In this Barrett Honors Thesis, I developed a model to quantify the complexity of Sankey diagrams, which are a type of visualization technique that shows flow between groups. To do this, I created a carefully controlled dataset of synthetic Sankey diagrams of varying sizes as study stimuli. Then, a pair of online crowdsourced user studies were conducted and analyzed. User performance for Sankey diagrams of varying size and features (number of groups, number of timesteps, and number of flow crossings) were algorithmically modeled as a formula to quantify the complexity of these diagrams. Model accuracy was measured based on the performance of users in the second crowdsourced study. The results of my experiment conclusively demonstrates that the algorithmic complexity formula I created closely models the visual complexity of the Sankey Diagrams in the dataset.
The goal of this thesis project was to develop a digital, quantitative assessment of executive functioning skills and problem solving abilities. This assessment was intended to serve as a relative measure of executive functions and problem solving abilities rather than a diagnosis; the main purpose was to identify areas for improvement and provide individuals with an understanding of their current ability levels. To achieve this goal, we developed a web-based assessment through Unity that used gamelike modifications of Flanker, Antisaccade, Embedded Images, Raven’s Matrices, and Color / Order Memory tasks. Participants were invited to access the assessment at www.ExecutiveFunctionLevel.com to complete the assessment and their results were analyzed. The findings of this project indicate that these tasks accurately represent executive functioning skills, the Flanker Effect is present in the collected data, and there is a notable correlation between each of the REFLEX challenges. In conclusion, we successfully developed a short, gamelike, online assessment of executive functioning and problem solving abilities. Future developments of REFLEX could look into immediate scoring, developing a mobile application, and externally validating the results.
The goal of this thesis project was to develop a digital, quantitative assessment of executive functioning skills and problem solving abilities. This assessment was intended to serve as a relative measure of executive functions and problem solving abilities rather than a diagnosis; the main purpose was to identify areas for improvement and provide individuals with an understanding of their current ability levels. To achieve this goal, we developed a web-based assessment through Unity that used gamelike modifications of Flanker, Antisaccade, Embedded Images, Raven’s Matrices, and Color / Order Memory tasks. Participants were invited to access the assessment at www.ExecutiveFunctionLevel.com to complete the assessment and their results were analyzed. The findings of this project indicate that these tasks accurately represent executive functioning skills, the Flanker Effect is present in the collected data, and there is a notable correlation between each of the REFLEX challenges. In conclusion, we successfully developed a short, gamelike, online assessment of executive functioning and problem solving abilities. Future developments of REFLEX could look into immediate scoring, developing a mobile application, and externally validating the results.
Aphasia is an impairment that affects many different aspects of language and makes it more difficult for a person to communicate with those around them. Treatment for aphasia is often administered by a speech-language pathologist in a clinical setting, but researchers have recently begun exploring the potential of virtual reality (VR) interventions. VR provides an immersive environment and can allow multiple users to interact with digitized content. This exploratory paper proposes the design of a VR rehabilitation game –called Pact– for adults with aphasia that aims to improve the word-finding and picture-naming abilities of users to improve communication skills. Additionally, a study is proposed that will assess how well Pact improves the word-finding and picture-naming abilities of users when it is used in conjunction with speech therapy. If the results of the study show an increase in word-finding and picture-naming scores compared to the control group (patients receiving traditional speech therapy alone), the results would indicate that Pact can achieve its goal of promoting improvement in these domains. There is a further need to examine VR interventions for aphasia, particularly with larger sample sizes that explore the gains associated with or design issues associated with multi-user VR programs.
Data integration involves the reconciliation of data from diverse data sources in order to obtain a unified data repository, upon which an end user such as a data analyst can run analytics sessions to explore the data and obtain useful insights. Supervised Machine Learning (ML) for data integration tasks such as ontology (schema) or entity (instance) matching requires several training examples in terms of manually curated, pre-labeled matching and non-matching schema concept or entity pairs which are hard to obtain. On similar lines, an analytics system without predictive capabilities about the impending workload can incur huge querying latencies, while leaving the onus of understanding the underlying database schema and writing a meaningful query at every step during a data exploration session on the user. In this dissertation, I will describe the human-in-the-loop Machine Learning (ML) systems that I have built towards data integration and predictive analytics. I alleviate the need for extensive prior labeling by utilizing active learning (AL) for dataintegration. In each AL iteration, I detect the unlabeled entity or schema concept pairs that would strengthen the ML classifier and selectively query the human oracle for such labels in a budgeted fashion. Thus, I make use of human assistance for ML-based data integration. On the other hand, when the human is an end user exploring data through Online Analytical Processing (OLAP) queries, my goal is to pro-actively assist the human by predicting the top-K next queries that s/he is likely to be interested in. I will describe my proposed SQL-predictor, a Business Intelligence (BI) query predictor and a geospatial query cardinality estimator with an emphasis on schema abstraction, query representation and how I adapt the ML models for these tasks. For each system, I will discuss the evaluation metrics and how the proposed systems compare to the state-of-the-art baselines on multiple datasets and query workloads.