Research Article
Semantic Labeling of User Location Context Based on Phone Usage Features
Figure 3
Classification rates (%) for different methods, using data set #1 and (a) visits, (b) places, and (c) cumulative samples approaches and (d) data set #2 and cumulative samples. The percentage of well-classified samples, that is, cases where the classification result is correct, for each class is given above the bars. The overall percentage of well-classified samples for the classifiers is shown below the bars.
(a) |
(b) |
(c) |
(d) |