➡ Check it out here
One in five adults living in the United States use fitness trackers and health-related apps on a daily basis. With this continuously growing statistic arise ethical concerns of big data collection, and how fitness data can be used. This project will explore and show the impacts of releasing personal data to health and exercise apps. With an artificial intelligence program, students will be able to choose what physical health data is accessible and then see what other medical information can be determined from these small pieces of recorded data. Physical health data will include calorie intake, heart rate, step count, distance walked, minutes of activity, and minutes of rest including possible other factors. Predictive analytics will be used in combination with connection to a medical database in the Python programming language for specific medical predictions according to small pieces of information. This tool will allow students to see how health and wellness data can be used, giving them the opportunity to understand and further discuss the ethics of releasing personal information to fitness trackers and health-related applications.
The purpose of this tool is to specifically aid students in having complex conversations about data collection and the ethics surrounding it. Specifically, this tool focuses on the impact of releasing personal health and wellness information. Artificial intelligence is a quickly growing field, raising ethical debates daily. In the case of healthcare, AI is beginning to be used for both diagnostics, and personalized medicine. However, with this growing field, arise concerns related to privacy, informed consent, and patient autonomy. This tool will give students insight into how personal health data can, and often is used, allowing them to form opinions about the ethics surrounding this field. In an artificial intelligence course, one of the most important ideas is to integrate the teaching of ethics, and allow students to form their own opinions about the use and growth of AI. This program will aid in incorporating ethics into courses at Allegheny College.
➡ Check it out here
Continuous integration allows developers to automate operations such as linting, code execution and testing. GitHub Actions provide a new and progressive way to automate, customize and execute continuous integration directly in your GitHub repository. This feature of GitHub is gaining in popularity; however, this is occurring with a lack of awareness and understanding of its versatility. There is an overwhelming plethora of jobs that can be run by GitHub Actions, and many individuals struggle with where to start or how to correctly implement a GitHub Actions configuration which meets their objectives. As a result, there are many developers who are implementing the same workflow files with the same five to ten jobs being run. A tool that analyzes GitHub Actions workflow files could prevent this, leading to an enhanced understanding and improved correctness of continuous integration configurations.
ActionTraction accepts as input one or more GitHub repositories. An analysis of the input results in a ranging output, that is specified by the user. These outputs include metrics of a single workflow: how a file changes over time, modifications of code lines, operating systems used, linting warnings and logic errors. After analyzing multiple repositories, ActionTraction will list the most popular jobs associated with top GitHub projects and programming languages. This analysis will surface suitable GitHub Actions that developers can use in specific projects. Storing this information will allow ActionTraction to make recommendations of jobs to be run for emerging workflow files based on the contents of a GitHub repository.
Due to ActionTraction’s versatility, it will be beneficial to developers, researchers, and faculty. It will allow developers to understand the evolution of their individual workflow files, as well as the trends that exist within industry and education. Gaining knowledge about existing workflow files shows GitHub Actions users where to start, and improve their continuous integration configurations, leading to increased productivity. Researchers can use the results from ActionTraction’s analysis of multiple repositories to understand relationships between GitHub projects, the trends associated with workflow configurations, and the implications of this information. Faculty could also use ActionTraction to aid in the creation and maintenance of their workflow files associated with GitHub Classroom projects and assignments. When this tool detects the use of a specific programming language it can recommend appropriate actions for accomplishing certain tasks, and highlights syntax errors in GitHub Actions files, reducing the time spent on continuous integration configurations. This tool could also provide insight into how workflow files change through the course of a class, as well as how they are being modified throughout multiple semesters of teaching.
Internships and Employment
📈 Data Analyst - Partner Applications | Overstock.com
- Analyzed data and performed user research to create personas for over 2,000 Overstock.com partners in 3 major research projects
- Quantified partner interactions, measuring platform engagement, revenue sales, partner satisfaction, product categories and overall success for partners on Overstock.com
- Research informed the Partner Applications and Partner Experience departments to further improve platforms for partner growth and development
💻 Student Software Engineer | Allegheny College
- Implemented Vigor, a predictive wellness tool, which utilizes 5 datasets, 3 classification algorithms and 1 web application platform to assess the health of a user
- Funded by the Mozilla Foundation’s Responsible Computer Science Challenge to aid in implementing ethics into Allegheny College courses
👩🏫 Technical Leader/Teaching Assistant | Allegheny College
- Assisted and advised students in 4 different classes of Allegheny College’s Computer Science and Biology departments
- Performed tasks relating to teaching coding basics, programming best practices, code review, computer science principles, data visualization, hypothesis development, and statistical analysis
⚙ Technical Skills
- Development Environments and Text Editors: Microsoft Visual Studio Code, Atom, R Studio, Linux, Jupyter Notebooks
- Machine Learning: Scikit-Learn, TensorFlow, Spacy, OpenCV
- Web Development: StreamLit, Netlify
- Developer Tools: Pytest, Docker, Poetry, pip, pipenv
- Data Science: Numpy, Pandas, Ggplot2, Dplyr
🗣 Collaborative Skills
- Active Listening
- Time management
⌨ Programming Language Proficiency
- Python: 5 years
- Java: 4 years
- R: 2 years
- SQL 1 year