Machine Learning of User Attentions in Sensor Data VisualizationReviewed
Keita Fujino, Sozo Inoue, Tom Shibata,
EAI International Conference on Mobile Computing, Applications and Services (MobiCASE)
In this paper, we propose a method to automatically esti- mate important points of large sensor data by collecting users attention points when visualized, and by applying supervised machine learning al- gorithm. For large scale sensor data, it is difficult to find important points just by visualization, because the points are buried in a large scope of visualization. We show the result of the estimation, where the accuracy was over 80% for multiple visualization. We also show the result of re- usability for new type of visualization, which performed still 70-80% of accuracies.