Abstract

Word matching is a string searching technique for information retrieval in Natural Language Processing (NLP). There are several algorithms have been used for string search and matching such as Knuth Morris Pratt, Boyer Moore, Horspool, Intelligent Predictive and many other. However, there some issues need to be considered in measuring the performance of the algorithms such as the efficiency for searching small alphabets, time taken in processing the pattern of the text and extra space to support a huge table or state machines. Intelligent Predictive (IP) algorithm capable to solve several word matching issues discovered in other string searching algorithms especially with abilities to skip the pre-processing of the pattern, uses simple rules during matching process and does not involved complex computations. Due to those reasons,<strong> </strong>IP algorithm is used in this study due to the ability of this algorithm to produce a good result in string searching process. This article aims to apply IP algorithm together with Optical Character Recognition (OCR) tool for mobile-based word matching detection. There are four phases in this study consists of data preparation, mobile based system design, algorithm implementation and result analysis. The efficiency of the proposed algorithm was evaluated based on the execution time of searching process among the selected algorithms. The result shows that the IP algorithm for string searching process is more efficient in execution time compared to well-known algorithm i.e. Boyer Moore algorithm. In future work, the performance of string searching process can be enhanced by using other suitable optimization searching techniques such as Genetic Algorithm, Particle Swarm Optimization, Ant Colony Optimization and many others.

Highlights

  • Nowadays, mobile devices such as smartphone and tablet have become an inseparable part in our daily life activities that used for entertainment, information searching, connecting to customer services, taking photos, GPS location and many others

  • Text processing for information retrieval referring to the process of searching, creating or manipulating the electronic text for string searching, writing, editing, formatting and printing tasks by using a computer program and related hardware [2]

  • Optical Character Recognition (OCR) is an electronic tool can be used to prepare an electronic document for data analysis

Read more

Summary

Introduction

Mobile devices such as smartphone and tablet have become an inseparable part in our daily life activities that used for entertainment, information searching, connecting to customer services, taking photos, GPS location and many others. Text Processing is one of the most common tasks in many machine learning applications such as in information retrieval, machine translation, sentiment analysis, information extraction, question answering etc. These applications deal with huge amount of text to perform classification or translation and it involves a lot of work on the back end. The advantage of using this tool is the document created will be in the form of text-searchable and editable This approach will help in fast processing and highly accurate performance to make sure the content of document is remains undamaged and it will increase the efficiency and effectiveness in text processing tasks [4]

Objectives
Methods
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call