ucsd_chei_AlbertLin_TopCoder

The partnership between the Qualcomm Institute’s Albert Lin, TopCoder and NASA invites coders to participate in a three-week challenge to build a powerful machine-learning algorithm to identify ground features in satellite images of Mongolia.

September 13, 2013 — A crowdsourcing effort led by University of California, San Diego research scientist Albert Yu-Min Lin is central to a new challenge as programmers worldwide are invited to develop a machine-learning algorithm to match human perception in picking out interesting features in satellite imagery. While the images come from Lin’s search for the lost burial site of Genghis Khan, a new algorithm could help NASA scientists decipher images of distant planets.

TopCoder, Inc., the world’s largest open innovation platform and competitive community of digital creators, announced Sept. 12 the new challenge through the NASA Tournament Lab (NTL), in partnership with UC San Diego’s Lin, who works in Calit2’s Qualcomm Institute and the Center of Interdisciplinary Science for Art, Architecture and Archaeology (CISA3) at UC San Diego. A National Geographic Emerg- ing Explorer, Lin is also a three-time alumnus of UCSD’s Jacobs School of Engineering in electrical engineering (BS ’04, MS ’05) and materials science (Ph.D. ’08).

The three-week Collective Minds & Machines Exploration Challenge asks TopCoder community members from around the world to study a massive data set of crowdsourced, human-generated analytics tags of satellite imagery of the uninhabited landscape of Northern Mongolia, a likely location of the lost tomb. They are challenged to develop an algorithm that learns from the crowd, and emulates the sensitivity of human perception when recognizing and categorizing subtle details and features in images (for example, to pick out topographical features that could indicate the presence of an ancient human-built structure). Once developed, the algorithm could integrate machines and crowds to accelerate discovery in a wide array of big data problems ranging from planetary to medical imaging exploration. The partnership between the Qualcomm Institute’s Albert Lin, TopCod- er and NASA invites coders to participate in a three-week challenge to build a powerful machine-learning algorithm to identify ground features in satellite images of Mongolia. Click here to watch a video about the challenge to the coding community.

Lin recently applied the concept of crowdsourcing to an ambitious satellite imagery labeling initiative. In the first-of-its-kind collective exploration experiment, tens of thousands of amateur analysts worldwide helped Lin’s team at UC San Diego identify sites of cul- tural and historical significance. “Here we turn towards the crowd not only to tackle the data size challenge of large-scale satellite remote sensing, but more importantly to pool human perception and intuition when sifting through the data for anything that looks ‘out of the ordinary,’” said Lin. His team then mounted a series of land expeditions to verify regions of high interest defined by the crowd.

On the heels of this successful crowdsourcing application, Lin turned to researchers at the Harvard NASA Tournament Lab and TopCoder to leverage open innovation. Their goal: to develop an algorithm that can amplify the power of crowdsourced human perception when presented with ill-defined patterns.

ucsd_chei_AlbertLin_TopCoder_Mongolia

Better algorithms for detecting human-built structures from satellite images will enhance exploration in space and on Earth, by accelerating how NASA assesses planetary imagery. The goal is to identify, protect and preserve the integrity of undiscovered sites of cultural and historical significance worldwide.

“In science, data sets continue to get bigger and answers continue to get fuzzier,” noted Lin. “A collaboration between machine and crowd is a natural next step as we face the increasingly overwhelming data avalanches of our digital world.”

To respect the traditional beliefs of indigenous people, Lin and his team have used state-of-the-art technologies to conduct a noninvasive survey of Genghis Khan’s homeland. While Lin’s work enabled the online crowd of explorers to detect and label human-built structures in satellite imagery, TopCoder is challenging its community to develop an active, machine-learning algorithm that matches human capabil- ity. The successful algorithm will allow machines to learn as they compute and respond to the human input data from the crowdsourcing initiative. The long-term goal of this project is to create an algorithm that exceeds human capability.

“The quest to find Genghis Khan’s tomb has mystified scientists for hundreds of years,” said TopCoder President and COO Rob Hughes. “This powerful new algorithm will accelerate Albert’s research and realize the full potential of blending collective human intelligence with machine learning created through open innovation. The TopCoder community’s cutting-edge solutions are a natural fit for NTL and a technology-enabled explorer like Lin, whose mission is to uncover humankind’s best kept secrets.”

The Collective Minds & Machines Exploration Challenge was developed through the NTL, a collaboration between NASA, Harvard Business School in association with the Institute of Quantitative Social Science, and TopCoder. It allows the TopCoder com- munity to compete to create the most in- novative, efficient and optimized solutions for specific, real-world challenges. UC San Diego, where Lin co-directs the Engineers for Exploration Program, is experimenting with mechanisms to discern locations of ancient archeological places using satel- lite images. NASA and UC San Diego will work together to harness UC San Diego’s previous efforts and the resources of the NTL to produce code that will analyze open-source aircraft and satellite images by using amateur feedback for classifica- tion. NASA can then apply this same technology to imagery assessment of planetary objects.

Registration for the challenge is now open and contestants must be TopCoder members. TopCoder membership and regis- tration are free at www.topcoder.com/reg. The competition ends on October 3, 2013. For more information on this adventurous algorithmic challenge, visit www.topcoder.com/collectiveminds.

The Valley of the Khans Project

Albert Lin’s research has taken him into the most remote regions of the world, has led to industry- changing innovations and has expanded the role of media in science. The effort he is most known for, the Valley of the Khans Project, is a high-tech ground-, aerial- and satellite- based, remote sensing, non-invasive search for the tomb of Genghis Khan that was featured in a one-hour National Geographic Channel documentary film, “Forbidden Tomb of Genghis Khan,” which he also narrated. The effort earned him recognition as National Geographic Adventure Magazine’s “2010 Readers Choice Adventurer of the Year” and the 2011 Lowell Thomas Medal for Exploration from New York- based Explorers Club. Lin’s goal is to enable international protection of a sacred region of Mongolia. His team’s use of digital media to perform massive satellite data analytics through crowdsourcing (recognized with the 2011 United States Geospatial Intelligence Founda- tion Academic Achievement award) has been emulated for applications ranging from emergency response to humanitarian monitoring and led to the formation of California-based Tomnod Inc. where he served as co-founder and chairman of the Board of Directors until 2013, when the company was successfully acquired by the Colorado-based commercial satellite imagery provider, Digital Globe. He has been invited to present his work on massive-scale collaboration and crowd-based collective intelligence to organizations including the US Geospatial Intelligence Agency, Harvard Business School, and the Department of Defense.

TopCoder

TopCoder is the world’s largest Open Innovation Community of digital creators with over 500,000 members representing algorithmists, software developers and creative artists from over 200 countries. The TopCoder Open Innovation Community creates digital assets in- cluding analytics, software and creative designs and solutions for a wide-ranging client base through a competitive, rigorous, standards based methodology. Combined with our extremely talented community this groundbreaking methodology results in superior outcomes for our clients.

September 10, 2013 — A team of researchers from the University of California, San Diego, has received $3.4 million in grant and matching funds to design and build new 3D display technologies for visualizing big data from macroscopic to microscopic scales.

ucsd_chei_ falko_vroom

Falko Kuester, profesor of visualization and virtual reality at UC San Diego’s Qualcomm Institute, stands in front of the VROOM digital display while viewing data on a tablet computer. The new $3.4 million SCOPE project is the next step in the evolution of digital display technologies at the Qualcomm Institute.

The project, called SCOPE, is both “an acronym and a visual metaphor for a combined microscope and telescope, enabling users to explore data from the nano to micro to macro to mega scale,” said principal investigator Falko Kuester, a professor of visualization and virtual reality in UC San Diego’s Qualcomm Institute and an associate professor of structural engineering in the Jacobs School of Engineering. “SCOPE stands for Scalable Omnipresent Environment, which also captures the vision behind the large-scale, ‘walk-in’ collaborative visual computing instrument,” he added. “It’s a Holodeck of sorts that will connect spatially distributed research teams working on big-data challenges.”

The funds for the project include $2.4 million from the National Science Founda- tion (NSF) Major Research Instrumentation (MRI) program, and an additional $1.4 million in matching funds from UC San Diego, its Jacobs School, and the Qualcomm Institute (the UC San Diego division of the California Institute for Telecommunications and Information Technology, or Calit2), as well as project partners Jackson State University (JSU) and the University of Texas Medical Branch (UTMB).

Kuester says the goal of SCOPE is to create a highly interactive collaboration instrument equipped with a natural human-computer interface that supports advanced 3D modeling and rendering capabilities. The data will be rendered to scales suitable for analyzing large amounts of visual and numerical data pertain- ing to phenomena of wide dimensions and extreme time scales.

UC San Diego Research Scientist Thomas A. DeFanti, a pioneer in virtual-reality systems, calls SCOPE “the next major evolution in our series of super high- resolution data visualization displays — scores of times higher resolution than HDTV.” DeFanti is a co-PI on the project, along with Tajana S. Rosing, an As- sociate Professor of Computer Science and Engineering (CSE), and Qualcomm Institute Assistant Research Scientist Jürgen P. Schulze, who is also an Adjunct Assistant Professor in the CSE department.

Over the past 20 years, SCOPE researchers and their partners have designed many of the world’s most advanced visualization display systems, including VizClass, HIPerWall, HIPerSpace, the CAVE, StarCAVE, NexCAVE, TourCAVE, and VROOM. SCOPE will allow remote collaboration from anywhere in the world. Its 40-100 gigabit/second high-speed networking and embedded flash memory technology — originally developed at the San Diego Supercomputer Center — will make it possible to explore big data interactively and collaboratively, even when the volume of data on display reaches hundreds of terabytes or even petabytes. SCOPE will eventually connect researchers at UC San Diego with team members at JSU and UTMB. Several years of hands-on work- shops at Calit2 with Minority Serving Institutions (MSI)-CyberInfrastructure Empowerment Coalition (MSI-CIEC) led to the partnership with JSU (an MSI) and UTMB.

ucsd_chei_nexcave_tom_defanti

UCSD Research Scientist Thomas A. DeFanti and the NexCAVE, one of the digital display technologies developed at the Qualcomm Institute.

SCOPE will be used by researchers in disciplines such as computer science, structural engineering, marine science, anthropology, art, health, geo-sciences and bioengineering.

The SCOPE team encompasses 45 researchers from more than a dozen different departments that rely on fundamental computer science visualization research. This set of researchers will be further augmented by: (a) faculty recipients of Calit2 Strategic Research Opportuni- ties (CSRO) grants; (b) graduate students in the NSF-funded Integrative Graduate Education and Research Traineeship (IGERT-TEECH) program for cultural heritage diagnostics and preservation; and (c) undergraduate researchers supported by Research Experiences for Undergraduates (REU) supplements.

IGERT-TEECH, which is based at the Qualcomm Institute’s Center of Interdisciplinary Science for Art, Architecture and Archaeology (CISA3) served as an inspiration for the SCOPE proposal, tracing its roots back to UCSD Chancellor’s Interdisciplinary Collaboratories Initiative. “It’s a win-win situation,” said Kuester. “This project allows us to develop a truly unique research instrument while building a team of highly interdisciplinary researchers driving innovation through collaboration.”