Federated Learning from Electronic Health Records Paper Receives Best Paper Honors

By Ioannis Paschalidis
August 29th, 2019

Our paper on

``Federated learning of predictive models from federated Electronic Health Records'' (with Theodora S. Brisimi, Ruidi Chen, Theofanie Mela, Alex Olshevsky, and Wei Shi), International Journal of Medical Informatics, Vol. 112, April, 2018, pages 59- 67,

has been selected as a Best Paper and is included in the 2019 Yearbook of the
International Medical Informatics Associations (IMIA), Section on Clinical
Research Informatics.

Know What’s Good for Your Health? Artificial Intelligence

By Ioannis Paschalidis
August 22nd, 2019

  • Art Jahnke


    Art Janke

    Art Jahnke began his career at the Real Paper, a Boston area alternative weekly. He has worked as a writer and editor at Boston Magazine, web editorial director at CXO Media, and executive editor in Marketing & Communications at Boston University, where his work was honored with many awards. Profile

How to Make Self-Driving Vehicles Smarter, Bolder

By Ioannis Paschalidis
August 22nd, 2019

With $7.5M DOD grant, BU researchers head international team developing bioinspired control systems for self-navigated vehicles

By Kat J. McAlpine (originally published on BU Today, April 17, 2019)

Autonomous vehicles that can maneuver themselves around any city are already out on our public roads, says Yannis Paschalidis, but operating off-road remains a challenge.

“These vehicles are designed for very structured environments, within roads and lanes,” says Paschalidis, a College of Engineering professor of biomedical, systems, and electrical and computer engineering, who uses data science and machine learning to develop new software algorithms and control systems. “They are only programmed to recognize a small number of different types of objects.”

Paschalidis has a vision for self-driving vehicles that would launch them from the mundane world of suburban commuting to the most dynamic (and sometimes harsh) places around the globe. “We are interested in developing fundamental principles that can be applied to autonomous vehicles capable of navigating themselves on the ground, underwater, and in the air,” he says.

To make that possible, the Department of Defense has awarded $7.5 million in Multidisciplinary University Research Initiative (MURI) funding for Paschalidis to team up with other scientists from Boston University, Massachusetts Institute of Technology, and Australian research universities.

“Our team spans two continents and brings together some of the preeminent experts in neuroscience—with emphasis on localization, mapping, and navigation functions—with experts in robotics, computer vision, control systems, and algorithms,” says Paschalidis, the team’s principal investigator. “We’re essentially going to use insights from neuroscience to better organize and control engineered systems.”

Their goal? To investigate how the brains of living organisms—namely ants, animals, and humans—process their spatial environments to derive meaningful navigation information. The international research team calls their efforts Project NeuroAutonomy.

“The research that we’ll be doing under this MURI is focused on the most interesting control system out there—the brain and its coordination of the neurosensory and neuromuscular systems in the body,” says co–principal investigator John Baillieul, an ENG Distinguished Professor of mechanical, systems, and electrical and computer engineering.

The Australian collaborators, particularly insect navigation expert Ken Cheng of Macquarie University, will draw insight from the way that ants use visual cues to move around. In the United States, BU collaborators will lead teams that examine animal and human spatial navigation.

“This project offers the potential for some major theoretical breakthroughs for understanding cognition,” says co–principal investigator Michael Hasselmo, director of BU’s Center for Systems Neuroscience and a College of Arts & Sciences professor of psychological and brain sciences.

Hasselmo will lead the team’s investigation of how rodents navigate their environment. He says that although this project is focusing on navigation, elements of the algorithm the team plans to develop could eventually be applied “to a broad range of different types of intelligent behavior.”

To develop the algorithm, the team will zero in on three big gaps between the navigation prowess of current autonomous vehicle technology and biological organisms, says co–principal investigator Chantal Stern, director of BU’s Cognitive Neuroimaging Center. Stern will lead team members in using functional MRI to investigate how humans develop a map of their environment and detect changing elements of their surroundings.

“An example that comes directly from robotics is known as the loop closure problem,” Stern says. “When you wander around in a circle through your house and come back to the kitchen, you know you are back in the kitchen; you have mapped your environment and recognize that you have returned to a location you were in before. In robotics, that’s a difficult problem for an autonomous system. An autonomous system will keep mapping a location it returns to, in the same way a Roomba vacuum keeps cleaning the same spot when it comes back around to the same location.”

Having a fully autonomous vehicle accurately map an area of land or water could be a useful application for military operations, allowing foreign landscapes to be charted without human assistance or putting any lives at risk.

“If you want to [use autonomous vehicles to] develop an accurate map of an area, then you don’t want [the vehicle] to overwrite the map every time [it returns] to the same place,” says Stern, a CAS professor of psychological and brain sciences.

Her team will also investigate how humans decide what’s valuable information and what’s visual clutter as they navigate their environment.

“How do you determine what is a landmark? For example, we can use the Citgo sign as a landmark, but we don’t tell people to turn right at the UPS truck,” Stern says. “The UPS truck is not a useful navigational landmark.” In other words, because it’s not a stable part of the environment, the UPS truck is just visual clutter.

The last problem the team will investigate is how we predict the changing dynamics of an environment.

“When you are driving down the street and see a child or a dog or bicyclist on the side of the road, you are already thinking that they might cross the street and you’ll be prepared for [them] to move,” Stern says. “But you know the mailbox isn’t going to move. How does the brain do that? How do you understand that prediction?”

John Leonard, a co–principal investigator and the head of MIT’s Marine Robotics group, says he’s looking forward to making use of recent advances in deep learning and object detection.

“Taking the best from biologically inspired models and biologically derived models and combining those with real robot experiments is very exciting,” Leonard says. “The potential impact of the research is awe-inspiring. The fact that memory formation is coupled to how an animal or human knows their position…perhaps could one day lead to better insights that ultimately might lead to better therapies for memory.”

Paschalidis, Project NeuroAutonomy’s team leader, predicts the biggest challenge for the team is that it will be impossible to read the “code” that animals and humans use to navigate.

“We have to infer that code from observations that we make,” he says. “The second challenge will be to translate those observations into specific, detailed control policies [for autonomous vehicles].”

The US-based team also includes Margrit Betke, a CAS professor of computer science, Roberto Tron, an ENG assistant professor of mechanical engineering, and from MIT, Nicholas Roy, a professor of aeronautics and astronautics.

Kat J. McAlpine can be reached at

BU-led Research Team Wins Competitive $7.5 million MURI Grant to Create Neuro-Autonomous Robots

By Ioannis Paschalidis
August 22nd, 2019

By Maureen Stanton, CISE

Dream Team of Engineers, Computer Scientists, and Neuroscientists from BU, MIT, and Australia to develop neuro-inspired capabilities for Land, Sea, and Air-based Autonomous Robots

A Boston University-led research team was selected to receive a $7.5 million Multidisciplinary University Research Initiative (MURI) grant from the U.S. Department of Defense (DoD).  With this prestigious grant, the researchers will develop a novel category of neuro-inspired autonomous robots for land, sea, and air that the investigators have termed “neuro-autonomous.”

The initiative will tackle the challenge of how to make robots truly autonomous as well as provide important insights into the process of learning and memory formation. The project will be led by Yannis Paschalidis, director of the Center for Information and Systems Engineering, and professor in the College of Engineering at Boston University.

The winning team of researchers is a Dream Team of experts from Boston University and the Massachusetts Institute of Technology. It includes experts in neuroscience, robotics, computer science, computer vision, artificial intelligence, mathematical systems theory, and a host of other related advanced technology domains. The project will also benefit from collaboration with renowned researchers from the University of Melbourne, Macquarie University, Queensland University of Technology, and the University of New South Wales.  (See researcher biographies.) 

Yannis Paschalidis, Director, BU Center for Information & Systems Engineering

Clearly, humans and animals are more effective at navigating than robots are,” said Professor Paschalidis.  “While there have been tremendous advances in intelligent systems, state-of-the-art autonomous systems are still limited in that they are programmed for specific objectives in well-structured environments.  Our research focus is to create a new class of neuro-autonomous robots, inspired by the fusion of multiple sensor modalities, spatial awareness, and spatial memory inherent in biological organisms.  These systems will have unprecedented capabilities for self-learning and on-the-fly adaptation to environmental novelty, enabling their ability to pursue complex goals in highly dynamic environments.”

Advancing a Science of Autonomy

Under this MURI grant entitled “Neuro-Autonomy: Neuroscience-Inspired Perception, Navigation, and Spatial Awareness for Autonomous Robots,” the research team will conduct experiments to gain insights into how humans and animals process visual and other stimuli to engage in goal-directed navigation.  With this greater understanding, the researchers will develop new algorithmic methods that can do the same for robots, enabling them to navigate autonomously. The implementation of the core algorithms will be agnostic to the specific robot used, enabling validation studies with ground, aerial, and underwater autonomous robots using experimental testbeds at BU, MIT, and Australian (AUS) institutions.

“This is fascinating science,” adds Professor Paschalidis. “We will develop the ability to make behavioral observations of animals and humans, correlate behavior with activity in the brain, and use the data to design control policies that will guide autonomous systems. This truly is the next frontier in advancing the field of robotics and autonomous vehicles.”

Cross-disciplinary Global Investigator Team

This MURI grant makes possible the multidisciplinary collaboration of an extraordinary team of researchers who bridge the neuroscience, engineering, and computer science worlds.  The team spans two continents and brings together some of the pre-eminent experts in neuroscience, with emphasis on localization, mapping, and navigation functions, with experts in robotics, computer vision, control systems, and algorithms.

The BU research team includes BU College of Engineering Professors John Baillieul, Yannis Paschalidis, and Roberto Tron, computer science Professor Margrit Betke, as well as neuroscience Professors Michael Hasselmo and Chantal Stern of the College of Arts and Sciences. The Massachusetts Institute of Technology is a subaward recipient on this grant. MIT Computer Science & Artificial Intelligence Laboratory (CSAIL) faculty John Leonard, Samuel C. Collins Professor of Mechanical and Ocean Engineering, and Nicholas Roy, Bisplinghoff Professor of Aeronautics and Astronautics, are the co-principal investigators.

Remarks from Principal Investigators

Michael Hasselmo, Director, BU Center for Systems Neuroscience

“While there are some very exciting computational theories, computational neuroscience has not yet fully accounted for the mechanisms and the function of all these interesting experimental phenomena,” says Professor Hasselmo, director of the Center for Systems Neuroscience at Boston University. “This project offers an exciting opportunity to collaborate with engineering in order to provide the mathematical and theoretical framework necessary. Further, this project offers the potential for some major theoretical breakthroughs for understanding cognition. While we will be focusing on navigation, elements of the algorithms we will develop could apply to a broad range of different types of intelligent behavior.”

John Leonard, MIT Computer Science and Artificial Intelligence Laboratory (CSAIL)

“As a roboticist, I am excited about combining insights into how scientists think the brain might work to make better robots and to exploit some of the recent advances in things like deep learning and object detection,” says Professor Leonard, MIT CSAIL. “Taking the best from biologically-inspired models and combining those with real robot experiments is very exciting. The potential impact of the research is awe-inspiring.  We understand now that memory formation is coupled to how an animal or human knows their position; there is a coupling there that perhaps could one day lead to better insights that ultimately might lead to better therapies for memories.”

Chantal Stern, Director, BU Cognitive Neuroimaging Center

“The MURI project is a fantastic opportunity for us to combine knowledge and expertise across disciplines,” says Professor Stern, Director, BU Cognitive Neuroimaging Center.  “As a neuroscientist, I find it fascinating to think about the speed and flexibility of human cognition, and I’ve learned a tremendous amount about what state-of-the-art robotics can and cannot do from my interactions with roboticists on the MURI team.  Spatial navigation is an ideal test bed for thinking about spatial awareness and problem solving across animals and humans, and I’m looking forward to working with the engineering and neuroscience faculty here at BU as well as with our robotics colleagues, John Leonard and Nick Roy, at MIT.”

John Baillieul, Distinguished Professor of Engineering, BU

Professor Baillieul, a Distinguished Professor of Engineering at Boston University states, “My career has been devoted to systems and control engineering.  The research that we’ll be doing under this MURI is focused on the most interesting control system out there–the brain and its coordination of the neurosensory and neuromuscular systems in the body.”



Margrit Betke, Co-director, BU Artificial Intelligence Research Initiative

“I am excited to lead the MURI research efforts around the video recordings of animals and their navigation behavior, as we monitor their brain activities,” said Professor Betke, co-director of the BU Artificial Intelligence Research Initiative. 

Professor Girish Nair at the University of Melbourne will lead the Australian-based researchers. “The Australian team is thrilled to participate in this project,” says Professor Nair.  “We look forward to a fruitful and exciting collaboration with our partners at Boston University and MIT.”

The BU-led MURI is one of 24 MURI awards announced by the DoD on April 3, 2019. The highly competitive MURI program supports basic research in science and engineering at U.S. institutions of higher education and is focused on multidisciplinary research efforts where more than one traditional discipline interacts to provide rapid advances in scientific areas of interest to the DoD.  

For details about this ONR MURI grant, see “Project Abstract approved for Public Release.”

BU Initiatives on Cities – Beyond Congestion: Pathways to Better Mobility

By Ioannis Paschalidis
August 22nd, 2019

By Doruntina Zeneli

On Tuesday March 26, panelists discussed how current transportation networks within major cities do not operate efficiently and future technology will serve a key role in incentivizing change and eliminating congestion. The conversation was initially led by Matthew Raifman, Senior Manager at Ford Smart Mobility. Raifman described congestion as an “excess of vehicles on a portion of roadway at a particular time resulting in a reduction below total possible throughput.” Traffic congestion serves as a negative externality for residents by inducing vehicle costs, greenhouse gas emissions, additional travel time and potential health risks.

He presented solutions to congestion by advocating for fewer vehicles, building more roads and spreading demand over time. However, cities simply do not have the available space to build more roads and repurposing green spaces, bike lanes and sidewalks, are not an effective solution in solving this ubiquitous issue. Raifman also emphasized that reducing the number of vehicles and implementing workplace policies that stagger arrival times of employees, serve as viable solutions to this issue.

Similarly, Yannis Paschalidis a BU Professor of Engineering, explained the severity of congestion in cities today. It is predicted that the cost of traffic congestion will reach $2.8 trillion by 2030 in the U.S. alone. Additionally, Boston was recently declared as the number one city in hours lost during rush hour traffic for each driver in 2018.

Moreover, Paschalidis showed an interactive model that illustrated congestion in Boston neighborhoods from 2012 to 2015. By providing these reference years, the audience was able to pinpoint increases in congestion within specific areas in Boston. Paschalidis also developed a transportation network model, which utilized a congestion function and demonstrated that drivers make optimally selfish decisions when choosing traffic routes.

Iram Farooq, the Assistant City Manager for the City of Cambridge also spoke about her role in developing policies that focuses on transportation, mobility and sustainability in Cambridge. Her involvement on transportation policies in the early 90’s enabled her local community to have manageable traffic levels with small commuting times during rush hour in comparison to Boston.

Jascha Franklin-Hodge, the former CIO for the City of Boston, emphasized the importance of new mobility as an emerging service industry. Recent services include Zipcar, ride-sharing, public bike-share systems and autonomous vehicles. Although there are benefits from new mobility, the issue of consumer protection arises. Many of these services are publicly traded or privately owned, so there is a potential risk consumers may lose the benefit of a marketplace. For instance, all forms of transportation modes are listed within these mobile apps. Eventually, one to two large companies will gain pricing power over consumers by capitalizing on the marketplace for their basic mobility needs. As a result, standards for consumer protection should be implemented as the industry of new mobility grows.

Click here to download slides from the panel.

BU Proposes to Build Data Sciences Center, Aiming to Become Leader in Booming Field

By Ioannis Paschalidis
August 22nd, 2019

BU Today reports that Boston University has announced plans to build a new 17-floor Data Sciences Center, furthering its leadership in data science and  interdisciplinary research.

Doug Most, Assistant VP, Executive Editor of BU Todaywrites, “Big data is playing a particularly major role in healthcare, allowing hospitals and doctors to move toward more personalized medicine.”

The story references related research initiatives of CISE affiliated faculty Yannis Paschalidis (ECE, BME, SE) and Christos Cassandras (ECE, SE) and BMC Associate Chief Medical Information Officer and BU School of Medicine Assistant Professor of Medicine Rebecca Mishuris.

Using Big Data, Machine Learning to Reduce Chronic Disease Spending

By Ioannis Paschalidis
August 22nd, 2019

Research by College of Engineering Professors Yannis Paschalidis (ECE, BME, SE) and Christos Cassandras (ECE, SE) and BMC Associate Chief Medical Information Officer and BU School of Medicine Assistant Professor of Medicine Rebecca Mishuris is featured in HealthIT Analytics

 The article discusses how they will use a new $900K grant from the National Science Foundation to advance machine learning and big data to reduce healthcare spending on chronic conditions, including diabetes and heart disease.

Researchers Win $900k NSF Grant to Predict Heart Disease, Diabetes Using Machine Learning

By Ioannis Paschalidis
August 22nd, 2019

By Maureen Stanton, CISE

Researchers (from left) Paschalidis, Mishuris, and Cassandras win $900K NSF grant to predict heart disease and diabetes using machine learning.


Researchers from the Boston University College of Engineering and Boston Medical Center (BMC) will use a three-year, $900,000 grant from the National Science Foundation to develop and pilot a health informatics system to predict patients at risk of heart disease or diabetes, and enable early intervention and personalized treatment.

“Our research vision is to deliver personalized healthcare, from prediction to diagnostics to population health management,” said Professor Ioannis Paschalidis (ECE, BME, SE), director of the Center for Information & Systems Engineering (CISE).  “In earlier work, we demonstrated how machine learning could predict hospitalizations due to these two chronic diseases about a year in advance with an accuracy rate of as much as 82 percent, a significant improvement over existing risk models — such as the Framingham study for cardiovascular disease.  Now, with our synergistic team of scientists and physicians, we are developing more robust predictive methods and capabilities for offering personalized recommendations that can guide physicians and patients as they make health-related decisions. This is a new frontier in medical informatics research and we expect it will impact medical practice.”

Diagnosing these chronic diseases requires complex sets of clinical and pathological data, which often are not comprehensive, consistent, nor up to date for treating physicians.  The result is that patients at higher risk often don’t get needed treatment, while those at lower risk do, leading to poor patient outcomes and unnecessary costs. The new, interdisciplinary research collaboration will be led by Paschalidis, CISE member Professor Christos Cassandras (ECE, SE) and BMC Associate Chief Medical Information Officer and BU School of Medicine Assistant Professor of Medicine Rebecca Mishuris. They will develop a new generation of predictive methods based on supervised machine learning techniques that are interpretable, have higher predictive power, and can handle more data.

The researchers will develop an approach based on novel mathematical methods and the requisite algorithms where electronic health records and real-time health data — including wearable, implantable, and home-based, networked diagnostic devices – can be used to develop prediction analytics that anticipate future events such as hospitalizations, re-admissions, and transitioning to an acute stage of a disease. These predictions trigger personalized interventions, ranging from increased monitoring and doctor visits to optimized treatment policies adapted to each patient.

The researchers will also focus on enabling personalized treatment based on learning and optimizing treatment protocols for chronic diseases. “Protocols of this type are typically empirical, using a one-size-fits-all approach,” explained Cassandras, head of the Systems Engineering Division. “They assess the stage of the disease and adapt medication based on the stage but not the patient. By incorporating specific personalized interventions with recommendations, clinicians can, therefore, intervene before a patient’s condition reaches a critical phase.”

In addition to methodological and algorithmic development, the project will pilot the newly developed algorithms by integrating them into the electronic health record system at BMC and with 14 affiliated Community Health Centers.

“Personalized, predictive healthcare is the future of medicine,” said Dr. Mishuris.  “Our research is geared toward providing clinicians with powerful, interpretable data to achieve that goal.  Physicians are drowning in data and administrative processes.  Our research approach will help physicians manage the deluge of clinical and patient data to make decisions in a more systematic fashion.”

Lectures in China

By Ioannis Paschalidis
July 9th, 2018

Professor Paschalidis will be visiting China in mid July 2018 to deliver a semi-plenary talk at the 2018 MTNS Conference and invited seminars at the Shanghai Jia Tong University (SJTU flyer) and the Huazhong University of Science and Technology.

The Price of Anarchy on the roads and how to reduce it

By Ioannis Paschalidis
January 10th, 2018

traffic-jamWe are publishing a new paper in the Proceedings of the IEEE which used minute-by-minute traffic data from the Boston area to estimate the effect on traffic congestion of drivers' selfish route selection as opposed to a more coordinated, socially optimal routing scheme. We found that during certain very congested periods, socially optimal routing can lead to as much as 50% reduction in congestion. This work is in collaboration with my colleague Christos Cassandras and two of our students, Jing Zhang and Sepideh Pourazarm. It was completed while I was on sabbatical at MIT.

A press release was released by MIT Sloan and KPCC, the southern California NPR station, aired a segment and posted a story on this work.

A related story appeared on the web site of the Center for Information and Systems Engineering.

We are grateful to the Boston region Metropolitan Planning Organization and to the City of Boston for providing access to the traffic data that made this work possible.