Artificial Neural Networks In Construction Engineering And Management

International Journal of Architecture, Engineering and Construction
Vol 6, No 1, March 2017, 50-60
Artificial Neural Networks
in Construction Engineering and Management
Baba Shehu Waziri1,∗
, Kabir Bala2
and Shehu Ahmadu Bustani3
1
Department of Civil and Water Resources Engineering, University of Maiduguri, Nigeria
2
Department of Building, Ahmadu Bello University Zaria, Nigeria
3
Department of Building Technology, Abubakar Tafawa Balewa University, Bauchi, Nigeria
Abstract: Artificial Neural Networks has gained considerable application in construction engineering and management in recent
time. Over 100 resources published in refereed journals and conference proceedings were screened and reviewed with the view to
exploring the trend and new directions of the applications of different ANN algorithms. The study revealed successful applications
of ANNs in cost prediction, optimization and scheduling, risk assessment, claims and dispute resolution outcomes and decision
making. It was observed that ANN have been applied to problems that are difficult to solve with traditional mathematical and
statistical methods. The integration of ANN with other soft computing methods like Genetic Algorithm, Fuzzy Logic, Ant Colony
Optimization, Artificial Bee Colony and Particle Swarm Optimization were also explored which generally indicated better results
when compared with conventional ANNs. The study provides comprehensive repute of ANN in construction engineering and
management for application in different areas for improved accuracy and reliable predictions.
Keywords: Artificial Neural Network, construction management, construction engineering, construction cost estimation, con-
struction scheduling
DOI: http://dx.doi.org/10.7492/IJAEC.2017.006
1 INTRODUCTION
Artificial Neural Networks (ANNs) are computational mecha-
nisms that have the ability to acquire, represent and compute
function from one multivariate space of information to another
given a set of data representing that function. ANNs are func-
tional abstraction of the biological neural structure of the central
nervous system that are more effective than traditional methods
for solving complex qualitative or quantitative problems where
the parameters for conventional statistical and mathematical
methods are highly interdependent and data is intrinsically noisy
or incomplete or prone to error (Rumelhart 1986; Adeli 2001;
Aleksander and Morton 1993; Rudomin et al. 1993; Arbib 1995;
Geon 2005; Sivanandam and Deepa 2006; Bala et al. 2014).
ANNs have been established to be powerful pattern recognizers
and classifiers which operate as a black box to learn significant
structures in data (Adeli 2001; Jain and Pathak 2014). They
are composed of a large number of highly interconnected pro-
cessing elements called neurons working in unison to solve spe-
cific problems. ANNS are fundamentally characterised by their
architecture (connection between neurons); training or learn-
ing (determining the weights on the connections) and activation
function.
According to earlier application of ANN to engineering can
be traced back to 1989. Subsequently, they have successful-
ly been applied to solve numerous problems in engineering and
management. In the field of construction management they have
been applied for tender price prediction (Li and Love 1999), con-
struction cost estimation (Williams 1994; Emsley et al. 2002;
Wilmot and Mei 2005; Sodikov 2005; Pewdum et al. 2009; Alex
et al. 2009; Waziri 2010; Bala and Waziri 2012; Bala et al.
2014), project cash flow (Boussabaine and Kaka 1998), produc-
tivity forecast (Chao and Skibniewski 1994; Portas and AbouR-
izk 1997; Boussabaine 1995; Savin et al. 1998; Al-Zwainy et al.
2012), dispute resolution (Yitmen and Soujeri 2010; Fatima et al.
2014), earth moving operation (Shi 1999), contractors prequalifi-
cation (Lam et al. 2001), contract performance (Zin et al. 2006;
Waziri 2012), mark up estimation (Li and Love 1999) risk quan-
tification (McKim 1993; Maria-Sanchez 2004; Wang and Elhag
2007; Xiang and Luo 2012; Liu and Guo 2014); time contin-
gency (Yahia et al. 2011). Inspite of the numerous advantages
of ANN (such as adaptive learning, Self-organisation, Real time
operation and Fault tolerance) over traditional statistical tool,
yet it offers little explanation on the relationships between the
parameters used for modelling which makes it difficult to explain
what is learnt from the network (Paliwal and Kumar 2011). It
is therefore envisaged that further research into the framework
and internal process within the neural network will offer better
*Corresponding author. Email: shehuwaziri@gmail.com
50

Waziri et al./International Journal of Architecture, Engineering and Construction 6 (2017) 50-60
explanatory insight into the influence of independent variables
in the modelling process.
A vast application of ANN in the fields of construction Engi-
neering and Management for solving crucial construction deci-
sions are based on the simple back propagation algorithm. The
Back Propagation (BP) training algorithm is the most popu-
lar typology and learning method. Several other neural netw-
orks other than the BP such as the regularization neural network
had been developed to deal with noise and over-fitting prob-
lems in data. The typical architecture of the feed forward Neu-
ral Network illustrated in Figure. 1 consists of an input layer,
hidden layers and output layer. The neurons in the input lay-
er are connected to those in the hidden layers by the synaptic
weights. The common transfer functions used are the summa-
tion function and the sigmoid squashing function.
Figure 1. Feed forward neural network
The first mathematical representation of neuron (processing
elements of the network) was attempted in 1943 by the Neu-
ro physiologist Warren McCulloch and the Logician Walter Pits
(Galkin 2002). The representation is shown in Figure. 2. The
McCulloch and Pitts (MCP) neuron is binary activated.
Figure 2. Artificial neuron
The paper reviewed literature form well over 100 resources
published in refereed journals and conference proceedings with
the view to exploring the trend and directions for the appli-
cations of different ANN algorithms in construction engineer-
ing and management. The resources were screened and selected
based on relevance and significance toward understanding and
documenting the trend and new direction of ANN application.
2 APPLICATIONS OF ANN IN
CONSTRUCTION ENGINEERING AND
MANAGEMENT
ANN have been successfully applied to predict tender price
(McKim 1993; Li and Love 1999), construction cost pre-
diction (Williams 1994; Emsley et al. 2002; Wilmot and Mei
2005; Sodikov 2005; Pewdum et al. 2009; Alex et al. 2009;
Waziri 2010; Bala and Waziri 2012; Bala et al. 2014), project
cash flow (Boussabaine and Kaka 1998), Labour productivity
(Chao and Skibniewski 1994; Portas and AbouRizk 1997; Savin
et al. 1998), earth moving operation (Shi 1999), contractors pre-
qualification (Lam et al. 2001), contract performance (Zin et al.
2006; Waziri 2012), mark up estimation (Li and Love 1999) risk
quantification (McKim 1993).
2.1 Cost Estimation
Construction cost estimation is a crucial activity for proper func-
tioning of any construction firm (ElSawy et al. 2011). The
application of ANN in cost estimation has been the subject of
many studies (Pearce 1997; Bhokha and Ogunlana 1999; Son-
mez 2004; Sodikov 2005; Kim et al. 2005; Cheng et al. 2009a;
Cheng et al. 2009b; Arafa and Alqedra 2011; Waziri and Bala
2011; Bala et al. 2014).
Williams (1994) used the BP algorithm for predicting changes
in construction cost indices for one and six months ahead and
concluded that the movement of the cost index is a complex
problem that is difficult to be predicted accurately using the BP
model. Hegazy et al. (1994) used ANN application for optimum
mark-up estimation and discussed its potential applications in
construction Engineering and Management. Hegazy and Ayed
(1998) developed a parametric cost estimating model for high-
way projects based on the ANN approach. In the study, two
alternative techniques namely Simplex optimization and Genet-
ic Algorithm (GA) were introduced to train the network weights.
Adeli presented a regularization neural network model for esti-
mating the construction cost of reinforced concrete pavement
projects. In the study they observed that highway construction
costs are noisy due to the multiplicity of interplaying factors fluc-
tuations, weather conditions and human judgement resulting in
over-fitting. The RNN model proved to be pragmatic for reli-
able and consistent cost estimation of highway projects. Geiger
et al. (1998) developed a model to estimate the cost of sheet
metals from direct material cost and cost of supplied parts by
the use of a ANN. The results showed that within the investi-
gated range, an accuracy of 5% to 15% was achieved. Elhag
and Boussabaine (1998) presented two ANN models to predict
the lowest tender price of primary and secondary school build-
ings using data of 30 completed projects for training the net-
works. The results revealed that the two models effectively
learned during training stage and gained good generalization
capabilities in training session resulting in prediction accuracy
of 79.3% and 82.2%. Al-Tabtabai et al. (1998) developed an
ANN model for the prediction of percentage increase in the cost
of typical highway project from a reference estimate. The model
achieved a MAPE of 8.1%.
51

Bhokha and Ogunlana (1999) in their study for developing
an ANN model for predicting the construction costs of building
projects in Thailand at the pre-design stage used historical da-
ta of 136 completed properties. The cost variables used in the
study as inputs are: structural system, building function, exteri-
or finishing, building height, decorating class and site accessibil-
ity. The validation results indicated a satisfactory performance
where on the overall 42.7% of the sample were underestimated
while 57.3% were overestimated. Fang and Froese (1999) used
neural network approach to establish relationship between the
qualities, cost of concrete and formwork for the structural ele-
ment of tall buildings using high performance concrete (HPC).
Hybrid and hierarchical neural networks were used to predict the
quantities/cost of HPC wall frame structures in tall commercial
buildings. The results of the comparison of the two strategies
revealed that the hybrid model is less accurate but easy to be
trained while the hierarchical models are more accurate but more
complicated in implementation. Both of the strategies were ob-
served to provide promising results. Shtub and Versano (1999)
proposed a system to estimate the cost of steel pipe bending us-
ing ANN and regression analysis. The results of the evaluation
of the models revealed that the neural network model outper-
formed the linear regression model by prediction performance
but the regression model has the best fit of the data. Assaf
et al. (2001) used ANN to investigate the overhead cost prac-
tices of construction firms in Saudi Arabia. The proposed model
would be used by construction firms to decide an optimum lev-
el of overhead costs that enables them to win and effectively
administer capital projects.
Emsley et al. (2002) compared the prediction performances of
regression analysis and ANN based on a dataset of 288 proper-
ties. The study considered 41 independent variables including
site related variables and design related variables. The results
showed that in the best case, the model indicated a Mean Ab-
solute Percent Error (MAPE) of 17%. This error term is too
large to enable the practical application of the model. In ad-
dition, the necessary input variables were extensive, making it
difficult to apply in early design stage. Setyawati et al. (2002)
used neural network to develop cost estimating model for insti-
tutional buildings and obtained an accuracy of 16%. Pathak and
Agarwal (2003) proposed a programme based on ANN for de-
sign, estimation and costing of intz and circular overhead water
tanks in Bhopal region of India. The input parameters for the
programme are height to diameter ratio, angle of conical wall,
number of columns. The trained network predicted the cost of
new tanks with a 3.16% error margin which indicated a satis-
factory performance. Such quick and reliable cost prediction of
water tanks will be helpful in the selection of tanks for design
and construction purposes. Günaydın and Doğan (2004) devel-
oped an ANN model for estimating cost of structural systems of
reinforced concrete skeleton buildings in Turkey. Cost and de-
sign data of thirty (30) projects with eight parameters were used
in training and testing the ANN methodology. An average cost
estimation accuracy of 93% was achieved. The model is useful
for design professionals to make appropriate decisions at early
project phase.
Sonmez (2004) compared regression and neural network mod-
els for conceptual cost estimation using construction year, lo-
cation index, proportion car parking area and area for comm-
ons as the independent variables. Two NN models and one re-
gression model were established for the study. One of the NN
models achieved an accuracy level of 12% which was considered
satisfactory for conceptual cost estimating. Kim et al. (2004)
examined the performances of multiple regression analysis, neu-
ral network and cased based reasoning in prediction of building
project cost. The results revealed that the neural network mod-
el performed the best prediction in terms of accuracy but cased
based reasoning indicated better performance in the long run.
Günaydın and Doğan (2004) proposed a neural network model
for cost estimation of structural system of buildings where the
model achieved an accuracy level of 93%. They concluded that
neural networks are capable of reducing the uncertainties of es-
timate for a structural system of building. Kim et al. (2004)
compared the prediction ability of ANN, CBR and regression
analysis based on a historical cost data of 530 Korea residential
construction projects. The results demonstrates the potentials of
modelling with ANN obtain more accurate results as opposed to
CBR and regression analysis. Wilmot and Mei (2005) employed
ANN models which related overall highway construction co-
sts described in terms of highway construction cost index to the
cost of construction of materials, labour and equipment. The
study indicated that the model was able to replicate past high-
way construction cost trends in Louisiana with reasonable ac-
curacy. Sodikov (2005) examined cost estimation for highway
projects by employing ANN and observed that neural network
is an appropriate tool for solving complex problems and can
also cope with imprecise data. The results demonstrate good
nonlinear approach ability and higher prediction accuracy of
back propagation neural network. Sayed and Iranmanesh and
Zarezadeh (2008) presented the application of ANN to forecast
actual cost of construction projects based on the Earned Value
Management system (EVMS) to reduce the risk of project cost
overrun. The model was evaluated by the MAPE criterion which
showed satisfactory performance. Bouabaz and Hamami (2008)
proposed a model for estimation of repair and maintenance of
bridges in developing countries based on the ANN technique for
better accuracy. Cost and design data for two categories of re-
pair bridges were used for training the network model which
achieved an accuracy level of 96
Sonmez and Ontepeli (2009) employed regression analysis and
ANN for developing parametric models for estimating construc-
tion cost of urban railway system. Two neural networks incor-
porating different independent variables were considered as an
alternative to regression model for the identification of the non-
linear relations. The performance evaluation of the models re-
vealed that one of the NN models provided the best results in
terms of accuracy. Wang et al. (2010) employed BP neural
network for estimating highway projects costs. The model was
trained by a dataset obtained from some successful highway en-
gineering projects to provide quick cost estimating. The results
indicated the practicability and reliability of the model posing
promising prospects of BP-NN for cost estimating of highway
engineering construction.
Arafa and Alqedra (2011) employed ANN to develop an effi-
cient model to estimate the cost of building construction projects
at the early stage. The study used datasets of 71 building
projects in Gaza strip. Significant parameters obtainable at the
pre-design stage were used as input variables for model develop-
ment. The results of the study indicated that ground floor area,
number of storeys, types of foundation and number of elevators
52

in the building are the most effective parameters influencing ear-
ly stage estimates of building cost. ElSawy et al. (2011) present-
ed a BP neural network model for the prediction of site overhead
cost in Egypt. The study used data of 52 real life projects exe-
cuted between 2002 and 2009 for training whereas five (5) new
projects data were used for the validation. The results indicated
a Root Mean Square Error (RMS) value of 0.2764 and an accura-
cy level of 80%. The model was observed to predict wrongly the
percentage of site overhead costs for only one project (20%) of
the testing sample. Ahiaga-Dagbui and Smith (2012) employed
ANN to model the final target cost of water projects in Scotland
based on the data of 98 water related projects executed between
2007 and 2011. Different models were developed for normal-
ize target cost and log of target cost variable transformations
and weight decay regularization were then explored to improve
the final models performance. The investigation revealed that
ANN was able to capture the interactions between the predictor
variables and final cost.
Vahdani et al. (2012) presented a computationally effi-
cient model called the support vector machine (SVM) to im-
prove the conceptual cost estimating accuracy during the early
phase of project lifecycle. The model was trained by a cross
validation technique and its performance results were compared
with those of non-linear regression and BP-NN which revealed
that the SVM had the best results. The work of Alqahtani and
Whyte (2013) also employed ANN technique to develop a new
framework for life Cycle Cost Analysis (LCCA) of construction
projects. The model computes whole life cycle costs of construc-
tion projects using the cost of significant items (CSI) to identify
main cost items. MATLAB and Excel solver were used to de-
velop the models using a dataset of 20 building projects. The
results revealed accuracy levels of 1% and 2% for the MATLAB
and Excel solver respectively.
Lyne and Maximinio (2014) developed an ANN model for the
prediction of total structural cost of building projects in Philip-
pines using historical data of 30 completed projects. The da-
ta was randomly divided into 60% for training, 20% for vali-
dating the performance while the remaining 20% as complete-
ly independent test for network generalization. Six input pa-
rameters namely; number of basements, floor area, number of
storeys, volume of concrete, area of formwork and weight of
reinforcement steel were used. The results showed that ANN
model reasonably predicted the total structural cost of building
projects with favourable training and testing phase outcomes.
Kim et al. (2004) investigated different parametric cost esti-
mating techniques for construction projects and discovered that
neural networks generated better results than CBR and multi-
ple regression analysis. El-Sawah and Moselhi (2014) employed
Back Propagation Neural Network (BP-NN), Probabilistic Neu-
ral Network (PNN) and Generalized Regression Neural Network
(GRNN) and regression analysis models for order of magnitude
cost estimating of low-rise structural steel buildings and their
respective cost. The results of the investigation revealed that
the MAPE of the neural network models ranges from 16.83%
to 19.3%, whereas for the regression model it was found to be
23.72%. The linear regression model was more sensitive to the
change in number of training data while the PNN was the most
stable network among all the three models with maximum dif-
ference in MAPE of 2.46%. The maximum difference in MAPE
was 19.47%, 17.91% and 61.45% for BPNN GRNN and regres-
sion model respectively. Yadav et al. (2016) developed a cost
estimating technique based on the principles of ANN to forecast
structural cost of residential buildings. Twenty three years data
were collected from schedule of rates records for training and
testing of networks. The parameters collected included, cost of
cement, sand, steel, aggregates, mason, skilled and non-skilled
worker. The parameters were simulated using NEURO XL ver-
sion 2.1. The neural model predicted total structural cost of
building projects with correlation coefficient R of 0.9960 and R2
value of 0.995.
2.2 Construction Scheduling
Adeli and Karim (1997) applied a general mathematical formula-
tion for the problem of highway construction scheduling. A neu-
ral dynamic model was employed to solve the non-linear prob-
lem with the goal of minimizing the direct construction dura-
tion. The model provides the capabilities of both Critical Path
Method (CPM) and linear scheduling approach yielding opti-
mum schedule with minimum cost. This methodology is consid-
ered satisfactory for solving cost-duration trade-off problem of
highway construction. The study also provides foundation for
development of a new generalization of more flexible and accu-
rate construction scheduling systems. Graham et al. (2006) used
ANN for predicting duration of Ready Mixed Concrete (RMC)
which is assumed to be seriously related to construction opera-
tions. The study used data obtained from four different projects
consisting of the variables; months of operation, type of opera-
tions, total operation volume, average inter-arrival time, num-
ber of loads, truck volume and number of rejected loads. Yahia
et al. (2011) employed ANN to develop a model for a more re-
liable prediction of the amount of time contingency that should
be added to the scheduled project completion time. Petruseva
et al. (2013) presented a supervised learning algorithm called
the support vector machine (SVM) for predicting construction
duration. Contracted and real price data of 75 building construc-
tion projects initiated and completed between 1999 and 2011 in
the Federation of Bosnia Herzegovina were obtained through
field survey for analysis. The study used regression analysis and
SVM network to achieve improvement in the accuracy of project
duration prediction. The results indicate that predicting with
SVM was significantly more accurate.
Maghrebi et al. (2014) used ANN to predict the duration of
a concrete operation by focusing on supply chain parameters of
RMC. The model was tested with a real life dataset of a RMC
in Sydney metropolitan area which has 17 depots and around
200 trucks. The results obtained compared favourably with re-
sults from other studies that only considered the construction
parameters for predicting productivity of concrete. Golizadeh
et al. (2016) proposed a tool for estimating duration of major
activities relating to the structural elements of concrete frame
buildings. Four AN models were develop to compute the du-
ration of installing column reinforcement, beam reinforcement,
column concreting and beam concreting activities. Then a web
based programme was developed as an automated tool for esti-
mating duration based on the ANN for more accurate activity
duration prediction.
53

2.3 Decision Making
Kamarthi et al. (1992) employed two layer BP neural network
for the selection of formwork systems. The study indicated a
satisfactory performance. Murtaza and Fisher (1994) presented
an ANN model which enables decision making on using modu-
larization or conventional method for building an industrial pro-
cess plant based on five categories of decision attributes namely
plant location, environmental and organizational factors, labour
related factors, plant characteristics and project risks. The NN
model was trained using cases collected from several engineering
consulting and client firms. Boussabaine (1995) developed a neu-
ral network system for forecasting productivity and construction
cost. The model proves the feasibility of an integral knowledge
based system for construction planning and productivity.
Masri et al. (1996) presented an ANN approach for detecting
changes in the characteristics of structure of unknown systems.
The neural network was trained for identification using vibra-
tion measurements from a healthy system. The trained network
was fed with comparable vibration measurements from the same
structure under different conditions of response in order to mon-
itor the health of the structure. The study revealed that the
proposed methodology is capable of detecting relatively small
changes in the structure parameters even if the vibration mea-
surements are noisy. Pearce (1997) used ANN for cost based
risk prediction and identification of project cost drivers. The
study investigated the effectiveness of ANN to predict risk re-
lated to final project cost and to identify potentially significant
cost drivers relating to construction projects. Neural network
models were developed over a set of permutations of input vari-
ables and used to generate a maximum cost versus probability
curves which can be used to evaluate risks of cost growth between
conceptual design and project completion. The cost variables
identified in the study includes floor to floor height, external
wall area, exterior window area, number of floors among others.
Results of the research further indicated that ANN can serve
as a robust tool for approximated multivariate analysis. Chua
et al. (1997) proposed an ANN model for the identification of
key measurement factors that affect budget performance in a
project. The technique has the capabilities of modelling even
if the functional interrelationships between input factors and
output performance could not clearly be defined. In the study,
eight (8) key variables were identified covering aspects related
to project manager, project team, and planning control efforts
viz; scope, completion of design, number of organizational lev-
els between project manager and craftsmen, experience on simi-
lar projects, constructability programme, project team turnover
rate, frequency of budget updates, frequency of control meet-
ings during construction and control system update. The model
could be used to predict different management strategies to ef-
fectively deploy resources to strengthen project management.
Yeh (1998) demonstrated the possibilities of adapting ANN to
predict the compressive strength of High Performance (HPC)
concrete. A set of trial batches produced in the laboratory were
used for the training and testing of the models. The results re-
vealed that ANN model is more accurate than a model based
on regression analysis. The study also indicated that it is con-
venient and easy to use ANN models for numerical experiments
to review the effects of the properties of each variable on the
concrete mix.
Elhassan et al. (2012) discussed the possibilities of address-
ing the difficulties in decision making in construction manage-
ment by the application of optimization techniques. The study
identified optimizing tools being a basis for making an optimal
decision in respect of construction project management. They
concluded that there are quite some research gaps in the use
of methodologies for optimum decision making and pointed out
the potentials of artificial (AI) such as ANN for future stud-
ies. AbouRizk et al. (2001) used a two-stage neural networks
analysis for the estimation of labour productivity rates for in-
dustrial construction activities. The method predicted with an
accuracy of 15%. Sawhney and Mund (2001) applied ANN based
on the Bayesian classifiers method for the selection of type and
model of crane. The model exhibited a satisfactory performance
in the selection of crane based on their type and model. Lou
et al. (2001) employed ANN to predict the short term future
conditions of pavement cracks based on past conditions records.
The model demonstrated the potential of applying ANN for such
predictions with satisfactory results. Morcous (2002) made com-
parison between CBR and NN in modelling bridge deterioration
based on bridge deck data obtained from Ministry of Transporta-
tion of Quebec to compare the advantages of two methods to
guide transportation agencies in selecting the most appropriate
approach.
Chew and Tan (2003) presented a maintainability grading sys-
tem using ANN which aids in enhancing decision-making of wet
areas design. The model was derived from comprehensive con-
dition surveys of 450 tall buildings and interviews with relevant
building professionals. In the study, 16 significant risk factors
were identified and tested according to their sensitivity in affect-
ing maintainability scoring of wet areas. The system provides
for complete evaluation of various alternative designs, construc-
tion, materials and maintenance practices so as to achieve best
possible solutions of technical attributes that lead to minimum
lifecycle maintenance cost. Al-Sobiei et al. (2005) used ANN
and GA to predict the risk of contractor default in construction
projects undertaken for the Saudi Arabia Armed Forces. The
study is useful in making a decision to engage the services of
a contractor. The outcome of the research is of importance to
clients and other sponsors of construction projects because it
proposes an approach that can allow the use of a rational and
effective policy. Apanaviciene and Juodis (2005) applied NN to
develop a model for predicting construction project management
effectiveness from the perspectives of construction management
organizations. Performance data from construction management
companies consisting of twelve key factors in Lithuania and the
USA were used for model development. The study recommends
the Construction Management Performance Evaluation Model
(CMPEM) as a decisionĺCsupport tool for competitive bidding
and for evaluating management risk of construction projects.
Zin et al. (2006) presented an ANN model for predicting the
time performance of traditional contract projects. Several neu-
ral network models were developed and tested using nine sample
projects data. The best model for the prediction is a MLP, BP
network with eight input nodes, five hidden nodes and three out-
put nodes with a very low error of prediction. Golpayegani and
Emamizadeh (2007) presented a framework for planning work
breakdown structure of construction projects based on ANN.
The approach uses the project control work breakdown structure
(PWBS), functional work breakdown structure (FWBS) and rel-
54

ative work breakdown structure (RWBS) to form the output of
the model and its modules. The framework was tested on a
sample domain and the results showed that the planned work
breakdown structure and activities have satisfied the expecta-
tions with different levels of validity. Khalafallah (2008) pre-
sented an ANN based model for predicting housing market per-
formance to support real estate investors and home developers.
The study used historical market performance dataset for train-
ing the NN in order to predict unforeseen future performances.
The validation results revealed prediction in the range of -2% and
+2%. Jamil et al. (2009) demonstrated the possibility of adapt-
ing ANN in the development of simulator and intelligent sys-
tem for the prediction of compressive strength and workability
of high performance concrete (HPC). The model demonstrated
satisfactory ability in learning the given input/output patterns
indicating the appropriateness of the application of ANN in the
field of HPC mix design.
Aibinu (2011) proposed a learning algorithm based on the
characteristics of completed projects for the quantitative and
objective estimation of the inaccuracies in pretender cost esti-
mates of new projects. A three layer feed forward ANN model
was developed and trained to generalize nine characteristics of
100 completed projects. Nine input variables namely, project
size, procurement route, project type, project location, princi-
pal structural material, sector, estimating method and estimated
sums were used. The model had a correlation coefficient (R) of
73%, Mean Absolute Error (MAE) of 3% and Mean Square Error
(MSE) of 0.2. Al-Zwainy et al. (2012) develop BP NN model
for construction productivity estimation of finishing works for
floors with marble. The study considered residential, commer-
cial and educational projects data from different parts of Iraq.
Ten (10) key factors including age, experience, number of the
assist labour, height of floor, size of the marble tiles, security
conditions, health status for the work team, weather condit-
ions, site conditions and availability of construction mater-
ials were used as input variables. The results showed that
ANN has the ability to predict the productivity for finishing
work with coefficient of correlation of 87.55% and prediction ac-
curacy of 90.9%. Aswed (2016) employed ANN for the prediction
of labour productivity based on thirty influencing factors in Iraq.
The factors used as input variable include, age, experience, gang
health, gang number, wages, weather, material availability, site
conditions wall length, wall height, mortar type, wall thickness
and site security. The model predicted actual labour produc-
tivity with a reasonable degree of accuracy with coefficient of
correlation of R = 86.28%. The study concludes that the model
can be employed to predict labour productivity of any build-
ing type using the influencing factors. Sharmik et al. (2016)
presented a cost and time effective feed forward BP-NN with
supervised learning algorithm for estimating soil characteristics.
The model revealed a satisfactory results when compared with
actual values of soil characteristics.
2.4 Dispute Resolution and Litigation
Yitmen and Soujeri (2010) presented an ANN model for the esti-
mation of the influence of change orders on project performance
for avoidance or resolution of disputes before litigation occurs.
Significant factors that describe the adverse effects of change
orders on project performance were identified through a field
survey conducted to contractors in North Cyprus which formed
the basis for model development. The model manages change
orders through all phases of project such that construction op-
erations can continue with the least amount of interruption that
usually results from disputes between different parties involved
in a project. The data for the study was obtained from 35 cas-
es collected from 22 building contractors comprising of 11 input
variables and their corresponding influence on performance. The
proposed model has been observed to be an efficient approach
to find the probability of dispute in respect of the identified pa-
rameters.
Chou (2012) presented a model for predicting dispute handling
methods in Public-Private-Partnership (PPP) projects. The
study used machine learning (ANN, SVM and Tree Augment-
ed Name (TAN), Bayesian), classification and regression based
techniques (classification and regression tree (CART), Quick Un-
biased and Efficient Tree (QUEST), Exhaustive Chi-square Au-
tomatic Interactive Detection (Exhaustive CHAID) and C5.0
and combination of these methods for possible better perfor-
mance for a set of PPP data. The results showed that the com-
bination of the techniques of QUEST + CHAID + C 5.0 demon-
strated best classification accuracy at 84.65% in predicting dis-
pute resolution outcomes (mediation, negotiation, arbitration,
litigation, adjudication, appeals or no dispute occur). The
CART model revealed the best classification with accuracy of
69.05%. The study demonstrates effective classification appli-
cation for early project dispute resolution related to public in-
frastructure projects. Fatima et al. (2014) identified significant
qualitative parameters and used to develop an ANN model for
minimizing construction disputes and reduce the cost of con-
struction by optimizing the identified parameters. The method-
ology integrates the concept of ANN with the current estimating
system and optimizes the frequency of occurrence of dispute pa-
rameters which in turn reduces the cost of the project.
2.5 Risk Assessment
Odeyinka et al. (2002) attempted to model the variation be-
tween predicted and actual cost flow due to inherent risk in
construction. They employed BP neural network to develop a
cost flow risk assessment model. The model was tested on 20
new projects with satisfactory prediction of variation between
forecast and actual cost flow at 30%, 70% and 100% stages.
Maria-Sanchez (2004) employed neural network approach to as-
sess the impact of environmental risk in construction projects
in Puebla, Mexico. The network was trained and tested with
data obtained from private contractors that are constantly in-
volved with projects facing environmental risks. The methodolo-
gy demonstrates the potential of ANN in evaluating environmen-
tal risks and providing valuable outcomes for project managers
working with government agencies. The system also offers a con-
siderable advantage in predicting the possible value of the total
environmental risks. Wang and Elhag (2007) compared the mod-
elling mechanisms of Neural Network (NN), Multiple Regression
Analysis (MRA) and Evidential Reasoning (ER) and evaluated
their performances using a set of bridge risk data. The study
revealed that ANN had better performance over ER, and MRA
for the case study considered.
Xiang and Luo (2012) proposed a principal project parties’
behavioural risk evaluation model based on BPĺCNN. The BP
55

was employed to avoid subjectivity factors in the risk evaluation
process. A likert scale of 1-5 was used to assess the risk factors
identified through field survey. The network simulation results
show that the model is satisfactory and practical. Polat (2012)
also proposed a contingency estimation model based on ANN to
enable managers assess the risk level of their projects in a more
objectives and systematic manner thereby allowing them to es-
timate cost contingency amount more reliably and accurately.
Training and testing data were obtained from the records of 195
completed international projects undertaken by 85 large-scale
contractors in Turkey. Statistical analysis of the results indicat-
ed that the model is valid and captures significant components of
the underlying complex nonlinear relationship between the risk
factors and contingency amount included in the bid price.
Lhee et al. (2014) presented a two-step neural network based
method for estimating optimal contingency for transportation
construction projects. The model provides the owner with opti-
mum solution with the view to improving budgeting decisions,
reducing the risk of either underutilizing or over committing of
funds. Liu and Guo (2014) constructed a risk evaluation model
of project construction quality on the basis of neural networks
and rough sets. A dataset of residential building projects in the
Guangzhou development zone were used to test the model ac-
curacy employing research tools of Rosetta based on rough sets
and MATLAB 7.0. Empirical results showed that the model has
great practical significance.
2.6 Evolutionary Neural Network in Construction
Engineering and Management
Yeh (1998) employed Simulated Annealing Neural Network
(SA-NN) to optimize construction site layout. SA is a probabilis-
tic hill-climbing search algorithm which can find a global min-
imum of the performance function by combining gradient des-
cent with a random process. This algorithm combined with ANN
demonstrates a satisfactory performance. Kim et al. (2004) em-
ployed BP neural network model and Genetic Algorithm (GA)
for cost estimation in a technique referred to as BP-GA. The
GA was introduced in the study to improve the accuracy of the
BPN. Cost data of 530 residential buildings constructed in Korea
between 1997 and 2000 were used for training and performance
evaluation. The hybrid BP-GA model was found to produce
effective and more reliable results compared to the BP model
based on trial and error (Kim et al. 2004).
Kim et al. (2005) presented a hybrid model comprising of
ANN and Genetic algorithm (GA) for the estimation of pre-
liminary costs of residential buildings. Residential construction
data initiated and completed between 1992 and 2000 in South
Korea were used for training. Comparison between actual and
predicted results showed that the mean, standard deviation and
the coefficient of determination (R2
) of the ratio between ac-
tual and predicted costs are 0.960, 0.420 and 97% respectively.
The results confirmed the ability of GA in overcoming the prob-
lem of lack of adequate rules for determining the parameters of
ANN. Chau (2007) applied Particle Swarm Optimization (PSO)
based ANN in the analysis of outcomes of construction claims in
Hong Kong considering cultural, social, psychological, environ-
mental and political factors. The results indicated a successful
prediction rate of PSO-ANN of up to 80%. Furthermore, the
technique is capable of providing faster and more accurate re-
sults than simple BP neural networks. The model provides an
option of whether or not to take a case to litigation. Cheng et al.
(2009a) presented a method combining three different soft com-
puting techniques namely, genetic algorithms, fuzzy logic theory
and neural networks under a mechanism referred to as Evolu-
tionary Fuzzy Hybrid Neural Network Model (EFHNN). The
proposed mechanism was developed for design phase cost esti-
mation of projects in Taiwan. The approach incorporates neural
networks and high order neural networks (HNN) which operates
with the alternative of linear and nonlinear neuron layer con-
nectors. The approach also incorporates fuzzy logic for handling
uncertainties. The approach therefore evolves fuzzy hybrid neu-
ral network (FHNN). For the optimization of the FHNN, GA is
used which resulted in EFHNN. The model achieved an overall
estimate error of 10.36% due to the use of GA, the method has
a high computing time, this being a disadvantage. Cheng et al.
(2009b) presented a web based hybrid model incorporating ge-
netic algorithms, fuzzy logic theory and neural networks under
a mechanism called Evolutionary Fuzzy Neural Inference Model
(EFNIM). However, EFNIM also runs long time due to the use
of GA.
The study of Shi and Li (2010) integrates the use of fuzzy log-
ic, PSO and ANN in quality assessment of construction projects.
In the study, fuzzy logic was used to define the elements of an
assessment matrix and a quality assessment model for construc-
tion was set up. PSO was adapted to train the perception in the
assessment and predicting the quality of construction projects in
china. Comparing BP-NN and ANN based on GA, the simulat-
ed results of quality assessment of construction projects shows
that training the network with PSO gave more accurate results
in terms of Sums of Squares Error (SSE) and faster in terms of
number of iterations and simulation time than the BP-NN and
GA-NN. Feng and Li (2013) presented an optimization method
for cost estimation by integrating GA and BP technique. Eigh-
teen project cases and two testing samples were used to observe
generalize ability of the model. Comparing with conventional
BP models, the study revealed that the GA-BP model can get
lower forecast error and iterations but runs long time. They
concluded that the model is appropriate for construction cost
estimation.
Hong et al. (2014) put forward a construction engineering cost
evaluation model and application based on RS-IPSO BP neural
network called “the model of construction engineering cost eva-
luation of optimized particle swarm and BP neural network”.
PSO was adopted to optimize the initial weights and threshold
of ANN. The main aim of the hybrid method is to improve the
rate of convergence of ANN and the ability to search for global
optimum. This method is considered to have a high practical
value and it can be applied to make scientific evaluation of con-
struction costs. Kayarvizhy et al. (2014) compared the improve-
ment in the prediction accuracy of ANN when it is trained using
swarm intelligence algorithms. Several models were formulat-
ed for evaluating the various ANN-swarm intelligence combina-
tions. The swarm intelligence algorithms considered in the st-
udy are Particle Swarm Optimization (PSO), Ant Colony Opti-
mization (ACO), Artificial Bee Colony (ABC) and Firefly. The
hybrid models were compared for their convergence speed and
prediction accuracy over traditional ANN models. The resul-
ts showed that swarm intelligence has higher convergence speed
and accuracy over ANN trained with gradient descent. Lee et al.
56

(2016) presented a hybrid model for estimating the quantity and
cost of waste in the early stage of construction. The approach
used ACO algorithm to optimise the selection of ANN parame-
ters. The proposed model can be used to address the cost over-
runs and improve construction waste management. The hybrid
model predicted more effectively the amount of waste concrete in
early project stage. The comparison of prediction results of ANN
and ANN-ACO showed that the hybrid model had minimum er-
ror demonstrating a higher accuracy than ANN.
3 DISCUSSION OF FINDINGS
ANN has gained considerable application to solve complex non-
linear problems in construction engineering and management
over the few decades. Their employment of ANN in construc-
tion cost prediction, schedule estimating, productivity forecast,
prediction of dispute occurrence and resolution outcomes and
contract performance demonstrates its potentials and robust-
ness in addressing problems that proved difficult for traditional
mathematical and statistical approaches to solve. Fundamental-
ly, the performance of ANN is data dependent which signifies
the importance of quality and quantity of data for training the
networks which is key to the outcomes of predictions, recogni-
tion and classification as indicated by Hegazy and Ayed (1998)
and Waziri and Bala (2011).
Prediction accuracy is one key attributes of ANN over tra-
ditional methods which adds to its popularity and usage. Ac-
curacy levels of most ANN based applications in prediction and
forecasting can get to as high as 98% over test samples as evident
in Geiger et al. (1998), Alqahtani and Whyte (2013) and Bala
et al. (2014). These performances are recorded on the bases of
minimum errors over test samples as measured by MSE, MAE,
MAPE and SSE. Findings also show that in most prediction
problems, ANN usually demonstrates high degree of data fitting
with high correlation coefficient usually higher than 90% (Kim
et al. 2005).
Neural network models are suitable for parametric modelling
and most a times are used as alternative to classical modelling
techniques especially for dataset involving nonlinear relationship
and formed the basis for decision support tools using supervised
learning algorithm for optimal decision making which is an im-
portant activity in construction engineering and management.
Its performance in such applications are outstanding and com-
pares favourably with other parametric models such as regres-
sion analysis (Sonmez 2004; Sonmez and Ontepeli 2009). It is
considered best for short term forecast and has the potentials
for mapping uncertainties in learning.
Despite its robustness and extremely high advantages for para-
metric modelling and other decision making applications, ANN
has been observed to lack general procedure especially for the se-
lection of its initial weights and other initial parameters for effec-
tive application. It is also observed to be unsuitable for long term
forecasting especially for changing trends (Kim et al. 2004). To
address this deficiency, several other learning algorithms and op-
timization tools are been employed to develop hybrid models for
improved performance. Findings revealed the successful integra-
tion of GA (Feng and Li 2013), ACO (Kayarvizhy et al. 2014),
PSO (Shi and Li 2010) and fuzzy logic (Cheng et al. 2009a) with
ANN demonstrating favourable performance as compared with
simple neural network algorithms except for ANN-GA showing
slow in computing taking long time to run.
4 CONCLUSION
ANNs have been recognised to be more powerful than tradition-
al mathematical and statistical methods in events of complex
qualitative and quantitative reasoning. They have been success-
fully employed in solving numerous complex nonlinear problems
of prediction, estimating, decision making, optimization, clas-
sification and selection in the fields of construction engineering
and management. They are identified to have the potentials of
dealing with noisy data and achieving high accuracy and reliable
prediction and forecasting. Neural Networks have also been in-
tegrated with several soft computing paradigms such as fuzzy
logic, Case Based Reasoning, Particle Swarm Optimization,
Ant colony Optimization, Artificial Bee Colony and Firefly with
the view to improving accuracy, over-fitting and under-fitting of
data and convergence speed.
REFERENCES
AbouRizk, S., Knowles, P., and Hermann, U. R. (2001). “Esti-
mating labor production rates for industrial construction ac-
tivities.” Journal of Construction Engineering and Manage-
ment, 127(6), 502–511.
Adeli, H. (2001). “Neural networks in civil engineering: 1989–
2000.” Computer-Aided Civil and Infrastructure Engineering,
16(2), 126–142.
Adeli, H. and Karim, A. (1997). “Scheduling and cost optimiza-
tion and neural dynamics model for construction.” Journal of
Construction Engineering and Management, 123(4), 450–458.
Ahiaga-Dagbui, D. D. and Smith, S. D. (2012). “Neural netw-
orks for modelling the final target cost of water projects.” Pro-
ceeding of the 28th Annual ARCOM Conference, Edinburgh,
United Kingdom.
Aibinu, A. (2011). “Use of artificial intelligence to predict the ac-
curacy of pre-tender building cost estimate.” Proceeding of the
Conference of Management and Innovation for a Sustainable
Built Environment, Amsterdam, the Netherlands.
Al-Sobiei, O. S., Arditi, D., and Polat, G. (2005). “Predicting
the risk of contractor default in saudi arabia utilizing artificial
neural network and genetic algorithm techniques.” Construc-
tion Management and Economics, 23(4), 423–430.
Al-Tabtabai, H., Alex, P., and Tantash, M. (1998). “Prelim-
inary cost estimating of highway construction using neural
network.” Cost Engineering, 41(3), 19–24.
Al-Zwainy, F. M. S., Rasheed, H. A., and Ibraheem, H. F.
(2012). “Development of the construction productivity estima-
tion model using artificial neural networks for finishing works
for floors with marble.” ARPN Journal of Engineering and
Applied Sciences, 7(6), 714–722.
Aleksander, I. and Morton, H. (1993). Neurons and Symbols:
The Stuff that Mind is Made of. Chapman & Hall, London,
United Kingdom.
Alex, D. P., Al Hussein, M., Bouferguene, A., and Fernando,
S. (2009). “Artificial Neural Network model for cost estima-
tion: City of Edmonton’s water and sewer installation ser-
vices.” Journal of Construction Engineering and Management,
136(7), 745–756.
57

Alqahtani, A. and Whyte, A. (2013). “Artificial Neural Netw-
orks incorporating cost significant items towards enhancing
estimation for (life-cycle) costing of construction projects.”
Construction Economics and Building, 13(3), 51–64.
Apanaviciene, R. and Juodis, A. (2005). “Modelling of construc-
tion project management effectiveness by applying neural net-
works.” Symposium on Sustainability and Value Through Con-
struction Procurement, Salford, United Kingdom.
Arafa, M. and Alqedra, M. (2011). “Early stage cost estimation
of buildings construction projects using artificial neural net-
works.” Journal of Artificial Intelligence, 4(1), 63–75.
Arbib, M. A. (1995). The Handbook of Brain Theory and Neural
Networks. MIT press, Cambridge, United Kingdom.
Assaf, S. A., Bubshait, A. A., Atiyah, S., and Al-Shahri, M.
(2001). “The management of construction company overhead
costs.” International Journal of Project Management, 19(5),
295–303.
Aswed, G. K. (2016). “Productivity estimating model for brick-
layers in construction projects using artificial neural netw-
orks.” Al-qadisiya Journal of Engineering Sciences, 9(2), 183–
199.
Bala, K., Bustani, S., and Waziri, B. (2014). “A computer-based
cost prediction model for institutional building projects in
Nigeria: An artificial neural networks approach.” Journal of
Engineering, Design and Technology, 12(4), 518–529.
Bala, K. and Waziri, B. (2012). “Parametric model for pre-design
building cost estimating.” Global Journal of Engineering and
Technology, 4(1), 115–122.
Bhokha, S. and Ogunlana, S. (1999). “Application of artificial
neural networks for the forecast of building cost at the pre-
design stage.” Seventh East-Asia Pacific Conference on Struc-
tural Engineering and Construction, Kochi, Japan.
Bouabaz, M. and Hamami, M. (2008). “A cost estimation model
for repair bridges based on artificial neural networks.” Amer-
ican Journal of Applied Sciences, 5(4), 334–339.
Boussabaine, A. H. (1995). “A neural network system for produc-
tivity forecasting.” Proceedings of the 12th ISARC, Warsaw,
Poland.
Boussabaine, A. H. and Kaka, A. P. (1998). “A neural networks
approach for cost flow forecasting.” Construction Management
and Economics, 16(4), 471–479.
Chao, L. C. and Skibniewski, M. J. (1994). “Estimating construc-
tion productivity: neural-network-based approach.” Journal
of Computing in Civil Engineering, 8(2), 234–251.
Chau, K. W. (2007). “Application of a pso-based neural network
in analysis of outcomes of construction claims.” Automation
in Construction, 16(5), 642–646.
Cheng, M. Y., Tsai, H. C., and Hsieh, W. S. (2009a). “Web-
based conceptual cost estimates for construction projects us-
ing evolutionary fuzzy neural inference model.” Automation
in Construction, 18(2), 164–172.
Cheng, M. Y., Tsai, H. C., and Sudjono, E. (2009b). “Evolution-
ary fuzzy hybrid neural network for conceptual cost estimates
in construction projects.” 26th International Symposium on
Automation and Robotics in construction, Austin, United S-
tates.
Chew, M. Y. L. and Tan, S. S. (2003). “Neural network ap-
proach for grading of maintainability of wet areas in high-
rise buildings.” International Journal of Architectural Science,
4(4), 150–167.
Chou, J. S. (2012). “Comparison of multilabel classification mod-
els to forecast project dispute resolutions.” Expert Systems
with Applications, 39(11), 10202–10211.
Chua, D. K. H., Kog, Y. C., Loh, P. K., and Jaselskis, E. J.
(1997). “Model for construction budget performance-neural
network approach.” Journal of Construction Engineering and
Management, 123(3), 214–222.
El-Sawah, H. and Moselhi, O. (2014). “Comparative study in
the use of neural networks for order of magnitude cost esti-
mating in construction.” Journal of Information Technology
in Construction, 19, 462–473.
Elhag, T. M. S. and Boussabaine, A. H. (1998). “An artificial
neural system for cost estimation of construction projects.”
Proceedings of the 14th ARCOM Annual Conference, Berk-
shire, United Kingdom.
Elhassan, S. M. M., Zawawi, N. A. W., and Ghazali, Z. B. (2012).
“Decision making framework for optimizing construction man-
agement objectives: A review.” Recent Advances in Engineer-
ing, 1(1), 169–173.
ElSawy, I., Hosny, H., and Razek, M. A. (2011). “A neural net-
work model for construction projects site overhead cost esti-
mating in egypt.” International Journal of Computers Science,
8(3), 273–283.
Emsley, M. W., Lowe, D. J., Duff, A. R., Harding, A., and
Hickson, A. (2002). “Data modelling and the application of a
neural network approach to the prediction of total construc-
tion costs.” Construction Management and Economics, 20(6),
465–472.
Fang, C. F. and Froese, T. (1999). “Cost estimation of High Per-
formance Concrete (HPC) high-rise commercial buildings by
neural networks.” Available at: <http://www.irbnet.de/>.
Fatima, A., Sekhar, T. S., and Hussain, S. A. M. (2014). “Anal-
ysis of construction dispute resolution process using artifi-
cial neural networks.” International Journal of Innovative Re-
search and Developments, 3(7), 81–86.
Feng, G. L. and Li, L. (2013). “Application of genetic algorithm
and neural network in construction cost estimate.” Advanced
Materials Research, 756–759, 3194–3198.
Galkin, I. (2002). “Crash introduction to artificial neural net-
works.” Available at: <http://ulcar.uml.edu/>.
Geiger, M., Knoblach, J., and Backes, F. (1998). “Cost esti-
mation of large scale production of sheet metal.” Production
Engineering, 2(2), 81–84.
Geon, N. C. (2005). “Using artificial neural networks to predict
power plant turbine hall key cost drivers.” M.S. thesis, Uni-
versity of Technology Malaysia, Johor Bahru, Malaysia.
Golizadeh, H., Sadeghifam, A. N., Aadal, H., and Majid, M.
Z. A. (2016). “Automated tool for predicting duration of con-
struction activities in tropical countries.” KSCE Journal of
Civil Engineering, 20(1), 12–22.
Golpayegani, S. A. H. and Emamizadeh, B. (2007). “Designing
work breakdown structures using modular neural networks.”
Decision Support Systems, 44(1), 202–222.
Graham, L. D., Forbes, D. R., and Smith, S. D. (2006). “Mod-
eling the ready mixed concrete delivery system with neural
networks.” Automation in Construction, 15(5), 656–663.
Günaydın, H. M. and Doğan, S. Z. (2004). “A neural network ap-
proach for early cost estimation of structural systems of build-
ings.” International Journal of Project Management, 22(7),
595–602.
58

Hegazy, T. and Ayed, A. (1998). “Neural network model for para-
metric cost estimation of highway projects.” Journal of Con-
struction Engineering and Management, 124(3), 210–218.
Hegazy, T., Fazio, P., and Moselhi, O. (1994). “Developing prac-
tical neural network applications using back-propagation.”
Computer-Aided Civil and Infrastructure Engineering, 9(2),
145–159.
Hong, Y., Liao, H., and Jiang, Y. (2014). “Construction engineer-
ing cost evaluation model and application based on RS-IPSO-
BP neural network.” Journal of Computers, 9(4), 1020–1026.
Iranmanesh, S. H. and Zarezadeh, M. (2008). “Application of
artificial neural networks to forecast actual cost of a project
to improve earned value management system.” International
Journal of Social, Behavioral, Educational, Economic, Busi-
ness and Industrial Engineering, 2(6), 658–661.
Jain, M. and Pathak, K. K. (2014). “Applications of artificial
neural networks in construction engineering and management:
A review.” International Journal of Engineering Technology,
Management and Applied Sciences, 2(3), 134–142.
Jamil, M., Zain, M. F., and Basri, H. B. (2009). “Neural network
simulator model for optimization in high performance concrete
mix design.” European Journal of Scientific Research, 34(1),
61–68.
Kamarthi, S. V., Sanvido, V. E., and Kumara, S. R. T. (1992).
“Neuroform-neural network system for vertical formwork sele-
ction.” Journal of Computing in Civil Engineering, 6(2), 178–
199.
Kayarvizhy, N., Kanmani, S., and Uthariaraj, R. V. (2014).
“ANN models optimized using swarm intelligence algorithms.”
WSEAS Transactions on Computers, 13, 501–519.
Khalafallah, A. (2008). “Neural network based model for pre-
dicting housing market performance.” Tsinghua Science and
Technology, 13(1), 325–328.
Kim, G. H., An, S. H., and Kang, K. I. (2004). “Comparison of
construction cost estimating models based on regression anal-
ysis, neural networks, and case-based reasoning.” Building and
Environment, 39(10), 1235–1242.
Kim, G. H., Seo, D. S., and Kang, K. I. (2005). “Hybrid mod-
els of neural networks and genetic algorithms for predicting
preliminary cost estimates.” Journal of Computing in Civil
Engineering, 19(2), 208–211.
Lam, K. C., Hu, T., Thomas Ng, S., Skitmore, M., and Cheung,
S. (2001). “A fuzzy neural network approach for contractor
prequalification.” Construction Management and Economics,
19(2), 175–188.
Lee, D., Kim, S., and Kim, S. (2016). “Development of hy-
brid model for estimating construction waste for multifamily
residential buildings using artificial neural networks and ant
colony optimization.” Sustainability, 8(9), 870–883.
Lhee, S. C., Flood, I., and Issa, R. R. (2014). “Development of
a two-step neural network-based model to predict construc-
tion cost contingency.” Journal of Information Technology in
Construction, 19(24), 399–411.
Li, H. and Love, P. E. D. (1999). “Combining rule-based ex-
pert systems and artificial neural networks for mark-up es-
timation.” Construction Management and Economics, 17(2),
169–176.
Liu, J. B. and Guo, F. (2014). “Construction quality risk man-
agement of projects on the basis of rough set and neural net-
work.” Computer Modelling and New Technologies, 18(11),
791–797.
Lou, Z., Gunaratne, M., Lu, J. J., and Dietrich, B. (2001). “Ap-
plication of neural network model to forecast short-term pave-
ment crack condition: Florida case study.” Journal of Infras-
tructure Systems, 7(4), 166–171.
Lyne, R. C. and Maximinio, O. J. (2014). “An artificial neural
networks approach to structural cost estimation of building
projects in Palestine.” DLSU Research Congress 2014, Mani-
la, Philippines.
Maghrebi, M., Sammut, C., and Waller, T. S. (2014). “Predicting
the duration of concrete operations via artificial neural net-
works and by focusing on supply chain parameters.” Building
Research Journal, 61(1), 1–14.
Maria-Sanchez, P. (2004). “Estimation of environmental risks in
construction projects in Puebla (Mexico): a neural network
approach.” WIT Transactions on Ecology and the Environ-
ment, 77.
Masri, S. F., Nakamura, M., Chassiakos, A. G., and Caugh-
ey, T. K. (1996). “Neural network approach to detection of
changes in structural parameters.” Journal of Engineering Me-
chanics, 122(4), 350–360.
McKim, R. A. (1993). “Neural networks and identification and
estimation of risk.” AACE International Transactions, 5.1–
5.10.
Morcous, G. (2002). “Comparing the use of artificial neural net-
works and case-based reasoning in modeling bridge deterio-
ration.” Annual Conference of the Canadian Society for Civil
Engineering, Montreal, Canada.
Murtaza, M. B. and Fisher, D. J. (1994). “A neural network
model for decision making with application in construction
management.” Journal of International Information Manage-
ment, 3(2), 27–38.
Odeyinka, H., Lowe, J., and Kaka, A. (2002). “A construction
cost flow risk assessment model.” ARCOM 18th Annual Con-
ference, Northumbria, United Kingdom.
Paliwal, M. and Kumar, U. A. (2011). “Assessing the contribu-
tion of variables in feed forward neural network.” Applied Soft
Computing, 11(4), 3690–3696.
Pathak, K. K. and Agarwal, R. (2003). “Cost prediction of over-
head water tanks using artificial neural networks.” Journal
of the Institution of Engineers. India. Civil Engineering Divi-
sion, 84, 153–158.
Pearce, A. R. (1997). “Cost-based risk prediction and identifica-
tion of project cost drivers using artificial neural networks.”
Final report submitted to the Graduate Program, Georgia In-
stitute of Technology, Atlanta, United States.
Petruseva, S., Zileska-Pancovska, V., and Zujo, V. (2013). “Pre-
dicting construction project duration with support vector ma-
chine.” International Journal of Research in Engineering and
Technology, 2(11), 12–24.
Pewdum, W., Rujirayanyong, T., and Sooksatra, V. (2009).
“Forecasting final budget and duration of highway construc-
tion projects.” Engineering, Construction and Architectural
Management, 16(6), 544–557.
Polat, G. (2012). “ANN approach to determine cost contingen-
cy in international construction project.” Journal of Applied
Management and Investments, 1(2), 195–201.
Portas, J. and AbouRizk, S. (1997). “Neural network model for
estimating construction productivity.” Journal of Construc-
tion Engineering and Management, 123(4), 399–410.
59

Rudomin, P., Arbib, M. A., Cervantes-Perez, F., and Romo,
R. (1993). Neuroscience: From Neural Networks to Artificial
Intelligence. Springer, Berlin, German.
Rumelhart, D. E. (1986). “Learning internal representations by
error propagation.” Parallel Distributed Processing, 1, 318–
362.
Savin, D., Alkass, S., and Fazio, P. (1998). “Calculating weight
matrix of neural network for resource leveling.” Journal of
Computing in Civil Engineering, 12(4), 241–248.
Sawhney, A. and Mund, A. (2001). “Intellicranes: An integrated
crane type and model selection system.” Construction Man-
agement and Economics, 19(2), 227–237.
Setyawati, B. R., Sahirman, S., and Creese, R. C. (2002). “Neural
networks for cost estimation.” AACE International Transac-
tions, ES13.1–ES13.9.
Sharmik, S., Lekha, G., and Kanshik, S. (2016). “Cost and time
effective prediction of soil characteristics using artificial neu-
ral networks model.” International Journal of Innovative Re-
search in Science, Engineering and Technology, 5(3), 3829–
3834.
Shi, H. W. and Li, W. Q. (2010). “Integration of fuzzy logic,
particle swarm optimization and neural networks in quality
assessment of construction project..” Journal of Software En-
gineering, 5(7), 737–744.
Shi, J. J. (1999). “A neural network based system for predict-
ing earthmoving production.” Construction Management and
Economics, 17(4), 463–471.
Shtub, A. and Versano, R. (1999). “Estimating the cost of
steel pipe bending, a comparison between neural networks and
regression analysis.” International Journal of Production Eco-
nomics, 62(3), 201–207.
Sivanandam, S. N. and Deepa, S. N. (2006). Introduction to Neu-
ral Networks using Matlab 6.0. Tata McGraw-Hill Education,
Columbus, United States.
Sodikov, J. (2005). “Cost estimation of highway projects in de-
veloping countries: artificial neural networks approach.” Jour-
nal of the Eastern Asia Society for Transportation Studies, 6,
1036–1047.
Sonmez, R. (2004). “Conceptual cost estimation of building
projects with regression analysis and neural networks.” Cana-
dian Journal of Civil Engineering, 31(4), 677–683.
Sonmez, R. and Ontepeli, B. (2009). “Predesign cost estimation
of urban railway projects with parametric modeling.” Journal
of Civil Engineering and Management, 15(4), 405–409.
Vahdani, B., Mousavi, S. M., Mousakhani, M., Sharifi, M., and
Hashemi, H. (2012). “A neural network model based on sup-
port vector machine (SVM) for conceptual cost estimation of
construction projects.” Journal of Optimization in Industrial
Engineering, 10, 11–18.
Wang, X. Z., Duan, X. C., and Liu, J. Y. (2010). “Application of
neural network in the cost estimation of highway engineering.”
Journal of Computers, 5(11), 1762–1766.
Wang, Y. M. and Elhag, T. M. (2007). “A comparison of neural
network, evidential reasoning and multiple regression analysis
in modelling bridge risks.” Expert Systems with Applications,
32(2), 336–348.
Waziri, B. S. (2010). “An artificial neural networks model for pre-
dicting the construction cost of institutional building projects
in Nigeri.” Proceedings of 2nd West Africa Built Environment
Research Conference, Accra, Ghana.
Waziri, B. S. (2012). “Modelling the performance of tradition-
al contract projects in Nigeria: An artificial neural networks
approach.” Proceedings of 4th West Africa Built Environment
Research Conference, Abuja, Nigeria.
Waziri, B. S. and Bala, K. (2011). “Predicting construction cost
of public building projects using regression and neural net-
work models.” International Journal of Architecture and Built
Environment, 3(1), 85–91.
Williams, T. P. (1994). “Predicting changes in construction cost
indexes using neural networks.” Journal of Construction En-
gineering and Management, 120(2), 306–320.
Wilmot, C. G. and Mei, B. (2005). “Neural network modeling
of highway construction costs.” Journal of Construction En-
gineering and Management, 131(7), 765–771.
Xiang, P. C. and Luo, K. (2012). “The evaluation for the be-
havioural risk of participants in construction projects based
on back propagation neural network.” Advances in Informa-
tion Sciences and Service Sciences, 4(14), 97–107.
Yadav, R., Vyas, M., Vyas, V., and Agrawal, S. (2016). “De-
velopment of cost estimating method for bricklayer cost.” In-
ternational Journal of Engineering Research and Technology,
5(1), 430–432.
Yahia, H., Hosny, H., and Razik, M. E. A. (2011). “Time contin-
gency assessment in construction projects in Egypt using arti-
ficial neural networks model.” International Journal of Com-
puter Science, 8(4), 523–531.
Yeh, I. C. (1998). “Modeling of strength of high-performance con-
crete using artificial neural networks.” Cement and Concrete
Research, 28(12), 1797–1808.
Yitmen, I. and Soujeri, E. (2010). “An artificial neural network
model for estimating the influence of change orders on project
performance and dispute resolution.” Proceedings of the In-
ternational Conference on Computing in Civil and Building
Engineering, Nottingham, United Kingdom.
Zin, M. R., Mansur, S. A., Bakri, A., and Caren, T. C. L. (2006).
“Predicting the performance of traditional general contract
(TGC) projects: A neural network based approach.” Proceed-
ings of the 6th Asia-Pacific Structural Engineering and Con-
struction Conference, Kuala Lumpur, Malaysia.
60

Artificial Neural Networks In Construction Engineering And Management

Recommended

Recommended

More Related Content

Similar to Artificial Neural Networks In Construction Engineering And Management

Similar to Artificial Neural Networks In Construction Engineering And Management (20)

More from Andrea Erdman

More from Andrea Erdman (20)

Recently uploaded

Recently uploaded (20)

Artificial Neural Networks In Construction Engineering And Management