This paper is centered on the use of generative adversarial networks (GANs) to convert or generate RGB images from grayscale ones. The primary goal is to create sensible and colorful versions of a set of grayscale images by training a discriminator to recognize failed or generated images and training a generator to attempt to satisfy the discriminator. The network design is described in further detail below; however there are several potential issues that arise including the averaging of a color for certain images such that small details in an image are not assigned unique colors leading to a neutral blend. We attempt to mitigate this issue as much as possible.

The NCAA is changing the current rules and regulations around a student-athlete’s name, image, and likeness. Previously, student-athletes were not allowed to participate in business activities or noninstitutional promotional activities. With the new rule changes, student-athletes will be able to engage in business activities related to their own name, image, and likeness. The goal of the team was to help “prepare athletes to understand and properly navigate the evolving restrictions and guidelines around athlete name, image, and likeness”. In order to accomplish this, the team had to understand the problems student-athletes face with these changing rules and regulations. The team conducted basic market research to identify the problem. The problem discovered was the lack of communication between student-athletes and businesses. In order to verify this problem, the team conducted several interviews with Arizona State University Athletic Department personnel. From the interviews, the team identified that the user is the student-athletes and the buyer is the brands and businesses. Once the problem was verified and the user and buyer were identified, a solution that would best fit the customers was formulated. The solution is a platform that assists student-athletes navigate the changing rules of the NCAA by providing access to a marketplace optimized to working with student-athletes and offering an ease of maintaining relationships between student-athletes and businesses. The solution was validated through meetings with interested brands. The team used the business model and market potential to pitch the business idea to the brands. Finally, the team gained traction by initiating company partnerships.

This paper is centered on the use of generative adversarial networks (GANs) to convert or generate RGB images from grayscale ones. The primary goal is to create sensible and colorful versions of a set of grayscale images by training a discriminator to recognize failed or generated images and training a generator to attempt to satisfy the discriminator. The network design is described in further detail below; however there are several potential issues that arise including the averaging of a color for certain images such that small details in an image are not assigned unique colors leading to a neutral blend. We attempt to mitigate this issue as much as possible.

When examining the average college campus, it becomes obvious that students feel rushed from one place to another as they try to participate in class, clubs, and extracurricular activities. One way that students can feel more comfortable and relaxed around campus is to introduce the aspect of gaming. Studies show that “Moderate videogame play has been found to contribute to emotional stability” (Jones, 2014). This demonstrates that the stress of college can be mitigated by introducing the ability to interact with video games. This same concept has been applied in the workplace, where studies have shown that “Gaming principles such as challenges, competition, rewards and personalization keep employees engaged and learning” (Clark, 2020). This means that if we manage to gamify the college experience, students will be more engaged which will increase and stabilize the retention rate of colleges which utilize this type of experience. Gaming allows students to connect with their peers in a casual environment while also allowing them to find resources around campus and find new places to eat and relax. We plan to gamify the college experience by introducing augmented reality in the form of an app. Augmented reality is “. . . a technology that combines virtual information with the real world” (Chen, 2019). College students will be able to utilize the resources and amenities available to them on campus while completing quests that help them within the application. This demonstrates the ability for video games to engage students using artificial tasks but real actions and experiences which help them feel more connected to campus. Our Founders Lab team has developed and tested an AR application that can be used to connect students with their campus and the resources available to them.

Obesity rates among adults have steadily grown in recent decades all the way up to<br/>42.4% in 2018. This is a 12% increase from the turn of the century (Center for Disease Control<br/>and Prevention, 2021). A major reason for this rise is increased consumption of processed,<br/>high-calorie foods. People eat these foods at a young age and develop bad eating habits that can<br/>last for the rest of their lives. It is essential to intervene early and help adolescents form<br/>balanced, healthy eating habits before bad habits are already formed. Our solution to this<br/>problem is Green Gamers. Green Gamers combines adolescent’s passion for gaming with<br/>healthy eating via in-game rewards for healthy eating. People will be able to purchase healthy<br/>food items, such as a bag of carrots, and on the packaging there will be a QR code. They will<br/>then be able to scan the code on our website, and earn points which will unlock in-game items<br/>and other rewards. Video game rewards act as effective motivators for you people to eat more<br/>healthy foods. After the solution was formulated, a preliminary survey was conducted to<br/>confirm that video game related rewards would inspire children to eat more healthy foods.<br/>Based on those results, we are currently in the process of running a secondary market research<br/>campaign to learn if gift card rewards are a stronger motivator. Our end goal for Green Gamers<br/>would be to partner with large gaming studios and food producers. This would allow us access to<br/>many gaming franchises, so that rewards are available from a wide variety of games: making the<br/>platform appealing to a diverse audience of gamers. Similarly, a relationship with large food<br/>producers would give us the ability to place QR codes on a greater assortment of healthy food<br/>items. Although no relationships with large companies have been forged yet, we plan to utilize<br/>funding to test our concept on small focus groups in schools

Robots are often used in long-duration scenarios, such as on the surface of Mars,where they may need to adapt to environmental changes. Typically, robots have been built specifically for single tasks, such as moving boxes in a warehouse or surveying construction sites. However, there is a modern trend away from human hand-engineering and toward robot learning. To this end, the ideal robot is not engineered,but automatically designed for a specific task. This thesis focuses on robots which learn path-planning algorithms for specific environments. Learning is accomplished via genetic programming. Path-planners are represented as Python code, which is optimized via Pareto evolution. These planners are encouraged to explore curiously and efficiently. This research asks the questions: “How can robots exhibit life-long learning where they adapt to changing environments in a robust way?”, and “How can robots learn to be curious?”.

As threats emerge, change, and grow, the life of a police officer continues to intensify. To help support police training curriculums and police cadets through this critical career juncture, this study proposes a state of the art approach to stress prediction and intervention through wearable devices and machine learning models. As an integral first step of a larger study, the goal of this research is to provide relevant information to machine learning models to formulate a correlation between stress and police officers’ physiological responses on and off on the job. Fitbit devices were leveraged for data collection and were complemented with a custom built Fitbit application, called StressManager, and study dashboard, termed StressWatch. This analysis uses data collected from 15 training cadets at the Phoenix Police Regional Training Academy over a 13 week span. Close collaboration with these participants was essential; the quality of data collection relied on consistent “syncing” and troubleshooting of the Fitbit devices. After the data were collected and cleaned, features related to steps, calories, movement, location, and heart rate were extracted from the Fitbit API and other supplemental resources and passed through to empirically chosen machine learning models. From the results of these models, we formulate that events of increased intensity combined with physiological spikes contribute to the overall stress perception of a police training cadet

The pandemic that hit in 2020 has boosted the growth of online learning that involves the booming of Massive Open Online Course (MOOC). To support this situation, it will be helpful to have tools that can help students in choosing between the different courses and can help instructors to understand what the students need. One of those tools is an online course ratings predictor. Using the predictor, online course instructors can learn the qualities that majority course takers deem as important, and thus they can adjust their lesson plans to fit those qualities. Meanwhile, students will be able to use it to help them in choosing the course to take by comparing the ratings. This research aims to find the best way to predict the rating of online courses using machine learning (ML). To create the ML model, different combinations of the length of the course, the number of materials it contains, the price of the course, the number of students taking the course, the course’s difficulty level, the usage of jargons or technical terms in the course description, the course’s instructors’ rating, the number of reviews the instructors got, and the number of classes the instructors have created on the same platform are used as the inputs. Meanwhile, the output of the model would be the average rating of a course. Data from 350 courses are used for this model, where 280 of them are used for training, 35 for testing, and the last 35 for validation. After trying out different machine learning models, wide neural networks model constantly gives the best training results while the medium tree model gives the best testing results. However, further research needs to be conducted as none of the results are not accurate, with 0.51 R-squared test result for the tree model.