BackgroundThe way we look at data has a great impact on how we can understand it, particularly when the data is related to health and wellness. Due to the increased use of self-tracking devices and the ongoing shift towards preventive medicine, better understanding of our health data is an important part of improving the general welfare of the citizens. Electronic Health Records, self-tracking devices and mobile applications provide a rich variety of data but it often becomes difficult to understand. We implemented the hFigures library inspired on the hGraph visualization with additional improvements. The purpose of the library is to provide a visual representation of the evolution of health measurements in a complete and useful manner.ResultsWe researched the usefulness and usability of the library by building an application for health data visualization in a health coaching program. We performed a user evaluation with Heuristic Evaluation, Controlled User Testing and Usability Questionnaires. In the Heuristics Evaluation the average response was 6.3 out of 7 points and the Cognitive Walkthrough done by usability experts indicated no design or mismatch errors. In the CSUQ usability test the system obtained an average score of 6.13 out of 7, and in the ASQ usability test the overall satisfaction score was 6.64 out of 7.ConclusionsWe developed hFigures, an open source library for visualizing a complete, accurate and normalized graphical representation of health data. The idea is based on the concept of the hGraph but it provides additional key features, including a comparison of multiple health measurements over time. We conducted a usability evaluation of the library as a key component of an application for health and wellness monitoring. The results indicate that the data visualization library was helpful in assisting users in understanding health data and its evolution over time.Electronic supplementary materialThe online version of this article (doi:10.1186/s12911-016-0275-6) contains supplementary material, which is available to authorized users.

No abstract

This paper studies the prediction of head pose from still images, and summarizes the outcome of a recently organized competition, where the task was to predict the yaw and pitch angles of an image dataset with 2790 samples with known angles. The competition received 292 entries from 52 participants, the best ones clearly exceeding the state-of-the-art accuracy. In this paper, we present the key methodologies behind selected top methods, summarize their prediction accuracy and compare with the current state of the art.