The term

“regression” was devised by Francis Galton in the nineteenth century to

describe a biological phenomenon. Regression analysis is a statistical method

for exploring the correlations between independent (xi) and dependent (y)

variables. Its purpose is to find the equation that most accurately predicts

the dependent variable as a linear function of two or more independent

variables according to the causal relationships among changes in internal

factors. Regression analysis includes many techniques for modeling and

analyzing several variables, when the focus is on the relationship between a

dependent variable and one or more independent variables (or ‘predictors’)

Regression analysis

also allows to assess the effects of variables measured on different scales,

these benefits help researchers / data analysts / data scientists to eliminate

and evaluate the best set of variables to be used for building predictive

models.

1.1.1 Artificial Neural Network (ANN)

Artificial neural

networks are purely data driven models which through training iteratively

transition from a random state to a final model. They do not depend on expectations about

functional form, probability distribution or smoothness,

ANN is a branch of

artificial intelligence (AI) in which structure is based on the biological

nervous system. It can exhibit a surprising number of the human brain’s

characteristics, e.g. learn from experience and generalize from previous

examples to new problems. ANN can provide expressive answers even when the data

to be processed include errors or are incomplete, and can process information

extremely rapidly when applied to solve real world problems (Lippmann 1988;

Smith 1993). Neural Networks (NN) are used in construction for modeling complex

relationships between inputs and outputs or to find patterns in data.

An ANN is typically

defined by three types of parameters (Nitin kumara et al 2013):

1-The interconnection pattern

between different layers of neurons.

2-The learning process for updating

the weights of the interconnections.

3-The activation function that

converts a neuron’s weighted input to its output activation.

Garrett (1994) has

given an interesting engineering definition of the ANN as: “a computational

mechanism able to acquire, represent, and compute mapping from one multivariate

space of information to another, given a set of data representing that

mapping.” Artificial neural networks (ANNs) are a functional abstraction of the

biologic neural structures of the central nervous system

Zayed and Halpin (2005)

defined ANN as “the process of developing the ability to generalize, which

correctly classify new patterns or to make forecasts and predictions”.

earning and

generalization of the problems in the ANN models could be achieved in spite of

incomplete or erroneous data. The data used to test the prediction capability

of the network is selected from the total data set. After a predetermined

number of iterations, the network training and testing is stopped whereas no

amelioration is done in the output.

ANN has some advantages

includes (Nitin kumara et al 2013):

·

Adaptive learning: An ability to

learn how to do tasks based on the data given for training or initial

experience.

·

Self-Organization: An ANN can create its own organization or

representation of the information it receives during learning time.

Also, ANN has some disadvantages include

(Nitin kumara et al 2013):

·

ANN can be used only if training

data is available. It is not necessary to have a mathematical model of the

problem of interest, and there is no need to provide any form of prior

knowledge.

·

The solution obtained from the

learning process usually cannot be interpreted.

·

Most neural network architectures

are black boxes. They cannot be checked whether their solution is probable,

i.e. their final state cannot be interpreted in terms of rules.

Applications of ANNs in

construction management go back to the early 1990s. These applications cover

many critical topics in productivity, quality, time estimation, bidding,

performance evaluation.

Among the numerous

artificial neural networks that have been proposed, backpropagation networks

have been extremely popular for their unique learning capability. 80% of

practical ANN applications used the backpropagation neural networks (Haykin

1999).

Artificial neural

networks (ANNs) models may be called by different names:

(1) connectionist models;

(2) parallel

distributed processing models;

(3) neuromorphic

systems; and

(4) neural computing.