الفهرس 
OVERVIEWOnly 14 pages are availabe for public view
 |  | from | 239 |  |  |
| | | from | 239 | | |
Abstract
Application Earned Value Management (EVM) as a construction project control technique is not very common in the Republic of Iraq, in spite of the benefit from EVA to the schedule control and cost control of construction projects. The present study mainly aims to introduce a novel, alternative approach of using Artificial Intelligence Techniques (AIT) for EV management for construction projects in the Republic of Iraq through the use of three techniques; Multi-Linear Regression (MLR), Artificial Neural Networks (ANN) and Support Vector Machine (SVM). These techniques are used to build mathematical models for estimating the Schedule Performance Index (SPI), Cost Performance Index (CPI) and To-complete Cost Performance Indicator (TCPI) in Iraqi residential buildings both before and during their execution stage. Web-based software is designed to perform the estimating calculations quickly, accurately and without much effort. The MLR technique was used to identify the impact parameters using Statistical Package for the Social Sciences (SPSS) program, which presented sufficient estimating results regarding the Average Accuracy percentage (AA%) and correlation coefficient (R) generated for the SPI, CPI and TCPI. The values of AA% were found to be (95.89%, 96.89%, and 95.91%), and those of R were (92.911%, 98.916% and 97.837%) for each of SPI, CPI, and TCPI, respectively. The ANN technique was applied in creating new prediction models through the use of the backpropagation algorithm in the Neuframe software. This technique provided great estimations as compared to the MLR. The obtained results of the average accuracy (AA%) were equal to (83.09%, 90.83%, and 82.88%), and those of the correlation coefficient (R) were equal to (91.95%, 93.00% and 92.30%) for SPI, CPI and TCPI respectively. Finally, the third technique applied in creating prediction models is the SVM, whereby the SMOreg algorithm is used in the WEKA software. The results were interpreted in terms of Average Accuracy (AA%) being equal to (94.12%, 71.76%, and 84.82%) and the correlation coefficient (R) being equal to (99.56%, 91.744% and 99.71%) for SPI, CPI and TCPI respectively. To sum up, the results indicate that the ANN and SVM techniques provide excellent results of estimation when compared to the MLR technique.