This subproject is one of many research subprojects utilizing theresources provided by a Center grant funded by NIH/NCRR. The subproject andinvestigator (PI) may have received primary funding from another NIH source,and thus could be represented in other CRISP entries. The institution listed isfor the Center, which is not necessarily the institution for the investigator. Physical and natural science research generates large amounts of high-dimensional data. This not only creates the need for the analysis of the data and interpretation of results, but also the need for the development of tools and methods that can successfully handle such data. Many are graphical in nature, such as scatter plots and histograms, and most can only represent two or three variables at a time. Our algorithms address such issues through integration of neural-networks and visualization techniques, mapping records based on their dimensional values, instead of the more common subset of records. Large data sets and detailed visualizations make these algorithms computationally intense. We address this by extending the algorithms to provide support for high-performance computational environments consisting of a large number of clustered computers. We measure the effectiveness of new visualizations using empirical evaluation targeted at task analysis, usability evaluation and usage analysis while the effectiveness of algorithms is measured in data size and in time required to process the data.
Showing the most recent 10 out of 179 publications
