Matching Items (6)
Filtering by

Clear all filters

135971-Thumbnail Image.png

NBA PlayerTrack: A Mobile Application Providing NBA Fans with Statistics, News, and Information about their Favorite Players

Description
Current popular NBA mobile applications do little to provide information about the NBA's players, usually providing limited statistical information or news and completely ignoring players' presence on social media. For fans, especially fans who are unfamiliar with the NBA, finding this information by themselves can be a daunting task, one…

Current popular NBA mobile applications do little to provide information about the NBA's players, usually providing limited statistical information or news and completely ignoring players' presence on social media. For fans, especially fans who are unfamiliar with the NBA, finding this information by themselves can be a daunting task, one which requires extensive knowledge about how the NBA provides media related to its players. NBA PlayerTrack has been designed to centralize player information from a variety of media streams, making it easier for fans to learn about and stay up-to-date with players and enabling fan discussion about those players and the NBA in general. By providing a variety of references to the locations of player information, NBA PlayerTrack also serves as a tool for learning about how and where the NBA presents player-related media, allowing fans to more easily locate information they desire as they become more invested in the NBA.
ContributorsSethia, Sumbhav (Author) / Davulcu, Hasan (Thesis director) / Faucon, Philippe (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
147743-Thumbnail Image.png

Evaluating STAT5 Signature in Recurrent Glioblastoma

Description

Background: Recurrent glioblastoma (GBM) is resistant to available treatments and continued growth of the tumor is inevitable; this process is facilitated by the expression of genes regulated by the Signal Transducer and Activator of Transcription (STAT) family of transcription factors, namely STAT5, active in the invasive rim of GBM tumors.…

Background: Recurrent glioblastoma (GBM) is resistant to available treatments and continued growth of the tumor is inevitable; this process is facilitated by the expression of genes regulated by the Signal Transducer and Activator of Transcription (STAT) family of transcription factors, namely STAT5, active in the invasive rim of GBM tumors. Currently, there are no targeted therapies for recurrent GBM that increase the overall patient survival rate. This study aims to analyze the differential expression of genes regulated by STAT5 between primary and recurrent GBM.<br/>Methods: Analysis of whole exome and RNA sequencing were performed on matched bulk primary and multiple recurrent tumor samples from GBM patients who received the current standard care to determine significant changes in gene expression of STAT3/5 targets. <br/>Results: Statistical analysis reveals a decrease in Synaptotagmin 2 (SYT2) and Pleckstrin Homology Domain Containing A3 (PLEKHA3) at recurrence, previously identified as potential STAT5 targets. <br/>Conclusions: To get a better understanding of the roles of STAT5 in GBM recurrence, their downstream effects need to be better understood. The transcriptomic program initiated by STAT5 activation is distinct from that of STAT3 activation. The roles of STAT5 target genes in GBM are poorly characterized, so further research should focus on understanding the effects of altered expression of these genes as they relate to STAT3/5 in GBM recurrence.
ContributorsPennett, Maya E (Author) / Martin, Thomas W. (Thesis director) / Tran, Nhan L. (Committee member) / Blomquist, Mylan (Committee member) / College of Integrative Sciences and Arts (Contributor) / Barrett, The Honors College (Contributor)
Created2021-05

Sports Analytics & Formula One: The Impact of Data Science & Analytics on Motorsports

Description

Sports analytics refers to the implementation of data science and analytics techniques within the sports industry. Several sports analysts and team managers have utilized analytical tools to boost overall team and player performance, often through the analysis of historical data. One of the most common techniques employed in sports analytics…

Sports analytics refers to the implementation of data science and analytics techniques within the sports industry. Several sports analysts and team managers have utilized analytical tools to boost overall team and player performance, often through the analysis of historical data. One of the most common techniques employed in sports analytics is that of data mining–the extensive practice of analyzing data in order to extract and deliver insights and findings. Data mining projects are frequently guided with the six-step Cross Industry Standard Process for Data Mining (CRISP-DM) framework. One such sport that has extensively used data science and analytics, and data mining specifically, is that of Formula One (F1). Given the sports’ reliance on technology, race engineers working for F1 constructors often develop statistical models analyzing historical race performance to derive insight of drivers’ success. For the purposes of this project, the perspective of a race engineer working for the F1 constructor McLaren was considered. As the constructor is seeking to gain a competitive advantage for the upcoming F1 season, race performance data concerning previous seasons was collected and analyzed as part of a larger data mining project utilizing the CRISP-DM framework. Statistical models, such as linear regression and random forest, were developed to predict the number of points scored by McLaren racers and the variables most strongly contributed to such scored points. The final results point to specific lap times having to be aimed for as the most important variable in determining the number of points gained, although specific locations also seem prone to McLaren race success. These results in turn will be utilized to develop race strategies for the upcoming season to ensure McLaren has high efficiency against its competitors.
ContributorsImam, Amir (Author) / Simon, Alan (Thesis director) / Sha, Xiqing (Committee member) / Barrett, The Honors College (Contributor) / Department of Information Systems (Contributor)
Created2023-05

A Graph-Based Machine Learning Approach to Realistic Traffic Volume Generation

Description
In this work, we explore the potential for realistic and accurate generation of hourly traffic volume with machine learning (ML), using the ground-truth data of Manhattan road segments collected by the New York State Department of Transportation (NYSDOT). Specifically, we address the following question– can we develop a ML algorithm…

In this work, we explore the potential for realistic and accurate generation of hourly traffic volume with machine learning (ML), using the ground-truth data of Manhattan road segments collected by the New York State Department of Transportation (NYSDOT). Specifically, we address the following question– can we develop a ML algorithm that generalizes the existing NYSDOT data to all road segments in Manhattan?– by introducing a supervised learning task of multi-output regression, where ML algorithms use road segment attributes to predict hourly traffic volume. We consider four ML algorithms– K-Nearest Neighbors, Decision Tree, Random Forest, and Neural Network– and hyperparameter tune by evaluating the performances of each algorithm with 10-fold cross validation. Ultimately, we conclude that neural networks are the best-performing models and require the least amount of testing time. Lastly, we provide insight into the quantification of “trustworthiness” in a model, followed by brief discussions on interpreting model performance, suggesting potential project improvements, and identifying the biggest takeaways. Overall, we hope our work can serve as an effective baseline for realistic traffic volume generation, and open new directions in the processes of supervised dataset generation and ML algorithm design.
ContributorsOtstot, Kyle (Author) / De Luca, Gennaro (Thesis director) / Chen, Yinong (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2022-05
132329-Thumbnail Image.png

Pay or Play: Austria and Germany Versus America. Examining Differences In Employment Benefit Preferences and Their Effects on Employees

Description
Differences between cultures have been (and continue to be) examined by researchers all over the world. Prominent studies performed by organizations such as GLOBE and Hofstede have created a foundation for our understanding of how culture affects business in different countries. They also inspired our study, which investigates how employment…

Differences between cultures have been (and continue to be) examined by researchers all over the world. Prominent studies performed by organizations such as GLOBE and Hofstede have created a foundation for our understanding of how culture affects business in different countries. They also inspired our study, which investigates how employment benefits vary in different cultures. We examined the difference in employee benefit preference of Austria and Germany compared to America and how that affects their perception of the organization. Specifically, we studied how employees in those countries would react to an increase in wage or an increase in vacation time. Each participant read a hypothetical scenario in which they received one of the two benefits. The alternative benefit was not disclosed to them. After reading about the reward, they were asked various questions about the company. These questions gauged their belief in the ability of the organization, their benevolence toward the organization, their perception of the integrity of the organization, their trust in the organization, their turnover intentions, and their obligation felt towards the organization.
Two of the six variables tested yielded statistically significant results after we performed a univariate analysis of variance test on each of the variables. The two variables that yielded statistically significant results were belief in the integrity of the organization and benevolence toward the organization. Americans expressed more benevolence and belief in the integrity of their organization when they received more vacation time, while Europeans exhibited the opposite reaction (to a lesser degree). These results could provide insight to companies that are looking to strengthen company culture or increase motivation of employees. The variables with non-significant results could be attributed to globalization, limitations of our study, or the concept of scarcity.
ContributorsMackey, Henry Aloysius (Author) / Baer, Mike (Thesis director) / Hom, Peter (Committee member) / Dean, W.P. Carey School of Business (Contributor) / Department of Management and Entrepreneurship (Contributor) / Department of Information Systems (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
131311-Thumbnail Image.png

Predicting Outcome of a Pitch Given the Type of Pitch for any Baseball Scenario

Description
This thesis serves as a baseline for the potential for prediction through machine learning (ML) in baseball. Hopefully, it also will serve as motivation for future work to expand and reach the potential of sabermetrics, advanced Statcast data and machine learning. The problem this thesis attempts to solve is predicting…

This thesis serves as a baseline for the potential for prediction through machine learning (ML) in baseball. Hopefully, it also will serve as motivation for future work to expand and reach the potential of sabermetrics, advanced Statcast data and machine learning. The problem this thesis attempts to solve is predicting the outcome of a pitch. Given proper pitch data and situational data, is it possible to predict the result or outcome of a pitch? The result or outcome refers to the specific outcome of a pitch, beyond ball or strike, but if the hitter puts the ball in play for a double, this thesis shows how I attempted to predict that type of outcome. Before diving into my methods, I take a deep look into sabermetrics, advanced statistics and the history of the two in Major League Baseball. After this, I describe my implemented machine learning experiment. First, I found a dataset that is suitable for training a pitch prediction model, I then analyzed the features and used some feature engineering to select a set of 16 features, and finally, I trained and tested a pair of ML models on the data. I used a decision tree classifier and random forest classifier to test the data. I attempted to us a long short-term memory to improve my score, but came up short. Each classifier performed at around 60% accuracy. I also experimented using a neural network approach with a long short-term memory (LSTM) model, but this approach requires more feature engineering to beat the simpler classifiers. In this thesis, I show examples of five hitters that I test the models on and the accuracy for each hitter. This work shows promise that advanced classification models (likely requiring more feature engineering) can provide even better prediction outcomes, perhaps with 70% accuracy or higher! There is much potential for future work and to improve on this thesis, mainly through the proper construction of a neural network, more in-depth feature analysis/selection/extraction, and data visualization.
ContributorsGoodman, Avi (Author) / Bryan, Chris (Thesis director) / Hsiao, Sharon (Committee member) / Computer Science and Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2020-05