Barrett, The Honors College Thesis/Creative Project Collection

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.

Drylands, though one of the largest biomes, are also one of the most understudied biomes on the planet. This leaves scientists with limited understanding of unique life forms that have adapted to live in these arid environments. One such life form is the hypolithic microbial community; these are autotrophic cyanobacteria colonies that can be found on the underside of translucent rocks in deserts. With the light that filters through the rock above them, the microbes can photosynthesize and fix carbon from the atmosphere into the soil. In this study I looked at hypolith-like rock distribution in the Namib Desert by using image recognition software. I trained a Mask R-CNN network to detect quartz rock in images from the Gobabeb site. When the method was analyzed using the entire data set, the distribution of rock sizes between the manual annotations and the network predictions was not similar. When evaluating rock sizes smaller than 0.56 cm2 the method showed statistical significance in support of being a promising data collection method. With more training and corrective effort on the network, this method shows promise to be an accurate and novel way to collect data efficiently in dryland research.

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?”.

Artificial Intelligence’s facial recognition programs are inherently racially biased. The programs are not necessarily created with the intent to disproportionately impact marginalized communities, but through their data mining process of learning, they can become biased as the data they use may train them to think in a biased manner. Biased data is difficult to spot as the programming field is homogeneous and this issue reflects underlying societal biases. Facial recognition programs do not identify minorities at the same rate as their Caucasian counterparts leading to false positives in identifications and an increase of run-ins with the law. AI does not have the ability to role-reverse judge as a human does and therefore its use should be limited until a more equitable program is developed and thoroughly tested.

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.

Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage their carbohydrate counting. This early model has a 68.3% accuracy of identifying 101 different food classes. A more refined model in future work could be deployed into a mobile application to identify food the user is about to consume and log it for easier carbohydrate counting.

The purpose of this paper is to discuss the history of artificial intelligence (AI) and its future implications in the healthcare industry. Utilizing information from research and medical journals, this paper will examine the foundations of AI and the people and events that influenced its development. Further, the various subsets of AI and its use in contemporary life will be discussed. While the technological evolution of AI will be discussed, this paper is not a technical treatise on the inner workings of AI software and technology, rather, it is a basic history of the development of AI and its respective subsets, and a look at current and potential future applications of AI. This information will be applied to the healthcare industry to discuss the history of AI in this field, detailing how AI was developed to find innovative solutions to complex medical problems. Finally, future prospects of AI in the medical industry will be discussed, explaining potential applications of this technology as well as various challenges and implications.