Computing and Information Systems - Theses
Permanent URI for this collection
Now showing 1 - 3 of 3
ItemSeamless proximity sensingAhmed, Bilal ( 2013)Smartphones are uniquely positioned to offer a new breed of location and proximity aware applications that can harness the benefits provided by positioning technologies such as GPS, and advancements in radio communication technologies such as Near Field Communication (NFC) and Bluetooth low energy (BLE). The popularity of location aware applications, that make use of technologies such as GPS, Wi-Fi and 3G, has further strained the already frail battery life that current generation smartphones exhibit. This research project is aimed to perform a comparative assessment of NFC, BLE and Classic Bluetooth (BT) for the purpose of establishing proximity awareness in mobile devices. We demonstrate techniques; in the context of a mobile application to provide seamless proximity awareness using the three technologies, with focus on accuracy and operational range. We present the results of our research and experimentation for the purpose of creating a baseline for proximity estimation using the three technologies. We further investigate the viability of using BT as the underlying wireless technology for peer to peer networking on mobile devices and demonstrate techniques that can be applied programmatically for automatic detection of nearby mobile devices.
ItemVisualising the impact of changes to precision grammarsLetcher, Ned ( 2010)The development of precision grammars is an inherently resource intensive process. In this thesis we investigate approaches for providing grammar engineers with greater feedback on the impact of changes made to grammars. We describe two different visualisations which are created by comparing parser output from two different states of the grammar. The first involves the ranking of features found in parser output according to their magnitude of change so as to provide a low-level picture of the affected parts of the grammar. The second involves performing clustering over sentences whose parsability has changed in an attempt to find related groups of changes and accompanying sentences which exemplify each locus of change. These approaches provide complimentary avenues of feedback which can hopefully improve the efficiency of the grammar engineering development process.
ItemImpact of user characteristics on online forum classification tasksLUI, MARCO ( 2009)We develop methods for describing users based on their posts to an online discussion forum. These methods build on existing techniques to describe other aspects of online discussions communities, but the application of these techniques to describing users is novel. We demonstrate the utility of our proposed methods by showing that they are superior to existing methods over distinct thread-level, post-level and user-level classification tasks, utilizing real world datasets. In all cases, we attain statistically significant improvements over baseline results. In post-level classification, we also see statistically significant improvements over state-of-the-art benchmark methods. Our major contributions in this work are • creation of a corpus with user-level annotations • detailed description and analysis of three relevant corpora • implementation of a data model for accessing forum data • implementation of feature extraction techniques • evaluation and analysis of user-level features over classification tasks Our work on preparing corpora and providing extensible implementations of feature extraction will be of particular value to researchers looking to work in this field.