A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Construction Legal Decision Support Using Support Vector Machine (SVM)
This paper represents a step in a line of research aiming at mitigating the negative effects of conflicts on the construction industry through developing a construction legal decision support methodology. This step developed Support Vector Machine (SVM) models to automatically extract latent legal factors, upon which judges base their verdicts, from precedent cases. The adopted research methodology developed and compared the output of first, second, and third degree polynomial kernel SVM models while implementing 4 weighing mechanisms namely term frequency (tf), logarithmic term frequency (ltf), augmented term frequency (atf), and term frequency inverse document frequency (tf.idf). The models were trained and tested over two sets of Differing Site Condition (DSC) cases compiled from the Federal Court of New York. The two sets were composed of 120 and 450 cases respectively. The highest accuracy of extraction of 76% was attained using first degree polynomial kernel SVM while implementing tf.idf weighing with the first set. With the second set, a higher accuracy of 85% was achieved using third degree polynomial kernel SVM while implementing tf.idf weighing.
Construction Legal Decision Support Using Support Vector Machine (SVM)
This paper represents a step in a line of research aiming at mitigating the negative effects of conflicts on the construction industry through developing a construction legal decision support methodology. This step developed Support Vector Machine (SVM) models to automatically extract latent legal factors, upon which judges base their verdicts, from precedent cases. The adopted research methodology developed and compared the output of first, second, and third degree polynomial kernel SVM models while implementing 4 weighing mechanisms namely term frequency (tf), logarithmic term frequency (ltf), augmented term frequency (atf), and term frequency inverse document frequency (tf.idf). The models were trained and tested over two sets of Differing Site Condition (DSC) cases compiled from the Federal Court of New York. The two sets were composed of 120 and 450 cases respectively. The highest accuracy of extraction of 76% was attained using first degree polynomial kernel SVM while implementing tf.idf weighing with the first set. With the second set, a higher accuracy of 85% was achieved using third degree polynomial kernel SVM while implementing tf.idf weighing.
Construction Legal Decision Support Using Support Vector Machine (SVM)
Mahfouz, Tarek (author) / Kandil, Amr (author)
Construction Research Congress 2010 ; 2010 ; Banff, Alberta, Canada
Construction Research Congress 2010 ; 879-888
2010-05-04
Conference paper
Electronic Resource
English
Construction Legal Decision Support Using Support Vector Machine (SVM)
| British Library Conference Proceedings | 2010
CONSTRUCTION MACHINE SUPPORT SYSTEM, CONSTRUCTION MACHINE SUPPORT PROGRAM
| European Patent Office | 2023
Evolutionary support vector machine inference system for construction management
| Online Contents | 2009
Efficacy of Using Support Vector Machine in a Contractor Prequalification Decision Model
| British Library Online Contents | 2010