APPLIED PHOTOPERIODS FOR THE STUDY OF PHYCOREMEDIATION ( CAFEO 33th at Penang, Malaysia)
Current Air Quality Levels and Source Apportionment of Particulate Air Pollution in Yangon,Myanmar
Basic Electrical Technology Lesson 1 Introducing the Course on Basic Electrical and Lesson 2 Generation, Transmission and Distribution of Electric Power an Overview
Basic Electrical Technology lesson 3&4
Basic Electrical Technology Lesson 5 9
APPLICATION OF SUPPORT VECTOR MACHINES IN FORECASTING NONRESIDENTIAL CONSTRUCTION QUANTITYDEMAND IN THAILAND
Wiwat Kittinaraporn^{1}, Napat Harnpornchai^{2}, Sutja Boonyachut^{3}
1) Ph.D. Candidate, Department of Civil Engineering, Mahanakorn University of Technology,
Bangkok, Thailand. Email: kittinaraporn@gmail.com
2) Assistant Professor, Faculty of Economics, Chiang Mai University, Chiang Mai, Thailand.
Email: napateconcmu@gmail.com
3) Assistant Professor, Department of Civil Engineering, Mahanakorn University of Technology,
Bangkok, Thailand. Email: sutjab@gmail.com
Abstract: This paper deals with the application of a novel neural network technique, so called Support Vector Machine (SVM). The objective of this study is to explore the variable and parameter of forecasting factors in the construction industry to build up forecasting model for construction quantity demand in Thailand. The scope of the research is to study the nonresidential demand of construction quantity in Thailand. There are 44 sets of yearly data available, ranging from 1965 to 2009. The correlation between economic indicators and construction demand with the lag of one year was developed by (ApichatBuakla, 2005). The selected variables are used to develop SVM models to forecast the nonresidential demand of construction quantity in Thailand. The parameters are selected by using tenfold crossvalidation method. The results are indicated in term of Mean Absolute Percentage Error (MAPE). The MAPE value for the nonresidential construction quantity predicted by EpsilonSVR in corporation with Radial Basis Function (RBF) of kernel function type is 5.90. Analysis of the experimental results show that the support vector machine modeling technique can be applied to forecast construction quantity time series which is useful for decision planning and management purpose.
Keywords: Forecasting, NonResidential, Construction, Support Vector Machines
1. INTRODUCTION
Construction industry plays an important role for economic and social development of Thailand. It is an industrial strategy for recovering economy and society. It is a fundamental industry in terms of economy development. The construction industry includes the infrastructure, residence, and industry constructions. The construction industry creates a huge amount of revenue for the country in terms of creating different kinds of job as well as construction material industry.
Forecasting is vital in the construction industry because the organization administrators always use the results of the forecasting to support the planning of construction projects in many respects. These include the establishments of organization policy, objectives, strategy, and decision making. In addition, it is useful for optimal and efficient resource allocation. Forecasting can be used as tools in performance evaluation by assessing situations and in creating future requirements which stimulates the organization operations.
There have been several research works on forecasting. (ApichatBuakla, 2005) studied the artificial neural network (ANN) model for predicting the construction quantity in Thailand. It is found that the ANN model yields better predicting results than Multiple Linear Regression. (Tanratanawong& Scott, 2000) developed the ANN model to predict the construction quantity in UK. The model used the quarterly data from 19551998 to create the relationship between the annual economic factors and the construction quantities of different types in the following years. There were three ANN models, namely residential construction, nonresidential construction, and repairing and maintenance work. It was found that the ANN models yielded better results than the regression model. The results of the study were compared with the prediction results that had been done by two local authorities which had used the Delphi technique and were published as the present references. The ANNbased and the Delphibased results had similar accuracy for the residual and nonresidential constructions. For the repairing and maintenance, the ANN model yielded better results.
It can be seen that previous research works utilized the ANN and linear regression models for prediction. This research applies the SVM to the forecasting of construction quantity. The application of the SVM has not been done in the area of construction management. The SVM model is for the prediction of the future construction quantity in Thailand. The results will be used for creating the database in decision making, planning, and investment of Thailand construction industry. It is thus beneficial for the construction industry. In addition, there will be comparison among the SVM model and other forecasting models for the purpose.
2. DATA AND METHODOLOGY
2.1 Data
(ApichatBuakla, 2005) showed the linear regression model for the nonresidential construction using the SPSS program to analyze the regression. The selection of the independent variables is carried out using the stepwise method according to Eq. (1)
NRES_{n+1} = ij + a_{1}X_{n1} + a_{2}X_{n2} + a_{3}X_{n3} + … + a_{n}X_{nk} (1)
Where
NRES_{n+1}is the future annual construction quantity of the nonresidential type.
are the regression coefficients.
are the factors that influence the construction quantity of the nonresidential type.
The selection of the linear regression model is based on the lowest MAPE.
The data for the input are the data of GDP collected from 1965 to 2009 altogether 44 years.
The analysis of data uses the software DTREG version 10.7.18 (Demonstration Version) http://www.dtreg.com, Phillip H. Sherrod
2.2Theoryof Support VectorMachine
SVM is the technique used for the pattern recognition and classification of data. It is developed by (Vapnik, 1995). The principle of SVM is the construction of hyperplane on the plane of training data to divide data into different groups. In the construction of the hyperplane, the distance between the points that are closest to the hyperplane on both sides will be defined, namely d_{+} + d_{}. Margin is defined as d_{+} + d_{}. The appropriate hyperplane is the one that has the largest margin, as shown in Figure 1. The data that lie on the edge of the margin will be referred to the support vector.
Figure 1.The classification of data by the hyperplane in SVM.
From Figure 1, there are 2 groups of data. The training data include the samples that can be expressed in terms of andin which is the input vector whereas is the class label. The principle of SVM is to construct appropriate hyperplane on the training data plane. The hyperplane is defined by the parameters. is the vector that is normal to the hyperplane and b is the constant which defines the position of the vectors that are related to the original position in the input space. The linear hyperplane equation is defined as. To avoid the scale problem, and will be defined by the equation for the point that is closest to the hyperplane. Consequently, the hyperplane equation is given by Eq.(2)
(2)
Accordingly, it is just only the classification of the data using the hyperplane equation. In order to apply the algorithm to the nonlinear dataset, it is necessary to transform the training data to higher dimensional space, namely feature space. Such a transformation is carried out through the nonlinear function. The method is performed in terms a constrained optimization as defined by Eq. (3)
 Maximize
Subject to (1)
(2) (3)
is referred to as the Positive Lagrange Multipliers, is the Kernel function and is the constant for compensating the error induced during training and model complexity.
A number of the kernel functions can be used, e.g.
Polynomial of degree d
(4)
Radial Basis Function (RBF)
(5)
Sigmoid Function
(6)
Linear
(7)
Consequently, the architecture of the SVM can be depicted in Figure 2. is the estimated output and x is the input. X_{i} is the support vector, is the weight, and b is bias.
Figure 2 Architecture of SVM.
3. RESULTS AND DISCUSSION
3.1 Testing of Models
The testing of the forecasting model uses the GDP 9 types of data, i.e. T11, T24, T29, T48, T72, T79, T89, T93 and T123 as the input. The 10 floatcrossvalidation is used in training and testing.
Two types of SVM are used including the EpsilonSVR and the NuSVR. Each type employs 3 kinds of kernel functions including the Radial Basis Function (RBF), Linear and Polynomial degree2.
Figure 3 Results from SMV modeling.
Table 1: MAPE of the SVM models for forecasting the non residential construction quantity.
SVM model 
SVM kernel function 
MAPE 

Training 
Validation 

EpsilonSVR 
Radial Basis Function (RBF) 
5.90 
16.24 
NuSVR 
Radial Basis Function (RBF) 
6.59 
14.88 
EpsilonSVR 
Linear 
13.09 
17.86 
NuSVR 
Linear 
17.98 
20.83 
EpsilonSVR 
Polynomial degree2 
13.44 
16.19 
NuSVR 
Polynomial degree2 
13.27 
16.41 
Table 1 and Figure 3 show that the SVM model for the forecasting of the construction quantity demand of the nonresidential type using the EpsilonSVR and NuSVR with the kernel functions of the Radial Basis Function (RBF) is the most efficient.
The next efficient one is the EpsilonSVR with the kernel function of the Linear and the NuSVR with the kernel function of the Polynomial degree2, respectively.
The forecasting by the EpsilonSVR with the kernel function of the Polynomial degree2 and the NuSVR with the kernel function of the Linear are less efficient.
4.2 Forecasting of Construction Quantity Demand
The model that yields least deviation is used for the forecasting construction quantity demand of the nonresidential type, i.e. the EpsilonSVR with the kernel function of the Radial Basis Function (RBF). The results of the forecasting are shown in Figure 4.
Figure 4 Forecasting of nonresidential construction quantity using SVM.
From Figure 4, the forecasting is compared with the real construction quantity data from 19652009 altogether 44 years. The forecasting results show that the MAPE is equal to 5.90% which is significantly low.
4. CONCLUSIONS
This paper uses the SVM to predict the nonresidential construction quantity demand. The EpsilonSVR with the kernel function of the Radial Basis Function (RBF) is the best SVM and yields MAPE equal to 5.90%. The information from this research can be used as the guidelines for planning and decision making in construction organizations. The SVM shows its potential in forecasting other constructionrelated quantities too, e.g. material costs, construction times. In addition, it is expected to be applicable for the quality and safety prediction too.
REFERENCES
AlBahar, J.F. (1988). Risk Management in Construction Project: A Systematic Analysis Approach for Construction, Dissertation in partial satisfaction of the requirement for the degree of Doctor of Philosophy: University of California at Berkeley, Berkeley, California.
ApichatBuakla (2005). “Neural network model to forecast Construction output in Thailand”, Thesis in partial fulfillment of the requirement for the degree of Master of Civil Engineering: Naresuan University, Phitsanulok, Thailand.
Goh, B.H. (1998). “Forecasting residential construction demand in Singapore: comparative study of the accuracy of time series, regression and artificial neural network techniques.” Engineering Construction and Architectural Management, 5(3), 261275.
Phillip H. Sherrod, “DTREG Predictive Modeling Software.” www.dtreg.com. Copyright 20032007.
Tanratnawong, S. and Scott, S. (2000). “A neural network model to forecast national construction output.Journal of Financial Management in Construction and Property. (5), 6577.
Vapnik, V. (1995).The Nature of Statistical Learning Theory, SpringerVerlag, New York.