Guardian Angel: Enabling Mobile Safety Systems

Prof. Marco Gruteser received a three-year NSF grant for the project Guardian Angel: Enabling Mobile Safety Systems

This is a collaborative grant with Rich Martin (CS Rutgers), Yingying Chen (Stevens), Jie Yang (Florida State). The total funding is $700K, with the Rutgers part being $350,000.

The project investigates the use mobile devices for enhancing personal safety by identifying dangerous situations
and mitigating them through appropriate intervention.

Abstract:

This project seeks to demonstrate that the mobile devices we carry and wear can play the protective role of a guardian angel and provide effective safety services. This is particularly relevant where our devices contribute to dangers by causing distractions for drivers and pedestrians. This project therefore pursues the vision of a system that offsets such unsafe use by continually sensing our activities and surroundings, identifying potentially dangerous situations, and mitigating them through appropriate interventions.

To date, safety services are typically constructed as dedicated stovepipe systems focusing on high reliability and a specific area of risk (e.g., automotive safety systems). Usage of such services remains limited since they require a dedicated investment for each system. This project trades off the ultra-high reliability of dedicated systems for the much more rapid adoption of safety services that comes with integrating them directly into mobiles and wearables. By demonstrating the feasibility of this approach, this project can contribute to saving lives, such as some of the more than 30,000 traffic fatalities in the United States each year. It can also inform regulatory policy for safety services at the CPSC, NHTSA, or FCC. Moreover, the PIs will not only train graduate students to conduct the research but also actively include undergraduates and high school students through research internship programs. Results will be disseminated through scholarly publications, active outreach to the wireless and mobile industry through WINLAB's industry events and connections.

At a technical level, the primary challenge lies not only in designing precise sensing techniques but in understanding and managing the level of confidence provided by these techniques. A key observation is that there are usually multiple possible interventions of varying levels of intrusiveness and tolerance to false positives. It is therefore important to match interventions to the confidence level provided by the sensors. To address this challenge, the project develops system support and a toolkit to help developers track and manage mobile sensing uncertainty. It explores crowdsourcing failure and relevance data from a large user population and automatically estimating the confidence provided by internal sensing and activity recognition components. The toolkit can further use the obtained metrics to help adapt sensing or application behavior. The system might conserve energy by switching one context sensor to a fallback mode from a diversity mode; or, the system could switch to a different intervention if the level of confidence has changed. System validation includes prototyping two application use cases, which sense and mitigate mobile device distractions for drivers and pedestrians. Together, these techniques form the guardian angel system, which supports development of many other effective safety services on mobile devices.

Status Updating Systems and Networks

Prof. Roy Yates received a three-year $476,000 grant award from the NSF for the project "Status Updating Systems and Networks".

Abstract:

Increasingly ubiquitous network connectivity has engendered applications in which sources send real-time updates of their status to interested recipients. Examples include position, velocity and acceleration updates from nearby cars that facilitate safe maneuvers in an intelligent transportation system; forest temperature and humidity updates that can help better predict and control forest fires; and status reports gathered from the human body that enable timely detection of bodily ailments. These applications need status updates to be as timely as possible despite limited network resources. This project explores new timeliness metrics as a basis for the evaluation and design of status update systems.

Starting from a time-average status-age measure that applies to a broad class of systems, this project analyzes queue-theoretic system abstractions consisting of a source, service facility and monitor. While initial conclusions have been based on queue-theoretic abstractions that are simpler than their real-world counterparts, the resulting insights are a useful starting point in understanding and designing systems that support real-time status updates. On this basis, the project goals include the design and evaluation of (1) distributed resource sharing algorithms for simple networks of competing status updaters, (2) multiple access protocols for status-updating wireless sensors sharing a random access channel, and (3) stochastic approximation algorithms for online optimization of status update systems operating in networks. An improved understanding of the analytic fundamentals of status updating will contribute to the development and ultimate deployment of efficient and timely status updating systems.

Automatic Workflow Capture & Analysis for Improving Trauma Resuscitation Outcomes

Prof. Ivan Marsic received a four year NIH grant for the project "Automatic Workflow Capture & Analysis for Improving Trauma Resuscitation Outcomes".

This is a collaborative project with Children's Nat'l Med Ctr, Washington DC, and Drexel University. The total grant is $1.6 M and Rutger's part is $750 K.

The project abstract is shown below.

Project Title: "Automatic Workflow Capture & Analysis for Improving Trauma Resuscitation Outcomes"

Although most deviations from trauma resuscitation protocols are variations that result from the flexibility needed for managing patients with different injuries, other deviations are "errors" that can contribute to significant adverse patient outcomes. Our long-term goal is to develop computerized decision support for trauma resuscitation and other fast-paced, high-risk critical care settings that monitors workflow for deviations that are known to be associated with adverse outcomes and provides alerts to these deviations, allowing remedial actions to be taken to prevent adverse outcomes. The overall objectives for this proposal, which are the next steps in the attainment of this long-term goal, are to:

(a) develop a scalable approach for recognizing activities during trauma resuscitation; and (b) identify deviations associated with adverse outcomes within the workflow of trauma resuscitation using process mining.

The central hypothesis is that trauma resuscitation activities can be monitored and analyzed in real time for workflow deviations that increase the likelihood of adverse patient outcomes. The rationale for the proposed research is that real-time identification of risk conditions for adverse outcomes will allow medical teams to take measures for reducing or preventing the impact of medical errors. The central hypothesis will be tested by pursuing two specific aims: 1) develop a scalable and automatic approach for creating an event log of activities occurring during trauma resuscitation; and 2) identify and characterize the team's ability to manage major errors during trauma resuscitation. Under the first aim, the approach will involve (i) the use of radiofrequency identification (RFID) technology and other modalities to create resuscitation event logs of human movement and object use and (ii) comparisons of sensor logs with logs obtained using manual video review ("ground truth"). For the second aim, the approach will involve the development and refinement of knowledge-based resuscitation workflow models using consensus sequences of activities from manually captured event logs. This project is significant because these methods are an essential early step toward the development of computerized decision support systems that can improve outcomes by monitoring and supporting the work of critical care teams. The proposed research is innovative because it represents a substantive departure from the status quo, focusing on developing methods for obtaining data from sensors to automatically track multiple, concurrent activities and for detecting deviations associated with adverse outcomes within a variable workflow. These methods are expected to form a basis for computerized systems for real-time decision support of medical teams that improve patient outcome during trauma resuscitation and other critical care processes.

Elastic Pathing - HCI work on MIT Technology Review

Prof. Lindqvist's work appeared in MIT Technology Review 
http://www.technologyreview.com/view/523346/how-to-track-vehicles-using-speed-data-alone/

The full article can be found at   http://arxiv.org/abs/1401.0052

Prof. Janne Lindqvist, a recently appointed assistant professor of electrical and computer engineering, member of WINLAB and director of the Human-Computer Interaction Laboratory, led a team to show how just your driving speed can be used to track where you drive.   This work, "Elastic Pathing: Your Speed is Enough to Track You" is part of a NSF-funded project for which Prof. Janne Lindqvist is the sole Principal Investigator.  

Prof. Janne Lindqvist's team included ECE PhD students Berhard Firner, Yulong Yang, and recently graduated Master's student Shridatt Sugrim.

janne-lindqvist-327x260c.jpg

 

The motivation for the project was that today people increasingly have the opportunity to opt-in to "usage-based" automotive insurance programs for reducing insurance premiums. In these programs, participants install devices in their vehicles that monitor their driving behavior, which raises some privacy concerns. Some devices collect fine-grained speed data to monitor driving habits.

Companies that use these devices claim that their approach is privacy-preserving because speedometer measurements do not have physical locations.

However, in their work the team showed that with knowledge of the user's home location, as the insurance companies have, speed data is sufficient to discover driving routes and destinations when trip data is collected over a period of weeks. To demonstrate the real-world applicability of their approach the team applied their algorithm, elastic pathing, to data collected over hundreds of driving trips occurring over several months. With this data and their approach, they were able to predict trip destinations to within 250 meters of ground truth in 10% of the traces and within 500 meters in 20% of the traces. This result, combined with the amount of speed data that is being collected by insurance companies, constitutes a substantial breach of privacy because a person's regular driving pattern can be deduced with repeated examples of the same paths with just a few weeks of monitoring.

Please contact Prof. Janne Lindqvist at   janne @ winlab.rutgers.edu for any further questions.

The motivation for the project was that today people increasingly have the opportunity to opt-in to "usage-based" automotive insurance programs for reducing insurance premiums. In these programs, participants install devices in their vehicles that monitor their driving behavior, which raises some privacy concerns. Some devices collect fine-grained speed data to monitor driving habits.

Companies that use these devices claim that their approach is privacy-preserving because speedometer measurements do not have physical locations.

However, in their work the team showed that with knowledge of the user's home location, as the insurance companies have, speed data is sufficient to discover driving routes and destinations when trip data is collected over a period of weeks. To demonstrate the real-world applicability of their approach the team applied their algorithm, elastic pathing, to data collected over hundreds of driving trips occurring over several months. With this data and their approach, they were able to predict trip destinations to within 250 meters of ground truth in 10% of the traces and within 500 meters in 20% of the traces. This result, combined with the amount of speed data that is being collected by insurance companies, constitutes a substantial breach of privacy because a person's regular driving pattern can be deduced with repeated examples of the same paths with just a few weeks of monitoring.

Please contact Prof. Janne Lindqvist at   janne @ winlab.rutgers.edu for any further questions.

A Novel MIMO Radar Approach Based on Sparse Sensing and Matrix Completion

Prof. A. Petropulu received a 3-year NSF grant for the project entitled: "A Novel MIMO Radar Approach Based on Sparse Sensing and Matrix Completion".

The abstract is as follows:

In both civilian and military applications, there is increasing interest in networked radars which are inexpensive and easily deployable, while at the same time enabling reliable surveillance of an area.

Examples include radar systems consisting of transmit and receive antennas placed on the nodes of a wireless sensor network, on backpacks, or on cars. The transmit antennas transmit probing waveforms. By jointly processing the signals from all receive antennas the desired target parameters can be extracted. This processing can be done at a fusion center, which collects the measurements of all receive antennas. Reliable surveillance requires collection, communication and fusion of vast amounts of data from various antennas, a task that is expensive and power consuming. This project proposes a novel approach for substantially reducing the amount of data that need to be communicated to a fusion center, while ensuring high target detection and estimation performance.

Multiple-input multiple-output (MIMO) radars have received considerable recent attention as they can achieve superior resolution. The proposed project will investigate a novel networked MIMO radar system that relies on advanced signal processing techniques, in particular, sparse sensing and matrix completion in order to achieve a tradeoff between reliability and cost. The project will (i) develop theoretical results on target recoverability and performance guarantees for matrix completion applied to MIMO radars. Insight from the analysis will be used to design new radar configurations that have improved performance; (ii) develop decentralized algorithms for implementing matrix completion, so that the proposed radar system can be implemented in a distributed fashion without the need for a fusion center; (iii) investigate the potential of the proposed scheme for spectrum sharing between radars and communication systems; (iv) investigate the possibility of further performance improvement by exploiting node mobility and optimal node placement though motion control.

Petropulu-mimo-radar-667x340.png

RADICAL Cybertools: Scalable, Interoperable and Sustainable Tools for Science

Prof. Shantenu Jha received an NSF grant for the project RADICAL Cybertools: Scalable, Interoperable and Sustainable Tools for Science.

To support science and engineering applications that are the basis of many societal and intellectual challenges in the 21st Century, there is a need for comprehensive, balanced and flexible distributed cyberinfrastructure (DCI). The process of designing and deploying such large scale DCI however, presents a critical and challenging research agenda. One specific challenge is to produce tools that provide a step change in the sophistication of problems that can be investigated using DCI, while being extensible, easy to deploy and use, as well as being compatible with a variety of other established tools. RADICAL Cybertools will meet these requirements by providing an abstractions based suite of well defined capabilities that are architected to support scalable, interoperable and sustainable science on a range of high performance and distributed computing infrastructure. RADICAL Cybertools builds upon important theoretical advances, production software development best practices and carefully analyzed usage and programming models. RADICAL Cybertools is posed to play a role in grand challenge problems, ranging from personalized medicine and health, to understanding long term global and regional climate.

There is a significant difference however, in the quality and capability required to support scalable end-usage science, compared to that of a research prototype. It is the aim of this project to bridge this gap between the ability to serve as a research prototype versus the challenges of supporting scalable end-usage science. This will be achieved by addressing existing limitations of usability, functionality, nd scalability. We will do so by utilizing conceptual and theoretical advances in the understanding of distributed systems and middleware, resulting in a scalable architecture and robust design. We will employ advances in performance engineering, data-intensive methods and cyberinfrastructure to deliver the next-generation of RADICAL Cybertools.

Jha-research-600x450.png

Microelectronically Stimulating and Actuating Nanofibers for Muscle Replacement and Regeneration

Prof. Laleh Najafizadeh, in collaboration with Joseph Freeman of biomedical engineering just received a 3 year award from the NSF for the project entitled, "Microelectronically Stimulating and Actuating Nanofibers for Muscle Replacement and Regeneration". In this project Professors Freeman and Najafizadeh will design and fabricate implantable, degradable devices to functionally replace muscle and regenerate new muscle tissue.

Using Big Data to Support Supply Chain Analytics and Optimization

ECE Research Professor Jaroslaw Zola with Javier Diaz-Montes received a collaborative NSF STTR I grant with a New Jersey startup (Optimal Solutions, Inc.). This is a $225K one year grant to work with OSI on big data problems in supply chain management. ECE Research Professor Jaroslaw Zola with Javier Diaz-Montesreceived a collaborative NSF STTR I grant with a New Jersey startup (Optimal Solutions, Inc.). This is a $225K one year grant to work with OSI on big data problems in supply chain management. 

Zola-S-caption.png

The NSF abstract of the proposal is available here:
http://www.nsf.gov/awardsearch/showAward?AWD_ID=1346452&HistoricalAwards=false

 

Polymer-Probe-Based Scanning Probe Microscope for Noninvasive, High-Speed, Broadband Investigation of Live Mammalian Cell

Prof. Jaeseok Jeon is part of a team that has been awarded an NSF grant of $636,557 for 3 years for the project   Development of a Polymer-Probe-Based Scanning Probe Microscope for Noninvasive, High-Speed, Broadband Investigation of Live Mammalian Cell.   This is a collaborative project with Profs. Qingze Zou (PI) of Mechanical and Aerospace Engineering and Nan Gao of Biological Sciences.

The goal of this IDBR project is to improve both the function and performance of scanning probe microscope (SPM) by one to two orders of magnitude for interrogating cellular and subcellular evolutions of mammalian cells. This goal will be achieved through the development of polymer-based cantilever probes coupling with a new imaging protocol of minimal-deformation and a new control-based nanomechanical measurement protocol for in-liquid SPM operation on live cells. Focused on SPM interrogation of mammalian cells of large volume and soft and corrugated membrane, the proposed research has four objectives: (1) Design, fabricate, and implement polymer-based cantilever probes with contact stiffness over four orders and allowable force (i.e., within the fracture limit of live cell membrane) over two orders of magnitude smaller than those of current silicon-based cantilever probes, and probe radius (~10 nm) two orders of magnitude smaller than that of bead-attached probes; (2) Design and implement a new imaging protocol that minimizes the scanning-caused cell membrane deformation while adaptively adjusting both the scanning speed and the force load to maximize the overall imaging efficacy, and a new nanomechanical measurement protocol for live cell and subcellular specimen in liquid that improves the accuracy in indentation measurement over an order of magnitude and increases the measurement frequency range over two orders of magnitude; (3) Demonstrate, validate, and evaluate the proposed SPM innovation through real-time quantification of viscoelasticity oscillation of cytoskeleton, and quantification/correlation of morphological and mechanical evolutions during cell division.

Pages

Subscribe to Rutgers University, Electrical & Computer Engineering RSS