A STUDY ON NON- DESTRUCTIVE ANALYSIS OF BUILDING MATERIALS USING HYPERSPECTRAL DATA BY ARTIFICIAL NEURAL NETWORK

Abstract

Different procedures are used in order to model the process of converting raw data into useful information that try to emulate the human ability to reason. Artificial Neural Networks (ANN) is a new alternate tool, which has the ability to solving complex problems using an “artificial reasoning system” constructed with basis on the human brain. These computational tools were inspired by the analysis of the neural structure of intelligent organisms like human and use knowledge acquired through the analysis of previous experiences to develop correlations between known initial conditions and results. The basic idea is to regenerate the vast array of relationships that are established between individual brain neurons, using different synaptic pathways to determine the output to a certain stimulus. This work is based on the idea that hyperspectral remote sensing data can be a useful way to study building materials. The working hypothesis of this research is that the process of analyzing building materials using hyperspectral remote sensing data for classification and regression can be facilitated and standardized using an ANN. The research aims to collect data of various types of cement , concrete and use ANN to establish models that correlate these materials with the actual value . The major aim of the work is to test, explore and demonstrate the potential of hyperspectral remote sensing data combine with ANN as an interesting tool for diagnosis, training and testing of building materials in the field of civil engineering .