Master of Science in Engineering (MSEgr), Wright State University, 2014, Industrial and Human Factors Engineering

Due to an abundance of data and dynamic nature of tasks, challenges with information retrieval in surveillance and target identification tasks have risen in today's Intelligence, Surveillance, and Reconnaissance (ISR) community. In this study, two variables, Area of Coverage and Amount of Activity (AOC/ACT), are manipulated to study their effects on the number of Watch Windows an observer can monitor. This research describes the analyst's task model, and explains how the level of AOC/ACT and number of Watch Windows affects the analyst's cognitive load. Results showed a significant difference in performance and physiological indicators of workload between high AOC/ACT conditions and low AOC/ACT conditions. Confidence levels were higher with low AOC/ACT conditions, while NASA-TLX ratings decreased. A linear correlation was exhibited between the number of Watch Windows and the number of fixations. The results show that these variables can be manipulated in tasking to maintain appropriate levels of cognitive workload.

Committee: Mary Fendley Ph.D. (Advisor); Subhashini Ganapathy Ph.D. (Committee Member); Alan Boydstun Ph.D. (Committee Member) Subjects: Engineering

MDes, University of Cincinnati, 2010, Design, Architecture, Art and Planning : Design

Current challenges in visual communication design demand an understanding beyond the semantic and semiotic elements of visual language. Today, interaction between humans and visual information is a relevant issue because of the complexity of information and artificial systems that create difficult human use. This implies that design needs a deeper understanding of how human differences and needs affect the performance of visual communication design in interaction. Contemporary approaches such as universal design or human-centered design intend to provide designers with methods and tools to improve interaction between design objects and human beings. Often, the design principles of these approaches try to cover broad human requirements, but not particular human differences and needs relevant to communication. This thesis is an exploratory research that studies visual intelligence and mood as two of the major hypothesized human differences for visual communication design. Qualitative and quantitative evidence shows that visual intelligence predicts adequate interaction patterns and qualitative observations of mood states indicate that high tense arousal and anger/ frustration states negatively affect the interaction with visual information. In addition, data suggest that mood change might be negatively associated with interaction experience, showing that mood effects have the potential to be used as a measurement of interaction design quality. Limitations and implications of these findings are discussed for further design research.

Committee: Paul Zender MFA (Committee Chair); Renee Seward (Committee Member); Gerald Matthews PhD (Committee Member) Subjects: Design

Master of Science, Miami University, 2024, Computer Science

Causal maps are graphical models that are well-understood in small scales. When created through a participatory modeling process, they become a strong asset in decision making. Furthermore, those who participate in the modeling process may seek to understand the problem from various perspectives. However, as causal maps increase in size, the information they contain becomes clouded, which results in the map being unusable. In this thesis, we transform causal maps into various mediums to improve the usability and accessibility of large causal models; our proposed algorithms can also be applied to small-scale causal maps. In particular, we transform causal maps into meaningful paragraphs using GPT and network traversal algorithms to attain full-coverage of the map. Then, we compare automatic text summarization models with graph reduction algorithms to reduce the amount of text to a more approachable size. Finally, we combine our algorithms into a visual analytics environment to provide details-on-demand for the user by displaying the summarized text, and interacting with summaries to display the detailed text, causal map, and even generate images in an appropriate manner. We hope this research provides more tools for decision-makers and allows modelers to give back to participants the final result of their work.

Committee: Philippe Giabbanelli (Advisor); Daniela Inclezan (Committee Member); Garrett Goodman (Committee Member) Subjects: Computer Science

MFA, Kent State University, 0, College of Communication and Information / School of Visual Communication Design

This thesis investigates the practices of female designers affected by Attention Deficit Hyperactivity Disorder (ADHD). The inadequacy of research on female designers with ADHD in academia propels the study. Women with ADHD are often left undiagnosed until later in life due to their distinct presentation, while men tend to be diagnosed during childhood. Significant life events, such as pursuing higher education or conducting thesis research, may lead a woman to pursue a diagnosis. This thesis seeks to employ design research methodologies to examine the intersection between female designers and the late diagnosis of ADHD. Historically, ADHD research has been largely focused on hyperactive boys, leading to gender inequality in the discourse on ADHD. However, women and girls tend to exhibit different ADHD symptoms. This research aims to foster dialogue on the combination of female designers and ADHD, with a view to appreciating their unique perspectives and impact on design and, at the same time, advocating for their recognition as an asset to any team. Additionally, this research contributes to developing AI and virtual assistants that provide essential external structures for female designers with ADHD by proposing a conceptual application that utilizes research results and AI to create a virtual assistant to aid female designers with ADHD in reaching their full potential.

Committee: Jessica Barness (Advisor); Aoife Mooney (Committee Member); Ken Visocky O'Grady (Committee Member) Subjects: Artificial Intelligence; Design; Higher Education; Psychology; Womens Studies

Doctor of Philosophy (PhD), Wright State University, 2020, Computer Science and Engineering PhD

Deep Neural Networks (DNNs) are powerful tools blossomed in a variety of successful real-life applications. While the performance of DNNs is outstanding, their opaque nature raises a growing concern in the community, causing suspicions on the reliability and trustworthiness of decisions made by DNNs. In order to release such concerns and towards building reliable deep learning systems, research efforts are actively made in diverse aspects such as model interpretation, model fairness and bias, adversarial attacks and defenses, and so on. In this dissertation, we focus on the research topic of DNN interpretations for visual intelligence, aiming to unfold the black-box and provide explanations for visual intelligence tasks in a human-understandable way. We first conduct a categorized literature review, systematically introducing the realm of explainable deep learning. Following the review, two specific problems are tackled, explanations of Convolutions Neural Networks (CNNs), which relates the CNN decisions with input concepts, and interpretability of multi-model interactions, where an explainable model is built to solve a visual inference task. Visualization techniques are leveraged to depict the intermediate hidden states of CNNs and attention mechanisms are utilized to build an instinct explainable model. Towards increasing the trustworthiness of DNNs, a certainty measurement for decisions is also proposed as an extensive exploration of this study. To show how the introduced techniques holistically realize a contribution to interpretable and reliable deep neural networks for visual intelligence, further experiments and analyses are conducted for visual entailment task at the end of this dissertation.

Committee: Derek Doran Ph.D. (Advisor); Michael Raymer Ph.D. (Committee Member); Tanvi Banerjee Ph.D. (Committee Member); Pascal Hitzler Ph.D. (Committee Member) Subjects: Artificial Intelligence

Doctor of Philosophy, The Ohio State University, 2019, Computer Science and Engineering

Recent advancements in the field of computational sciences and high-performance computing have enabled scientists to design high-resolution computational models to simulate various real-world physical phenomenon. In order to gain key scientific insights about the underlying phenomena it is important to analyze and visualize the output data produced by such simulations. However, large-scale scientific simulations often produce output data whose size can range from a few hundred gigabytes to the scale of terabytes or even petabytes. Analyzing and visualizing such large-scale simulation data is not trivial. Moreover, scientific datasets are often multifaceted (multivariate, multi-run, multi-resolution, etc.), which can introduce additional complexities to the analyses and visualization activities. This dissertation addresses three broad categories of data analysis and visualization challenges: (i) multivariate distribution-based data summarization, (ii) uncertain analysis in ensemble simulation data, and (iii) simulation parameter analysis and exploration. We proposed statistical and machine learning-based approaches to overcome these challenges. A common strategy to deal with large-scale simulation data is to partition the simulation domain and create data summaries in the form of statistical probability distributions. Instead of storing high-resolution raw data, storing the compact statistical data summaries results in reduced storage overhead and alleviated I/O bottleneck issues. However, for multivariate simulation data using standard multivariate distributions for creating data summaries is not feasible. Therefore, we proposed a flexible copula-based multivariate distribution modeling strategy to create multivariate data summaries during simulation execution time (i.e, in-situ data modeling). The resulting data summaries can be subsequently used to perform scalable post-hoc analysis and visualization. In many cases, scientists execute their simulations mu (open full item for complete abstract)

Committee: Han-Wei Shen (Advisor); Rephael Wenger (Committee Member); Yusu Wang (Committee Member) Subjects: Computer Science; Statistics

Doctor of Philosophy, The Ohio State University, 1957, Graduate School

Committee: Not Provided (Other) Subjects: Psychology

Master of Science in Industrial and Human Factors Engineering (MSIHE) , Wright State University, 2015, Industrial and Human Factors Engineering

In the ISR domain, time-critical decision-making and dealing with multiple information feeds places high demands on the human. When designing aids and tools, the decision maker must be taken into account. This research looks toward designing a decision aid based the personality type of the operator. The BFI is used to determine the impact of personality and decision aid type (graphical vs. textual) on performance. Results show Openness and Agreeableness to be the strongest single factors for decision aid impact on performance. A model was also developed to show how the human takes the information and relates it to a mental model for use in making an identification. This can assist the ISR community in developing an adaptive aiding system to reduce the cycle time in the decision making process and have the greatest impact on performance.

Committee: Mary Fendley Ph.D. (Advisor); Richard Warren Ph.D. (Committee Member); Pratik Parikh Ph.D. (Committee Member) Subjects: Engineering; Industrial Engineering; Information Technology; Personality Psychology