Study on Early Warning of Building Safety Based on SVM
Journal Title: Journal of Applied Quantitative Methods - Year 2006, Vol 1, Issue 2
Abstract
The building is important strut industry of our national economy. But the safety accidents in building domain occur frequently every year. The safety problem of building directly influences or even restricts the development of building industry. Support Vector Machine (SVM) is a kind of new machine learning method developed on the basis of statistical learning theory. This method based on the principle of structural risk minimization can solve the problem of overfitting effectively and has good generality capability and better classification accuracy. In this paper, the author applied this method in safety management of building and carried on the study of early warning system of building safety based on SVM. At last, we carried on the data experiment to this problem and proved that the method of SVM has good generality capability.
Authors and Affiliations
Li-Jun FENG, Shu-Quan LI
Standards Review on Mission of Management Information Systems Audit
The purpose of auditing is to verify that all hardware and software functions, automated processes, declared and published performance criteria are producing correct results, within the confines of system integrity, secu...
THE CREDIBILITY, COMPLETENESS AND ACCURACY OF INFORMATION ABOUT FIRST AID IN CASE OF CHOKING ON THE ROMANIAN WEBSITES
A large number of studies assessing the quality of medical websites in various languages have shown that the quality of health related information is problematic. Nevertheless, the Romanian medical cyberspace has not yet...
ANALYSIS AND COMPARISON OF UNDER FIVE CHILD MORTALITY BETWEEN RURAL AND URBAN AREA IN BANGLADESH
Knowledge of factors that affect the under-five year child mortality is important because it pertains to policy and programs. Causes and differences of under-five mortality between rural and urban area help decision make...
A STEP-WISE METHOD FOR EVALUATION OF DIFFERENTIAL ITEM FUNCTIONING
Item bias or differential item functioning (DIF) has an important impact on the fairness of psychological and educational testing. In this paper, DIF is seen as a lack of fit to an item response (IRT) model. Inferences a...
The Estimation of Maximum Effort in Weight Lifting Processes
Starting from defining the processes connected to lifting weights this article wishes to accomplish a quantitative analysis applied to the lifting processes. Also, based on the data collected at the recently ended Olympi...