CHAPTER ONE
INTRODUCTION
1.1 Background
Cost is one of the three main challenges for the construction manager, where the success of a project is judged by meeting the criteria of cost with budget, schedule on time, and quality as specified by the owner (Rezaian, 2011). In which, poor strategy or incorrect budget or schedule forecasting can easily turn an expected profit into loss (Cheng, et al., 2010). Therefore, effective estimating is one of the main factors of a construction project success (Al-Shanti, 2003). Accordingly, cost estimate in early stage plays a significant role in any construction project (Ayed, 1997), where it allows owners and planners to evaluate project feasibility and control costs effectively (Feng, et al., 2010).In addition, the cost of a building is significantly affected by decisions made at the early phase. While this influence decreases through all phases of building project (Gunaydın & Dogan, 2004).
Due to this prominence of cost estimate in early stage and limited availability of information during the early phase of a project, construction managers typically leverage their knowledge, experience and standard estimators to estimate project costs. As such, intuition plays a significant role in decision-making. Inasmuch the essential needs of project owners and planners to a tool to help them in their early decisions; researchers have worked hard to develop cost estimate technique that maximize the practical value of limited information in order to improve the accuracy and reliability of cost estimation work (Cheng, et al., 2010). Thus, many methods either traditional or artificial intelligence methods were studied and examined for their validity in estimating the project cost at conceptual stage.
In the last years a new approach, based on the theory of computer systems that simulate the learning effect of the human brain as Artificial Neural Networks (ANNs) has grown in popularity (Cavalieri, et al., 2004).
One major benefit of using ANN is its ability to understand and simulate more complex functions than older methods such as linear regression (Weckman, et al., 2010). In addition, it can approximate functions well without explaining them. This means that an output is generated based on different input signals and by training those networks, accurate estimates can be generated. (Verlinden, et al., 2007).
1.2 Problem Statement
In preliminary stage of a construction project in Lagos , there is a limited available data and a lack of appropriate cost estimate methods, where most of common estimate techniques that are used in Lagos are still inadequacy traditional methods (Al- Shanti, 2003).
All parties involved in construction project are in need of reliable information about the cost of a project in the early stages. Therefore, many researchers are still searching and developing a new technique that is capable of dealing with very limited data and giving more accurate cost estimate.
However, many researchers in recent years applied ANN approach in various fields of engineering prediction and optimization, but the authors reckon that the researches and studies on utilizing neural networks to estimate the cost of construction projects at various stages are very limited until now (Arafa & Alqedra, 2011; Gunaydın & Dogan, 2004; Harding, et al., 1999; Adeli & Wu, 1998; Sonmez, 2004).
1.3 Research Aim
The aim of this research is to develop a new model for early cost estimate of building projects in Lagos by developing an Artificial Neural Network (ANN) model. This model is able to help parties involved in construction projects (owner, contractors, consultants, and others) in obtaining a cost estimate at the early stages of projects with limited available information and within possible time and high accuracy.
1.4 Research Objectives
The principal objectives of this study are:
1. Identify the most prominent parameters affecting the accuracy of estimating the building project cost in Lagos .
2. Develop a comprehensive tool for parametric cost estimation using the optimum Neural Network model.
1.5 Research Importance
The contributions of this thesis are expected to be relevant to both researchers and practitioners:
§ To researchers, the findings should help to investigate the accuracy of applying Artificial Neural Network model on several building types (not only one type), in addition to identifying the most influential parameters on the total cost of these several types.
§ As for practitioners, the findings should help to easily estimate the cost of new building projects after programing the developed model into marketing programs.
1.6 Research Scope and Limitation
This research focuses on buildings sector of construction projects in Lagos ; including the main two phases of construction building; skeleton and finishing phases. Thus, many building projects that were implemented between 2009 and 2012 were collected, and some types of these building projects were excluded according to lack of available frequency such as hospitals, laboratories and universities.
1.7 Methodology Outline
The objectives of this study will be achieved through performing the following steps:
- Conduct a literature review of previous studies that are related to construction cost estimate and paying special attention of using ANN.
- Conduct quantitative and qualitative survying techneques to ldentify the influntial factors on cost of building projects in Lagos .
- Conduct exploratory interviews with all engineering institutions to obtain the relevant data of building projects; to be used in building the model.
- Select the application Neurosolution software to be used in modeling the neural network.
- Examine the validity of the adopted model by using statistical performane measurements and applying sesitivity analysis.
1.8 Organization of the study
The current study was included six chapters explained as follow:
Chapter (1) Introduction
An introductory chapter defines the problem statement, the objectives of this study, the methodology and an overview of this study.
Chapter (2) literature Review
Presents a literature review of traditional and present efforts that are related to the parametric cost estimating, and application of Artificial Neural Network (ANN) model in related field with its characteristics and structures.
Chapter (3) Research Methodology
The adopted methodology in this research was presented in this chapter including the data-acquisition process of influential factors that relate to cost estimating of building projects and historical data of building projects that necessary for the proposed model.
Chapter (4) Data Results
Presents statistical analysis for questionnaire surveying, Delphi technique and data frequency. It also presents the adopted influential factors in this study and the encoded data for model implementation.
Chapter (5) Model Development
Presents the selected application software and type of model chosen and displays the model implementation, training and validation. As well, the results of the best model with a view of influence evaluation of the trained ANN model are showed.
Chapter (6) Conclusion and Recommendations
Presents conclusions and recommendations outlines for future work.
