Young Scholar Rajalakshmi Nandakumar: An App to Fight Opioid Overdoses

Segment Guest: Rajalakshmi Nandakumar – Rajalakshmi Nandakumar is a PhD candidate in the Paul G. Allen School of Computer Science and Engineering at the University of Washington in Seattle, Washington.


Listen to the entire episode on Science Friday.


Nandakumar App

If a person fails to interact with the app, it will contact someone who can administer naloxone. Credit: Mark Stone/University of Washington

Last year, about 47,000 people in the United States died from an opioid overdose, including prescription and synthetic drugs like fentanyl, according to the CDC.

And as the epidemic of opioid abuse continues, those looking to reduce death rates are searching for ways to keep drug users safer.

But what if your smartphone could monitor your breathing, detect early signs of an overdose, and call for help in time to save your life? Researchers writing in Science Translational Medicine this week think they have just that: smartphone software that can ‘hear’ the depressed breathing rates, apnea, and changes in body movement that might indicate a potential overdose.

University of Washington PhD candidate Rajalakshmi Nandakumar explains how the software, which uses smartphone speakers and microphones to mimic a bat’s sonar, can ‘hear’ the rise and fall of someone’s chest—and could someday even coordinate with emergency services to send help.

Sparking Young Minds to Solve Air Pollution and Traffic Fatality Problems

By Aakanksha Chowdhery

The Celestini Program’s objective is to grow the next generation of networking and communications innovators in developing countries by empowering undergraduate students to create social and economic transformation in their communities through technology. The Marconi Society and our Young Scholars achieve this by selecting universities with promising telecommunications and engineering undergrads and providing them with support and mentorship to help tap their students’ true potential.

Two Years, Two Big Issues

In 2016, the Celestini Program started in Uganda and in 2017 it expanded to India under the leadership of young scholar Dr. Aakanksha Chowdhery (Google) in partnership with Prof. Brejesh Lall (IIT Delhi). Student teams are selected through a technical screening exam, as well as an interview in spring. The selected student teams work over the summer at IIT Delhi to identify an important problem in their community that they would like to solve and then to prototype their projects. In 2017, the first year of the project pilot, thirty students expressed interest in working on the project and six students were selected to work on the problem of improving road safety.

In the second year of the project, 2018, more than one hundred students expressed interest in working on the program during the summer and three student teams, comprising eight students, were selected. They chose problem statements related to air pollution and road safety in Delhi. One team prototyped a website that forecasts air pollution levels in Delhi over the next 24 hours. Another team designed an Android app that uses a user-uploaded photos to estimate air pollution levels. A third team prototyped a low-latency platform to transmit vehicle-to-vehicle alerts about potential road safety hazards/collisions using Xbee radios.

Unique Approaches to Improving Air Quality

Preserving air quality is a critical challenge in the industrial and urban areas of many emerging economies. According to the World Health Organization (WHO) Global Ambient Air Quality Database released in Geneva, India has 14 out of the 15 most polluted cities in the world in terms of PM (particulate matter) 2.5 concentrations. One potential solution is to increase awareness of the problem by enabling users to understand and track the level of air pollution, as well as to receive forecasts for the next day along with information about the potential sources of pollution. This could provide the basis for taking effective pollution control measures.

One of the student teams worked on designing a temporal forecasting solution to predict the real-time and fine-grained air quality information in five locations around Delhi, based on the historical data reported by Central Pollution Control board. The solution predicts the air quality over the next 24 hours based on the level of different air pollutants including sulphur dioxide (SO2), nitrogen dioxide (NOx), PM2.5 and PM10. It also tracks the seasonal variations of the major pollutants and the potential sources of pollution at different points in time. The challenge in their project is to build accurate machine learning models that effectively adapt to the daily and seasonal variations of various pollutants. They developed an advanced machine learning model called CLair using LSTM techniques. The team deployed their solution approach on the Google Cloud Platform to automatically generate predictions every few hours on this website for five Delhi locations.

They showcase their project in this video.

Temporal forecasting can predict air pollution levels in locations where the Delhi government provides air quality data hourly, but this is limited to specific locations. A scalable approach requires crowdsourcing where we use inputs from the entire population and the easiest way to leverage crowdsourcing is via smartphone applications that are widely used by Delhi residents. Toward this goal, one of the student teams developed an Android smartphone application called Air Cognizer.

This application allows users to upload an input image of the sky horizon taken from their smartphone camera. Based on the certain features of the sky, such as how blue it is, the app predicts air quality particulate matter indicator, PM2.5 concentration, with an error less than 5%. The application combines image processing with machine learning using Tensorflow Lite to generate estimates by combining a pre-training machine learning model with a model trained online for each location based on all the user-uploaded photos. Two key challenges that students solve are preprocessing the data collected from different smartphone cameras so that the machine learning model works accurately and deploying this machine learning model on the smartphone with Tensorflow Lite to enable a low-latency real-time prediction experience. The video below provides a sample of the Android application that the team has launched in Google Play store

Year Two of Improving Road Safety

Another challenging problem that the student teams worked on is road safety. Over 200,000 people in India lost their lives in road accidents in 2015. Traffic accidents are the top cause of death for people aged 19-25. In Delhi, many of these accidents are caused by buses hitting pedestrians and cyclists. In 2017, one student team worked on prototyping a solution using Raspberry Pis and dashboard cameras to detect pedestrians and cyclists on potential collision course with the vehicle showcased in this video.

This year, a student team prototyped a solution that allows multiple vehicles to talk to one another at low latencies (tens of milliseconds) to send real time alerts about possible impending collisions to drivers behind them to prevent chain-reaction car accidents. This system leverages computer vision to classify a given scenario as one that may result in collision. Then the system uses vehicle to vehicle communications to broadcast alerts. Each vehicle, acting as a node, broadcasts information about its speed, location etc. and the other nodes receive and process this information based on the degree of relevance that the message holds. The solution approach was designed over Xbee radios as a low-latency solution (~30-40ms) available off-the shelf at low cost. This video and website link showcases their work during the project.

Going Forward

The concluding ceremony of this year was held on November 1 at IIT Delhi where Marconi Society board member, Prof. Andrea Goldsmith (Stephen Harris Professor of Electrical Engineering, Stanford University), gave an inaugural address. The ceremony was attended by the IIT Delhi Dean of Alumni Affairs & International Programmes, faculty members from EE and CS and industry partners. The winning team who developed the smartphone application Air Cognizer for air pollution analytics using smartphone camera photos was awarded a cash prize of $1500.

 

44958422754_546519e58b_o-705x481

Our results so far show that the Celestini Program brings hands-on learning and critical decision-making skills to participating students and that we are inspiring these students to pursue STEM-related studies to solve the problems they see in their communities. The participating students value the experience of developing prototypes that solve real-world problems with the potential to improve the well-being of their communities. We have already had the privilege of working with 14 outstanding students in the Celestini Program India and look forward to seeing the exceptional ways that they use STEM in their careers.

A Step Toward the Quantum Internet

By Paula Reinman and Joe Lukens

For the past two years, Joe Lukens, Marconi Society Young Scholar and Research Scientist at Oak Ridge National Laboratory, has been interested in frequency-based quantum information processing as an approach to making the quantum Internet a reality. By using ideas and models from the current Internet, Lukens believes that we can bring the benefits of the quantum Internet to people more quickly and in a more scalable way. He recently co-authored a paper in Optica by OSA outlining an approach to do just that.

Creating a More Practical Quantum Internet

While the classical Internet is built to transmit bits to different locations, the quantum Internet transmits quantum bits, or qubits, the basic unit of information in a quantum computer. If you have a small, low-power quantum computer in one location, you can connect it to a larger quantum computer elsewhere and transmit qubits between them. The quantum Internet would allow this on a global scale.

This is easier said than done. “Qubits are so squirrely,” says Lukens. “They degrade if they interact with their environment. You cannot copy a qubit without messing it up. You cannot amplify a qubit in order to send it further. These are the intrinsic challenges of quantum information.”

Frequency encoding leverages well-understood tools used in the classical Internet, such as pulse shapers and modulators, to control bits going through the system. By making the quantum Internet compatible with the classical Internet, we can make the quantum Internet more practical.

Why Do We Need a Quantum Internet?

While many more use cases for the quantum Internet will no doubt emerge when it is available, just like they did in the classical Internet, there are some immediate applications:

  • Security– When we have a quantum Internet, we can realize secure information between nodes, with security based on quantum mechanics rather than computational complexity. Quantum sensing can, in principle, let you detect quantities of dangerous chemicals more quickly and effectively. With entangled quantum sensors at different locations, we may even be able to detect new physics, such as dark matter.
  • Quantum computing – Although high in its hype cycle right now, quantum computing has real potential to solve problems that cannot be done efficiently with today’s technology. One example is Shor’s algorithm, which is an efficient way to factor large numbers. Public key cryptography exists today to let us communicate securely on the Internet precisely because of the difficulty of this problem. Quantum computing will make solving problems like Shor’s algorithm much more accessible and will become a disruptive technology in many fields.
  • Quantum simulation – When problems become very large and cannot be solved on traditional computers, quantum computers will be able to efficiently simulate other quantum systems. This could be very useful in basic sciences to help us understand particle physics, quantum chemistry, and more generally expand our understanding of the universe on scales ranging from atoms to galaxies.

What Was the Discovery?

All the applications above fall under the general umbrella of “quantum information processing”—using quantum systems to encode and process data. While quantum information processing can be achieved with any quantum particle (atoms, ions, electrons, superconducting circuits), single particles of light—or photons—are the best for traveling over long distances and connecting devices in the emerging quantum Internet. In the case of Lukens and his co-authors, the focus is on how to encode, manipulate, and measure information carried in some property of the individual photons.

One of the novel aspects of Lukens’ research is encoding this information in the photon’s color, or frequency, which means that the frequency of the photon corresponds to 0 or 1 – say the photon is 0 at red and 1 at green. Each frequency forms a “bin” in which a photon can exist, so that each photon can be described as a frequency-bin qubit. This is very similar to the principles of WDM, a widespread technology used in classical optical communications. WDM has great tools to control and use frequencies at high data rates, and it is only recently becoming clear how we can apply these ideas in quantum computing and make full use of these existing tools.

In order to develop large quantum networks with frequency bins, we will need to be able to apply quantum gates (basic logic operations) in parallel in optical fiber. Lukens and his co-authors discovered that they could have two different qubits and that they could apply two different gates, even on the same fiber.

The ability to have different gates on the same fiber and control the qubits in parallel is a technical achievement that could allow us to connect quantum nodes at different wavelengths, which otherwise would not be able to be linked together. This creates a quantum interconnect which takes quantum systems that are physically far away from each other and connects, or quantum entangles, them. This approach to building the quantum Internet leverages tools and technology from the classical Internet, providing a step forward to the many promising applications of connected quantum devices.

For more detail on the solution created by Lukens and Oak Ridge colleagues Nick Peters, Brian Williams, and Pavel Lougovski, as well as Purdue collaborators Hsuan-Hao Lu and Andy Weiner, check out the full article in Optica.

Marconi Society Names Four 2018 Paul Baran Young Scholars

Innovative researchers are honored for game-changing work advancing wireless and optical networking and disruptive healthcare applications

MOUNTAIN VIEW, CA, September 11, 2018

The Marconi Society, dedicated to furthering scientific achievements in communications and the Internet, has named four 2018 Paul Baran Young Scholars, honoring them for their outstanding research and academic performance. The four will receive their awards at the Society’s annual awards ceremony in Bologna, Italy on October 2, 2018.

Dr. Di Che, a Member of Technical Staff at Nokia Bell Labs, is selected for his work on short-reach optical links for applications like data center inter-connectivity and optical access networks. His work is critical for companies like Google and Facebook, who build data centers around the world to support huge data transfers. These networks use large numbers of optical transceivers and Che’s proposed digital subsystems can be applied to upgrade existing systems in a cost-effective manner that increases speed while reducing power consumption.

Che’s advisor from the University of Melbourne, Professor William Shieh, says, “Di has conducted breakthrough work on coherent optical short-reach communications that significantly and cost-effectively increases the capacity-distance product. Some of this original work on novel digital optical subsystems has created new research directions which are being investigated in recent top-tier conferences like the Optical Fiber Communication Conference (OFC) and the European Conference on Optical Communication (ECOC).”

Qurrat-Ul-Ain Nadeem, Marconi Young ScholarQurrat-Ul-Ain Nadeem, a PhD candidate at King Abdullah University of Science and Technology (KAUST), is recognized for her work in full-dimension (FD) massive MIMO technology. FD-MIMO has attracted significant attention from the wireless industry as a promising technology for Fifth Generation (5G) cellular systems. Her research bridged the gap between the 3GPP’s vision for FD-MIMO and the theoretical study of elevation beamforming by proposing efficient active antenna array designs, developing 3D channel models and characterizing spatial correlation functions to support and evaluate this technology. The proposed elevation beamforming schemes can significantly increase the number of served mobile broadband subscribers in 3D urban macro/micro scenarios while guaranteeing a significantly improved quality of service.

“Qurrat’s work establishes a proper link between the industry’s vision for FD-MIMO and the theoretical study of 3D beamforming,” says KAUST Professor Mohamed-Slim Alouini, Nadeem’s advisor. “She published pioneering works on the development of 3D channel models and spatial correlation functions. More recently, she put different aspects of FD-MIMO together to provide a mathematical framework for the design of elevation beamforming schemes in single-cell and multi-cell scenarios. Her works have gained a lot of visibility in a short time.”

Rajalakshmi Nandakumar, Marconi Young ScholarRajalakshmi Nandakumar is PhD candidate at the University of Washington conducting ground-breaking work that enables the detection of potentially life-threatening health issues using commonly available smartphones. Taking inspiration from the sonar-based navigation system that bats use, Nandakumar created technology that turns an ordinary smartphone into an active sonar system capable of detecting physiological activities, such as movement and respiration, without requiring physical contact with the device. Her technology has been licensed by a leading provider to help patients detect sleep apnea from the comfort of their own bedrooms, rather than in expensive and uncomfortable sleep lab settings. Nandakumar’s technology is also being tested to detect opioid overdoses.

“Rajalakshmi has a knack for selecting problems with high social impact,” says Dr. Shyam Gollakota, an associate professor at the University of Washington’s Paul G. Allen School of Computer Science & Engineering and Nandakumar’s advisor. “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. It is rare for a graduate student to have such impact with even one application, and she is doing it time and again.”

Ding Nie, Marconi Society Young ScholarDr. Ding Nie, an RF Engineer at Apple, is recognized for his work in developing models and systems to greatly increase throughput in wireless systems. Over the past decades, technical advances and consumer demand started the shift to devices with multiple antennas. While multiple antennas should theoretically increase throughput, they often suffer from issues associated with coupling, or the transmission of power between the antennas. Nie developed new throughput bounds for today’s multi-antenna systems by understanding the effects of coupling, guiding the design of antennas and circuits that will lead to increased throughput and faster wireless communications for consumers worldwide.

“Ding is the kind of person that you can let loose on a problem with little guidance and he comes up with very original ideas for solutions. He made a big advance in solving an open problem by coming up with new results that let us apply Bode-Fano bounds to multi-antenna systems,” says Dr. Bertrand Hochwald, Nie’s PhD advisor at the University of Notre Dame. “Ding’s work is so important that it attracted funding and leaves a legacy in my lab for another group of researchers.”

Young Scholar candidates are nominated by their academic advisors. Winners are selected by an international panel comprised of engineers from leading universities and companies and receive a $5000 prize plus expenses to attend the annual awards event. This year’s Young Scholars will be honored at the annual Marconi Awards Dinner where Akamai Co-founder, Dr. F. Thomson Leighton, a pioneer in the content delivery network services industry, will receive the $100,000 Marconi Prize.

About the Marconi Society

Established in 1974 by the daughter of Guglielmo Marconi, the Nobel Laureate who invented radio, the Marconi Society promotes awareness of key technology and policy issues in telecommunications and the Internet and recognizes significant individual achievements through the Marconi Prize and Young Scholar Awards. More information may be found at www.marconisociety.orgSubscribe. Follow: LinkedIn,Twitterand Facebook

Contact:

Hatti Hamlin
Hattihamlin@MarconiSociety.org
925.872.4328

Paula Reinman
Preinman@MarconiSociety.org
415.254.2004