Click to enlarge

This work explores the use of machine learning algorithms on clinical data to predict dementia in patients. Factors that were taken into consideration were the patient's age, education level, socioeconomic status, mini mental state examination score, estimated total intracranial volume, and normalized whole brain volume, and atlas scaling factor. Multiple models such as logistic regression, random forest classifier, and decision tree classifier were tested with the random forest classifier producing the highest cross validation score of 85%. Furthermore, it was found that the most prominent features for determining dementia were mini mental state examination scores and normalized whole brain volumes.

Click the upper right hand corner to enlarge

This paper returns to the centuries-old discussion of pulsating variable stars as a distance metric, using well-formulated period-luminosity relations (PLR) to find the distance to a single High Amplitude Delta Scuti (HADS) star. We additionally investigate our accuracy compared to GAIA parallax data. Using R-band exposures taken with the Stanford Student Observatory, we have fit the light curve of HADS star SZ Lyncis with Fourier analysis methods and extracted its period for use in a specialized PLR. We report a 20 percent error on a distance of 416pc when compared to GAIA 2020 parallax measurements, and a 4 percent error when compared to GAIA 2018 measurements.

Click to access website

The goal of this project is to compare and contrast the soul samples between two classic hip-hop albums from different generations. Through analyzing "Paid In Full" (1987) by Eric B and Rakim and "To Pimp a Butterfly" (2015) by Kendrick Lamar, this website hopes to highlight the influence of soul in hip hop and how it has changed throughout the years.