Collaborating with the Arizona Simulation Technology and Education Center, Indiana University School of Nursing and East Carolina University we will build and test a clinical decision support tool (CDSS) to improve methadone (AMP: Advancing Methadone Prescribing) and AI-assisted patient simulations for primary care medical residents and advanced practice nursing students.

VR of Historical Places - Shared Churches after the 30-years war For students who have completed Virtual Reality and simulation game classes with tools such as the Unity Engine. A global team of scholars is collecting information including 360 degree (photosphere) images of simultaneum mixtum, shared Catholic and Protestant churches from 16th century and later. We are looking for students to explore methods of making this information available in VR as well as WWW environments. End users should be able to explore an interior space in VR and point to teleport to a new location or bring up additional information such as images, text, and audio describing objects or spaces in the scene. https://sharedchurches.arizona.edu/

Biological field stations (BFS) are used for a hundred years or more to conduct short-term and long-term studies of all aspects of the natural environment. Access to the data from prior scientific studies allow scientists to leverage new data to build new knowledge. According to the Global Database of BFS there are over 1200 BSF globally. However there is no comprehensive inventory of the data produced at these stations. Some of this data exists in long-lived repositories. Some of the less documented data is referenced in journal articles. This project will use named entity recognition and other text processing methods to discover the previously difficult to find data, aka dark data, to develop a global catalog of ecological data sets.

VR of Historical Places - Shared Churches after the 30-years war For students who have completed Virtual Reality and simulation game classes with tools such as the Unity Engine. A global team of scholars is collecting information including 360 degree (photosphere) images of simultaneum mixtum, shared Catholic and Protestant churches from 16th century and later. We are looking for students to explore methods of making this information available in VR as well as WWW environments. End users should be able to explore an interior space in VR and point to teleport to a new location or bring up additional information such as images, text, and audio describing objects or spaces in the scene. https://sharedchurches.arizona.edu/

Work with Prof Daly on the open textbook Humans R Social Media including textbook development and an open governance plan with researchers from CU Boulder.

A fully funded Ph.D. position is available for candidates interested in the interdisciplinary research project titled "Generalized Stochastic Nash Equilibrium Framework: Theory, Computation, and Application.", seeks a candidate with a strong background in mathematics, computer science, or related fields to develop theoretical frameworks, computational tools, and real-world applications for generalized stochastic Nash equilibria. The successful candidate will receive a competitive stipend and full tuition coverage.

Using Machine Learning to Disambiguate Software Entity Mentions in PMC We have a disambiguation problem for software mentions in scientific literature. There is no "gold standard dataset" so we have to manually annotate a training set to evaluate our model. Data: We are using the Chan Zuckerburg software citation mentions. Students' roles: We need students to create a corpus of annotated software mentions to assist with disambiguating the software entities. We will then work with a CS professor to train a disambiguation model for the software entities. Learning outcomes: data science applications, research methods, time management Data Analysis: Once disambiguated, the software entities can be analyze. We can ask: Where in a paper does Software get Cited in the Scientific literature?

Project Title: Mapping the Global "Supply Chain" of Genomics Research Datasets Datasets are produced by scientists all over the world, who deposit data to international research data repositories. The datasets are then (re)used to pursue scientific knowledge, develop scientific innovations, and shape the allocation of resources to support further discovery. However: the infrastructures for producing and sharing data are skewed toward western nations who possess the resources and historical cyberinfrastructure (e.g. computing systems, data repositories) to produce and share research data. Drawing from a novel source of data, the 'big metadata' from GenBank, this project describes the volume of data produced by geographic regions and analyzes the international distribution of labor on datasets in biomedical research and genomics. We also take a critical perspective in this project to focus on power and influence of gatekeepers and industry actors on shaping the production and diffusion of knowledge in data-intensive science. Data Collection: Scrape data from BioSamples. Find out if papers on BioSample and BioProject are already linked.If not: Scrape BioSamples and BioProject data (using Selenium?) for as many GenBank records as possible. Store BioSamples and BioProject Data on server; link to GenBank records if possible. Data Analysis: Calculate to what extent is there alignment between the genetic sample country of origin and the authors of the associated publication? Analyze the location of the sample from 1992-2021 have the locations changed? RQs (based on student interest): 1. Who are the industry vs academia vs etc collaborators on these? 2. Genomics has become a commercialized affair. The supply chain includes industry as well as academics. Who funds the projects with high misalignment? Use NIH ExPoRter data. Who is the funder of biosamples? 3. Who is the PI on the grant of the funding? (See NIH ExPorteR data) Data: GenBank, NCBI Taxonomy, S&T capacity index Skills/tools preferred: python, R, linux, statistics, data visualization Skills you will learn: Social network analysis, visualization in R

iSchool Capstone or Directed Study Topic Analysis and Financial Modeling of Federal Grant Programs How have federal funding patterns for research changed over the past 25 years? How many funds have gone to each topic? What topics are likely to be funded next and at what levels? How successful have the funding programs been in terms of papers published and data produced per unit investment? We have previously analyzed data from a couple of programs for just a few years at the National Science Foundation. We would like to scale in terms of programs at NSF and other agencies and look further back in time. Our initial analysis used Latent Dirichlet Allocation (LDA), a Bayesian network to do analysis. We’d like to try out other topic analysis techniques such as Doc2Vec, Bert, correlated topic models, and others for these data sets. Other students have moved the tools to a supercomputing network but more could be done to enable larger models. In this capstone project, you could analyze different data from NSF or data from NASA or the Department of Energy. You could work on different algorithms or visualization techniques. The final project depends on your interests and skills.

Ecological Image Processing and Analysis iSchool Capstone or Directed Study Professor Heidorn has a couple of datasets and problems that may be appropriate for the MS capstone projects. The data selection process has largely been worked out and most data cleaning tools have been developed. This should allow you to advance a little faster in the single-semester course. While Dr. Heidorn can help you to understand the data and the types of problems that can be solved with the data, each student is expected to develop their own unique capstone project that will demonstrate the skills that they have when approaching graduation from our program. This is different from an internship because you need to develop your own project and project report. Should any of this work eventually lead to publication, students will be appropriately acknowledged. Professor Heidorn has a couple of datasets and problems that may be appropriate for the MS capstone projects. The data selection process has largely been worked out and most data cleaning tools have been developed. This should allow you to advance a little faster in the single-semester course. While Dr. Heidorn can help you to understand the data and the types of problems that can be solved with the data, each student is expected to develop their own unique capstone project that will demonstrate the skills that they have when approaching graduation from our program. This is different from an internship because you need to develop your own project and project report. Should any of this work eventually lead to publication, students will be appropriately acknowledged. We wish to be able to automatically track plant phenophase from camera images. In this capstone project, you would develop tools to improve this process. This might be through statistics, supervised or unsupervised machine learning, data integration, and/or visualization techniques. In the face of climate change, plants and animals are having varied success in adapting to changing environments. One way that this can be studied is through the evaluation of changes in phenophase. These changes can have cascading impacts on ecosystems. For example, the timing of when leaves form on trees drives the populations of insects that eat the leaves. In temperate environments, many birds time their migration back to the region in the spring to coincide with increasing insect populations. If the leaves emerge sooner, the insects may increase their numbers sooner. Unfortunately, the birds that time their migration on hours of sunlight in a day may not migrate back north in time to eat the insects and have sufficient nutrition to feed their young. Traditionally data on the phenophase for the trees have been collected by human observers. However, this is labor intensive and there are not enough people collecting data. About 5 years ago a consortium of researchers and government officials started placing cameras on towers and at ground level at hundreds of locations around the country and the world in the Phenocam project. The cameras take photographs every 5-15 minutes 24 hours a day in visible light and infra-red. There is a growing database of hundreds of thousands of images that can be used in this capstone project. The USA National Phenology Network provides a database of human observations of phenophase for many but not all of the camera locations. Developing image analysis tools is challenging. Most machine learning methods for images have been for human-built landscapes and not the natural environment. While there are many images their depth in time is only about 5 years so deep learning methods that need a lot of data do not work in a straightforward manner. In this capstone project, you would build tools to identify changes in phenophase from the images. You would need to develop your own approach to some subproblems in this space and report on that.