Filtering by
- All Subjects: artificial intelligence
- Creators: Computer Science and Engineering Program
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?”.
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.
Language has a critical role as a social determinant of health and a source of healthcare disparities. Rhetorical devices are ubiquitous in medicine and are often used to persuade or inform care team members. Rhetorical devices help a healthcare team acknowledge and interpret narratives. For example, metaphors are frequently used as rhetorical devices by patients to describe cancer, including winning or losing a battle, surviving a fight, war, potentially implying that the patient feels helpless like a pawn fighting in a struggle directed by the physician, thus reducing patient autonomy and agency. However, this occidental approach is flawed because it excessively focuses on the individual's agency and marginalizes external factors, such as cultural beliefs and social support (Sontag, 1989). Although there is a large body of research about how the rhetoric of medicine affects patients in the United States, there is a lack of such research about how patient experiences' rhetoric can help increase the understanding of Latino populations' unique social determinants. This creative project aims to analyze the rhetorical differences in the description of disease amongst Latino and American communities, translating to creating an educational module for a Spanish for biomedical sciences class. The objective is to increase future healthcare professionals' ability to understand how the composition of descriptions and medical rhetoric in different mediums of humanities can serve as critical tools to analyze social determinants in Latino healthcare delivery.
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.
Healthcare facilities are essential for any community, and they must stay up-to-date with the latest equipment and technology. They provide necessary resources for keeping populations healthy and safe. In order to provide healthcare services, these healthcare facilities must be adequately equipped with appropriate physical capital as well as software to meet the demands of their patients. Healthcare capital equipment planning involves building up a facility with all it’s equipment and is a part of the healthcare supply chain. Attainia is a healthcare capital equipment planning software used to assist equipment planners in organizing the procurement of equipment for their projects. Attainia has a large amount of data about the capital equipment supply chain through the Attainia equipment catalog. Analysis of this catalog data reveals different patterns in the spending patterns of capital equipment planners as well as trends in the supplier offerings. Since Attainia itself is a software, Attainia’s users have experience with implementing and integrating software into healthcare IT solutions. Their experiences give some insight into the complex nature of software implementations at healthcare facilities. The COVID-19 pandemic has affected healthcare facilities all over the world. Impacting the supply chain and hitting hospitals’ finances, COVID-19 has drastically changed many parts of the healthcare system. This paper will examine some of these ongoing effects from COVID-19 along with analysis on capital equipment planning, supply chain, and healthcare software implementation.
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.
is challenging due to cognitive biases, varying
worker expertise, and varying subjective scales. This
work investigates new ways to determine collective decisions
by prompting users to provide input in multiple
formats. A crowdsourced task is created that aims
to determine ground-truth by collecting information in
two different ways: rankings and numerical estimates.
Results indicate that accurate collective decisions can
be achieved with less people when ordinal and cardinal
information is collected and aggregated together
using consensus-based, multimodal models. We also
show that presenting users with larger problems produces
more valuable ordinal information, and is a more
efficient way to collect an aggregate ranking. As a result,
we suggest input-elicitation to be more widely considered
for future work in crowdsourcing and incorporated
into future platforms to improve accuracy and efficiency.