Surface Type Estimation from GPS Tracked Bicycle Activities

Road conditions affect both machine and human powered modes of transportation. In the case of human powered transportation, poor road conditions increase the work for the individual to travel. Previous estimates for these parameters have used computationally expensive analysis of satellite images. In this work, we use a computationally inexpensive and simple method by using only GPS data from a human powered cyclist. By estimating if the road taken by the user has high or low variations in their directional vector, we classify if the user is on a paved road or on an unpaved trail. In order to do this, three methods were adopted, changes in frequency of the direction of slope in a given path segment, fitting segments of the path, and finding the first derivative and the number of points of zero crossings of each segment. Machine learning models such as support vector machines, K-nearest neighbors, and decision trees were used for the classification of the path. We show in our methods, the decision trees performed the best with an accuracy of 86\%. Estimation of the type of surface can be used for many applications such as understanding rolling resistance for power estimation estimation or building exercise recommendation systems by user profiling as described in detail in the paper.

Cross-Modal Health State Estimation

Individuals create and consume more diverse data about themselves today than any time in history. Sources of this data include wearable devices, images, social media, geospatial information and more. A tremendous opportunity rests within cross-modal data analysis that leverages existing domain knowledge methods to understand and guide human health. Especially in chronic diseases, current medical practice uses a combination of sparse hospital based biological metrics (blood tests, expensive imaging, etc.) to understand the evolving health status of an individual. Future health systems must integrate data created at the individual level to better understand health status perpetually, especially in a cybernetic framework. In this work we fuse multiple user created and open source data streams along with established biomedical domain knowledge to give two types of quantitative state estimates of cardiovascular health. First, we use wearable devices to calculate cardiorespiratory fitness (CRF), a known quantitative leading predictor of heart disease which is not routinely collected in clinical settings. Second, we estimate inherent genetic traits, living environmental risks, circadian rhythm, and biological metrics from a diverse dataset. Our experimental results on 24 subjects demonstrate how multi-modal data can provide personalized health insight. Understanding the dynamic nature of health status will pave the way for better health based recommendation engines, better clinical decision making and positive lifestyle changes.