| NSF Org: |
OAC Office of Advanced Cyberinfrastructure (OAC) |
| Recipient: |
|
| Initial Amendment Date: | February 3, 2014 |
| Latest Amendment Date: | June 21, 2019 |
| Award Number: | 1350374 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Alan Sussman
OAC Office of Advanced Cyberinfrastructure (OAC) CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | June 1, 2014 |
| End Date: | May 31, 2020 (Estimated) |
| Total Intended Award Amount: | $446,143.00 |
| Total Awarded Amount to Date: | $588,826.00 |
| Funds Obligated to Date: |
FY 2015 = $18,000.00 FY 2016 = $52,683.00 FY 2017 = $18,000.00 FY 2018 = $18,000.00 FY 2019 = $18,000.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
1 LOMB MEMORIAL DR ROCHESTER NY US 14623-5603 (585)475-7987 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
One Lomb Memorial Drive Rochester NY US 14623-5603 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): |
CAREER: FACULTY EARLY CAR DEV, Information Technology Researc, EDUCATION AND WORKFORCE |
| Primary Program Source: |
01001516DB NSF RESEARCH & RELATED ACTIVIT 01001617DB NSF RESEARCH & RELATED ACTIVIT 01001718DB NSF RESEARCH & RELATED ACTIVIT 01001819DB NSF RESEARCH & RELATED ACTIVIT 01001920DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Individualized assessment of high-dimensional spatiotemporal systems - such as in-vivo human physiological systems - has been increasingly enabled by paralleled advances in two fields: computer modeling that supports quantitative understanding of the dynamic behavior and mechanism of these systems, and modern sensor technologies that continuously improve the quantity and quality of measurement data available for analysis. There is, however, a gap between the two fields that is ubiquitous in many application domains: the current state of computer modeling is generally decoupled from specific measurements of an individual system, while individualized data-driven analysis often struggles for realistic domain contexts. This project aims to bridge this gap by investigating and developing new methodologies, algorithms, and software that will enable the integration of complex domain knowledge - yielded by computer simulation of domain physical models - into the process of data-driven inference. The overarching theme of this research is flexibility and robustness. Specifically, it addresses the following three challenges: 1) to enable a plug-and-play inclusion of domain physical models catering to different efficiency vs. accuracy needs; 2) to further overcome the lack of measurements and potential errors in domain physical models by exploiting the low-dimensional structure in high-dimensional systems; and 3) to enable a robust adaptation of the time-varying error that potentially exists in domain physical models. The driving application of this project is individualized modeling of in-vivo cardiovascular systems - using noninvasive biomedical and physiological data - for improved prevention, diagnosis, and treatment of heart diseases.
The outcome of this project will contribute theoretically, algorithmically, and computationally to the foundations of statistical inference, and extend to a wide range of applications such as tumor modeling, climate modeling, systems biology, and finance. In addition, this project will deliver publicly-available multicore/GPU software that will encapsulate the most effective algorithms developed. These toolkits will contribute to the national effort toward noninvasive medicine and healthcare, while supporting numerous scientific applications involving data-driven modeling and inference. This project also includes an integrated educational and outreach program to foster interdisciplinary research training and to increase participation of underrepresented groups in STEM disciplines. It includes: 1) development and evaluation of "learning-by-doing" concept in graduate and undergraduate education; 2) research training for students from graduate to high-school levels, with a focus on engaging women and underrepresented students at an early stage; and 3) broader outreach activities to area K-12 students and Paramedic communities. The participation of women, underrepresented, K-12, and Paramedic groups are reinforced through continued partnerships between the PI and different programs offered in RIT, local school district, and community college.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
This CAREER project delivered a suite of algorithms and codes to resolve the challenges in integrating physics-based simulation models with data-driven inference. This is important for the analysis, prediction, and control of complex systems where the understanding of data must be put in the context of rich domain knowledge. Examples include personalized physiological systems, which was a driving application of this CAREER project, as well as a large variety of natural and engineered systems such as those in astrophysics, material sciences, and manufacturing systems.
Specifically, the outcome of this project addressed three important challenges in integrating rich domain knowledge into the learning from data. First, how do we adapt the prior knowledge to available observational data, such that the inference can generalize outside the existing knowledge – whether such knowledge is physics-based or driven from previous training data. Second, how do we quantify the uncertainty in the prior knowledge, especially in forms of model parameters associated with physics-based simulations. Finally, how do we address the heterogeneity in data and regularize the data-driven learning such that we are able to learn from a small number of data but generalizes well outside the training data. These covered the challenges associated with the data, knowledge, and integration aspects essential to the project goal. By addressing these challenges, this project delivered algorithmic and methodological solutions that facilitated the integration of knowledge and data, which is relevant to a wide range of science and engineering domains where knowledge is important in the understanding of data.
Among the variety of domains that can benefit from the proposed methodological research, the driving application of this project was in personalized approaches to the diagnosis, prognosis, and treatment planning of heart diseases. This covered approaches with a range of complexity including those more heavily data-driven, those more towards building personalized virtual heart models based on physics, and those in the middle of the spectrum that integrates physics and data. The outcome of this project has supported innovations and developments of technology along each of these fronts, including improving existing techniques for 3D imaging of abnormal rhythms of the heart, equipping existing virtual heart models with uncertainty measures, and delivering new prototypes of software for guiding clinicians to intervention target of ventricular arrhythmia in real time during a procedure. These outcomes collectively will help advance personalized care of heart rhythm disorders. The outcomes of this project also helped the PI initiate collaborations with experts from a broad range of other domains including astrophysics, molecular science, and digital manufacturing, seeding many exciting collaborations with potential scientific and practical impact in the future.
This CAREER project also provided significant education and professional development opportunities for both the PI and a large number of students ranging from high-school to doctoral levels. It supported in total eight PhD students with five completed dissertation (three of which were female PhD students in Computing) and two dissertations to be completed by summer 2021. It also supported 18 master research assistants (one thesis completed and two theses in progress) and 18 REU undergraduate research assistants – the most recent one has joined the PI’s group to continue his PhD study. These students have first-authored 35 peer-reviewed journal articles or full-length conference papers, disseminated in a variety of domains including deep learning, data mining, computer vision, medical image computing, and cardiology. It also provided research exposure to eight high-school research interns, five of which were girls. This CAREER project has supported the PI to transition from her early career independence to the leader of a mature research group and of various initiative both within her institute, who is committed to continue her efforts in educating and promoting the next generation of engineers and scientists who are able to use computing to resolve some of the society’s most challenging problems.
Last Modified: 09/30/2020
Modified by: Linwei Wang
Please report errors in award information by writing to: awardsearch@nsf.gov.
