Introduction to linear regression analysis. ”Induction of decision trees.” Machine learning 1, no. ”ML-KNN: A lazy learning approach to multi-label learning.” Pattern recognition 40, no. ”Support vector machines.” IEEE Intelligent Systems and their applications 13, no. Dumais, Edgar Osuna, John Platt, and Bernhard Scholkopf. ”Automatic estimation of fine terrain models from multiple high-resolution satellite images.” In Image Processing (ICIP), 2009 16th IEEE International Conference on, pp. Champion, Nicolas, Didier Boldo, Marc Pierrot-Deseilligny, and Georges Stamon.These can be combined in order to recommend suitable activities to improve the user’s health condition. Hence at the end of analysis, we will know the weather preference of the user, the kind of roads he prefers to cycle on, the time during which he regularly performs the activity and much more. Other relevant insights can be drawn from the data we collect through Strava, weather, and social media platforms. Because certain cyclists may prefer smooth roads, versus mountain bike riders who prefer dirt roads, we can being to understand user preferences for bicycle travel paths. Understanding rolling resistance for power estimation estimation or buildingĮxercise recommendation systems by user profiling as described in detail in theĪnother avenue of future work is in building recommendation systems for the users to suggest activities. Methods, the decision trees performed the best with an accuracy of 86%.Įstimation of the type of surface can be used for many applications such as Machine learning models such as support vector machines, K-nearest neighbors,Īnd decision trees were used for the classification of the path. Slope in a given path segment, fitting segments of the path, and finding theįirst derivative and the number of points of zero crossings of each segment. This, three methods were adopted, changes in frequency of the direction of Taken by the user has high or low variations in their directional vector, weĬlassify if the user is on a paved road or on an unpaved trail. Using only GPS data from a human powered cyclist. In this work, we use a computationally inexpensive and simple method by
Previous estimatesįor these parameters have used computationally expensive analysis of satellite In the case of human powered transportation, poor roadĬonditions increase the work for the individual to travel. Road conditions affect both machine and human powered modes of