Sports analytics is a growing field that attempts to showcase interesting aspects of a sport with the use of modern technology and machine learning techniques. This thesis will demonstrate how the NBA has progressed in the past decade by comparing the performance have five teams (SAS, OKC, PHO, MIN, and SAC). It will also provide key insight on what an NBA team should focus on to build an optimized NBA team composition, which will better their performance in the league, which will improve their chances of making into the playoffs. These teams were chosen after conducting extensive analysis on all NBA teams. These five teams were chosen because of the variability in performance (two successful and three less successful teams). Two successful teams, SAS and OKC, and three less successful teams, PHO, MIN, and SAC, were chosen to exemplify the different approaches of teams in the NBA and to distinguish what an NBA team should consider build an optimized team composition to better their performance in the league stage.

The field of biomedical research relies on the knowledge of binding interactions between various proteins of interest to create novel molecular targets for therapeutic purposes. While many of these interactions remain a mystery, knowledge of these properties and interactions could have significant medical applications in terms of understanding cell signaling and immunological defenses. Furthermore, there is evidence that machine learning and peptide microarrays can be used to make reliable predictions of where proteins could interact with each other without the definitive knowledge of the interactions. In this case, a neural network was used to predict the unknown binding interactions of TNFR2 onto LT-ɑ and TRAF2, and PD-L1 onto CD80, based off of the binding data from a sampling of protein-peptide interactions on a microarray. The accuracy and reliability of these predictions would rely on future research to confirm the interactions of these proteins, but the knowledge from these methods and predictions could have a future impact with regards to rational and structure-based drug design.

This paper describes a project involving the optimization of the analysis process of FreeSurfer and ANTS Registration for neuroscience analytics of patients at risk of cognitive decline using Nipype. The paper details the process of discovering more about Nipype, learning to use a supercomputer, and implementing the open-source python code to fit the needs of the research lab. Nipype is a python-based initiative to unify the various software packages used within the neuroscience community for data analysis. This paper also serves as documentation of the steps taken to complete the project so that future students are able to continue the optimization process to result in one cohesive workflow in which data is able to flow through a unified pipeline of analysis in the future.

Machine learning has a near infinite number of applications, of which the potential has yet to have been fully harnessed and realized. This thesis will outline two departments that machine learning can be utilized in, and demonstrate the execution of one methodology in each department. The first department that will be described is self-play in video games, where a neural model will be researched and described that will teach a computer to complete a level of Super Mario World (1990) on its own. The neural model in question was inspired by the academic paper “Evolving Neural Networks through Augmenting Topologies”, which was written by Kenneth O. Stanley and Risto Miikkulainen of University of Texas at Austin. The model that will actually be described is from YouTuber SethBling of the California Institute of Technology. The second department that will be described is cybersecurity, where an algorithm is described from the academic paper “Process Based Volatile Memory Forensics for Ransomware Detection”, written by Asad Arfeen, Muhammad Asim Khan, Obad Zafar, and Usama Ahsan. This algorithm utilizes Python and the Volatility framework to detect malicious software in an infected system.

Financial decisions, which are major life decisions, can often be overly complicated. Day-to-day financial calculations and investment decisions can be time-consuming and prone to human error. Thus, keeping in mind the complicated nature of finance and the heavy dependence on these formulas for decision-making, the need for a comprehensive financial calculator rises. The financial calculator is a set of comprehensive logical formulas that takes user input and provides recommendations along with numerical values. The program uses Python scripting language and is focused on the core logic. The program also uses a variety of finance topics and related concepts.