The last few years have marked immense growth in the development of digital twins as developers continue to devise strategies to ensure their devices replicate their physical twin’s actions in a real-time virtual environment. The complexity and predictability of these environments can be the deciding factor for adequately testing a digital twin. As of the last year, a digital twin was in development for a capstone project at Arizona State University: CIA Research Labs - Mechanical Systems in Virtual Environments. The virtual device was initially designed for a fixed environment with known ahead-of-time obstacles. Due to the fact that the device was expected only to be traversing set environments, it was unknown how it would handle being driven in an environment with more randomized and unexpected obstacles. For this paper, the device was test driven in the original and environments with various levels of randomization to see how usable and durable the digital twin is despite only being built for environments with expected object locations. The research allowed the creators of this digital twin, utilizing the results of the trial runs and the number of obstacles unsuccessfully avoided, to understand how reliable the controls of the digital twin are when only trained for fixed terrains

This research paper explores the effects of data variance on the quality of Artificial Intelligence image generation models and the impact on a viewer's perception of the generated images. The study examines how the quality and accuracy of the images produced by these models are influenced by factors such as size, labeling, and format of the training data. The findings suggest that reducing the training dataset size can lead to a decrease in image coherence, indicating that AI models get worse as the training dataset gets smaller. Moreover, the study makes surprising discoveries regarding AI image generation models that are trained on highly varied datasets. In addition, the study involves a survey in which people were asked to rate the subjective realism of the generated images on a scale ranging from 1 to 5 as well as sorting the images into their respective classes. The findings of this study emphasize the importance of considering dataset variance and size as a critical aspect of improving image generation models as well as the implications of using AI technology in the future.

My creative project is an extension of my Computer Science capstone project, a Tamagotchi-style game in which the user takes care of an ocean animal. It focuses specifically on expanding upon two of the project’s design goals: improving user retention and fostering a bond between the user and the virtual character they are taking care of. The project consists of researching Human Computer Interaction principles, selecting an assortment that are most relevant to my project, and integrating them into the design of mechanics for the game. The goal of this project is to demonstrate how integrating HCI design principles into game design can foster new ideas and improve the experience of the game for its users.

Augmented reality offers a unique and innovative way to interact and connect with the natural world through the digital world. In an effort to better facilitate learning, this project makes use of web-based augmented reality. This project employs JavaScript libraries, AR.js and Three.js, to provide an augmented reality experience that better links real-world objects to information in a more digestible format. As well as discusses the many issues with technology and how to work around them and ultimately solve them.

NASA has partnered with multiple colleges, including ASU, on a mission to study an asteroid called Psyche. Psyche is the first asteroid discovered made of metal, mostly iron, that is close enough for us to study and could give insight into what Earth’s core is like. The mission plans and research documents on how the various measurement tools work are not engaging to those without a background in STEM. This serves as inspiration to make a web-based game in order to make the information more engaging to the player. This web-based game will take the user through the Psyche mission going from the assembly of the measurement tools all the way to when the satellite is orbiting the asteroid. The creative project consisted of creating a simulation for a young audience, between ages 10 and 18, to experience what the mission could look like once the satellite is at the Psyche asteroid and what the data collected could mean. The asteroid could have been formed through a process called the dynamo process or it could be a piece of a larger parent body. It could be made mostly of metal or silicates, which will be determined during the mission. These are some of the results that will be generalized and relayed to the player. This creative project includes the four main sections of the orbit phase of the mission in which the users will perform tasks to collect some data in order to see some of the generalized possible results of the study of Psyche. Some of the data collected would be the amount of metal making up the asteroid and figuring out what the gravitational pull is. The first main section will use the magnetometer, the second section will use the multispectral imager, the third section will use X-Band Radio Waves, and the fourth section will use the gamma ray and neutron spectrometer.

2018, Google researchers published the BERT (Bidirectional Encoder Representations from Transformers) model, which has since served as a starting point for hundreds of NLP (Natural Language Processing) related experiments and other derivative models. BERT was trained on masked-language modelling (sentence prediction) but its capabilities extend to more common NLP tasks, such as language inference and text classification. Naralytics is a company that seeks to use natural language in order to be able to categorize users who create text into multiple categories – which is a modified version of classification. However, the text that Naralytics seeks to pull from exceed the maximum token length of 512 tokens that BERT supports – so this report discusses the research towards multiple BERT derivatives that seek to address this problem – and then implements a solution that addresses the multiple concerns that are attached to this kind of model.