There were three projects:
Enhancing physical performance through personalized training and assistive devices
H-CORE areas: humans and analytics
Faculty Mentor: Dr. Jessica Avilés
The goal of this project is to examine performance-based metrics that can guide training progression for assistive technology use (e.g., exoskeleton devices) and balance training to individualize training. This data-driven approach will leverage wearable technology to detect small but meaningful changes in an individual’s physical performance and increase training complexity to promote motor learning among individuals learning to use a new wearable technology device or when improving their balance to recover from a trip. Students will have hands-on experiencing conducting human subjects research to investigate how someone’s individual characteristics such as physical fitness, age, gender, and cognitive fitness should be considered in training to reduce injury of a worker and improve performance. Students will also assist with data analysis of common biomechanical outcome measures such as body position, muscle activation, and strength to determine the success of individualized training.
Optimizing worker allocation policies in high-cognitive workload environments
H-CORE areas: humans, systems, and analytics
Faculty Mentor: Dr. Tuğçe Işık
In collaboration with Clemson Vehicle Assembly Center (CVAC) and an industry partner, BMW Manufacturing Co., LLC, this project will implement two phases of research to investigate optimal worker allocation policies in environments with high cognitive workloads: (i) hypotheses development, experimentation, and data analysis, (ii) model development and analysis. In the first phase, the students will conduct controlled experiments at CVAC (located near Greenville, SC) and collect data on the impact of high cognitive workloads on worker performance. CVAC features a fully reconfigurable mock assembly line which will be reconfigured to match the real assembly line at the BMW Manufacturing plant. Manufacturing workers with automotive assembly experience will be recruited as study participants. In the second phase, the students will analyze the data collected through the experiments to develop and parametrize optimization models. The models will be analyzed to develop ideas to improve workflow, reduce worker errors, and increase job satisfaction among manufacturing workers.
Optimizing community access to local parks
H-CORE areas: humans and systems
Faculty Mentor: Dr. Emily Tucker
Access is focused on ensuring that everyone in the community is able to use resources (e.g., parks). Students will learn about person-centered concepts of access and the challenges of expressing them mathematically. They will evaluate different indices available as proxies for park access. The first goal of the project will be to study current park access through these different lenses of access and the corresponding limitations. The second goal will be to develop a decision-recommendation model (an optimization model) to recommend areas to invest in new parks via imperfect indices of access. Students will learn to consider how to appropriately develop and use data-driven recommendations and develop GIS-based visualizations. Students will get to meet with park experts and consider the real-world impacts of strategic optimization models.
