Study Information:

We are almost there! DAY 4 of AGING WEEK! 

Follow us on Twitter, Facebook, and Instagram (UMBCAging). And, join our myumbc group for updates too!

Computers can crunch mind-boggling arrays of data. They can even win quiz shows. But are there more powerful applications of this analytical power yet to come? Claudia Pearce ’89 M.S., ’94 Ph.D., computer science, is the Senior Computer Science Authority at the National Security Agency (NSA). The winner of UMBC’s Alumna of the Year Award in Engineering and Information Technology in 2014, Pearce is diligently seeking the answer to that question.

Watson is IBM’s Deep Question Answering system. You might recall that when Watson was put to the test against human contestants on the television quiz show, Jeopardy!, the system successfully bested its competitors in providing questions to answers whose associated question was already known. (And won $1,000,000.)

But like any game, Jeopardy! has its rules – and its limits. Along with my colleagues and others in the field who study big data and predictive analytics, I’ve been wondering whether the techniques implemented in Watson could be used as a powerful knowledge discovery tool to find the questions to answers whose associated questions are unknown.

Subspecialties in the fields of computer science and statistics such as knowledge discovery, machine learning, data mining, and information retrieval are commonly applied in medicine and in the natural and physical sciences – and increasingly in the social sciences, advertising, and cybersecurity, too. (It’s often called “computational biology” or “computational advertising.”)

And as the scope of computational practices has increased, the resources needed to perform it have shrunken tremendously. Ten years ago, massive computation was primarily in the areas of physics, astronomy, and biology, where petabytes of data were collected and analyzed using massive high performance computing systems. The advent of Cloud computing technologies –and their increasing public availability – now allows institutions, companies, and users to rent time for large-scale computation without the enormous costs of creating and maintaining supercomputers.

Additionally, programming and data storage paradigms have evolved to make use of the inherent parallelism in many domain applications. This trend has created new applications for computer science that provide individuals and organizations access to a plethora of online information in real time.

Real-time data sources spur not only social media, but online commerce, video streaming, and geolocation. Wireless technologies and smartphones put that information in the palm of our hands.

The power and speed of these technologies have aided the machine learning and data mining techniques at the heart of analytics, from retrieval of simple facts to trends and predictions. Advertising applications, for instance, analyze your click stream and cookies so that ads tailored to your interests appear as you browse in real time.

Yet the process of developing and maintaining analytics has its costs. First, there is labor. It usually requires teams of people to identify and solve problems in various domains. Analysts (who are usually experts in their subject) develop a collection of research questions in their discipline. They are teamed with statisticians, computer scientists, and others to develop and write programs to put the data in a usable form and create machine learning applications, tools, and algorithms. This combination of data and programming combines into analytics designed to answer a question in a given line of inquiry.

Labor isn’t the only cost. Depending on the application, analytics can be reused – but eventually need to be refreshed with new data. This is particularly true when the analytic is designed to be predictive. Real-time financial industry data, for example, requires that credit card fraud models must be recreated at least annually. Computational advertising models must be refreshed weekly.

Outdated analytics become an artifact of the maintenance cycle. Reuse requires knowledge specific to the analytic, data, and inherent question, and is most likely unknown outside of a small development team. So how can we get beyond these limitations and make a simple easy-to-use system that helps people get answers to questions beyond Googling them?

Part of the answer may be found in a series of Beyond Watson workshops and other activities involving university, government, and industry partners, including one held at UMBC in February.

We’re looking at things like natural language, which is at the core of the ultimate computer human interface. Think back to Star Trek, when Spock would say something like: “Computer, what is the probability the Klingons will attack the Enterprise in this sector of the galaxy?” The computer would often engage in a back and forth interaction with Spock, asking for more information or clarification before offering one or more scenarios (and probabilities supporting those scenarios) to aid the crew of the Enterprise in their next move. When we can ask a computer a question and then engage in a dialogue with it in this way, we can freely use computers to their best advantage. This sort of exchange allows us to hone in on an answer (or answers) to our question, supported by knowing both how the information was derived and what level of confidence to place in it.

Envisioning such a model opens up new vistas. We may not be limited to retrieving existing answers from Wikipedia-like text, but use all available data to elicit answers to non-obvious questions, or to queries that have never been asked. We might also dispense with arcane interfaces that are poorly matched to both the task at hand and the needs of users and consumers. Database management systems, for instance, have historically been developed to ask a few specific questions of data, but imposing such a structure on the data makes it very difficult to anticipate (or answer) questions we weren’t thinking of when we built the system.

Pushing our thinking – and technology – to generalize on the automation of building big data analytics could permit us to leverage existing tools and build on them instead of shelving them. And pulling these tools together in yet another set of big data analytics may even allow for the entire enterprise of analytics (newly created systems as well as existing ones) to help us advance particular knowledge.

Your cell phone has a plethora of apps (collected in an “app store”) to help you make the best use of it. Creating a similar “analytics store” for our Question Answering systems will accelerate automation of these processes and encourage crowd sourcing in analytics development. It’s a vision of the future for which technology already exists. By specifying and clarifying what we want big data analytics to accomplish, we can start to build that future now.

Note: The views and opinions expressed are those of Claudia Pearce and do not reflect those of NSA/CSS.

April 2015 · by umbcalumni · Bookmark the permalink. ·

By Andrew Myers

From the Apple Watch to Fitbit, the rage in technology these days is all about wearable, touchable devices. Tech gurus and cutting-edge engineers talk of a day when all the many electronic devices that surround us will be networked together in a magical electrical collaboration that will change how we live our daily lives. Many of these devices, if not all, will be controlled by touch.

Some have taken to calling this vision the “Internet of Things,” but others have begun to believe even that grandiose thinking may be too narrow. The “Internet of Everything” is more accurate, they say.

Unfortunately, for millions of people who are paralyzed or challenged by neuromuscular diseases, that vision of an “everything” Internet may be largely (and literally) out of reach.

The myriad touch-based interfaces that are filling, and will continue to fill, our world will be lost on them. And so, too, will the ability to control their lives and, perhaps, the dream of an independent life.

Buz Chmielewski is one of those people. At seventeen, a surfing accident confined him to a wheelchair. His legs no longer worked, but Chmielewski retained some movement in his arms and hands.

Putting that “Internet of Everything” into play for Chmielewski and others like him is what motivates a team of UMBC engineers working together as the ECLIPSE Cluster.

“Ironically, these are exactly the people who need these devices most of all, but they won’t be able to access or control the electronics that surround them if they can’t use a touch device,” says Nilanjan Banerjee, an assistant professor of computer science and electrical engineering at UMBC. “We’re trying to give them that control of their lives.”

Indeed, the numbers of those who need such help navigating new technologies are bigger than most would imagine. In the United States alone, some 1.5 million people are hospitalized yearly just from spinal injuries, strokes, and traumatic brain injuries.

So the researchers who make up the ECLIPSE Cluster are designing and building devices that will provide greater facility of use of electronics and other technology.   They are collaborating with willing partners like Chmielewski and other researchers – including those at the University of Maryland, Baltimore – to find out if they work and how they can be improved.

With his fellow professors of engineering Ryan Robucci and Chintan Patel, and a group of eager students, Banerjee is imagining ways that the highly connected world of tomorrow and designing products today that could vastly improve the lives of people like Chmielewski.

MANUFACTURING TOUCH

The touchscreens and touch-based wearables at the heart of technological innovation don’t work very well for people with motor control issues.

Touchscreens are too rigid and too fragile for many of these users on a day-to-day basis and they are too sensitive to inadvertent motions to be practical for people with motor control problems.

“We’re working on touchless gestural devices that use sensors similar to what is used in your smartphone to control household electronics,” says Banerjee. “But in our case, the hand or arm only needs to be in the vicinity of the pad, not actually on it, for the sensor to detect the motion.”

So why not use flexible fabric-based touch interfaces? The ECLIPSE researchers observe that while this technology solves the first two issues, it raises a third one. These interfaces require direct and repeated contact with the fabric, which can cause abrasions from the constant rubbing, often without notice to users who may lack sensation in the extremities.

“These abrasions can become severe, so we really wanted a device that did not require the user to make physical contact,” Robucci says.

Working closely with Sandy McComb Waller, an associate professor of physical therapy and rehabilitation science at the University of Maryland School of Medicine, the ECLIPSE Cluster has designed and developed a fabric integrated with sensors that can read a person’s slightest gesture.

The ECLIPSE device is unassuming in appearance. It looks like a simple patch of fabric about the size of an electric heating pad. Woven into the fabric, however, is a grid of electrically conductive threads that can sense the changing electrical charge when a human hand or finger passes close by.

In engineering terms, these are known as capacitive sensors. They work in a way similar to the touchscreen technologies in smartphone and tablet computers, but they don’t require the user to physically touch the screen.

“In this case, close is more than good enough,” Banerjee says.

Such controllers might one day be integrated into bed sheets, pillows, wheelchair pads, or clothing. Their potential uses? Manipulate light switches, televisions, thermostats, or even make a 911 call. Virtually any electronic device, even a computer, could be controlled from this one device.

TRAINING THE DEVICE

The flexible fabrics hold many advantages over their glass-screened cousins. First off, they conform to practically any surface without any loss of sensitivity. A user could wear it over a knee one day, on a forearm the next, and the device would work the same. No rigid glass touchscreen could ever be so versatile.

Second, the ECLIPSE device is trainable. “We started out with predefined gestures, but the people we are designing for have limited range of motion and most have limited motor control, so they didn’t like it. It was too difficult for everyone to learn the same motions,” Robucci says.

Instead, the ECLIPSE team recalibrated. They began designing algorithms that help the users record their own gestures and to tell the computer what the gestures mean.

“Sometimes, a user is capable of only a finger twitch, but we can even map those motions to specific instructions. People will be able to control the devices around them with the slightest of movements,” Banerjee says.

Best of all, perhaps, the ECLIPSE sensors are ultra-low power and extremely affordable, costing just 5 to ten cents per device to produce.

Down the road, Banerjee talks of forward-looking applications that will help not only those with physical challenges, but just about everyone on the planet.

“You could imagine putting these sensors in car seats, where a driver might be falling asleep at the wheel or distracted looking at a smartphone. Our capacitors can be embedded to detect whole body motion: Is the driver facing the road? Is he is on a phone? Is she falling asleep?” Banerjee explains. “Instead of an Internet of Everything, we’ll have an Internet of Everyone.”

Banerjee adds that these or similar systems based on similar technologies also could be deployed in life-saving situations, such as in cribs to detect breathing patterns that could prevent Sudden Infant Death Syndrome (SIDS), a mysterious killer in which infants simply stop breathing in their sleep.

GETTING END RESULTS

Things are beginning to blossom for ECLIPSE, especially as researchers and funders outside the close-knit UMBC community to begin take note of their work and invest in it.

Last August, the National Science Foundation and the National Institutes of Health placed a big bet on their work, seeding the group with a $650,000, three-year grant to fuel their research. TEDCO, a program sponsored by the State of Maryland to facilitate transfer and commercialization of technology flowing out from the state’s research labs, soon followed with an additional $150,000. Microsoft Research and its “Lab of Things” rapid prototyping program are also supporters of the ECLIPSE work.

Robucci says that one key to the success of the ECLIPSE Cluster and its researchers are their focus – and capacity – to see the big picture and make it happen within their own lab. Banerjee is the software expert. Robucci focuses on analog to digital signal processing that turns the real world into data a computer can understand. And Patel is a chipmaker – an expert in very large-scale integrated circuits. The goal of ECLIPSE is to build end-to-end cyber-physical systems.

“We’re working on complete systems here, not on individual components,” observes Robucci, “so we have to be able to imagine the end result – the product – and then work at all levels…to design and optimize the components and algorithms to make it a reality.”

Though ECLIPSE began as a loose affiliation of like-minded engineers, it is quickly growing into something more – an incubator of ideas and solutions to some of the most challenging questions of the day.

“If you’re working alone you often think, ‘Can I do this? Is this possible?’ and then you have to find the answers on your own,” Robucci says, “but at ECLIPSE we’re sort of all-inclusive. If you ask the same question, someone else has the answer, ‘Yeah, we could do that.’”

Banerjee agrees: “I couldn’t do it alone, and neither could Ryan or Chintan. Each of us brings unique and important expertise to the equation and the sum is greater than the parts. It’s as if you added three individuals together and you end up as four.”

      

U.S. Naval Academy Superintendent Vice Adm. Ted Carter signed a Cooperative Research Acquisition and Development Agreement (CRADA) with University of Maryland, Baltimore County (UMBC) President Freeman Hrabowski April 21st on the UMBC campus.

This agreement will support future partnerships between the two schools, beginning with five cyber security research projects from teams of faculty from both institutions.

This collaboration has its roots from when Chief of Naval Operations, Adm. Jonathan Greenert, visited the University of Maryland, Baltimore County (UMBC), in February 2014. During the visit Greenert met with Hrabowski to discuss ways to work together on Science, Technology, Engineering and Math (STEM) initiatives. This initial visit between the two illuminated the institutions’ mutual strengths and interests in cybersecurity.

The initial cyber collaborative projects between the USNA and UMBC will involve areas from tactile authentication for mobile devices to detecting anomalies in cyber-physical systems to securing cloud services using policy-based approaches.

“I wanted to do this since I assumed the position of Superintendent last year,” said Carter, from the UMBC campus. “To partner with a school like UMBC is a great opportunity, particularly a school represented with so many opportunities for woman, international students and minorities.”

The Naval Academy continues to take steps to ensure future graduates are invested with the skills and knowledge necessary to operate in an emerging cyber security environment. The academy is the only U.S. institution of higher learning that has mandatory cyber security classes. The baseline is to provide every academy graduate with an understanding of the cyber domain and how it impacts their commands and their ability to conduct their missions.

The academy also now offers a cyber operations major, an interdisciplinary course of study that covers a wide range of cyber-related operations, both technical and non-technical. And, in December 2014, Congress approved funding for a dedicated building to house USNA's Center for Cyber Security Studies.

"I predict 30 years from now, what we did here (at the CRADA signing) will be vital to national defense," said Carter.

Source: USNA Public Affairs (text and photo)