ECE's Heng Huang Receives $1.2M NSF BIGDATA Award to Address Computational Challenges in Big Brain Data Research Collaborations

Electrical & Computer

PITTSBURGH (December 20, 2018) … The National Science Foundation BIGDATA program awarded $1,200,000 to a research team led by the University of Pittsburgh Swanson School of Engineering to study the big brain data for complex brain disorders and design new algorithms that address computational challenges in multi-site collaborative data mining. Heng Huang, the Swanson School’s John A. Jurenko Professor of Computer Engineering, is principal investigator of the study, "Asynchronous Distributed Machine Learning Framework for Multi-Site Collaborative Brain Big Data Mining." Huang currently leads seven NSF projects and an NIH R01 project on machine learning, big data mining, computational neuroscience, health informatics, and precision medicine. “Research in emerging fields, such as brain imaging genomics and human connectomics, holds great promise for a systems biology study of the brain,” said Huang. “This research can help us better understand complex neurobiological systems, from genetic determinants to the interplay between brain structure, connectivity, function, and cognition.” While researchers currently have access to brain data collected from a series of funded projects, they have failed to attain additional data collected by different local institutes due to data privacy and security issues preventing cross-institutional distribution. In this project, Huang will create a framework to address these issues and facilitate data and computing resource sharing. “In collaborative data analysis, the participating institutes keep their own data, which are analyzed and computed locally, and only share the computed results via communicating with the server,” explained Huang. “The server communicates with all institutes and updates the computational model such that the trained machine learning models indirectly use all data and are shared to all institutes.” According to Huang, most machine learning algorithms were not designed for such distributed architecture due to difficulties in designing efficient algorithms and providing theoretical foundations. This is the first project to create these type of algorithms for the study of brain imaging genomics and human connectomics. The goal of this project is to alleviate these computational challenges and enable investigators in neuroimaging, genomics, neuroscience, and other brain-related disciplines to securely and more efficiently further their research. “The result of our project will be new distributed machine learning algorithms with theoretical foundations that can be used for multi-site collaborative big brain data mining, creating large-scale computational strategies and effective software tools,” said Huang. “We hope that this work will help researchers harness the full potential of big brain data, potentially leading to the next major brain science discoveries.” ###

Pitt's power lab at Energy Innovation Center will be one-of-a-kind

Electrical & Computer

By early next year, Pittsburgh will have one of the country’s most advanced academic labs for the study of electrical power. The Energy Innovation Center in the Lower Hill District will be the site of the University of Pittsburgh’s high-voltage, high-capacity electric power lab. The state-of-the-art facility will be a distribution-level location with a microgrid, high-tech control and operation, and connectivity to solar, wind and natural gas generation. Greg Reed, director of Pitt’s Center for Energy and the Energy GRID Institute, said no academic center will have anything like it in terms of capacity and flexibility: It will have 15,000 volts and 5 megawatts of capacity, and both alternating current (AC) and direct current (DC) in the lab. Read the full story (with subscription) at the Pittsburgh Business Times.
Author: Paul J. Gough, Reporter, Pittsburgh Business Times

Pitt Engineers Get First Look at Next Project Bound for ISS

Electrical & Computer

PITTSBURGH (October 29, 2018) … Computer and electrical engineers at the University of Pittsburgh Swanson School of Engineering got a sneak peek at their new space supercomputer as it finishes final integration testing before heading to the International Space Station (ISS).The photos, which were taken by an engineer at NASA Kennedy Space Center, show the Space Test Program-Houston 6 (STP-H6) pallet featuring a hybrid and reconfigurable space supercomputer developed at Pitt. The spaceflight computer is the first of its kind and is supported by dual high-resolution cameras capable of capturing five megapixel images of Earth.“This new research experiment and testbed is called Spacecraft Supercomputing for Image and Video Processing, or SSIVP,” explains Dr. Alan George, the Mickle Chair Professor of Electrical and Computer Engineering (ECE) at the Swanson School. “Space is the ultimate challenge, where systems face big-data demands in an extreme environment with limited power, size, and weight.  Our SSIVP system represents a leap forward for high-speed computing in space.”Dr. George is the founder of the National Science Foundation (NSF) Center for Space, High-performance, and Resilient Computing (SHREC). The research center focuses on “mission-critical computing,” a field of ECE that includes space computing, high-performance computing and data analytics, and resilient computing to ensure system dependability at high speed and low power in harsh environments like outer space. The SSIVP system at the University of Pittsburgh (left) and a close-up of the system on the STP-H6 pallet (right, edited for clarity) at NASA Kennedy.Credit: (left) Swanson School of Engineering; (right) NASA The STP-H6 pallet, including Pitt’s SSIVP system, completed integration and testing at NASA Johnson Space Center in Texas last spring. Further environmental testing took place at NASA Langley Research Center in Virginia over the summer. The pallet is at NASA Kennedy this fall for final integration and testing before launch in February 2019. “We collaborated with a team of Pitt mechanical engineers led by Professors Dave Schmidt and Matthew Barry to design and build our enclosure to meet NASA requirements,” says Dr. George. “They managed mechanical design challenges and ensured the system was safe and could dissipate heat generated by the high-performance electronics.” A team of ECE students assembled the SSIVP enclosure and electronics in a cleanroom at the Spacecraft Assembly Lab at SHREC. The enclosure, a golden outer case emblazoned with the Pitt script, can be seen in the middle of the pallet. The SSIVP team traveled to NASA Goddard Space Flight Center in Maryland to conduct environmental testing to assess the SSIVP payload’s ability to survive the vibrations of launch and the thermal vacuum of space. The team also traveled to NASA Johnson to integrate and validate the SSIVP payload on the STP-H6 pallet and NASA Langley Research Center to program and validate the final flight software. “We handled testing for the power systems to characterize our payload and ensure conformance with NASA and Department of Defense standards,” says Nicholas Franconi, an ECE PhD student on the SSIVP team. “We delivered and integrated the SSIVP payload this past spring and are excited to see it launch in spring 2019.” The STP-H6 pallet is headed for the ISS via a SpaceX rocket. Once aboard the space station, it will join its predecessor STP-H5, which launched in 2017. The SHREC team developed a payload for the H5 pallet as well, and the two systems will work on a variety of space technology experiments conducted by the Pitt engineers. ###
Matt Cichowicz, Communications Writer