Virtual useR! 2024

The difficulty of open source technology is to make the best use of their limited resources (people and money) to achieve their goals and objectives. When an entity invests resources in a project that is unlikely to benefit the organization, it misses out on possibilities. R programmers and users should be aware of an organization's allocation and investment policies to determine whether the business is well-positioned to maximize its resource allocation. Traditionally, talks about the return on investment (ROI) of IT investments between senior management and IT experts have focused on financial benefits, such as the effects on the organization's budget and finances. To better appreciate and assess nonfinancial benefits, it is advised that they be rendered visible, which includes the implications on mission performance and operational outcomes. To better understand and assess nonfinancial benefits, it is suggested that they be made visible and verifiable utilizing algorithms that convert them into monetary units. In this session, we will find the most significant intellectual and affective benefits that R programming has and yet to be provided to the community.

In the realm of clinical research, a web application known as MINT+ is revolutionizing the process of SDTM automation. At its core, MINT+ utilizes a set of R-packages to power the entire solution. Its intuitive React UI empowers users to create custom SDTM mapping specifications, accommodating diverse study requirements. Leveraging DocumentDB for data storage, MINT+ enables easy metadata sharing and facilitates reuse across studies, significantly reducing workload and improving accuracy. During this session, we will explore the R-based components that power MINT+ and are responsible for data processing and backend processes. The "rmint.sdtm" automates SDTM mappings, "rsaffron.api" serves as the backend API, and "roak" allows customization of mappings. Users can address complex scenarios that often arise in the SDTM mapping creation process, making R packages the preferred choice for overcoming industry challenges. With advanced algorithms, a user-friendly interface, and seamless integration, MINT+ streamlines SDTM creation workflow, greatly reducing the time and effort required.

In marine biology, fish behavior understanding is essential to detect environmental changes induced by climate change or pollution. Fish behaviors can be characterized by their swimming trajectories. In this session I will present how to use a set of R libraries to analyze fish trajectories captured from underwater video. I’ll guide you through every processing step, beginning with data reading, trajectory visualization, feature extraction, model training, and evaluation. I will present how to train an Isolation Forest model for anomaly detection and how to visualize the results.

The use of different Learning Management Systems (LMS) for various objectives has become a key tool in education. A huge volume of student and teacher data is generated by LMS on a daily basis. Transforming this data into relevant information for decision-making is a major challenge due to the complexity of the data structure and the difficulty of summarizing the learning process with registered information. This talk focuses on statistical tools for the evaluation and monitoring of LMS use by students and teachers. First, a web application was developed as a tool that allows monitoring the use of educational platforms in a user-friendly manner. Additionally, statistical learning methods were used to predict students' performance in tests using LMS information as predictors. Challenges such as data structure and size present many hurdles in this project. Most of these challenges are addressed using efficient computational tools at each stage of data analysis. Postgres serves as the SQL engine, data.table is used for data wrangling, and shiny, plotly, and ggplot2 are employed for communication and visualization. Finally, tidymodels and dbart are utilized for predictive models.

The drinking water industry has several models that can be used to predict treatment performance and water quality. Modeling can help with treatment optimization, resiliency, and future planning, but there is no single tool that provides all models. Piecing models together requires great expertise and manual effort. Therefore, water treatment professionals are under-utilizing the wealth of data collected by utilities and published knowledge already available. Tidywater is an open-source R package that aims to make this modeling accessible. Models are added to the package as separate functions so that users have the building blocks to assemble models in any configuration. R and tidyverse provide the data science tools that aid modeling and we’ve found R is easy for engineers to learn. It was important that the package was open-source because of the potential value of the modeling. The industry needs a reliable foundation that more complex tools can be built upon so that drinking water utilities can utilize model outcomes long-term. Our goal is to expand the package so that it is used in teaching and research settings and the number of contributors and models continues to grow.