| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | September 16, 2015 |
| Latest Amendment Date: | September 16, 2015 |
| Award Number: | 1545071 |
| Award Instrument: | Standard Grant |
| Program Manager: |
David Corman
CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | October 1, 2015 |
| End Date: | September 30, 2020 (Estimated) |
| Total Intended Award Amount: | $224,000.00 |
| Total Awarded Amount to Date: | $224,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
160 ALDRICH HALL IRVINE CA US 92697-0001 (949)824-7295 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
Bren Hall, Room 2082 Irvine CA US 92697-2725 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | CPS-Cyber-Physical Systems |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
he goal of this project is to facilitate timely retrieval of dynamic situational awareness information from field-deployed nodes by an operational center in resource-constrained uncertain environments, such as those encountered in disaster recovery or search and rescue missions. This is an important cyber physical system problem with perspectives drawn at a system and platform level, as well as at the system of systems level. Technology advances allow the deployment of field nodes capable of returning rich content (e.g., video/images) that can significantly aid rescue and recovery. However, development of techniques for acquisition, processing and extraction of the content that is relevant to the operation under resource constraints poses significant interdisciplinary challenges, which this project will address. The focus of the project will be on the fundamental science behind these tasks, facilitated by validation via both in house experimentation, and field tests orchestrated based on input from domain experts.
In order to realize the vision of this project, a set of algorithms and protocols will be developed to: (a) intelligently activate field sensors and acquire and process the data to extract semantically relevant information; (b) formulate expressive and effective queries that enable the near-real-time retrieval of relevant situational awareness information while adhering to resource constraints; and, (c) impose a network structure that facilitates cost-effective query propagation and response retrieval. The research brings together multiple sub-disciplines in computing sciences including computer vision, data mining, databases and networking, and understanding the scientific principles behind information management with compromised computation/communication resources. The project will have a significant broader impact in the delivery of effective situational awareness in applications like disaster response. The recent :World Disaster Report" states that there were more than 1 million deaths and $1.5 trillion in damage from disasters within the past decade; the research has the potential to drastically reduce these numbers. Other possible applications are law enforcement and environmental monitoring. The project will facilitate a strong inter-disciplinary education program and provide both undergraduate and graduate students experience with experimentation and prototype development. There will be a strong emphasis on engaging the broader community and partnering with programs that target under-represented students and minorities.
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.
The overall goal of this collaborative project (with UC, Riverside) was to facilitate the timely retrieval of dynamic situational awareness information from field deployed nodes in resource-constrained uncertain environments. While the project spanned several interrelated components ranging from data acquisition and analysis in resource constrained to information fusion methods, the project focused on Cost-effective query formulation and retrieval focusing on effectively prioritizing queries, retrieval of and processing of sensor data based on query needs. The project led to several significant outcomes.
First, it enabled a novel research direction of supporting progressive computing in the context of online analytical queries over sensor data. Such analytic queries require raw sensor data to be appropriately interpreted typically using expensive machine learning methodologies. The project explored novel ways in which such expensive functions could be executed in a phased manner so as to support progressively improving analysis over input data. Techniques to identify which objects to process in which order using which functions so as to optimize the overall quality of data were developed. Ideas of progressive computation were applied at the campus scale testbed created at UCI wherein WiFi connectivity data was used to determine dynamic localization of individuals inside buildings using machine learning techniques for data cleaning. Using the progressive framework, complex building analytics could be implemented on the fly. Several such applications were designed and implemented including applications that helped in monitoring spaces within UCI for occupancy levels. This app was deployed in several campus buildings and used extensively as official part of campus reopening from COVID-19.
Adaptive resource efficient monitoring techniques for community spaces were also developed that used reinforcement learning were developed that adaptively selects workflows of devices and operators to maintain adequate quality of information for the application at hand while judiciously consuming the limited resources available on edge servers.
As an unanticipated outcome, the project helped launch a new area of research on privacy preserving data sharing in IoT settings. In particular, motivated by the sensor-based applications, the research team developed the PEIoT system that orchestrate privacy-enhanced sensor data flows based on user/subject policies. An another outcome, the project helped motivate a large number of undergraduate students who used the campus level sensing and programming infrastructure developed by the researchers to develop several applications including those related to monitoring for COVID-19 and for recycling efforts within campus in addition to smart building applications. The technology produced in part funded by the project was transitioned to US Navy and used to support campus level smart applications. It is being also deployed in other campuses in the context of COVID-19 apps.
Last Modified: 01/08/2021
Modified by: Sharad Mehrotra
Please report errors in award information by writing to: awardsearch@nsf.gov.
