Hexadecimal Submission-Combination For Quranic-Arabic Words Information Retrieval

Digital Quran refers to the electronic text of the Quran either in Arabic font or images of the verses distributed to an electronic device. There are 77,439 words int the Quran. These words were translated into machine language in the form of binary format before they can read by machine. Among thes...

全面介绍

Saved in:
书目详细资料
主要作者: Ahmad Akmaluddin bin Mazlan
格式: Thesis
语言:English
主题:
标签: 添加标签
没有标签, 成为第一个标记此记录!
实物特征
总结:Digital Quran refers to the electronic text of the Quran either in Arabic font or images of the verses distributed to an electronic device. There are 77,439 words int the Quran. These words were translated into machine language in the form of binary format before they can read by machine. Among these issues the needs to have standard way to store and display digital Quran and implementation of word representation in hexadecimal format. Important issues on high cost reduction of Information Retrieval based on memory usage and retrieval time (processing speed) where image storage approach of digital Quran uses a significant amount of memory space. Based on literature review, there is mush work that need to be done using machine translation (MT) technique and Machine Language Processing (MLP) for the Quranic representation. Therefore, this study proposed the word representation model and conversion algorithm as cost reduction technique by using QuHex Model and Hexadecimal Submission-Combination Conversion Algorithm for Arabic information retrieval system. This technique allows keywords search in hexadecimal representation of Quran verses as the test case. Dataset was experimented using the cost-reduction technique were Surah Al-Fatihah and Surah Al- Baqarah. This study reveals that the purposed cost reduction technique in representing the Digital Quran can reduce the size of storage around 11% up to 50% and retrieval time up to 47%. This finding might be applied for any Arabic based search engine as it can reduce the query cost especially for small electronic devices.