In 2018, the United States generated 37.4 million more U.S. tons of paper and cardboard material compared to in 1960 (EPA, 2020). As the United States produces a disproportionate amount of packaging waste every year when accounting for population size, it has become increasingly difficult to mitigate waste production, lessen the environmental impact of generating more paperboard materials, and move towards a more ethical circular economy. In efforts to adopt the principles of a green economy, deviate from the linear supply chain model, minimize packaging waste, and encourage more sustainable lifestyles, we developed a business centered around a circular, service based model called Room & Cardboard. Our initiative collects cardboard waste generated in and around the ASU community and repurposes it for dorm-style furniture available for students to rent throughout the school year. Using cardboard, we have built prototypes for two products (desk lamps and shoe racks) that are sturdy, visually pleasing, and recyclable. Our initiative helps to reduce cardboard packaging waste by upcycling cardboard waste into products that will increase the lifespan of the cardboard material. At the end of the product’s life span, in cases of severe damage, we will turn the product into a seed board made with blended cardboard paste that can then be used to plant a succulent we will make available to students to buy as dorm decor. The feedback on our initiative through online surveys and in-person tabling has generated enough traction for Dean Rendell of Barrett, the Honors College at Arizona State University to consider a test-drive of our products in the upcoming Fall semester.

Breast cancer is one of the most common types of cancer worldwide. Early detection and diagnosis are crucial for improving the chances of successful treatment and survival. In this thesis, many different machine learning algorithms were evaluated and compared to predict breast cancer malignancy from diagnostic features extracted from digitized images of breast tissue samples, called fine-needle aspirates. Breast cancer diagnosis typically involves a combination of mammography, ultrasound, and biopsy. However, machine learning algorithms can assist in the detection and diagnosis of breast cancer by analyzing large amounts of data and identifying patterns that may not be discernible to the human eye. By using these algorithms, healthcare professionals can potentially detect breast cancer at an earlier stage, leading to more effective treatment and better patient outcomes. The results showed that the gradient boosting classifier performed the best, achieving an accuracy of 96% on the test set. This indicates that this algorithm can be a useful tool for healthcare professionals in the early detection and diagnosis of breast cancer, potentially leading to improved patient outcomes.

The purpose of this thesis is to contextualise Hindsight, a sustainability-focused historically based city-simulation and resource management game built by the author. The game and game engine were coded from scratch using the C# programming language and the Unity game development suite of tools. The game focuses on the management of the city of London in two time periods, London from 1850 and the other set in 2050. Both versions of the city are divided into 21 zones, each of which can be managed by the player through the construction, upgrading, or destruction of various buildings within the zone. The player must manage both the city’s resources and the resources of the environment upon which the city depends in order to bring about a more sustainable future and bring the 2050-era version of the city back from the brink of environmental devastation. Along the way, the player must address the cultural views of the society they are managing to ensure their reforms will be accepted and can also see those views slowly change over time. The goal of the game is to provide an interactive learning experience for both the historical element of London and the importance of making sustainable choices.

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.