Estimate at Completion for construction projects using Evolutionary Support Vector Machine Inference Model

2010 ◽  
Vol 19 (5) ◽  
pp. 619-629 ◽  
Author(s):  
Min-Yuan Cheng ◽  
Hsien-Sheng Peng ◽  
Yu-Wei Wu ◽  
Te-Lin Chen
Keyword(s):  
Support Vector Machine ◽  
Construction Projects ◽  
Support Vector ◽  
Inference Model

scholarly journals PREDICTING PRODUCTIVITY LOSS CAUSED BY CHANGE ORDERS USING THE EVOLUTIONARY FUZZY SUPPORT VECTOR MACHINE INFERENCE MODEL

2015 ◽  
Vol 21 (7) ◽  
pp. 881-892 ◽  
Author(s):  
Min-Yuan Cheng ◽  
Dedy Kurniawan Wibowo ◽  
Doddy Prayogo ◽  
Andreas F. V. Roy
Keyword(s):  
Support Vector Machine ◽  
Construction Projects ◽  
Productivity Loss ◽  
Support Vector ◽  
Model Parameters ◽  
Inference Model ◽  
Fuzzy Support Vector Machine ◽  
Change Orders ◽  
Artificial Neural Network Ann ◽  
The Impact

Change orders in construction projects are very common and result in negative impacts on various project facets. The impact of change orders on labor productivity is particularly difficult to quantify. Traditional approaches are inadequate to calculate the complex input-output relationship necessary to measure the effect of change orders. This study develops the Evolutionary Fuzzy Support Vector Machines Inference Model (EFSIM) to more accurately predict change-order-related productivity losses. The EFSIM is an AI-based tool that combines fuzzy logic (FL), support vector machine (SVM), and fast messy genetic algorithm (fmGA). The SVM is utilized as a supervised learning technique to solve classification and regression problems; the FL is used to quantify vagueness and uncertainty; and the fmGA is applied to optimize model parameters. A case study is presented to demonstrate and validate EFSIM performance. Simulation results and our validation against previous studies demonstrate that the EFSIM predicts the impact of change orders significantly better than other AI-based tools including the artificial neural network (ANN), support vector machine (SVM), and evolutionary support vector machine inference model (ESIM).

scholarly journals A Whole Process Cost Prediction System for Construction Projects Based on Improved Support Vector Machines

2022 ◽  
Vol 16 ◽  
pp. 278--286
Author(s):  
Xueqing Zhang ◽  
Jie Song ◽  
Chaolin Zha
Keyword(s):  
Support Vector Machine ◽  
Construction Projects ◽  
Construction Project ◽  
Principal Component ◽  
Support Vector ◽  
Prediction System ◽  
Cost Prediction ◽  
Project Cost ◽  
Whole Process ◽  
Process Cost

The current project cost system requires high data scale, small amount of data and large prediction deviation. In order to improve the prediction accuracy of the whole process cost of construction project, this paper designs a whole process project cost prediction system based on improved support vector machine. In the hardware part of the system, the control core adopts arm controller S3C6410 and introduces 4G communication module to analyze the actual engineering data with the support of hardware. In the software part, the whole process cost prediction index system of the construction project is established, the index is reduced by the principal component method, and the support vector machine is improved by particle swarm optimization algorithm to realize the whole process cost prediction of the project. The system function test results show that the average prediction deviation of the designed system is 4.11%, the average prediction deviation of the cost prediction system is 3.05%, and the average prediction deviation of the system is 1.57%.

Sign in / Sign up

Export Citation Format

Share Document