Physical Sciences and Mathematics Commons^™

Lightcraft Previzion In Distance Education, Perry L. Cox

Open Access Theses

Visual Effects has continued to progress at an astonishing rate and green screen technology can be seen in all aspects of the video industry from Hollywood blockbusters down to training videos and distance education.

As video technology has increased, so has the quality and capability of distance education. Purdue University has set itself to be at the forefront of distance education. This study looked to evaluate Purdue's investment in the Lightcraft Technology's Previzion system and its impact on distance education at Purdue. There were 65 initial participants and this study compared the impact of two separate videos on their learning. …

Computational Environment For Modeling And Analysing Network Traffic Behaviour Using The Divide And Recombine Framework, Ashrith Barthur

Open Access Dissertations

There are two essential goals of this research. The first goal is to design and construct a computational environment that is used for studying large and complex datasets in the cybersecurity domain. The second goal is to analyse the Spamhaus blacklist query dataset which includes uncovering the properties of blacklisted hosts and understanding the nature of blacklisted hosts over time.

The analytical environment enables deep analysis of very large and complex datasets by exploiting the divide and recombine framework. The capability to analyse data in depth enables one to go beyond just summary statistics in research. This deep analysis is …

Knowledge Modeling Of Phishing Emails, Courtney Falk

Open Access Dissertations

This dissertation investigates whether or not malicious phishing emails are detected better when a meaningful representation of the email bodies is available. The natural language processing theory of Ontological Semantics Technology is used for its ability to model the knowledge representation present in the email messages. Known good and phishing emails were analyzed and their meaning representations fed into machine learning binary classifiers. Unigram language models of the same emails were used as a baseline for comparing the performance of the meaningful data. The end results show how a binary classifier trained on meaningful data is better at detecting phishing …

Unsupervised Learning Framework For Large-Scale Flight Data Analysis Of Cockpit Human Machine Interaction Issues, Abhishek B. Vaidya

Open Access Theses

As the level of automation within an aircraft increases, the interactions between the pilot and autopilot play a crucial role in its proper operation. Issues with human machine interactions (HMI) have been cited as one of the main causes behind many aviation accidents. Due to the complexity of such interactions, it is challenging to identify all possible situations and develop the necessary contingencies. In this thesis, we propose a data-driven analysis tool to identify potential HMI issues in large-scale Flight Operational Quality Assurance (FOQA) dataset. The proposed tool is developed using a multi-level clustering framework, where a set of basic …

Enhancing The Campus Experience: Helping International Students To Adapt To North American Campus Life, Qiaoying Wang

Open Access Theses

This thesis investigates how culture adaption topic can be applied to a design solution by enhancing international students experience on North American campus. Each year more than half a million international students enroll in American colleges and universities. Many will spend several years on a campus working toward their degree. Most of them arrive with clear academic goals, but they may have no clue what their social lives will be like. In that case, a common phenomenon that most of the international students need to get along with is called “Culture Shock”, which involves culture and academic adapting difficulties, limited …

A Study Of How Chinese Ink Painting Features Can Be Applied To 3d Scenes And Models In Real-Time Rendering, Muning Cao

Open Access Theses

Past research findings addressed mature techniques for non-photorealistic rendering. However, research findings indicate that there is little information dealing with efficient methods to simulate Chinese ink painting features in rendering 3D scenes. Considering that Chinese ink painting has achieved many worldwide awards, the potential to effectively and automatically develop 3D animations and games in this style indicates a need for the development of appropriate technology for the future market.

The goal of this research is about rendering 3D meshes in a Chinese ink painting style which is both appealing and realistic. Specifically, how can the output image appear similar to …

Integration Of Z-Depth In Compositing, Kayla Steckel

Open Access Theses

It is important for video compositors to be able to complete their jobs quickly and efficiently. One of the tasks they might encounter is to insert assets such as characters into a 3D rendered environment that has depth information embedded into the image sequence. Currently, a plug-in that facilitates this task (Depth Matte®) functions by looking at the depth information of the layer it's applied to and showing or hiding pixels of that layer. In this plug-in, the Z-Depth used is locked to the layer the plug-in is applied. This research focuses on comparing Depth Matte® to a custom-made plug-in …

Online Naturalization: Evolving Roles In Online Knowledge Production Communities, Jeremy David Foote

Open Access Theses

Web-based peer production communities, like Wikipedia and open source software, have created digital artifacts of growing cultural, financial, and technological importance. Understanding how and why people choose to join these communities, and why they eventually leave them, is therefore an important topic.

We take all of the edit data from six years of activity on the online genealogy wiki WeRelate, and create monthly snapshots of behavior and interaction networks for all 9,570 users who edited the site. We use machine learning to cluster these behavioral snapshots into four "behavioral roles". We identify one of these roles as being indicative of …

Senescence: An Aging Based Character Simulation Framework, Suren Deepak Rajasekaran

Open Access Theses

The 'Senescence' framework is a character simulation plug-in for Maya that can be used for rigging and skinning muscle deformer based humanoid characters with support for aging. The framework was developed using Python, Maya Embedded Language and PyQt. The main targeted users for this framework are the Character Technical Directors, Technical Artists, Riggers and Animators from the production pipeline of Visual Effects Studios. The characters that were simulated using 'Senescence' were studied using a survey to understand how well the intended age was perceived by the audience. The results of the survey could not reject one of our null hypotheses …

Mispronunciation Detection For Language Learning And Speech Recognition Adaptation, Zhenhao Ge

Open Access Dissertations

The areas of "mispronunciation detection" (or "accent detection" more specifically) within the speech recognition community are receiving increased attention now. Two application areas, namely language learning and speech recognition adaptation, are largely driving this research interest and are the focal points of this work.

There are a number of Computer Aided Language Learning (CALL) systems with Computer Aided Pronunciation Training (CAPT) techniques that have been developed. In this thesis, a new HMM-based text-dependent mispronunciation system is introduced using text Adaptive Frequency Cepstral Coefficients (AFCCs). It is shown that this system outperforms the conventional HMM method based on Mel Frequency Cepstral …