The Women’s Center and Student Life’s Mosaic Center will be hosting several designated safe space sessions to talk about the recent events in Ferguson. These are not intended to be open discussions or debates. Rather, these opportunities are meant to provide intentional healing and supportive space for UMBC community members to process and share their thoughts, emotions, and reactions as related to racism, institutionalized violence, and anti-Blackness.

Added dates: 

• Monday, September 8 from 12-1 pm in the Women's Center
• Friday, September 19 from 2:30-3:30 pm in the Mosaic Center

Faculty, staff, and students are welcome to attend any/all of the community safe spaces scheduled for the following times:

• Wednesday, August 21st from 12-1pm in the Mosaic Center 
• Friday, August 22nd from 12-1pm in the Women’s Center
• Wednesday, August 27th from 12-1pm in the Mosaic Center
• Thursday, August 28th from 12-1pm in the Women’s Center

Contact womens.center@umbc.edu or mosaic@umbc.edu for further information.

UMBC Professors Nilanjan Banerjee and Ryan Robucci have been awarded an NSF grant from the NSF-NIH Smart and Connected Health program. The total sum is $650,000 over 3 years. It is a collaboration between UMBC, Madonna Rehabilitation Hospital and UA.

The collaborators include Dr. Susan Fager, a physical therapist from Madonna, and Dr. James Parkerson from UA, who is helping with the energy harvesting component of the project. The SCH program is very competitive, and last year the acceptance rate was close to 6%. The project deals with building wearable sensing systems for environmental control and therapy for paralysis patients, and cuts across electronics, sensor analytics, and usability.

According to Banerjee, “What we mean by environmental control is controlling appliances, and so on and so forth, and therapies basically helping…[patients] to improve their motion over time. So, we are building the sensors, we are building the software on the sensors, and also…the ensuing systems around it.”

Banerjee goes on to describe the project as “a marriage between electronics, software and usability.”

Robucci adds that “We’re working on this project to take into account the patient, and integrate them in as part of the system, rather than forcing them to use the system in a particular way. We want to make sure that the technology and interfaces that we’re building are adaptable to each person and their needs.”

The project is described in greater detail in this abstract from the NSF website:

An estimated 1.5 million individuals in the United States are hospitalized each year because of strokes, brain injuries and spinal cord injuries. Severe impairment such as paralysis, paresis, weakness and limited range of motion are common sequels resulting from these injuries, requiring extensive rehabilitation. This project is developing invisible sensing systems embedded into bed sheets, pillows, wheelchair pads, and clothing, for environmental control and physical therapy for such paralysis patients. The system detects gestures regardless of evolving environmental and patient conditions and provides explicit real-time feedback to the user. Through the use of low-cost and ultra-low power capacitive sensing, the system reduces hospital visits and therapy costs.

The proposed system addresses the limitations of existing assistive care sensors through three novel technical contributions: (1) The use of a self-sustainable hierarchy of sensors; textile-based capacitive sensor arrays (CSA) and inertial sensors on the human body; to improve the accuracy of gesture recognition while consuming minimal energy. The inertial sensors train the capacitive sensor arrays for different body positions; (2) A self-learning algorithm that determines gestures automatically regardless of the position of the patient’s body and conditions using templates of gestures and patient conditions over time; and (3) Seamless integration of the patient in the feedback loop using amplification and animation to provide explicit real-time feedback to the user on how she/he is performing on his/her physical therapy, and how the system is interpreting his/her gestures. Additionally, the PIs are developing a cross-disciplinary undergraduate and graduate course that focuses on developing sensing systems while being cognizant of the actual needs in a rehabilitation hospital. The PIs are also using local university initiatives to engage minority and women researchers in the project.

Banerjee notes that, “The project would not be possible without the efforts of very motivated and hard-working students in the Analog/Digital and MPSS labs: Rebecca Baldwin, Alexander Nelson, Stanislav Bobovych, and Gurashish Singh.”

In the next month or so, Microsoft Research will be developing a five minute video showcasing Robucci, Banerjee, and Dr. Sandy McCombe-Waller. Microsoft has expressed an interest in advertising the wearable sensing system, because the system utilizes the Lab of Things, Microsoft’s home automation tool. (This video is in addition to the live interview that Banerjee recently conducted with Microsoft Research.)

In related news, Robucci, Banerjee and fellow UMBC professor Chintan Patel have been given a TEDCO award of $150, 000 for the wearable sensing systems project. According to Banerjee, “The TEDCO grant deals with developing a prototype for environmental control for patients with paralysis. It will also help [us in] designing a product for the system. As part of the grant we will build the system, and evaluate it on real patients at University of Maryland, Baltimore.”

Related Links:

NSF Grant Award Details and Brief

Brief on TEDCO Grant

Attention all UMBC student employees!

What could be better than having an on-campus job?

Having an on-campus job and getting a notation on your transcript that tells employers you made the effort to enhance your professional development!

Make your campus experience count! Enroll in PRAC 102 Building Skills for Career Success TODAY!

Enrollment is limited to the first 100 student employees. Don’t let this opportunity pass you by!

Click HERE to enroll in this zero credit practicum.  Also, obtain the Syllabus below (SEE DOCUMENT DOWNLOAD).

Open to all levels and majors.

Must be a UMBC student employee working at least eight hours per week on campus.

Supervisor endorsement will be requested.

QUESTIONS, please contact Caroline Bodnar at the Career Services Center at carolc@umbc.edu or (410) 455-2216.

Interested in helping new computing majors transition to UMBC and their majors?

1 Teaching Fellow (aka TA) and 2 Peer Mentor positions are available for fall 2014. The course, CMSC101/IS101Y is for new freshmen computing majors (BTA, CS, CMPE, and IS) that will be taught by Dr. Seaman (IS) and Dr. Martin (CWIT).

Please read the attached job descriptions for more details. Must be a continuing BTA, IS, CS, or CMPE major.

TA Requirements: Juniors with at least a 3.0 GPA are eligible. Must be able to attend the lecture which meets on Tuesday and Thursday 1-2:15. 10 hours/week, $10 per hour.

Peer Mentor Requirements:Sophomores with a 3.0 are eligible for the peer mentor position. Must be able to attend the professional development session Fridays 1-2 pm. 4 hours per week, $9.25 per hour.

To apply send your resume, unofficial UMBC transcript and class schedule to Dr. Susan Martin, susan@umbc.edu by 5 PM, Friday August 8th.

Dissertation Defense

Virtual Circuit Provisioning in Challenged Sensor Internetworks:
with Application to the Solar System Internet

Ed Birrane

10:00am-12:00pm Monday, 11 August 2014, ITE325b

In this thesis, we present a challenged sensor internetwork (CSI) networking architecture which federates heterogeneous constituent networks behind an overlay routing mechanism abstracted from individual data link layers. The CSI is unique and required to implement expanding sensor networks.

Demand for sensing networks with increasing spatial footprints is evidenced by ongoing efforts to build geo-political border monitoring networks, intelligent highway initiatives, automated undersea surveillance, and NASA effort to construct a Solar System Internet. Existing network technologies fail to address multiple physical links, frequent disruptions, and significant signal propagation delays. The construction and maintenance of virtual circuits in an internetwork abstracted from differences in the physical, data-link, and transport layers of an internetwork represents a unique research contribution with immediate utility for a wide variety of sensing network concepts.

We describe the CSI architecture as the intersection of wireless, delay-tolerant, and heterogeneous networks and describe special characteristics of this architecture than enable useful assumptions to optimize messaging. We define an internetwork routing (INR) framework that decomposes the routing function into discrete logical steps and we provide algorithms for each of these steps. An inferred Contact Graph Routing (iCGR) algorithm populates logical graphs from local nodes. A Contact Graph Routing with Extension Blocks (CGR-EB) algorithm provides a hybrid source-path algorithm for synchronizing link state along network paths. A Predictive Capacity Consumption (PCC) algorithm exploits CGR-EB data to build a congestion model. Payload Aggregation and Fragmentation (PAF) and Traffic-Shaping Contacts (TSC) algorithms condition data and place limits on the amount of internetwork traffic carried over local networks.

From simulation, iCGR performs within ~15% of a perfect-knowledge system. CGR-EB has a speedup over standard approaches by 300% in stable topologies, by 3000% in unstable topologies, and by 11000% in unstable topologies with non-monotonic cost functions. PCC delivers 97% more data in congested networks over table-based approaches and 37% more data than the INR framework without the congestion model. PAF/TSC reduces message count by 43% while increasing goodput by 63%.

Together, these algorithms build and monitor virtual circuits in the CSI architecture. Portions of this work are in consideration for deployment in NASA networks.

Committee: Drs. Alan Sherman (Co-Chair, UMBC), Mohammed Younis (Co-Chair, UMBC), Dhananjay Phatak (UMBC), Vinton Cerf (Google), Keith Scott (MITRE), Hans Kruse (OU)

PhD Dissertation Proposal

“S:PT.-HAS NO PMD.”
Information Extraction from Clinical Notes

Clare Grasso

11:00am Monday, 4 August 2014, ITE 325b

Clinical decision support (CDS) systems aid clinical decision making by matching an individual patient’s data to a computerized knowledge base in order to present clinicians with patient-specific recommendations. The need for methods to extract the clinical information in the free-text portions of the clinical record into a form that clinical decision support systems could access and utilize has been identified as one of the top five grand challenges in clinical decision support. This research focuses on investigating scalable machine learning and semantic techniques that do not rely on an underlying grammar to extract medical concepts in the text in order to apply them in CDS on commodity hardware and software systems. Additionally, by packaging the extracted data within a semantic representation, the facts can be combined with other semantically encoded facts and reasoned over. This allows other clinically relevant facts to be inferred which are not directly mentioned in the text and presented to the clinician for decision making.

Committee: Drs. Anupam Joshi (chair), Tim Finin, Aryya Gangopadhyay, Charles Nicholas, Claudia Pearce and Eliot Siegel