Allen School News

It is with great sadness that the faculty, staff, and students of the Paul G. Allen School of Computer Science & Engineering mark the passing of Paul Allen — pioneering innovator, generous philanthropist, and faithful friend. Mr. Allen was a visionary who opened up new frontiers and pushed the limits of scientific discovery. His connection to the University of Washington ran deep. Through his vision, his leadership and his generosity, he transformed our program, our campus, our region, and the world.

“Paul’s vision of the role of science and technology in society coupled scientific discovery with the quest for solutions to humankind’s greatest challenges,” said Allen School professor Ed Lazowska. “It led him to establish the Allen Institutes for Artificial Intelligence, Brain Science, and Cell Science — and to invest in us, the Paul G. Allen School. We are deeply saddened by his death, and we recommit ourselves to the pursuit of this vision.”

When the Allen School was announced in March 2017, Mr. Allen expressed optimism that we were entering a golden age of innovation in computer science. “I look forward to watching the new Paul G. Allen School of Computer Science & Engineering continue to make profound contributions both to the field and to the world,” he said. “I look ahead with anticipation to the advances that will continue to flow from the school — advances that I hope will drive technology forward and change the world for the better.”

We did not have nearly enough time to demonstrate how we would repay his faith, but we will continue to draw inspiration from his words and his belief in what the Allen School could achieve.

“Paul was a truly remarkable person who changed the world multiple times in his lifetime, and whose initiatives will continue to change the world for decades to come,” said Allen School Director Hank Levy. “We can only hope to follow his example, by searching for the most important scientific and societal challenges of our era and applying our energies to solving them.”

Mr. Allen was a giant. As we said on our very first day as the Allen School, his gift will inspire us to reach higher every day.

A team led by Allen School professor Su-In Lee and Ph.D. student Scott Lundberg has developed a machine-learning system that both predicts and explains why some patients are at risk for developing hypoxemia, a potentially dangerous drop in blood oxygen levels that can occur in people under general anesthesia. A growing number of predictive machine-learning models have shown high accuracy in medical applications, but understanding how they arrive at their predictions remains a challenge. The aptly-named Prescience analyzes factors specific to the patient and procedure that may presage hypoxemia and explains their impact on a patient’s risk in real time to aid anesthesiologists in preventing life-threatening complications during surgery. The project, which was developed in collaboration with physicians at UW Medicine, Seattle Children’s, and the Veterans Affairs Puget Sound Health Care System, is featured on the cover of the latest issue of Nature Biomedical Engineering.

Hypoxemia during surgery is associated with a range of adverse medical outcomes, including cardiac arrest, post-operative infection, decreased cognitive function, and more. While operating room personnel are able to continuously monitor a patient’s blood oxygen saturation with the aid of pulse oximetry, such data do not enable them to anticipate a hypoxemic event — only react to one that is in process. Prescience supplements pre-surgery and real-time patient data with minute-by-minute data from more than 50,000 past surgeries to reliably predict when hypoxemia is likely to occur and which combination of factors led to its prediction.

Because it can both anticipate and explain hypoxemia risk, Prescience represents a marked improvement over existing decision support systems — which tend to support interventions that are more reactive than proactive — and over uninterpretable machine learning solutions. By providing both predictions and explanations, this approach can help doctors to establish an appropriate level of trust in the model. It’s this difference, Lee says, that makes Prescience such a powerful tool to improve patient outcomes. “Modern machine-learning methods often just spit out a prediction result. They don’t explain to you what patient features contributed to that prediction,” Lee explained in a UW News release. “Our method opens this black box and actually enables us to understand why two different patients might develop hypoxemia.”

The “why” is determined via a complex combination of factors, including patient physiology, medical history, vital signs, ventilator settings, medication, and time. Prescience relies on feature-importance estimates to weigh the strength of each factor in formulating its prediction, which an anesthesiologist can use to determine the most appropriate intervention. The team tested the ability of anesthesiologists to anticipate hypoxemic events with and without the aid of Prescience and found that, using the system, they could correctly predict whether a patient was at risk nearly 80% of the time.

Prescience team members, left to right: Bala Nair, Su-In Lee, Monica Vavilala, and Scott Lundberg. Mark Stone/University of Washington

Extrapolating the results of their experiments to the roughly 30 million surgeries performed annually in the United States alone, the researchers found that using Prescience could double from 15% to 30% the proportion of hypoxemic events that could be anticipated and potentially prevented — the equivalent of 2.4 million incidents per year. Given that 20% of the predicted risk is driven by settings under an anesthesiologist’s control, Prescience could become an indispensable tool for achieving better post-operative outcomes for a significant number of patients. “Prescience doesn’t treat anyone,” Lundberg noted. “Instead it tells you why it’s concerned, which then enables the doctor to make better treatment decisions.”

Contributors to the paper presenting Prescience include Drs. Bala Nair and Monica Vavilala, and software engineer Shu-Fang Newman of UW Medicine’s Department of Anesthesiology & Pain Management; Dr. Mayumi Horibe of the Veterans Affairs Puget Sound Health Care System; and Drs. Michael Eisses, Trevor Adams, David Liston, Daniel King-Wai Low, and Jerry Kim of Seattle Children’s. Kim and Lee initially conceived of the project. The team is planning to make further refinements to both the system and the interface before Prescience can be deployed in operating rooms around the country.

For more on Prescience, read the Nature Biomedical Engineering paper, “Explainable machine-learning predictions for the prevention of hypoxaemia during surgery,” and the UW News release. Also see related coverage by GeekWire.

The research team, from left: Vikram Iyer, Shyam Gollakota, Jennifer Mankoff, Ian Culhane, and Justin Chan. Mark Stone/University of Washington

Last year, researchers in the Allen School’s Networks & Mobile Systems Lab unveiled a set of prototypes and schematics that represented the first 3D-printed objects capable of communicating over WiFi without built-in electronics. Now, those smart objects are about to get even smarter thanks to new built-in analytics that can wirelessly track and store data about their use — even when they are out of the range of WiFi.

The new system is the product of a collaboration between the original group, led by professor Shyam Gollakota, and the Allen School’s Make4All Group led by professor Jennifer Mankoff. Together, this multidisciplinary team demonstrated how 3D-printed items imbued with analytic capabilities could be used for a variety of applications to improve quality of life or potentially even save a life, from smart assistive devices that absorb feedback from the user, to smart pill bottles that record when a patient last took their medication.

But first, they had to find a way to perform room-scale sensing while registering a range of bi-directional and rotational movements. The team also needed an effective means of storing and retrieving the collected data even if the object does not maintain a WiFi connection while relying on plastic parts. “Using plastic for these applications means you don’t have to worry about batteries running out for your device getting wet,” Gollakota noted in a UW News release. “But if we really want to transform 3D-printed objects into smart objects, we need mechanisms to monitor and store data.”

The team began by building on previous, groundbreaking work from Gollakota and colleagues that successfully married mechanical gears and switches with the digital capabilities of backscatter communication. Backscatter enables devices to transmit data by reflecting ambient radio frequency (RF) signals that are decoded by a WiFi receiver. For this project, the researchers aimed to extend the transmission range of their first 3D-printed objects to room scale — a necessity if such devices are to be practical for everyday living. By applying interference cancellation techniques, which enabled the receivers to pick up weaker backscattered signals from farther away, the team demonstrated their devices could successfully transmit data from a distance of four meters.

In 3D-printed smart objects, a switch made of conductive plastic filament, not electronic components, is used to transmit the data when activated by the mechanical turning of a gear. The original design contained a uni-directional switch with a single antenna. But as Vikram Iyer, a Ph.D. student in the Department of Electrical & Computer Engineering who works with Gollakota, explained, they had to switch up their approach to sense bi-directional movement. “This time we have two antennas, one on top and one on bottom, that can be contacted by a switch attached to a gear,” he said. “So opening a pill bottle cap moves the gear in one direction, which pushes the switch to contact one of the two antennas. And then closing the pill bottle cap turns the gear in the opposite direction, and the switch hits the other antenna.”

A 3D-printed e-NABLE prosthetic device that collects and stores data about its use. Mark Stone/University of Washington

To determine the direction of movement, Iyer and his colleagues embedded an asymmetric code into the gear’s teeth. As the gear turns, the specific direction of movement is indicated via the encoded sequence — “like Morse code,” according to Allen School Ph.D. student Justin Chan.

The team, which also includes undergraduate Ian Culhane of the Department of Mechanical Engineering, aimed to produce “anywhere analytics” by enabling the devices to collect and store data over time even as the user moves in and out of WiFi range. To accomplish this, the researchers developed a mechanical data capture and storage mechanism that relies on a ratchet system. The system holds state as data is collected out of range of WiFi; when the device is once again within range, the press of a button releases the ratchet so it can wirelessly transmit the stored data. As proof of concept, the team designed a special insulin pen that employs the ratchet system to store a user’s dosage history, based on how far the syringe’s plunger has been depressed.

Having solved the technical issues, the team was interested in finding out whether its approach could benefit the users of a particular class of 3D-printed objects: customized prosthetic devices. While the growing popularity and affordability of 3D printing has the potential to lower barriers of access to such specialized equipment, there is no practical way to track what happens with the devices once they are with the user — and evidence suggests that the abandonment rate for assistive technologies could be as high as 75%. But armed with embedded analytics, technologies such as the e-NABLE prosthetic limb, which assists children with hand abnormalities, could potentially track frequency of use as well as finer-grained data on rotation angle and direction to paint a fuller picture of how users are – or aren’t – benefiting from these devices.

For Mankoff, who has done extensive work in this area, the combination of 3D printing and backscatter technology is an opportunity to not only get to the root of those statistics, but hopefully, to turn the numbers around. “This system will give us a higher-fidelity picture of what is going on,” Mankoff explained. “Right now we don’t have a way of tracking if and how people are using e-NABLE hands. Ultimately what I’d like to do with these data is predict whether or not people are going to abandon a device based on how they’re using it.”

The team will present its research paper at the Association for Computing Machinery’s Symposium on User Interface Software and Technology (UIST 2018) next week in Berlin, Germany.

For more on this project, read the UW News release here and visit the project page here. Also check out related stories by Engadget, MIT Technology Review, Silicon Republic, and Professional Engineering.

Irene Zhang (left) with award committee chair Emmett Witchel

Allen School alumna Irene Zhang (Ph.D., ’17) has been recognized with the 2018 Dennis M. Ritchie Doctoral Dissertation Award at the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI) taking place in Carlsbad, California. The award committee selected Zhang’s dissertation, “Towards a Flexible, High–Performance Operating System for Mobile/Cloud Applications,” for its breadth and potential to inspire future research.

Zhang’s thesis makes multiple contributions spanning mobile and cloud computing. Today’s applications have become incredibly difficult to write; no longer simple desktop programs, they are now surprisingly complex distributed systems with components spread across geographically and functionally diverse mobile devices and cloud servers. Zhang presents multiple systems that address the challenges of programming in this space.

The first of Zhang’s contributions, Sapphire, offers both a new methodology for writing distributed applications and a system supporting that methodology. The Sapphire system greatly simplifies programming for distributed applications by separating generic application logic from distributed deployment decisions, such as where data or computation should be located, what data should be cached or replicated, and what consistency guarantees are necessary.

Another system, named Diamond, is concerned with a relatively new property of modern applications: reactivity. Applications such as games and social networking expect changes to distributed state to be propagated automatically and instantly to other users and to durable storage, so that all users see the same values in the same order. With Diamond, changes to shared application variables on any device automatically cause those values to be made durable in the cloud, update the values on other devices sharing them, and trigger those devices to “react” to the changes by updating the user interface so the user quickly sees the change.

Finally, in TAPIR (“Transactional Application Protocol for Inconsistent Replication”), Zhang dissects the protocols used in today’s distributed storage systems to improve the performance of consistency management among replicas. By simplifying the replication protocol with a technique she calls “inconsistent replication,” Zhang is able to provide both lower latency and higher throughput on distributed storage systems without sacrificing transactional properties.

The Dennis M. Ritchie Award was created by the Association for Computing Machinery’s Special Interest Group in Operating Systems (ACM SIGOPS) to recognize and encourage creative research in software systems in honor of A. M. Turing Award winner Dennis Ritchie, who was a pioneer in operating systems theory and implementation of the UNIX operating system. The award is presented during alternating years at OSDI and the ACM Symposium on Operating Systems (SOSP).

Zhang, who earned her Ph.D. working with professors Arvind Krishnamurthy and Hank Levy and is now a researcher at Microsoft Research, is the second Allen School student to be acknowledged by the Ritchie Award. Alumna Roxana Geambasu (Ph.D., ’11) earned an Honorable Mention for her dissertation “Empowering Users with Control over Cloud and Mobile Data” in 2013, the first year in which the award was given.

Congratulations, Irene!

Silin Zeng (center) with Lisa Simonyi (left) and Charles Simonyi

Every autumn, the Allen School kicks off the new academic year by highlighting the role of women in computing and sending off our delegation to the Grace Hopper Celebration of Women in Computing in style. This year, we broadened the scope of one of our favorite events of the year to celebrate the contributions of all underrepresented groups and highlight our expanding efforts to broaden participation in the field through activities such as the Grace Hopper conference, the ACM Richard Tapia Celebration of Diversity in Computing, the College of Engineering’s STARS program, AccessCSForAll, and more.

Nearly 100 students, faculty, staff, alumni, and friends gathered in the Paul G. Allen Center last night for our Diversity in Computing reception. The Allen School’s Assistant Director for Diversity & Outreach, Raven Avery, provided an overview of our recent activities, and fifth-year master’s students Melissa Hovik and Nicole Riley shared their experiences representing the Allen School at the Grace Hopper and Tapia conferences, respectively. Anat Caspi, Director of the Taskar Center for Accessible Technology, was also on hand to discuss how members of the Allen School community can get involved in the center’s work to promote inclusive design practices and produce technologies that increase independence and improve quality of life for people with motor and speech impairments.

Another of the evening’s highlights came when Charles and Lisa Simonyi, longtime friends and supporters of the Allen School, announced undergraduate Silin Zeng as the winner of the 2018 Lisa Simonyi Prize. The award recognizes a student each year who exemplifies the Allen School’s commitment to excellence, inclusiveness, and leadership. Zeng, who is in her final year at UW majoring in Computer Science and Finance, is an alumna of the UW Academy early entrance program for exceptionally talented students run by the Robinson Center for Young Scholars. She has been an enthusiastic contributor to the campus community as Treasurer of the UW chapter of the Association for Computing Machinery (ACM), Creative Director for the Asian Business Student Association, and a member of ACM-W and the Society of Women Engineers. She also has completed internships at Microsoft and Goldman Sachs — an experience that galvanized her commitment to advancing diversity via her work with ACM and as a mentor to her peers. As Lisa Simonyi noted when announcing the award, Zeng has spunk.

Thanks to the Simonyis for supporting diversity and excellence, and thanks to everyone who came out to celebrate the people who are making our school and our field a more welcoming destination for all. And congratulations to Silin on her well-deserved recognition for putting these values into practice every day!

For more about our efforts to advance diversity in computing, read about the Allen School’s contributions to this year’s Tapia conference in a recent blog post here, and check out our inclusiveness statement here.

The following post was authored by Raven Avery, Assistant Director for Diversity & Outreach at the Allen School

The author and students at Tapia 2018, left to right: Raven Avery, Alexandra Klezovich, Kat Wang, Nicole Riley, Esteban Posada, and Temo Ojeda.

The Allen School was well-represented at the 2018 Richard Tapia Celebration of Diversity in Computing last week in Orlando, with an impressive delegation of students, faculty, and alumni in attendance. This is the Allen School’s second year as a conference sponsor, and our fourth year sending students to connect with peers, explore new advances in research, and learn about how leaders in our field are working to make it more inclusive for everyone.

As the Allen School’s Assistant Director for Diversity & Outreach, it’s exciting to be in a space totally devoted to diversity in tech. It’s especially meaningful to hear the individual stories and perspectives of attendees, including our own students. These stories help us better understand the experiences of underrepresented groups in ways that numbers and data can’t represent. As undergraduate participant Temo Ojeda said, “The community that Tapia attracts is like no other: attendees, sponsors, and speakers have such a positive energy, with so many ideas to make an impact in the field.”

Tapia welcomes around 1,400 diverse computer scientists, mostly from groups that have been historically underrepresented in tech: people of color, people with disabilities, LGBTQ individuals, and women. The conference is an opportunity to expand our perspective on what computer science is and accomplishes, with presentations ranging from an exploration of the ways technology has negatively impacted the working class to the untold stories of Black Women Ph.D.s. Nicole Riley, a student in the Allen School’s fifth-year master’s program, described the experience: “I am so glad I was able to attend a conference that emphasized intersectionality — including race, gender, disability and more — so that I felt empowered to have important conversations regarding these topics.”

In my role, I have a lot of conversations about inclusion in the Allen School. But to make real progress in increasing inclusion, it’s crucial to view our work in a broader context: to appreciate our success, share our ideas with others, and to see clearly where we can improve. As undergraduate Alexandra Klezovich put it, “The Tapia conference has a dedication to diversity that makes it clear that we have a lot more work to do at UW in terms of inclusivity.” But along with highlighting the areas we need to improve, Tapia also provides a supportive community interested in seeing us succeed. “The talks I had with attendees were so genuinely open and caring that I forgot the stress of attending, presenting, or recruiting at the conference,” Alexandra said.

Seeing our student presenters in action was the highlight of Tapia for me, and I’m incredibly proud of their work: Alexandra and Nicole presented to a crowd of about 50 people on addressing impostor syndrome. Their session inspired faculty from other universities, one of whom said she plans to create an imposter syndrome workshop for her own students. Another said she learned more from Alexandra and Nicole than from any other speaker at Tapia.

In another session, Nicole and undergraduate Siyu (Kat) Wang shared their experience creating and implementing the Allen School Student Advisory Council — once again leading audience members to share ways they plan to adapt our model for the benefit of students at their own schools. Kat described the impact of presenting at the conference this way: “Being able to share my own experience at Tapia and learn from many others is exciting, amazing, and intimidating. It’s an incredible feeling when someone comes up to you after your presentation and thanks you for the inspiration. This experience made me feel like I can make a difference in the world, and I am doing it. ”

The Allen School was well-represented by alumni and faculty throughout the conference, a testament to our long-held commitment to diversity. Professor Emeritus Richard Ladner helped shape the Tapia celebration early in its history by convincing organizers to include disability as an aspect of diversity, and he was a strong presence throughout the conference again this year, speaking to large crowds and getting name-dropped by multiple speakers for being a leader in accessible technology. Alumnus Tao Xie (Ph.D., ’05), a professor at the University of Illinois Urbana-Champaign, served as the conference chair, while Hakim Weatherspoon (B.S., ’99) and Shiri Azenkot (Ph.D., ’14) were featured speakers. Weatherspoon, a faculty member at Cornell University, took part in an opening night panel on the potential and risks of autonomous systems. Azenkot, a faculty member at Cornell Tech, delivered a keynote on Designing Tech for People with Low Vision.

Tapia was also a chance for the Allen School to connect with other institutions and students participating in the FLIP Alliance, an initiative aimed at diversifying Ph.D. programs and faculty at leading universities that was launched last year with support from the National Science Foundation. And this week, more than 30 students traveled to Houston for the annual Grace Hopper Celebration of Women in Computing — another great venue for sharing ideas and promoting diversity in our field.

For any interested Allen School students who missed the opportunity to participate in Tapia or GHC this year, keep an eye out for funding applications in late spring to join us at the 2019 events!

Photo of the moon from afar uploaded to #MemoriesInDNA. This and thousands of other images encoded in synthetic DNA will be sent to the actual moon in 2020.

The #MemoriesInDNA Project spearheaded by a team of researchers in the Molecular Information Systems Laboratory is heading for the moon. The MISL, a partnership between the University of Washington and Microsoft, is working with Twist Bioscience to encode a collection of digital artifacts in synthetic DNA to be launched into space as part of the Arch Mission Foundation’s Lunar Library. The DNA archive, which will include thousands of photos crowdsourced from people around the world in addition to a selection of books from Project Gutenberg, is scheduled to make its lunar landing in 2020.

Space adds a new dimension to the technical challenges associated with storing and retrieving vast quantities of digital data in synthetic DNA. The MISL team has already achieved a number of milestones in its work, including the development of an effective system for random access of individual data files from among millions of DNA molecules. With the Lunar Library mission, the researchers face their most extreme test yet when it comes to preserving such data from the ravages of time, temperature, and radiation. For #MemoriesInDNA (tagline: “What do you want to remember forever?”), it offers an opportunity to engage humankind in advancing digital storage technology that is out of this world.

“Sending DNA into space is a great opportunity for us to make our storage system more robust,” Allen School professor Luis Ceze told UW News. “How can we protect the DNA so that it will still be readable thousands of years into the future?”

Ceze and his collaborators have partnered with the Arch Mission Foundation to explore novel ways of packaging the data to ensure that the archive survives the extreme heat of launch and potentially millions of years in space. For example, the foundation is designing a special payload to protect the DNA, complete with instructions on how to sequence the strands and retrieve the information contained within. But even with an optimal canister design, the research team anticipates some degradation from radiation will occur. To protect their precious cargo from the cosmic rays, the researchers will build both physical and logical redundancy into the archive. The former involves adding multiple copies of the same strand of DNA, so that even as strands degrade, others containing the same data will remain intact and readable. For strands that do not remain intact, the team plans to include additional information about the data itself — the logical redundancy — that will enable someone reading it to piece together any missing data should a portion of the contents be lost.

Members of the Molecular Information Systems Lab have developed a system for storing digital data in synthetic DNA. They are now working on ways to build in redundancy to protect against data loss from conditions in space.

The goal of the Arch Mission Foundation is to preserve and disseminate humankind’s most important information across time and space for the benefit of future generations. The DNA archive is the first special collection slated for inclusion in the Lunar Library, and one that the foundation hopes to grow over time into the largest repository of human knowledge encoded in DNA. Anyone on Earth can add their photo to the launch collection by uploading it via memoriesindna.com or by emailing it as an attachment to lunarlibrary@memoriesindna.com.

“With this collaboration, we show the value of human knowledge and the incredible density achieved with storing digital information in DNA,” said Microsoft senior researcher Karin Strauss, who is also an associate professor in the Allen School. “This work with Arch continues to push the boundaries of what’s possible in increasingly exciting ways and remarkable directions.”

Read the Arch Mission Foundation press release here and the UW News story here.

The University of Washington has announced that the Department of Electrical Engineering (EE) is changing its name to the Department of Electrical & Computer Engineering (ECE). This name change updates the identity of one of the Allen School’s closest campus collaborators to better reflect their current teaching and research — and the growth of interest by electrical engineering students in embedded systems and other hardware-related research. The change from EE to ECE is a natural outgrowth of the evolution of the field and a reflection of the longtime partnership between the former EE department and the Paul G. Allen School of Computer Science & Engineering.

“ECE and the Allen School have a long history of collaboration when it comes to research and teaching that spans the boundary between computing and electrical engineering,” said Hank Levy, director of the Allen School and Wissner-Slivka Chair in Computer Science & Engineering. “This name change recognizes UW’s strength at the intersection of these two exciting fields, where students, faculty and alumni of both programs are shaping the future of hardware innovation and doing extraordinary work in sensors, wireless, chip design, and more.”

Eleven years ago, the two programs created the UW Experimental Computer Engineering Lab (ExCEL), an initiative to facilitate the recruitment of faculty and interdisciplinary collaboration at the intersection of their fields. The result was the hiring of outstanding joint faculty who are driving innovation at the nexus of computing and electrical engineering, including Shwetak Patel in sensing systems for energy and health, Georg Seelig in synthetic biology, Linda Shapiro in computer vision for medical applications, Joshua Smith in wireless-power and zero-power devices, and Michael Taylor in microprocessors, ASICs, and hardware design. By minimizing the barriers at the boundary of their programs, the Allen School and ECE are enabling students to participate in high-impact, cross-cutting computer engineering research.

“These top caliber faculty have attracted sought-after graduate students, which feeds the cycle of excellence, and we believe our new name will only strengthen such recruitment efforts,” said ECE chair Radha Poovendran. “The field of electrical and computer engineering has produced inventions that have changed the world and the way we live. As our department begins a new era, the opportunities for impact are endless.”

The change in name to ECE has no impact on degrees granted. The Allen School will continue to award UW’s degrees in Computer Science and Computer Engineering, while ECE will continue to award UW’s Electrical Engineering degree.

Read the ECE announcement here.

Photo by Kathleen B. Turner/University of Washington

Nandakumar’s workspace, including the collection of smartphones used in her research.

Allen School Ph.D. student Rajalakshmi Nandakumar’s research has awakened a lot of interest in how mobile devices can be used to improve health and quality of life, from detecting signs of sleep apnea to alerting emergency services of a drug overdose.

Fresh off her selection as a Paul Baran Young Scholar by the Marconi Society, Nandakumar is featured in the latest edition of GeekWire’s Geek of the Week. In addition to fielding questions about her favorite Star Trek captain (Kirk), her favorite gadget (3D printer), and other suitably geeky pursuits, Nandakumar explained to GeekWire what motivates her to push the boundaries of what a smartphone can do.

“Often people associate wireless signals with communication,” she noted. “Though it is the primary purpose, these wireless signals we are surrounded with can also be used to enable novel applications in other domains like healthcare, human computer interaction and security.”

Check out the full article here, and read more about Nandakumar’s Young Scholar Award here.

Way to go, Rajalakshmi!

Photo by Mark Stone/University of Washington

Allen School Ph.D. student Rajalakshmi Nandakumar has been recognized with a Paul Baran Young Scholar Award from the Marconi Society for her work on mobile apps capable of detecting potentially life-threatening health issues. She is the first Allen School student to receive the award, which honors outstanding early-career researchers in wireless communications and the internet. Young Scholars are selected by an international panel of engineers from industry and academia. According to internet pioneer and Marconi Society Chairman Vinton Cerf, Nandakumar represents those qualities that the organization aims to promote through the program.

“Our Young Scholar award attracts the world’s brightest young communications researchers,” he said. “Rajalakshmi embodies every characteristic that we seek—unparalleled intellectual capability, entrepreneurial spirit, and the vision to use her work to better humankind.”

Nandakumar is a researcher in the Allen School’s Networks & Mobile Systems Lab, where she works with professor Shyam Gollakota on a range of projects that leverage the increasingly sophisticated sensing capabilities of smart devices to improve health and quality of life.

“Rajalakshmi has a knack for selecting problems with high social impact,” observed Gollakota. “What’s incredible is that she has developed technology that seems like science fiction and has gotten it adopted by hundreds of thousands of people in the real world.”

Gollakota is referring to ApneaApp, a contactless smartphone app that Nandakumar developed to measure minute changes in a person’s respiration and movement during sleep. The app analyzes those measurements to detect whether a person is suffering from sleep apnea, a breathing disorder that affects more than 18 million adults in the United States alone. The condition often goes undiagnosed, as the usual methods of identifying sleep apnea involve either an expensive polysomnography test requiring an overnight stay in a hospital or sleep clinic, or the use of in-home systems that tend to have high failure rates. Taking inspiration from how bats navigate, Nandakumar turned a smartphone into an active sonar system that can be used to monitor an individual’s sleep from the comfort of their own bedroom, without any special instrumentation.

Nandakumar’s work on ApneaApp earned her the UW CoMotion Graduate Innovator Award in 2016. The technology, which was developed in collaboration with Dr. Nathaniel Watson of the UW Medicine Sleep Clinic, was subsequently licensed by ResMed, a global leader in the sleep industry. The company built the capability into its SleepScore app released earlier this summer to enable individuals to track their sleep quality and share data with their physicians.

Nandakumar chose to focus on mobile apps for health based on her experience growing up in India with a father in the healthcare industry, which exposed her to many of the issues she is trying to address through her research. She also liked the idea of working on projects that have far-reaching impact outside of the lab.

“The best part of my work is seeing real people using my technology and knowing that it benefits their well-being,” Nandakumar told the Marconi Society. “As a computer scientist, I find that very fulfilling.”

Nandakumar has since turned her attention to another pressing public health issue: the opioid epidemic. For her latest project, she is exploring how to use a smartphone and sonar to monitor a person’s condition and summon help in the event of an overdose. Around 100 people in the United States die each day from opioid use. It will be the latest in a line of projects that have sought to extend the capabilities of mobile devices beyond mere communication.

“It is rare for a graduate student to have such impact with even one application, and she is doing it time and again,” Gollakota said.

Nandakumar and her three fellow Young Scholar recipients will be formally recognized next month at the Marconi Society’s symposium in Bologna, Italy.

Read the Marconi Society’s press release recognizing Nandakumar here and the full award announcement here. Learn more about the Young Scholars program here.

Congratulations, Rajalakshmi!

Photos by Mark Stone/University of Washington