63] Y. M. Goh and D. K. H. Chua, “Case-Based Reasoning Approach to
Construction Safety Hazard Identiication: Adaptation and Utilization,”
Journal of Construction Engineering and Management, vol. 136, no. 2, pp.
170–178, 2010, doi: 10.1061/(asce)co.1943-7862.0000116.
[64] D. Goldberg and K. Deb, “Rapid, accurate optimization of dificult
problems using messy genetic algorithms,” proceedings of the ifth
international conference on genetic algorithms, pp. 56–64, 1993.
[65] D. GOLDBERG, “Messy Genetic Algorithms: Motivation, Analysis, and
First Results,” Complex Systems, vol. 3, no. 5, pp. 493–530, 1989.
[66] F. Hartman and R. A. Ashrai, “Project Management in the Information
Systems and Information Technologies Industries,” Project Management
Journal, 2002, doi: 10.1177/875697280203300303.
[67] H. Hashemi, S. M. Mousavi, and S. M. H. Mojtahedi, “Bootstrap technique
for risk analysis with interval numbers in bridge construction projects,”
J. Constr. Eng. Manag., 2011, doi: 10.1061/(ASCE)CO.1943-7862.0000344.
[68] H. Hashemi, S. M. Mousavi, R. Tavakkoli-Moghaddam, and Y. Gholipour,
“Compromise Ranking Approach with Bootstrap Conidence Intervals for
Risk Assessment in Port Management Projects,” Journal of Management
in Engineering, vol. 29, no. 4, pp. 334–344, 2013, doi: 10.1061/(asce)
me.1943-5479.0000167.
[69] T. Hegazy, “Optimization of construction time - Cost trade-off analysis
using genetic algorithms,” Canadian Journal of Civil Engineering, vol. 26,
no. 6, pp. 685–697, 1999, doi: 10.1139/l99-031.
[70] D. Heiss-Czedik, “An Introduction to Genetic Algorithms.,” Artiicial Life,
vol. 3, no. 1, pp. 63–65, 1997, doi: 10.1162/artl.1997.3.63.
[71] F. Herrera, “Genetic fuzzy systems: Taxonomy, current research trends
and prospects,” Evolutionary Intelligence, vol. 1, no. 1, pp. 27–46, 2008,
doi: 10.1007/s12065-007-0001-5.
[72] X. Hu, B. Xia, M. Skitmore, and Q. Chen, “The application of case-
based reasoning in construction management research: An overview,”
Automation in Construction, vol. 72. pp. 65–74, 2016, doi: 10.1016/j.
autcon.2016.08.023.
[73] Y. Hu, X. Zhang, E. W. T. Ngai, R. Cai, and M. Liu, “Software project risk
analysis using Bayesian networks with causality constraints,” Decision
Support Systems, vol. 56, no. 1, pp. 439–449, Dec. 2013, doi: 10.1016/j.
dss.2012.11.001.
[74] S. V. Ioannou, A. T. Raouzaiou, V. A. Tzouvaras, T. P. Mailis, K. C.
Karpouzis, and S. D. Kollias, “Emotion recognition through facial
expression analysis based on a neurofuzzy network,” Neural Networks,
vol. 18, no. 4, pp. 423–435, 2005, doi: 10.1016/j.neunet.2005.03.004.
[75] H. Ishibuchi, “Genetic fuzzy systems: evolutionary tuning and learning
of fuzzy knowledge bases,” Fuzzy Sets and Systems, vol. 141, no. 1, pp.
161–162, 2004, doi: 10.1016/s0165-0114(03)00262-8.
[76] M. Jain and K. K. Pathak, “Applications of artiicial neural network in
construction engineering and management - A review,” International
Journal of Engineering Technology, Management and Applied Sciences,
vol. 2, no. 3, pp. 134–142, 2014.
[77] H. R. Jantan, A. A. Hamdan, and Z. Othman, “Human Talent Forecasting
using Data Mining Classiication Techniques,” International Journal
of Technology Diffusion, vol. 1, no. 4, pp. 29–41, 2011, doi: 10.4018/
jtd.2010100103.
[78] H. Jantan, “Human Talent Prediction in HRM using C4 . 5 Classiication
Algorithm,” International Journal on Computer Science and Engineering,
vol. 02, no. 08, pp. 2526–2534, 2010.
[79] C. D. Jeffries, “Tracking, code recognition, and memory management
with high-order neural networks”,Applications and Science of Artiicial
Neural Networks, 1995, vol. 2492, pp. 964–973, doi: 10.1117/12.205207.
[80] L. Jin, C. Zhang, X. Shao, and G. Tian, “Mathematical modeling and a
memetic algorithm for the integration of process planning and scheduling
considering uncertain processing times,” Proceedings of the Institution of
Mechanical Engineers, Part B: Journal of Engineering Manufacture, vol.
230, no. 7, pp. 1272–1283, 2016, doi: 10.1177/0954405415625916.
[81] V. Kachitvichyanukul, “Comparison of Three Evolutionary Algorithms:
GA, PSO, and DE,” Industrial Engineering and Management Systems, vol.
11, no. 3, pp. 215–223, 2012, doi: 10.7232/iems.2012.11.3.215.
[82] V. Kalaivani and M. M. Elamparithi, “An Eficient Classiication
Algorithms for Employee Performance Prediction,” International Journal
of Research in Advent Technology, vol. 2, no. 9, pp. 27–32, 2014.
[83] S. A. Kalogirou, “Artiicial neural networks and genetic algorithms for
the optimisation of solar thermal systems,” in Artiicial Intelligence in
Energy and Renewable Energy Systems, Nova Science Publishers, Inc.,
2006, pp. 131–162.
[84] T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman,
and A. Y. Wu, “An eficient k-means clustering algorithms: Analysis
and implementation,” IEEE Transactions on Pattern Analysis and
Machine Intelligence, vol. 24, no. 7, pp. 881–892, 2002, doi: 10.1109/
TPAMI.2002.1017616.
[85] S. Kar, S. Das, and P. K. Ghosh, “Applications of neuro fuzzy systems: A
brief review and future outline,” Applied Soft Computing Journal, vol. 15.
pp. 243–259, 2014, doi: 10.1016/j.asoc.2013.10.014.
[86] H. Kargupta, “SEARCH, polynomial complexity, and the fast messy
genetic algorithm,” Urbana, vol. 51, no. 95008, p. 188, 1996.
[87] N. A. Kartam, R. E. Levitt, and D. E. Wilkins, “Extending Artiicial
Intelligence Techniques for Hierarchical Planning,” Journal of Computing
in Civil Engineering, vol. 5, no. 4, pp. 464–477, 1991, doi: 10.1061/
(asce)0887-3801(1991)5:4(464).
[88] G. H. Kim, S. H. An, and K. I. Kang, “Comparison of construction cost
estimating models based on regression analysis, neural networks,
and case-based reasoning,” Build. Environ., 2004, doi: 10.1016/j.
buildenv.2004.02.013.
[89] G. H. Kim, S. H. An, and K. I. Kang, “Comparison of construction cost
estimating models based on regression analysis, neural networks, and
case-based reasoning,” Building and Environment, vol. 39, no. 10, pp.
1235–1242, 2004, doi: 10.1016/j.buildenv.2004.02.013.
- 11 -
Article in Press
[90] O. Kisi, “Modeling solar radiation of Mediterranean region in Turkey by
using fuzzy genetic approach,” Energy, vol. 64, pp. 429–436, 2014, doi:
10.1016/j.energy.2013.10.009.
[91] M. Klumpp, “Automation and artiicial intelligence in business logistics
systems: human reactions and collaboration requirements,” International
Journal of Logistics Research and Applications, vol. 21, no. 3, pp. 224–242,
2018, doi: 10.1080/13675567.2017.1384451.
[92] C. H. Ko and M. Y. Cheng, “Hybrid use of AI techniques in developing
construction management tools,” Automation in Construction, vol. 12,
no. 3, pp. 271–281, May 2003, doi: 10.1016/S0926-5805(02)00091-2.
[93] C.-H. Ko and M.-Y. Cheng, “Dynamic Prediction of Project Success
Using Artiicial Intelligence,” Journal of Construction Engineering and
Management, vol. 133, no. 4, pp. 316–324, 2007, doi: 10.1061/(asce)0733-
9364(2007)133:4(316).
[94] C. H. Ko, M. Y. Cheng, and T. K. Wu, “Evaluating sub-contractors
performance using EFNIM,” Automation in Construction, vol. 16, no. 4,
pp. 525–530, 2007, doi: 10.1016/j.autcon.2006.09.005.
[95] K. A. H. Kobbacy, “Application of Artiicial Intelligence in maintenance
modelling and management,” in IFAC Proceedings Volumes (IFAC-
PapersOnline), 2012, doi: 10.3182/20121122-2-ES-4026.00046.
[96] K. A. H. Kobbacy, “Application of Artiicial Intelligence in maintenance
modelling and management,” in IFAC Proceedings Volumes (IFAC-
PapersOnline), 2012, vol. 45, no. 31, pp. 54–59, doi: 10.3182/20121122-2-
ES-4026.00046.
[97] M. Kumar, M. Husain, N. Upreti, and D. Gupta, “Genetic Algorithm:
Review and Application,” SSRN Electronic Journal, vol. 2, no. 2, pp. 451–
454, 2020, doi: 10.2139/ssrn.3529843.
[98] H. K. Kwan, “High-order feedbackward neural networks,” 1991, pp. 49–
51, doi: 10.1109/ciccas.1991.184277.
[99] H. Kwasnicka and M. Przewozniczek, “Multi population pattern
searching algorithm: A new evolutionary method based on the idea of
messy genetic algorithm,” IEEE Trans. Evol. Comput., 2011, doi: 10.1109/
TEVC.2010.2102038.
[100] M. Lahmann, “AI will transform project management. Are you ready?,”
Pwc Switzerland, 2018. [Online]. Available: https://www.pwc.ch/en/
insights/risk/transformation-assurance-ai-will-transform-project-
management-are-you-ready.html.
[101] M. Laumanns and J. Ocenasek, “Bayesian optimization algorithms for
multi-objective optimization,” in Lecture Notes in Computer Science
(including subseries Lecture Notes in Artiicial Intelligence and Lecture
Notes in Bioinformatics), 2002, vol. 2439, pp. 298–307, doi: 10.1007/3-540-
45712-7_29.
[102] G. G. Lendaris, K. Mathia, and R. Saeks, “Linear Hopield networks and
constrained optimization,” IEEE Transactions on Systems, Man, and
Cybernetics, Part B: Cybernetics, vol. 29, no. 1, pp. 114–118, 1999, doi:
10.1109/3477.740171.
[103] F. L. Lewis and D. Vrabie, “Reinforcement learning and adaptive dynamic
programming for feedback control,” IEEE Circuits and Systems Magazine,
vol. 9, no. 3, pp. 32–50, 2009, doi: 10.1109/MCAS.2009.933854.
[104] M. Y. Leyva Vázquez, K. Pérez Teruel, A. Febles Estrada, and J. Gulín
González, “Mapas cognitivos difusos para la selección de proyectos de
tecnologías de la información,” Contaduría y Administración, vol. 58, no.
4, pp. 95–117, 2013, doi: 10.1016/s0186-1042(13)71235-x.
[105] X. Li, L. Gao, and W. Li, “Application of game theory based hybrid
algorithm for multi-objective integrated process planning and
scheduling,” Expert Systems with Applications, vol. 39, no. 1, pp. 288–
297, 2012, doi: 10.1016/j.eswa.2011.07.019.
[106] Z. Li, Y. Wang, and K. S. Wang, “Intelligent predictive maintenance for
fault diagnosis and prognosis in machine centers: Industry 4.0 scenario,”
Advances in Manufacturing, vol. 5, no. 4, pp. 377–387, 2017, doi: 10.1007/
s40436-017-0203-8.
[107] R. . Lozada, “Redes neuronales y logica difusa aplicado a un sistema
climatológico,” Universidad nacional de San Agustin, 2017.
[108] P. C. K. Luk, K. C. Low, and A. Sayiah, “GA-based fuzzy logic control of a
solar power plant using distributed collector ields,” Renewable Energy,
vol. 16, no. 1–4, pp. 765–768, 1999, doi: 10.1016/s0960-1481(98)00275-4.
[109] M. M. Mijwil, “Artiicial Neural Networks Advantages and Disadvantages,”
Linkedin, no. March, 2018.
[110] V. Machairas, A. Tsangrassoulis, and K. Axarli, “Algorithms for
optimization of building design: A review,” Renewable and Sustainable
Energy Reviews, vol. 31. pp. 101–112, 2014, doi: 10.1016/j.rser.2013.11.036.
[111] J. G. MacKinnon, “Bootstrap methods in econometrics,” in
Economic Record, 2006, vol. 82, no. SPEC. ISS. 1, doi: 10.1111/j.1475-
4932.2006.00328.x.
[112] D. Magaña Martínez and J. C. Fernandez-Rodriguez, “Artiicial Intelligence
Applied to Project Success: A Literature Review,” International Journal of
Interactive Multimedia and Artiicial Intelligence, vol. 3, no. 5, p. 77, 2015,
doi: 10.9781/ijimai.2015.3510.
[113] R. Mahajan and G. Kaur, “Neural Networks using Genetic Algorithms,”
International Journal of Computer Applications, vol. 77, no. 14, pp. 6–11,
Sep. 2013, doi: 10.5120/13549-1153.
[114] M. G. Marchetta and R. Q. Forradellas, “An artiicial intelligence planning
approach to manufacturing feature recognition,” CAD Computer Aided
Design, vol. 42, no. 3, pp. 248–256, 2010, doi: 10.1016/j.cad.2009.11.007.
[115] A. Mellit, S. a Kalogirou, and M. Drif, “Application of neural networks and
genetic algorithms for sizing of photovoltaic systems,” Renewable Energy,
vol. 35, no. 12, pp. 2881–2893, 2010, doi: 10.1016/j.renene.2010.04.017.
[116] V. M. Menon and H. A. Rahulnath, “A novel approach to evaluate
and rank candidates in a recruitment process by estimating emotional
intelligence through social media data,” in 2016 International Conference
on Next Generation Intelligent Systems, ICNGIS 2016, 2017, doi: 10.1109/
ICNGIS.2016.7854061.
[117] S. Mirjalili and A. Lewis, “The Whale Optimization Algorithm,” Advances
in Engineering Software, vol. 95, pp. 51–67, 2016, doi: 10.1016/j.
advengsoft.2016.01.008.
[118] J. R. Montoya-Torres, E. Gutierrez-Franco, and C. Pirachicán-Mayorga,
“Project scheduling with limited resources using a genetic algorithm,”
International Journal of Project Management, vol. 28, no. 6, pp. 619–628,
2010, doi: 10.1016/j.ijproman.2009.10.003.
[119] A. Moreno and T. Redondo, “Text Analytics: the convergence of Big
Data and Artiicial Intelligence,” International Journal of Interactive
Multimedia and Artiicial Intelligence, vol. 3, no. 6, p. 57, 2016, doi:
10.9781/ijimai.2016.369.
[120] O. Moselhi, T. Hegazy, and P. Fazio, “Neural Networks as Tools
in Construction,” Journal of Construction Engineering and
Management, vol. 117, no. 4, pp. 606–625, 1991, doi: 10.1061/(asce)0733-
9364(1991)117:4(606).
[121] G. P. Moustris, S. C. Hiridis, K. M. Deliparaschos, and K. M. Konstantinidis,
“Evolution of autonomous and semi-autonomous robotic surgical
systems: A review of the literature,” International Journal of Medical
Robotics and Computer Assisted Surgery, vol. 7, no. 4. pp. 375–392, 2011,
doi: 10.1002/rcs.408.
[122] K. N. Mutter, Z. M. Jafri, and A. A. Aziz, “Hopield Neural Network (HNN)
Improvement for color image recognition using multi-bitplane and multi-
connect architecture,” in Computer Graphics, Imaging and Visualisation:
New Advances, CGIV 2007, 2007, pp. 403–407, doi: 10.1109/CGIV.2007.24.
[123] M. Mylrea and N. G. Gourisetti, “Cybersecurity and optimization in
smart ‘autonomous’ buildings,” in Autonomy and Artiicial Intelligence:
A Threat or Savior?, 2017, pp. 263–294.
[124] G. Napoles, “Algoritmo para mejorar la convergencia en Mapas
Cognitivos Difusos Sigmoidales,” Universidad Central “Marta Abreu” de
Las Villas Facultad de Matemática, Física y Computación., 2014.
[125] D. Nau, S. Gupta, and W. Regli, “Manufacturing-Operation Planning
Versus AI Planning,” in AAAI Spring Symposium on Integrated Planning
Applications, 1995.
[126] M. Obayashi, T. Nishida, T. Kuremoto, K. Kobayashi, and L. B. Feng, “A
reinforcement learning system embedded agent with neural network-
based multi-valued pattern memory structure,” in ICCAS 2010 -
International Conference on Control, Automation and Systems, 2010, pp.
176–181, doi: 10.1109/iccas.2010.5669888.
[127] D. A. Patel and K. N. Jha, “Neural Network Model for the Prediction of
Safe Work Behavior in Construction Projects,” Journal of Construction
Engineering and Management, vol. 141, no. 1, p. 04014066, 2015, doi:
10.1061/(asce)co.1943-7862.0000922.
[128] M. Pelikan, D. E. Goldberg, and E. Cantú-Paz, “BOA : The Bayesian
Optimization Algorithm 1 Introduction,” Proceedings of the genetic and
evolutionary computation conference GECCO-99, vol. 1, pp. 525–532,
1999.
[129] T. Pfeufer and M. Ayoubi, “Application of a hybrid neuro-fuzzy system to
the fault diagnosis of an automotive electromechanical actuator,” Fuzzy
- 12 -
International Journal of Interactive Multimedia and Artificial Intelligence
Sets and Systems, vol. 89, no. 3, pp. 351–360, 1997, doi: 10.1016/S0165-
0114(97)00022-5.
[130] PMI, PMBOK Guide | Project Management Institute. 2017.
[131] S. M. Pourkiaei, M. H. Ahmadi, and S. M. Hasheminejad, “Modeling
and experimental veriication of a 25W fabricated PEM fuel cell by
parametric and GMDH-type neural network,” Mech. Ind., 2016, doi:
10.1051/meca/2015050.
[132] R. Prieto, “Impacts of Artiicial Intelligence on Management of Large
Complex Projects,” PM World Journal, vol. 8, no. 5, pp. 1–20, 2019.
[133] A. Rehman and T. Saba, “Evaluation of artiicial intelligent techniques to
secure information in enterprises,” Artiicial Intelligence Review, vol. 42,
no. 4, pp. 1029–1044, 2014, doi: 10.1007/s10462-012-9372-9.
[134] C. Renzi, F. Leali, M. Cavazzuti, and A. O. Andrisano, “A review on
artiicial intelligence applications to the optimal design of dedicated
and reconigurable manufacturing systems,” International Journal of
Advanced Manufacturing Technology, vol. 72, no. 1–4, pp. 403–418, 2014,
doi: 10.1007/s00170-014-5674-1.
[135] L. Ricalde, B. Cruz, and E. Sánchez, “Control neuronal recurrente de
alto orden para turbinas de viento con generador síncrono de imán
permanente,” Computación y Sistemas, vol. 14, no. 2, pp. 133–143, 2010.
[136] L. Rodriguez-Repiso, R. Setchi, and J. L. Salmeron, “Modelling IT projects
success with Fuzzy Cognitive Maps,” Expert Systems with Applications,
vol. 32, no. 2, pp. 543–559, 2007, doi: 10.1016/j.eswa.2006.01.032.
[137] L. Rutkowski, K. Cpałka, R. Nowicki, A. Pokropińska, and R. Scherer,
“Neuro-fuzzy systems,” in Computational Complexity: Theory,
Techniques, and Applications, vol. 9781461418, 2012, pp. 2069–2081.
[138] A. N. Sadigh, H. Mokhtari, M. Iranpoor, and S. M. T. Fatemi Ghomi,
“Cardinality constrained portfolio optimization using a hybrid approach
based on particle swarm optimization and hopield neural network,”
Advanced Science Letters, vol. 17, no. 1, pp. 11–20, 2012, doi: 10.1166/
asl.2012.3666.
[139] E. L. O. Savaş Bayram, Mehmet Emin Öcal, “Analysis of Cost and
Schedule Variances in Construction Works with Artiicial Intelligence
Approaches: The Case of Turkey,” in International Students’ Conference
of Civil Engineering, ISCCE, 2012, pp. 10–11.
[140] T. Schmitt, P. Caillou, and M. Sebag, “Matching Jobs and Resumes:
a Deep Collaborative Filtering Task,” 2018, vol. 41, pp. 124–109, doi:
10.29007/17rz.
[141] S. G. Selivanov, S. N. Poezjalova, and O. A. Gavrilova, “The Use of
Artiicial Intelligence Methods of Technological Preparation of Engine-
Building Production,” American Journal of Industrial Engineering, vol. 2,
no. 1, pp. 10–14, 2014, doi: 10.12691/AJIE-2-1-3.R.
[142] R. Sonmez, “Parametric Range Estimating of Building Costs Using
Regression Models and Bootstrap,” Journal of Construction Engineering
and Management, vol. 134, no. 12, pp. 1011–1016, 2008, doi: 10.1061/
(asce)0733-9364(2008)134:12(1011).
[143] C. D. Stylios and P. P. Groumpos, “Modeling Complex Systems Using
Fuzzy Cognitive Maps,” IEEE Transactions on Systems, Man, and
Cybernetics Part A:Systems and Humans., vol. 34, no. 1, pp. 155–162,
2004, doi: 10.1109/TSMCA.2003.818878.
[144] L. Suganthi, S. Iniyan, and A. A. Samuel, “Applications of fuzzy logic
in renewable energy systems - A review,” Renewable and Sustainable
Energy Reviews, vol. 48. pp. 585–607, 2015, doi: 10.1016/j.rser.2015.04.037.
[145] M. Sugeno and T. Yasukawa, “A Fuzzy-Logic-Based Approach to
ualitative Modeling,” IEEE Transactions on Fuzzy Systems, vol. 1, no. 1,
pp. 7–31, 1993, doi: 10.1109/TFUZZ.1993.390281.
[146] H. K. Sulehria and Y. Zhang, “Hopield Neural Networks — A Survey,”
Engineering, pp. 125–130, 2007.
[147] R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction,”
IEEE Transactions on Neural Networks, vol. 9, no. 5, pp. 1054–1054, Sep.
1998, doi: 10.1109/tnn.1998.712192.
[148] N. Syam and A. Sharma, “Waiting for a sales renaissance in the fourth
industrial revolution: Machine learning and artiicial intelligence in sales
research and practice,” Ind. Mark. Manag., vol. 69, pp. 135–146, 2018, doi:
10.1016/j.indmarman.2017.12.019.
[149] J. L. Thames, R. Abler, and A. Saad, “Hybrid intelligent systems for
network security,” in Proceedings of the Annual Southeast Conference,
2006, vol. 2006, pp. 286–289, doi: 10.1145/1185448.1185513.
[150] M. K. Tiwari and C. Chatterjee, “Development of an accurate and reliable
hourly lood forecasting model using wavelet-bootstrap-ANN (WBANN)
hybrid approach,” Journal of Hydrology, vol. 394, no. 3–4, pp. 458–470,
2010, doi: 10.1016/j.jhydrol.2010.10.001.
[151] M. K. Tiwari and C. Chatterjee, “Uncertainty assessment and ensemble
lood forecasting using bootstrap based artiicial neural networks
(BANNs),” Journal of Hydrology, vol. 382, no. 1–4, pp. 20–33, 2010, doi:
10.1016/j.jhydrol.2009.12.013.
[152] A. Tsakonas and B. Gabrys, “A fuzzy evolutionary framework for
combining ensembles,” Applied Soft Computing Journal, vol. 13, no. 4,
pp. 1800–1812, 2013, doi: 10.1016/j.asoc.2012.12.027.
[153] TutorialPoint.com, “Artiicial Intelligence - Fuzzy Logic Systems.”
[Online]. Available: https://www.tutorialspoint.com/artiicial_
intelligence/artiicial_intelligence_fuzzy_logic_systems.htm.
[154] H. Umit, “Digital business strategies in blockchain ecosystems :
transformational design and future of global business (E-book),”
Contributions to Management Science, pp. 569–599, 2000.
[155] N. T. T. Vu, N. P. Tran, and N. H. Nguyen, “Adaptive neuro-fuzzy inference
system based path planning for excavator arm,” Journal of Robotics, vol.
2018, 2018, doi: 10.1155/2018/2571243.
[156] K. Wang and Y. Wang, “How AI Affects the Future Predictive
Maintenance: A Primer of Deep Learning,” in Lecture Notes in Electrical
Engineering, 2018, doi: 10.1007/978-981-10-5768-7_1.
[157] Z. Wang and R. S. Srinivasan, “A review of artiicial intelligence based
building energy use prediction: Contrasting the capabilities of single
and ensemble prediction models,” Renewable and Sustainable Energy
Reviews. 2017, doi: 10.1016/j.rser.2016.10.079.
[158] M. Wauters and M. Vanhoucke, “Support Vector Machine Regression
for project control forecasting,” Automation in Construction, vol. 47, pp.
92–106, 2014, doi: 10.1016/j.autcon.2014.07.014.
[159] R. Wehrens, H. Putter, and L. M. C. Buydens, “The bootstrap: A tutorial,”
Chemometrics and Intelligent Laboratory Systems, vol. 54, no. 1, pp.
35–52, 2000, doi: 10.1016/S0169-7439(00)00102-7.
[160] G. C. Whitley, D., Beveridge, J.R, GuerraSalcedo C., “Messy Genetic
Algorithms for Subset Feature Selection,” Department of Computer
Science, pp. 568--575, 1997.
[161] T. C. Wong, K. M. Y. Law, H. K. Yau, and S. C. Ngan, “Analyzing supply
chain operation models with the PC-algorithm and the neural network,”
Expert Systems with Applications, vol. 38, no. 6, pp. 7526–7534, 2011, doi:
10.1016/j.eswa.2010.12.115.
[162] J. A. Yacim and D. G. B. Boshoff, “Impact of artiicial neural networks
training algorithms on accurate prediction of property values,” Journal of
Real Estate Research, 2018.
[163] L. A. Zadeh, “Fuzzy sets,” Information and Control, vol. 8, no. 3, pp. 338–
353, 1965, doi: 10.1016/S0019-9958(65)90241-X.
[164] S. M. Zahraee, M. Khalaji Assadi, and R. Saidur, “Application of
Artiicial Intelligence Methods for Hybrid Energy System Optimization,”
Renewable and Sustainable Energy Reviews, vol. 66. pp. 617–630, 2016,
doi: 10.1016/j.rser.2016.08.028.
[165] G. Zhang, B. Eddy Patuwo, and M. Y. Hu, “Forecasting with artiicial neural
networks: The state of the art,” International Journal of Forecasting, vol.
14, no. 1, pp. 35–62, 1998, doi: 10.1016/S0169-2070(97)00044-7.
[166] J. Zhang, “Developing robust non-linear models through bootstrap
aggregated neural networks,” Neurocomputing, vol. 25, no. 1–3, pp. 93–
113, 1999, doi: 10.1016/S0925-2312(99)00054-5.
- 13 -
Article in Press
Jesús Gil Ruiz
Jesús Gil Ruiz is a PhD Candidate in computer science and
is also an industrial engineer, civil engineer, and industrial
organization engineer. He received an Msc Executive
MBA, an Msc in Financial Management and Cost Control,
and an Msc In Project, Construction, and Maintenance
of Infrastructures and Facilities of Rail Lines from the
University of Barcelona. Articial Intelligence Program
Applied to Strategic Management by MIT Management Executive Education
and Business Analytics Program by Wharton Executive Education (University
of Pennsylvania). He is a project manager in the renewable energy and oil and
gas sectors, working in prestigious, internationally renowned companies such as
TSK, Técnicas Reunidas, ABENGOA, and SENER Engineering and Systems.
He has also participated in projects of great international importance, including
BenBan Solar, the world’s largest solar plant as of 2019 (1,800 MW), and
Cauchari Solar (330MW), one of the largest photovoltaic plants built in Latin
America in 2018. He is also an assistant professor at the University of La Rioja,
where he works in the eld of mathematics. He is also a trainer, lecturer, and
speaker at Inicitivas Empresariales (an international company in Barcelona),
working in the areas of project management, high-speed rail engineering and
renewable energies.
Javier Martínez Torres
Dr. Javier Martínez Torres is a Mathematician and
Engineering PhD from the University of Vigo. He is
currently an Assistant Professor at the University of Vigo
and has participated in more than 20 research projects
as principal investigator. He has published more than 50
papers in JCR indexed journals and participate in more
than 25 international conferences.
Rubén González Crespo
Dr. Rubén González Crespo has a PhD in Computer
Science Engineering. Currently he is Vice Chancellor of
Academic Aairs and Faculty from UNIR and Global
Director of Engineering Schools from PROEDUCA Group.
He is advisory board member for the Ministry of Education
at Colombia and evaluator from the National Agency for
Quality Evaluation and Accreditation of Spain (ANECA).
He is member from dierent committees at ISO Organization. Finally, He has
published more than 200 papers in indexed journals and congresses.
