A Context-Aware Reminder System for Tracking SMS in Mobile Device Environment Using Artificial Neural Network

Abstract

Reminder systems have always been a major companion of human life. With the proliferation of mobile devices such as mobile phones, smartphones and tablets, users readily rely on them by using such applications as calendar, notes and alarm systems provided by these devices to prompt them of impending activities. One major communication system employed in almost all human endevours is short messages (SMS) which are used for sending reminders and notices. However, there is no mechanism to remind users of mobile devices information contained in SMS. This paper implements a context-aware reminder system using a trained Artificial Neural Network (ANN) based on gradient-descent delta rule backpropagation algorithm as the reasoning engine. SMS which are classified as activity context are abstracted and normalised based on users’ preferences. The abstracted data is used to develop a reminder system which prompts the user when the date and time contained in the SMS are due. The developed system effectively retrieves and classifies data that followed the specified formats with 95% accuracy level. The work revealed that simple intelligent systems that eliminate cumbersome rule set architectures whilst taking into consideration the dynamics of users’ preferences are better than the existing systems