| NSF Org: |
CNS Division Of Computer and Network Systems |
| Recipient: |
|
| Initial Amendment Date: | July 19, 2013 |
| Latest Amendment Date: | July 19, 2013 |
| Award Number: | 1262814 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Sylvia Spengler
sspengle@nsf.gov (703)292-7347 CNS Division Of Computer and Network Systems CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | August 1, 2013 |
| End Date: | July 31, 2017 (Estimated) |
| Total Intended Award Amount: | $900,000.00 |
| Total Awarded Amount to Date: | $900,000.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
240 FRENCH ADMINISTRATION BLDG PULLMAN WA US 99164-0001 (509)335-9661 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
WA US 99164-2752 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | CCRI-CISE Cmnty Rsrch Infrstrc |
| 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
There is considerable current interest in developing smart environment technologies. Such efforts present research challenges in, and integration of research outcomes from, diverse disciplines including artificial intelligence, pervasive computing, robotics, interfaces, middleware, and sensor networks. The lack of availability of large-scale sharable data sets from smart environments is a major stumbling block for rapid advances in this area. Against this background, this project aims to develop and deploy a data and tool repository needed by the smart environment research community.
The anticipated results of this infrastructure project include 1) a streamlined, do-it-yourself smart home kit, 2) a web interface to upload, access, and annotate smart environment data, 3) meta data including functional assessment scores and energy usage, and 4) software tools to recognize, visualize, and analyze home-based behaviors. The investigators aim to assess the impact of the resulting repository (CASAS) using measures such as number and diversity of researchers utilizing the repository, number of datasets and tools contributed to the repository, research, education, and commercial advances related to the repository, and publication citations to the repository.
Broader impacts of the project include (i) the do-it-yourself smart home toolkit, data sets and software tools that enable research and educational efforts by a large community of researchers in artificial intelligence, pervasive computing, robotics, interfaces, middleware, and sensor networks; (ii) enhanced opportunities for researchers in cognitive psychology, gerontology, and sociology to contribute to interdisciplinary research in smart environments; and (iii) enhanced research-based training opportunities for students from underrepresented groups. The datasets, software tools and educational materials that result from this work will be made available as part of the CASAS repository at http://ailab.wsu.edu/casas/.
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.
Intellectual Merit: The major goal of this project was to create a large community repository of human behavioral data that builds on the concept of a “smart home in a box”. Our CASAS smart home in a box facilitates scaling of smart home datasets. To validate the theory that we can scale such datasets, we shipped our smart home kit to a variety of homes and other sites in order to collect behavioral and activity data from a wide variety of smart environment settings. We used our existing machine learning and data mining techniques to create useable patterns and models from the data and made raw data and learned patterns available in our public repository. The infrastructure represents a part of the CASAS smart environment project, which has a proven track record for collecting and disseminating data that is valuable for the scientific community. Our enhanced community research infrastructure includes support of smart home installation and data collection in these sites, access to raw data, annotated data, and learned patterns through our Web repository, and dissemination of a wide collection of tools for visualizing and analyzing the data.
To accomplish this goal, we installed smart home kits at 133 locations. Some locations are homes (with a mix of single residents, multiple residents, older adults, and younger adults), some are office buildings, and one is at a children's museum. The collected data represents over 200 years of activity and over 500 million sensor data points.
Additionally, we designed and disseminated activity learning software that performs activity discovery, recognition, and prediction on the collected data. Activity recognition yields 98% accuracy for 33 activities using 3-fold cross validation and 78% accuracy using leave-one-site-out testing.
Broader Impact: The CRI resource has been used by researchers around the world. There have been over 500,000 accesses to the datasets and 25,000 visitors to the web site. The research disciplines using this resource include not only computer science but also psychology, sociology, nursing, civil engineering, and power engineering.
Last Modified: 08/01/2017
Modified by: Diane J Cook
Please report errors in award information by writing to: awardsearch@nsf.gov.
