These MATLAB-ready .mat data files contain pixel data for the Boston remote sensing testbed. This is the same data that is provided with Classer. However, all the Classer preprocessing scripts have been run, so the mat file is ready for use with ARTMAP in MATLAB without any further effort.
In both files, ground-truth label indexes are decremented by 1 relative to those in Classer, since no ground-truth points are mapped to class 1 ("miss"), and it's convenient to have unlabeled pixels have label "-1". Also, the first 3 input features are removed, as they're only for visualization, and the last feature is removed, since it is 0 for all points.
Default ARTMAP 2
Default ARTMAP combines winner-take-all category node activation during training, distributed activation during testing, and a set of default parameter values that define a ready-to-use, general-purpose neural network system ... Article Details
Boston Remote Sensing Testbed
The Boston remote sensing testbed describes a remotely sensed area (data from a Landsat 7 Thematic Mapper satellite), 360 pixels wide by 600 pixels in height, or 5.4 km x 9 km in area. Data Details: 41 dimensions, 8 classes ... Dataset Details