PROJECT TITLE :

The Data Context Map: Fusing Data and Attributes into a Unified Display

ABSTRACT:

Various strategies have been described that permit the visualization of the data matrix. However all suffer from a standard downside - observing the information points within the context of the attributes is either not possible or inaccurate. We tend to describe a method that enables these sorts of comprehensive layouts. We tend to achieve it by combining two similarity matrices typically utilized in isolation - the matrix encoding the similarity of the attributes and the matrix encoding the similarity of the data points. This combined matrix yields 2 of the four submatrices needed for a full multi-dimensional scaling kind layout. The remaining 2 submatrices are obtained by making a fused similarity matrix - one that measures the similarity of the information points with respect to the attributes, and vice versa. The resulting layout places the information objects in direct context of the attributes and hence we have a tendency to call it the info context map. It permits users to simultaneously appreciate (1) the similarity of information objects, (2) the similarity of attributes in the precise scope of the collection of data objects, and (three) the relationships of knowledge objects with attributes and vice versa. The contextual layout conjointly permits data regions to be segmented and labeled based on the locations of the attributes. This permits, for instance, the map's application in selection tasks where users ask for to spot one or more data objects that best fit a sure configuration of factors, using the map to visually balance the tradeoffs.