Matching Items (4)
Filtering by
- All Subjects: Machine Learning
Description
In this project, the use of deep neural networks for the process of selecting actions to execute within an environment to achieve a goal is explored. Scenarios like this are common in crafting based games such as Terraria or Minecraft. Goals in these environments have recursive sub-goal dependencies which form a dependency tree. An agent operating within these environments have access to low amounts of data about the environment before interacting with it, so it is crucial that this agent is able to effectively utilize a tree of dependencies and its environmental surroundings to make judgements about which sub-goals are most efficient to pursue at any point in time. A successful agent aims to minimizes cost when completing a given goal. A deep neural network in combination with Q-learning techniques was employed to act as the agent in this environment. This agent consistently performed better than agents using alternate models (models that used dependency tree heuristics or human-like approaches to make sub-goal oriented choices), with an average performance advantage of 33.86% (with a standard deviation of 14.69%) over the best alternate agent. This shows that machine learning techniques can be consistently employed to make goal-oriented choices within an environment with recursive sub-goal dependencies and low amounts of pre-known information.
ContributorsKoleber, Derek (Author) / Acuna, Ruben (Thesis director) / Bansal, Ajay (Committee member) / W.P. Carey School of Business (Contributor) / Software Engineering (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
An increasingly sedentary population in the United States, specifically with adolescents, is putting youth at risk of future health related trauma and disease. This single-case design study, Walking Intervention Through Text Messaging for Adolescents (WalkIT-A), was used to intervene with a 12-year old, physically inactive male, in an attempt to test the efficacy of a 12-week physical activity program that may help reduce health risks by increasing number of steps walked per day. The components of the intervention consisted of a FitBit Zip pedometer, physical activity education, text messages, monetary incentives, and goal setting that adapted personally to the participant. Mean step count increased by 30% from baseline (mean = 3603 [sd = 1983]) to intervention (mean = 4693 [sd = 2112]); then increased slightly by 6.7% from intervention to withdrawal (mean = 5009 [sd = 2152]). Mean "very active minutes" increased by 45% from baseline (mean = 8.8 [sd = 8.9]) to intervention (mean = 12.8 [sd = 9.6]); then increased by 61.7% from intervention to withdrawal (mean = 20.7 [sd = 8.4]). Weight, BMI, and blood pressure all increased modestly from pre to post. Cardiovascular fitness (estimated VO2 max) improved by 12.5% from pre (25.5ml*kg-1*min-1) to post (28.7ml*kg-1*min-1). The intervention appeared to have a delayed and residual effect on the participant's daily steps and very active minutes. Although the idealistic ABA pattern did not occur, and the participant did not meet the target of 11,500 daily steps, a positive trend toward that target behavior in the latter 1/3rd of the intervention was observed. Results suggest the need for an extended intervention over a longer period of time and customized even further to the participant.
ContributorsLamb, Nicholas Reid (Author) / Adams, Marc (Thesis director) / Ainsworth, Barbara (Committee member) / Barrett, The Honors College (Contributor) / School of Nutrition and Health Promotion (Contributor)
Created2014-12
Description
While developing and maintaining a connection between a brand and a customer has always been in the forefront of marketers' agendas, it has become an even more pressing goal as digital trends in marketing surface. Although the idea of using rewards to foster consumer-brand connection has been around for decades, marketers are still struggling to optimize the benefits. How can marketers use rewards to better connect with their customers? Are there certain types of rewards that are more effective than others? Are certain rewards more effective when being implemented under brands of a certain personality type? In a society that values connection and relationship, marketers cannot lose their ability to appreciate customers under digital constraints and to marketplace competition. Through a field study and scenario-based experiment, we explore how and why low conditional vs. high conditional rewards influence consumer-brand connection and the role brand personality plays.
ContributorsBryant, Kelly Amber (Co-author) / Bauer, Madelaine (Co-author) / Lisjak, Monika (Thesis director) / Samper, Adriana (Committee member) / W.P. Carey School of Business (Contributor) / Department of Marketing (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Abstract: The Ultimate Fighting Championship or UFC as it is commonly known, was founded in 1993 and has quickly built itself into the world's foremost authority on all things MMA (mixed martial arts) related. With pay-per-view and cable television deals in hand, the UFC has become a huge competitor in the sports market, rivaling the popularity of boxing for almost a decade. As with most other sports, the UFC has seen an influx of various analytics and data science over the past five to seven years. We see this revolution in football with the broadcast first down markers, basketball with tracking player movement, and baseball with locating pitches for strikes and balls, and now the UFC has partnered with statistics company Fightmetric, to provide in-depth statistical analysis of its fights. ESPN has their win probability metrics, and statistical predictive modeling has begun to spread throughout sports. All these stats were made to showcase the information about a fighter that one wouldn't typically know, giving insight into how the fight might go. But, can these fights be predicted? Based off of the research of prior individuals and combining the thought processes of relevant research into other sports leagues, I sought to use the arsenal of statistical analyses done by Fightmetric, along with the official UFC fighter database to answer the question of whether UFC fights could be predicted. Specifically, by using only data that would be known about a fighter prior to stepping into the cage, could I predict with any degree of certainty who was going to win the fight?
ContributorsMoorman, Taylor D. (Author) / Simon, Alan (Thesis director) / Simon, Phil (Committee member) / W.P. Carey School of Business (Contributor) / Department of Information Systems (Contributor) / Department of Management and Entrepreneurship (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05