Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11889/8616
Title: Investigating artificial intelligence and modern technologies enhancement in stone and marble cutting in Palestine
Authors: Abu Hanieh, Ahmed 
Hasan, Afif Akel 
Abdelall, Sadiq 
Alhanjouri, Mohammed A. 
Keywords: Artificial Intelligence;Image processing;Integrated modeling;Machine learning;Stone-cutting - Palestine
Issue Date: Mar-2024
Publisher: Hashemite University
Source: Ahmed Abu Hanieh, Afif Akel Hasan, Sadiq AbdEall and Mohammed Alhanjouri, Investigating Artificial Intelligence and Modern Technologies Enhancement in Stone and Marble Cutting in Palestine, Jordan Journal of Mechanical and Industrial Engineering, Volume 18 Number 1, pp 207-218 March 2024. DOI: https://doi.org/10.59038/jjmie/180116
Abstract: Stone and Marble sector in Palestine has a significant contribution to the GDP. There are some modern factories that use computerized and numerical controls for stone cutting employing modern tools and processes, but most of the marble cutting factories depend on manual and small machinery production lines. This paper examines integrating modern technologies; artificial intelligence (AI) and mechatronic systems like sensors, actuators and control systems, in these cutting factories in order to increase their efficiency, improve the added value and contribute in the occupational safety for human labor and cutting processes. In particular artificial intelligence, machine learning and image processing tools will be investigated as examples of modern technologies that can be implemented in marble and stone cutting processes in Palestine. Four Convolutional Natural Network (CNN) types were employed to classify marble slabs, comparing colored and gray-level databases. Gray-level yielded superior recognition rates due to marble's prevalent gray color. Texture, not color, drove classification; ResNet-152 achieved 100% Recognition Rate (RR) for gray-level and 98.6% for colored. In terms of efficiency, Inception CNN excelled. Ultimately, gray-level images best served marble classification, rendering color irrelevant.
URI: http://hdl.handle.net/20.500.11889/8616
DOI: https://doi.org/10.59038/jjmie/180116
Appears in Collections:Fulltext Publications

Files in This Item:
File Description SizeFormat
28_JJMIE_2024_Stone AI.pdf2.14 MBAdobe PDFView/Open
Show full item record

Page view(s)

64
checked on Jun 18, 2024

Download(s)

44
checked on Jun 18, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.