NEURAL NETWORK-ENHANCED STEREOSCOPIC VISUALIZATION

这个子项目是许多研究子项目中利用 资源由NIH/NCRR资助的中心拨款提供。子项目和 调查员(PI)可能从NIH的另一个来源获得了主要资金， 并因此可以在其他清晰的条目中表示。列出的机构是 该中心不一定是调查人员的机构。 物理和自然科学研究产生了大量的高维数据。这不仅产生了分析数据和解释结果的需要，而且还需要开发能够成功处理这些数据的工具和方法。许多都是图形化的，如散点图和直方图，而且大多数一次只能表示两到三个变量。我们的算法通过集成神经网络和可视化技术来解决这些问题，基于记录的维值来映射记录，而不是更常见的记录子集。庞大的数据集和详细的可视化使得这些算法的计算量很大。我们通过扩展算法来解决这个问题，为由大量集群计算机组成的高性能计算环境提供支持。我们使用针对任务分析、可用性评估和使用分析的经验评估来衡量新可视化的有效性，而算法的有效性是通过数据大小和处理数据所需的时间来衡量的。

This subproject is one of many research subprojects utilizing the resources provided by a Center grant funded by NIH/NCRR. The subproject and investigator (PI) may have received primary funding from another NIH source, and thus could be represented in other CRISP entries. The institution listed is for 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.