Web-based mathematical document retrieval for mobile Android application

• Main Author: Akbar, Deka Auliya
• Other Authors: Hui Siu Cheung
• Format: Final Year Project
• Language: English
• Published: 2017
• Subjects: DRNTU::Engineering::Computer science and engineering::Software::Software engineering; DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing; DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval; DRNTU::Engineering::Computer science and engineering::Information systems::Information systems applications
• Online Access: http://hdl.handle.net/10356/70426
• Institution: Nanyang Technological University

Advancement in web and mobile technology has developed innovations to human needs in various fields. One of them is to assist students learning better the subjects. Mathematics is an essential subject that can be made interesting through mobile application platform. This project aims to enrich student’s learning experience by developing a mobile Android application for a Mathematical Learning System named MathQA. The MathQA app intends to provide intuitive user interfaces for displaying educational mathematical contents and support search utilities for finding relevant mathematical documents. A mathematical document contains textual and mathematical formula information hence LaTeX typesetting is used to represent these documents. Building a mathematical document retrieval service is non-trivial due to the highly symbolic and structured nature of the mathematical formulas, therefore, formula-based retrieval techniques proposed in [1] and [2] were first investigated and evaluated. Based on the evaluation results, these techniques were found to have a promising performance and thus incorporated into the MathQA system. This project can be divided into three main phases: (i) to explore mathematical document retrieval techniques, develop the database and mathematical document retrieval services in the MathQA server; (ii) to research various resources and best practices for developing web-based and android applications and incorporate them during MathQA development; (iii) to combine photographic capability in modern cameras with Optical Character Recognition (OCR) and retrieval services for finding relevant documents. Available image pre-processing and OCR tools for Android were explored to develop a reliable and robust OCR engine for recognising document images. MathQA was developed with good design practices which follow Agile software lifecycle in order to produce a maintainable, flexible and extensible software applications. From the process and output of the project, it can be concluded that the MathQA application is useful to facilitate learning mathematics. Keywords: Mobile Learning, Android, Django, Mathematical Document Retrieval, LaTeX, Document Image Analysis and Recognition, OCR.