We study the problem of detecting and analyzing change in physical activity patterns. More specifically, we introduce a framework called Physical Activity Change Detection, or PACD, to determine if a significant change exists between two windows of time series physical activity data sampled from a wearable fitness device.
Our PACD approach can also detect changes in smart home-detected behavior data that occur as a result of health events, such as starting cancer treatment.
We are investigating changes exhibited in physical performance during inpatient rehabilitation. The majority of patients we recruit for our study are recovering from a stroke, brain injury, or spinal cord injury. We use wearable inertial sensors to collect data from patients as they perform physical therapy. From the sensor signals, we compute over 40 different metrics related to gait and movement. After one week of inpatient rehabilitation, we quantitatively compare these metrics at both the individual and group levels. To do this, we use statistical measures such as the standardized mean difference effect size and the reliable change index. Our results provide insight about which metrics exhibit the highest changes and how each individual is progressing.
For this project, we explored the predictive utility of features derived from wearable sensors and patient medical records for predicting future patient functioning. To do this, we utilized several machine learning techniques. For feature selection we utilized recursive feature elimination, for oversampling we implemented a variant of synthetic minority oversampling technique (SMOTE) for regression, and we trained several models with cross validation. Our results indicated a statistically significant improvement in prediction accuracy when training with a combination of wearable sensor and medical record derived features over medical record features alone.
Our research with wearable technology for rehabilitation is interesting from a computer science and bioengineering perspective, but what is its utility for clinicians? Are therapists interested in the outputs of our algorithms? Would they even use wearable technology during physical therapy? These are a few of the questions we are trying to answer by interviewing physical therapists. We hope the results of these one-on-one interviews will provide insight for the research community regarding clinical adoption of the wearable technology and directions for future work.
In our latest research endeavor, we are collecting movement data from wearable sensors continuously during inpatient rehabilitation. More details to come.
We are looking into useful and intuitive ways to present data derived from wearable sensors. Researchers, physical therapists, caregivers, and patients are all potential users of wearable technology. We are investigating visualizations of data collected and computed from wearables that are easy to understand for each one of these potential viewers. I am working on building a browser-based Visualization Dashboard for our wearable sensor metrics and associated visualizations (currently only the metric "Gait Cycle Duration" has plots uploaded on the server).
As digital/computer design complexity continues to increase at a substantial rate, new innovative tools that increase observability and analysis are required. This research project introduced a novel technique to address these requirements by real-time data abstraction in a highly visual, interactive environment. This was a project I worked on during my first year of graduate school with Dr. Delgado-Frias and later during the Summer of 2013 with Doug Boyce at an internship at Intel Corp.
Some (but not all!) students who are interested in computer science are also avid gamers. Whether that be video games, board games, sports, etc., most of like games in some form. While teaching an introduction to C programming course during Summer of 2014, I undertook an experiment to bring games into the programming lab. I was curious to see if it increased participation and student enjoyment in the course material. C programming can be bit dry at times, and I found this was an excellent approach to increasing enthusiasm in programming.
Please see our CougarQuest "Learn to Code!" workshop page for project ideas. The GIF to the left is from AdaFruit and is an example of the hardware we are using to inspire middle school students to pursue computer science. Please check out my Light Array frame designer for helping the students design their animations!