Physical Sciences and Mathematics Commons^™

How Reliable Are Shap Values When Trying To Explain Machine Learning Models, Jason Lawless

Senior Honors Theses and Projects

With the rapid growth and application of machine learning and artificial intelligence models that can not be understood by humans, there is a growing movement calling for an increase in interpretability. There are numerous methods that attempt to explain these models that vary drastically in the process of evaluating models. In this paper, we investigate a local post-hoc method called SHAP. SHAP utilizes Shapley values from game theory to attribute an importance value to each input in a model at each datapoint. Shapley values can require significant computation time, especially as the number of inputs increases. In order to shorten …

A Literary Analysis Of The Oort Cloud: Summarising Its History And Proposing A Mission To Image Oort Cloud Objects, Avital Keeley

Senior Honors Theses and Projects

The Oort Cloud was hypothesised in 1950 but has lost popularity as a research topic. This literary research summarises the most notable articles and simulations on the Oort Cloud with an analysis on the outdated simulations and assumptions. Finally, this research conflates the hypothesised values of Oort Cloud parameters to calculate the required specifications of instrumentation needed to image an Oort Cloud Object, and a rough budget is proposed of $5 million to launch a 35 km interferometer.

Applying Machine Learning To Categorize Distinct Categories Of Network Traffic, Isaac M. Dunham

Senior Honors Theses and Projects

The recent rapid growth of the field of data science has made available to all fields opportunities to leverage machine learning. Computer network traffic classification has traditionally been performed using static, pre-written rules that are easily made ineffective if changes, legitimate or not, are made to the applications or protocols underlying a particular category of network traffic. This paper explores the problem of network traffic classification and analyzes the viability of having the process performed using a multitude of classical machine learning techniques against significant statistical similarities between classes of network traffic as opposed to traditional static traffic identifiers.

To …

Soil And Compost Tea: A New Restoration Technique?, Carol E. Day

Master's Theses and Doctoral Dissertations

Historically, prairie restorations have lacked the plant diversity seen in remnant prairies. Most restoration practices focus on reestablishing the plant community but overlook the soil microbial community even though microbes are critical to habitat functioning. Developing techniques that increase soil microbes in prairie restorations is critical to ensuring diverse restored habitats. We compared how microbial communities differed between remnant and restored prairie sites. We also investigated if soil and compost teas could be used to reintroduce microbes to restored prairie soil and if the teas affected native plant establishment. We found significant differences in the levels of bacterial taxa between …