MARCH/APRIL 2003 (Vol. 5, No. 2) pp. 12-13
1521-9615/03/$31.00 © 2003 IEEE
Published by the IEEE Computer Society
Published by the IEEE Computer Society
Guest Editors' Introduction: High-Dimensional Data Acquisition, Computing, and Visualization
PDFs Require Adobe Acrobat
Today, more complex data is generated and collected than ever before in human history. This avalanche creates opportunities and information as well as difficulties and challenges. Many people and places are dedicated to data acquisition, computing, and visualization, and there is a great need for sharing information and approaches. We called for a special issue of papers in CiSE to investigate and study creative methods and systems in receiving, processing, and understanding high-dimensional data. The response was so overwhelming that we had to divide the theme into two separate issues—part II will appear later this year.
The issue you hold in your hands aims to address the challenges in handling and understanding high-dimensional data in different research and application areas, featuring visual clustering, materials visualization, time-varying volume rendering, and an access and analysis server. Our intention was to bring together different research and applications in processing and visualizing high-dimensional data so as to foster more insight among this fast-growing community. The topics span innovative approaches and systems for general multidimensional data reduction, clustering, and visualization to specific applications in materials science, Earth science, and medical imaging. We believe that you will find the articles in this issue informative, valuable, and rewarding.
"Using Projections to Visually Cluster High-Dimensional Data" by Alexander Hinneburg, Daniel Keim, and Markus Wawryniuk proposes a new approach to clustering in high-dimensional data sets. They implement this approach in a system called High-Dimensional Eye (HD-Eye). Their method combines the strengths of an advanced automatic clustering algorithm with new visualization techniques. Their experimental evaluation shows that the combination of automatic and visual techniques significantly improves the effectiveness of the data mining process and achieves a better understanding of the results.
"Large Multidimensional Data Visualization for Materials Science" by Ashish Sharma, Rajiv K. Kalia, Aiichiro Nakano, and Priya Vashishta presents creative methods for understanding material processes such as fracture and hypervelocity impact. How does a crack propagate in a composite material? How does a high-speed projectile interact with its target? How can we use this knowledge to make materials with high fracture toughness and impact damage resistance? This article describes a system that can visualize very large data sets and provide materials scientist with the key to such questions.
"Visualizing Time-Varying Volume Data" by Kwan-Liu Ma describes novel approaches for encoding and rendering time-varying, multivariate volume data. Current scientific computing technologies enable accurate numerical modeling of many physical and chemical processes in both their spatial and temporal domains. An increasingly challenging problem is how to effectively explore and understand the resulting time-varying volume data that is large in space, time, and variable domain. How to reduce the storage requirement of a data set without removing fine features is thus the focus of time-varying data visualization research. The article also identifies and discusses emerging trends in time-varying data visualization research and their potential effects on the scientific research community.
"A Distributed Enhanced Server for Multidimensional Scientific Data" by Ruixin Yang, Menas Kafatos, Brian Doty, James L. Kinter III, and Long Pham discusses a three-phase data access model and related data systems that support scientific data search and access. With explosively increasing volumes of remote sensing, modeling, and other Earth science data available, scientists now face the challenge of finding and accessing interesting multidimensional scientific data sets via the Internet. The article presents an Internet server called the enhanced server (ES) for Earth data that greatly benefits researchers in Earth science.
The diverse insights developed in these articles are really impressive. The authors have done a great job in writing about their innovations with illustrative and colorful images. We've tried to summarize the contents here, but you'll get much more from the articles themselves. Happy reading!
Jim X. Chen is an associate professor in the Department of Computer Science at George Mason University. He is currently the director of the Graphics Lab at GMU, the Visualization Corner department editor for CiSE magazine, and the program cochair of VR2003. His research interests include graphics, visualization, virtual reality, networking, and simulation. He received his PhD in computer science from the University of Central Florida, and is a member of the IEEE Computer Society. Contact him at the Dept. of Computer Science, George Mason Univ., MS 4A5, Fairfax, VA 22030-4444; firstname.lastname@example.org; www.cs.gmu.edu/~jchen.
Aiichiro Nakano is an associate professor of Computer Science with joint appointments in Physics & Astronomy, Materials Science & Engineering, and the Collaboratory for Advanced Computing and Simulations at the University of Southern California. His interests include scalable scientific algorithms, Grid computing on geographically distributed parallel computers, and scientific visualization. He received the US National Science Foundation Career Award in 1997, the Louisiana State University Alumni Association Faculty Excellence Award in 1999, the LSU College of Basic Sciences Award of Excellence in Graduate Teaching in 2000, and the Best Technical Paper Award at the IEEE/ACM Supercomputing Conference in 2001. He is a member of the IEEE, ACM, APS, and MRS. Contact him at the Dept. of Computer Science, Univ. of Southern California, 610 Vivian Hall, 3651 Watt Way, Los Angeles, CA 90089-0242; email@example.com.