Digital Commons Network^™

Improving The Accuracy Of Mobile Touchscreen Qwerty Keyboards, Amanda Kirk

Electronic Theses and Dissertations

In this thesis we explore alternative keyboard layouts in hopes of finding one that increases the accuracy of text input on mobile touchscreen devices. In particular, we investigate if a single swap of 2 keys can significantly improve accuracy on mobile touchscreen QWERTY keyboards. We do so by carefully considering the placement of keys, exploiting a specific vulnerability that occurs within a keyboard layout, namely, that the placement of particular keys next to others may be increasing errors when typing. We simulate the act of typing on a mobile touchscreen QWERTY keyboard, beginning with modeling the typographical errors that can …

A Bi-Encoder Lstm Model For Learning Unstructured Dialogs, Diwanshu Shekhar

Electronic Theses and Dissertations

Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing a Retrieval-based Chatbot systems. This thesis presents a Long Short Term Memory (LSTM) based Recurrent Neural Network architecture that learns unstructured multi-turn dialogs and provides implementation results on the task of selecting the best response from a collection of given responses. Ubuntu Dialog Corpus Version 2 (UDCv2) was used as the corpus for training. Ryan et al. (2015) explored learning models such as TF-IDF (Term Frequency-Inverse Document Frequency), Recurrent Neural Network (RNN) and a Dual Encoder (DE) based on Long …

Developing An Affect-Aware Rear-Projected Robotic Agent, Ali Mollahosseini

Electronic Theses and Dissertations

Social (or Sociable) robots are designed to interact with people in a natural and interpersonal manner. They are becoming an integrated part of our daily lives and have achieved positive outcomes in several applications such as education, health care, quality of life, entertainment, etc. Despite significant progress towards the development of realistic social robotic agents, a number of problems remain to be solved. First, current social robots either lack enough ability to have deep social interaction with human, or they are very expensive to build and maintain. Second, current social robots have yet to reach the full emotional and social …

Studying Facial Expression Recognition And Imitation Ability Of Children With Autism Spectrum Disorder In Interaction With A Social Robot, Farzaneh Askari

Electronic Theses and Dissertations

Children with Autism Spectrum Disorder (ASD) experience limited abilities in recognizing non-verbal elements of social interactions such as facial expressions [1]. They also show deficiencies in imitating facial expressions in social situations. In this Master thesis, we focus on studying the ability of children with ASD in recognizing facial expressions and imitating the expressions using a rear-projected expressive humanoid robot, called Ryan. Recent studies show that social robots such as Ryan have great potential for autism therapy. We designed and developed three studies, first to evaluate the ability of children with ASD in recognizing facial expressions that are presented to …

Motivations, Team Dynamics, Development Practices And How They Impact The Success Of Open Source Software: A Study Of Projects Of Code For America Brigades, Le Chang

Electronic Theses and Dissertations

Open data movement has nurtured the growth of civic open source software (OSS) in the recent decade. This emerging phenomenon has demonstrated a way that a community can collectively utilize technology to solve its problems.

This study is based on software projects in brigades of Code for America, which is a network of organizations that group volunteers to create digital solutions to community problems. In this study, we analyze the software engineering practices of current civic open source software development, participants' motivations and perceptions of the projects, and provide insights on the antecedents of success of the application development.

A …

Algorithmic Music Generation For Pedagogy Of Sight Reading, Ryan Stephen Davis

Electronic Theses and Dissertations

Autodeus is the name of the program that has been developed and was designed to aid guitar students in the attainment and betterment of musical notation sight reading skills. Its primary goal is to provide a very flexible tool that has the ability to generate virtually endless types of sight reading exercises at many various skill levels.

A complimentary 2 year-long comprehensive guitar sight-reading course syllabus can be implemented via Autodeus as it is capable of generating all the necessary exercises. It is able to generate these exercises quickly and efficiently through the use of a back tracking algorithm that …

Predictive Modeling Of Hip Dislocation: Assessment Of Surgical And Patient Factors To Reduce The Occurrence Of Hip Instability And Adverse Clinical Outcomes, Daniel N. Huff

Electronic Theses and Dissertations

Instability and dislocation remain leading indications for revision of primary Total Hip Arthroplasty (THA). Many studies have addressed the links between implant design and propensity for dislocation, however a comprehensive review of the ability of modern THA constructs to protect against joint instability is needed.

Accordingly, the objective of this study is to provide objective data about THA risks to be considered in the treatment algorithm to protect against adverse joint loading conditions and joint instability. Adverse loading conditions were assessed in a population of activities of daily living using data from telemetric hip implant representation in an FE simulation …

Rnn-Based Generation Of Polyphonic Music And Jazz Improvisation, Andrew Hannum

Electronic Theses and Dissertations

This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based recurrent neural network architecture char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.