Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.

The following paper will explore The Analysis of Sorority Interactions & Engagement During an Event for the purpose of Barrett, The Honors College Thesis Creative Project. My topic will be explored as a Creative Project with this document being written documentation supporting and explaining the creative project along with research, reason & findings from the event. The event itself stands for the majority of this creative project as that is where this written report gained & sourced its survey results from. An analysis of the event taking place and the attendees themselves created data into the ever-changing event industry. Specifically, a creative project like this shows the importance of events in everyday life especially the need for events post-COVID-19 restrictions.