Congratulations to Kyeong T. Min, whose poster was awarded "Best In Session" at the 2015 American Industrial Hygiene Association Conference & Expo, held here in Salt Lake City, Utah. Kyeong designed and built the "Utah Modified Dylos Sensor", an air quality sensing server and Android app which form a unified sensing, wireless interface, database, and user interface for use in human subjects air quality sensing research. The poster is titled "Development of a low-cost environmental sensor with remote real-time monitoring of indoor particulate, temperature and relative humidity", and its authors are Ben S Cryder, Darrah K Sleeth, Yue Zhang, Kyeong T Min, Chong Zhang, and Scott C Collingwood.
The NSF has funded our research project "Advanced Radio Frequency (RF)-based Environmental Monitoring Systems" to be performed collaboratively at Georgia Tech and the University of Utah. Prof. Neal Patwari and the SPAN lab will conduct the research at the University of Utah, and Prof. Gregory D. Durgin and the Propagation Lab will conduct the research at Georgia Tech.
The award is an investigation in the science of temporal fading as it is useful for new radio frequency (RF) environmental monitoring (REM) systems. Temporal fading is the change in the radio channel between a transmitter and receiver, for example, a fluctuating "number of bars" or signal strength between a laptop and access point, even when neither are moving. Past research in temporal fading treats it only as a problem that degrades wireless communication. Emerging research has shown that temporal fading can be exploited to locate, automatically recognize the activity or gesture, and monitor the health of people in the vicinity of a wireless network. These localization, recognition, and monitoring systems are called RF-based environment monitoring (REM) systems. Improvements in REM technologies could aid in the design of police and search-and-rescue systems that locate breathing people in dangerous or collapsed buildings. As another example, REM technologies deployed in a home could detect falls and detect signs of cognitive or physical decline as part of an aging-in-place sensor system. REM technologies could allow people to diagnose disordered sleeping via wireless devices (e.g., cell phones) left on their bedside. Finally, REM systems could revolutionize indoor and outdoor security systems, helping to protect areas and buildings which are difficult to monitor with existing technologies. To date, no fundamental research in temporal fading mechanisms has been performed to support REM applications. Research in this project considers temporal fading and seeks to establish how it is affected by the movements of people in the environment so that it can be exploited for environmental monitoring.
Congratulations to Ossi Kaltiokallio, Hüseyin Yigitler, Riku Jäntti, and Neal Patwari! Their paper, "Catch a Breath: Non-invasive Respiration Rate Monitoring via Wireless Communication", was awarded the Best Paper Award at the 13th IEEE/ACM International Conference on Information Processing in Sensor Networks (IPSN 2014), held April 15-17 in Berlin, Germany. Ossi Kaltiokallio, Hüseyin Yigitler, and Riku Jäntti are affiliated with Aalto University in Espoo, Finland. Ossi was a visiting researcher in the SPAN lab in 2012.
Brad Mager had a great night at the ECE Technical Open House Award Banquet. He was awarded "Outstanding Computer Engineering Student", and also awarded one of six "Best Presentation" awards for his talk on his senior thesis, "Fall Detection Using RF Sensor Networks". His talk was also mentioned by the keynote speaker and distinguished alumnus award winner Dr. John Sutherland as an example of useful research into the "internet of things". Congrats to Brad on his awards!
Ossi Kaltiokallio, Ph.D. student at Aalto University in Finland, and Maurizio Bocca and Neal Patwari, of the SPAN lab at the University of Utah, were awarded the "Best Paper Award" at the IEEE SenseApp workshop for their paper, "Follow @grandma: Long-Term Device-Free Localization for Residential Monitoring". Ossi Kaltiokallio presented the work today, 22 October 2012, in Clearwater, Florida. The work for the paper was conducted while Ossi was a visiting student in the SPAN lab. The best paper award was judged on quality of both the written paper and the oral presentation. IEEE SenseApp, an annual conference in its seventh year, is the short name of the IEEE International Workshop on Practical Issues in Building Sensor Network Applications. Only 20% of submissions were accepted as regular papers, and three were finalists for the best paper award.
A University of Utah team of researchers has won two awards at “EvAAL”, a prestigious international competition on tracking technologies. The competition, organized by the Ambient Assisted Living Open Association, involved ten research teams from around the world, including Canada, Spain, Germany, Switzerland, France, and the US. The University of Utah’s team is called the cyber-physical systems (CPS) Group, a team led by Dr. Maurizio Bocca, with participation from faculty from the School of Computing (Dr. Suresh Venkatasubramanian and Dr. Sneha K. Kasera) and Department of Electrical and Computer Engineering (Dr. Neal Patwari). The CPS Group won the 1st place award for tracking accuracy, and the 2nd place award overall. The accuracy of the team’s localization system was superior to all other teams, but took 2nd place in the overall score, which also includes scores given by a team of judges for “installation complexity” and “user acceptance”.
The first place award for tracking accuracy awarded to the CPS Group showed that their localization system had the best tracking performance of any of the systems of the participating teams. Each team developed and tested systems that locate and track a person while they are in their own home. The teams’ systems were tested, live, at the competition, held at the Smart House Living Lab in Universidad Politecnica de Madrid (UPM) in Madrid, Spain. During the test, a person walked around in a path that was unknown to any of the teams. Each team’s system continuously reported its best guess of where it believed the person was. Then the evaluators compared the estimates to the actual path; the difference was the team’s localization error. The team with the lowest localization error was the University of Utah’s team.
Localization and tracking of people in their home may sound like a big-brother surveillance technology, however, it is meant to be used only with the person’s permission, and only when a person requires it. One major application where people need such location sensing technologies is in ambient assisted living. The idea of “ambient” assisted living is ensure the health and well-being of a person who might not be otherwise able to live in their own home. For the very elderly or those who need long-term home-based care, the use of some technology may enable to them to stay in their home longer, rather than to needing move to assisted living facilities. Localization sensing is part of this -- a caretaker could be alerted if, for example, a person has fallen and hasn’t gotten up, or if a person has been laying in bed all day.
The Utah team developed a system that doesn’t require the person to wear what is called an active badge. An active badge has a radio transmitter that periodically sends the system a message, and the system locates where that message originates. However, the user must remember to wear the active badge -- and for elderly or infirm people, it is a disadvantage that the system only works when they remember to wear the active badge. The Utah team’s technology is based on transceivers deployed in the home that use radio tomography to determine where people are moving. Radio tomography (RT) is like computed tomography (CT) scans in medical environments, except that RT uses 2.4 GHz radio waves, just like WiFi devices, rather than x-rays, like medical CT scanners. This technology has been in development at the U. of U. for four years, and its accuracy has been improving with each new technological development at the lab. The team’s tests in an apartment here in Salt Lake City, prior to the competition, showed that a person could be located within 30 cm (1 foot). No other team used radio tomography (RT) as the basis for their sensing systems.
The Utah team’s localization system was highly accurate, significantly better than the other competitors. During the test, the evaluators were so surprised with the system’s accuracy that they stopped the test to make sure that there wasn’t something wrong. The evaluators re-ran the test when they realized that the system was just that accurate.
The “evaluating ambient assisted living technologies”, or EvAAL, competition, is an annual competition that draws competitors world-wide. The competition web site (http://evaal.aaloa.org/) describes in detail the localization and tracking competition rules and the teams participating in this year’s competition. The announcement was made Tuesday, Sept 25, 2012, at the AAL Forum, a conference and exposition of AAL technologies in Eindhoven, The Netherlands.
The CPS Group is funded by the U.S. National Science Foundation from Grant #1035565, “Enabling and Advancing Human and Probabilistic Context Awareness for Smart Facilities and Elder Care”.
This video shows the experimental results from a radio tomography (RT)-based two-person tracking experiment in an apartment. The people are not wearing any radio tags, instead, a wireless network of 33 (IEEE 802.15.4) transceivers deployed in the apartment measure changes in received signal strength (RSS), known as "the number of bars", caused by the people. Based on which links experience changes, the RT algorithm comes up with an image (shown at left) that has highest values (red) where it guesses that a person is located, and lowest values (blue) where it guesses that no person is located. A multi-target tracking algorithm developed by Dr. Maurizio Bocca at the University of Utah identifies from the image where the "blobs" are and what path they are taking through the apartment, using computer vision methods adapted to the RT problem. On the left, the video shows the apartment with black indicating walls, grey indicating furniture, white circle indicating the actual person location, and white X indicating the current estimate of the person. Dr. Bocca's algorithm track the two people to within an average error of about 30 cm (1 foot). Dr. Bocca and his University of Utah team used this system to compete in the EvAAL 2012 tracking competition and win 1st place for localization accuracy and 2nd place overall (overall score is an average of accuracy and other qualititative metrics from a panel of judges). (Video credit: Dr. Maurizio Bocca)
Congratulations to SPAN director Dr. Neal Patwari for winning the University of Utah Early Career Teaching Award! This award given only to a few professors at the University who have demonstrated exceptional teaching qualities. Here's the description:
"A nominee for the Early Career Teaching Award shall have demonstrated distinction in teaching, demonstrated by activities that result in increased learning by students, such as the development of new methods or other curricular innovation. Nominations may be made by any member of the University Community, i.e., students, faculty, administrators, alumni, etc. The University Teaching Committee evaluates nominees based on a Teaching Portfolio, a curriculum vitae, three letters of support, and student evaluations."
Congratulations Neal for this outstanding accomplishment!
The University of Utah's Lassonde center has selected the SPAN lab's radio tomographic imaging (RTI) technology for the 2009-2010 business development program. Each year, the Lassonde center chooses a few university-owned technologies that show promise of successful commercialization. Lassonde students studying business, law, and engineering form teams that research the commercial viability of the technologies, then prepare business plans.
Troy D'Ambrosio (director of the Lassonde program), Matt Dee, Deven Dustin, Vatsala Kaul, and Joey Wilson (from the SPAN lab) will make up the team. For more information about the Lassonde entrepreneur center, see their website at www.lassonde.utah.edu.
Congratulations to graduate student Joey Wilson, who on Wed. September 17 won the MobiCom 2008 Student Research Demo Competition! (See the U of U's "Recognizing U" site) Joey presented the demo, "Radio Tomographic Imaging", on Tuesday, September 16, among nineteen student research demos presented at the Mobicom 2008 conference. It had been accepted from among 28 demo proposals submitted. On Wednesday morning, Joey found out his demo was accepted to be a finalist along with two other demos. He prepared a talk and participated in a talk competition with the other finalists. Wednesday evening, it was announced that Joey had won the student research demo competition.
The demo, "Radio Tomographic Imaging" (RTI) demonstrates Joey's research into radio signal strength-based passive imaging of people and objects who are within a wireless network deployment area. The goal is to use large networks of extremely simple radio devices to image motion within rooms and buildings from behind walls. The research is funded by an NSF CAREER award #ECCS-0748206, for "RF-Sensing Networks for Radio Tomographic Environmental Imaging", supervised by Prof. Neal Patwari.
ACM MobiCom 2008, held in San Francisco, is the 14th in a series of annual conferences sponsored by ACM SIGMOBILE dedicated to addressing the challenges in the areas of mobile computing and wireless and mobile networking. The MobiCom conference series serves as the premier international forum addressing networks, systems, algorithms, and applications that support the symbiosis of mobile computers and wireless networks. MobiCom is a highly selective conference focusing on all issues in mobile computing and wireless and mobile networking at the link layer and above.