Tingjian Ge Receives a Total of $773K in Funding
By Edwin L. Aguirre
The National Science Foundation (NSF) has awarded computer science Asst. Prof. Tingjian Ge
two research grants totaling nearly $773,000.
The first is the prestigious, highly competitive “CAREER
” award, which is presented annually to young faculty members “who exemplify the role of teacher-scholars through outstanding research, excellent education and the integration of education and research within the context of the mission of their organizations.”
Ge, who joined UMass Lowell in January, will use his CAREER award worth $474,110 spread over a period of five years to support his research project dubbed MUSE (managing uncertain scientific experimental data).
Ge’s second NSF grant, worth $298,751, is for continuing his research project called RURAL (querying rich uncertain data in real time), which he started when he was still teaching at the University of Kentucky.
“In both projects, my students and I blend concepts and techniques from the areas of databases, probability and information theory, statistics, machine learning and artificial intelligence,” says Ge.
“The MUSE project crosses the boundaries between computer science and mathematics to analyze large-scale experimental data in a number of science domains, while the RURAL project solves real-time query-processing problems in newly arising computing environments where large amounts of uncertain raw data come in dynamically,” he explains.
An Integrated Approach to Data Management
Ge says with advances in technologies and engineering, science is becoming increasingly data intensive.
“For example, in earth and environmental sciences, sensors continuously send out data,” he says. “In medical sciences, experiments such as microarrays used in cancer research are also known to produce vast amounts of data.”
Over time, as data accumulates within or across institutions and research groups, managing this wealth of information becomes a challenge.
“We soon have a database containing data for many experiments, each having a number of replicates,” notes Ge. “However, little has been done to query this data repository in an integrated and automatic manner, mainly because the results among different replicates of an experiment often show a large degree of inconsistency and variance. MUSE aims to solve some of the major query-processing challenges in such a database.”
The ability to effectively and accurately share, query and monitor diverse scientific experimental data on a large scale will greatly benefit the science community, he says.
“The extra data-analysis capability provided to scientists can even change the way they conduct their research,” he adds.
Uncertain Data: Not Ideal for Making Solid Decisions
Real-time (but noisy) data is very common nowadays, says Ge.
“Smartphones, GPS, wi-fi, medical monitoring devices, highway traffic sensors, radio-frequency IDs and computer/phone networks are just some technologies that continuously produce raw, noisy data at high rates,” he says. “Effectively querying, analyzing and monitoring such data quickly in real time is a critical and challenging problem.”
He says compared to traditional deterministic data, uncertain data carries more information, and the data cannot be completely “cleaned” to remove uncertainty.
“Forcing uncertain data to be deterministic can cause significant information loss in query results, possibly leading to wrong judgments for queries that involve decision-making,” says Ge.
Real-time decisions based on these data can have a significant impact on the quality of life, on the economy and our security.
“The goal of our RURAL project is to provide precise and informative answers to users’ queries within a given deadline,” he says.
Ge earned a bachelor’s degree in computer science from Tsinghua University in China, a master’s degree from the University of California, Davis and a doctorate from Brown University. In addition to Ge, other UMass Lowell professors in the Computer Science Department who have been recognized with NSF CAREER grants include Jie Wang, Holly Yanco, Fred Martin and Benyuan Liu.