1 AIT Asian Institute of Technology

Determination of neural network architecture for accident analysis

AuthorPhusak Yuthayanont
Call NumberAIT Thesis no. ST-98-46
Subject(s)Neural networks (Computer science)
Construction industry--Accidents
NoteA thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering, School of Civil Engineering
PublisherAsian Institute of Technology
Series StatementThesis ; no. ST-98-46
AbstractThis study presents the procedure and results of a system for construction accident analysis, which uses neural network techniques. The neural network recognizes the accident from the patterns of the historical records. In this study, simple characteristics were selected as the design factors affecting to the models. These characteristic factors were used as the input data to the neural network. The neural network learning procedure used a generalized delta rule, namely, a back-propagation algorithm. This approach makes use of the ability of learning, generalizing and nonlinear dynamic processing of neural network. The neural network can learn from a limited set of data. Therefore, this thesis proposes to implement neural network as an alternative solution to the stated problem. From the results of this application of a neural network, it was concluded that it would be possible to use the method to analyze accident in a construction site.
Year1998
Corresponding Series Added EntryAsian Institute of Technology. Thesis ; no. ST-98-46
TypeThesis
SchoolSchool of Civil Engineering
DepartmentOther Field of Studies (No Department)
Academic Program/FoSStructural Engineering (STE) /Former Name = Structural Engineering and Construction (ST)
Chairperson(s)Minato, Takayuki
Examination Committee(s)Chotchai Charoenngam; Kazama, So
Scholarship Donor(s)Partial Scholarship
DegreeThesis (M.Eng.) - Asian Institute of Technology, 1998


Usage Metrics
View Detail0
Read PDF0
Download PDF0