Search In this Thesis
   Search In this Thesis  
العنوان
Using geo-information neural systems for forecasting remaining time of heritage buildings assets /
المؤلف
Mohamed, Hana Sabry Mokhtar.
هيئة الاعداد
باحث / هناء صبرى مختار محمد سرايا
مشرف / أحمد أبوالفتوح صالح
مشرف / شريف إبراهيم بركات
مناقش / منى جمال
الموضوع
Historic buildings. Geographic information systems. Virtual reality.
تاريخ النشر
2017.
عدد الصفحات
online resource (175 pages) :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
Information Systems
تاريخ الإجازة
01/04/2017
مكان الإجازة
جامعة المنصورة - كلية الحاسبات والمعلومات - Information Systems Department
الفهرس
Only 14 pages are availabe for public view

from 175

from 175

Abstract

Architectural heritage represents a witness to the nation’s Civilizations and its history and is considered a strong element to confirm the identity of the peoples and their privacy. But sadly, Architectural Heritage exposed too many of dangers and environmental pressures that lead to its destructions, distortion and then reduce its lifetime. Architectural heritage suffers from a lack of sufficient researches, studies and severe neglect by governments and organizations. In addition lack of awareness and perception the importance of heritage buildings as architectural and cultural symbols. As well as other factors such as lack of maintenance, demolition, sabotage, and misuse.The main objective of this research is to study, analyze of geographic factors and their impact on heritage buildings by simulating the Architectural Heritage environment. According to this study, Architectural Heritage lifetime can be predicted.The study presents a design framework for the integration of two new developments in this area, Architectural Information Systems, and Rough Neural Networks. Research approach involves integration between different information technologies GIS, 3D Virtual Reality and Rough Neural Networks at two phases. The first phase, a 3D Virtual Reality stage and the integration of the 3D model into a 3D GIS for further management and analysis. The second Phase represents Rough Neural Networks to build the prediction model to predict the remaining time of heritage building in the near future depending on the resulting data from the first Phase. This integration demonstrates the potential of Rough Neural Networks, GIS and 3D Virtual Reality as emerging tools in acquiring and analyzing spatial and attributes data to improve the accuracy of predictive value.