Explore ARCExplore ARC

MIDAS Data Science for Music Challenge Initiative announces funded projects

By | Data, General Interest, Happenings, News, Research

From digital analysis of Bach sonatas to mining data from crowdsourced compositions, researchers at the University of Michigan are using modern big data techniques to transform how we understand, create and interact with music.

Four U-M research teams will receive support for projects that apply data science tools like machine learning and data mining to the study of music theory, performance, social media-based music making, and the connection between words and music. The funding is provided under the Data Science for Music Challenge Initiative through the Michigan Institute for Data Science (MIDAS).

“MIDAS is excited to catalyze innovative, interdisciplinary research at the intersection of data science and music,” said Alfred Hero, co-director of MIDAS and the John H. Holland Distinguished University Professor of Electrical Engineering and Computer Science. “The four proposals selected will apply and demonstrate some of the most powerful state-of-the-art machine learning and data mining methods to empirical music theory, automated musical accompaniment of text and data-driven analysis of music performance.”

Jason Corey, associate dean for graduate studies and research at the School of Music, Theatre & Dance, added: “These new collaborations between our music faculty and engineers, mathematicians and computer scientists will help broaden and deepen our understanding of the complexities of music composition and performance.”

The four projects represent the beginning of MIDAS’ support for the emerging Data Science for Music research. The long-term goal is to build a critical mass of interdisciplinary researchers for sustained development of this research area, which demonstrates the power of data science to transform traditional research disciplines.

Each project will receive $75,000 over a year. The projects are:

Understanding and Mining Patterns of Audience Engagement and Creative Collaboration in Large-Scale Crowdsourced Music Performances

Investigators: Danai Koutra and Walter Lasecki, both assistant professors of computer science and engineering

Summary: The project will develop a platform for crowdsourced music making and performance, and use data mining techniques to discover patterns in audience engagement and participation. The results can be applied to other interactive settings as well, including developing new educational tools.

Understanding How the Brain Processes Music Through the Bach Trio Sonatas
Investigators: Daniel Forger, professor of mathematics and computational medicine and bioinformatics; James Kibbie, professor and chair of organ and university organist

Summary: The project will develop and analyze a library of digitized performances of Bach’s Trio Sonatas, applying novel algorithms to study the music structure from a data science perspective. The team’s analysis will compare different performances to determine features that make performances artistic, as well as the common mistakes performers make. Findings will be integrated into courses both on organ performance and on data science.

The Sound of Text
Investigators: Rada Mihalcea, professor of electrical engineering and computer science; Anıl Çamcı, assistant professor of performing arts technology

Summary: The project will develop a data science framework that will connect language and music, developing tools that can produce musical interpretations of texts based on content and emotion. The resulting tool will be able to translate any text—poetry, prose, or even research papers—into music.

A Computational Study of Patterned Melodic Structures Across Musical Cultures
Investigators: Somangshu Mukherji, assistant professor of music theory; Xuanlong Nguyen, associate professor of statistics

Summary: This project will combine music theory and computational analysis to compare the melodies of music across six cultures—including Indian and Irish songs, as well as Bach and Mozart—to identify commonalities in how music is structured cross-culturally.

The Data Science for Music program is the fifth challenge initiative funded by MIDAS to promote innovation in data science and cross-disciplinary collaboration, while building on existing expertise of U-M researchers. The other four are focused on transportation, health sciences, social sciences and learning analytics.

Hero said the confluence of music and data science was a natural extension.

“The University of Michigan’s combined strengths in data science methodology and music makes us an ideal crucible for discovery and innovation at this intersection,” he said.

Contact: Dan Meisler, Communications Manager, Advanced Research Computing
734-764-7414, dmeisler@umich.edu

Eric Parish, Aero Ph.D student, wins Von Neumann Fellowship from Sandia National Labs

By | Happenings, News, Research

Eric Parish

Eric Parish, who will graduate this spring with a Ph.D in Aerospace Engineering, is the 2018 recipient of the prestigious John von Neumann Postdoctoral Research Fellowship from Sandia National Laboratories (SNL). The highly competitive fellowship offers the opportunity to establish his own program at SNL to conduct innovative research in computational mathematics and scientific computing on advanced computing architectures.

Parish came to U-M from the University of Wyoming, and has developed innovative methodologies of computational math and physics with Prof. Karthik Duraisamy.

Parish said two of his accomplishments in his doctoral work have been developing data-driven solutions to computational physics problems using the NSF-funded ConFlux computing cluster, and bringing together ideas from statistical mechanics to develop efficient numerical solutions of complex partial differential equations.

“It was bridging a gap between communities,” he said of the latter effort.

“Eric came up with a particularly clever way of generalizing concepts from physics to develop a foundation to solve complex equations at a low cost in a mathematically rigorous fashion,” Duraisamy said. “He is one of the rare students who commands an exceptional grasp of applied mathematics, computing and physics, while being well-rounded in his organizational and communication skills. It has been a pleasure and a privilege to work with him.”

Parish said this research could eventually help usher the next generation of flight, for example, “hypersonic” aircraft that can travel at speeds of Mach 8-10. To help get there, his work moves the field toward a better understanding of the underlying physical phenomena via accurate numerical simulations.

At Sandia’s labs in Livermore, Calif., Parish said he plans to continue the work he started at U-M to develop “reduced order models”, which can process past simulation data to greatly reduce the computational cost of future simulations.

Parish said that conducting research at U-M, with the availability of high performance computing resources and a community of computational scientists to bounce ideas off of, helped push his research to a higher level.

“Within Aero, there are five or six very strong computational groups, which really helps me understand the fundamental aspects of what we’re doing, and what the addition of my small little delta means,” he said. “It’s very exciting to do computational research in that environment; it motivates me to come up with better code.”

In 2016, Parish received a $4,000 fellowship from the Michigan Institute for Computational Discovery and Engineering (MICDE). He used some of the funds to attend the International Workshop on Variational Multiscale Methods in Spain last year, where he met a few dozen people from around the world working on similar problems.

“It was fantastic to network and learn from them,” he said.

Parish grew up in Laramie, Wyo., before attending the University of Wyoming, where he played Division 1 golf. He said there was a small but active computational science community at U-W.

“For its size, there was a lot of good computational stuff there,” he said, adding that 10 years ago he would never have predicted the current direction of his career.

Golf played a significant role in his development as well, Parish said: “Being a successful student-athlete takes an extraordinary amount of work. The successes and failures I had … played an integral part in the development of my work ethic, time management skills, mental attitude, and overall growth as a person…I believe that the experience I gained as a student-athlete gave me a unique perspective and skill set that I was able to use to my advantage.”

As far as his future goes after Sandia, Parish said he plans to either continue in the national lab environment or to explore faculty positions so that he can teach and motivate students as his professors at Wyoming and Michigan did for him.

“I’m grateful for everyone’s help,” he said. “The doors that Michigan can open and the quality of people here are very apparent.”

A simulation of magnetohydrodynamic turbulence done on the ConFlux cluster with roughly 1 billion degree of freedom computation generating about 4TB of data.

Peers Health and U-M begin research partnership using disability and workers’ comp healthcare data

By | General Interest, Happenings, News, Research

Peers Health and the University of Michigan are starting a two-year research project that will apply advanced learning technologies to a proprietary global database of millions of de-identified disability and workers’ compensation cases. The goals of the project include developing a prescriptive modeling framework to facilitate development of optimal return-to-work plans for injured or ill patients.

Public policy experts have begun to connect patients’ ability to perform their productive endeavors, such as their job, to their state of general health and well-being. The findings from this project, by helping define when someone objectively has returned to health, could inform decision-making in virtually every healthcare episode.

The principal investigators in the project, Dr. Brian Denton and Dr. Jenna Wiens, are both renowned experts in medical machine learning. Dr. Denton, a professor of Industrial and Operations Engineering and Urology, and Dr. Wiens, an assistant professor of Computer Science and Engineering, are both affiliated with the Michigan Institute of Data Science (MIDAS) at U-M.

Peers Health recently announced an expanded partnership with ODG, an MCG company and part of the Hearst Health Network, to aggressively acquire new data to enhance ODG functionality and to fuel this research. Jon Seymour, MD, CEO of Peers, said, “This is a new phase in medical publishing where raw data collection is the editorial function and cutting-edge machine learning is the technology factor. We turned to the University of Michigan due to its impressive data science programs spanning multiple departments, as well as the specific experience of Dr. Denton and Dr. Wiens in medical applications. We’re confident this initiative will attract many new data contributors along the way.”

“The collaboration with Peers Health is exciting because it provides data that can help build a model that will reduce the time — from both a safety and productivity perspective — for people to return to work following sickness or injury,” Denton said. “Streaming data in from existing patients will allow our model to adapt and improve over time.”

Wiens added: “These data contain a particularly interesting training label: days away from work. We hypothesize that this will be a strong signal for the type, timing, and effectiveness of the treatments and therapies.”

The U-M partnership with Peers was established by MIDAS and the university’s Business Engagement Center (BEC).

“This partnership illustrates the power of combining data from the healthcare industry with the data science expertise of U-M faculty,” said Dr. Alfred Hero, professor of Engineering and co-director of MIDAS.

“It is energizing for the BEC to be part of these innovative collaborative relationships that create real impact in the world,” added BEC Director Amy Klinke.

 

U-M fosters thriving artificial intelligence and machine learning research

By | General Interest, HPC, News, Research

Research using machine learning and artificial intelligence — tools that allow computers to learn about and predict outcomes from massive datasets — has been booming at the University of Michigan. The potential societal benefits being explored on campus are numerous, from on-demand transportation systems to self-driving vehicles to individualized medical treatments to improved battery capabilities.

The ability of computers and machines generally to learn from their environments is having transformative effects on a host of industries — including finance, healthcare, manufacturing, and transportation — and could have an economic impact of $15 trillion globally according to one estimate.

But as these methods become more accurate and refined, and as the datasets needed become bigger and bigger, keeping up with the latest developments and identifying and securing the necessary resources — whether that means computing power, data storage services, or software development — can be complicated and time-consuming. And that’s not to mention complying with privacy regulations when medical data is involved.

“Machine learning tools have gotten a lot better in the last 10 years,” said Matthew Johnson-Roberson, Assistant Professor of Engineering in the Department of Naval Architecture & Marine Engineering and the Department of Electrical Engineering and Computer Science. “The field is changing now at such a rapid pace compared to what it used to be. It takes a lot of time and energy to stay current.”

Diagram representing the knowledge graph of an artificial intelligence system, courtesy of Jason Mars, assistant professor, Electrical Engineering and Computer Science, U-M

Johnson-Roberson’s research is focused on getting computers and robots to better recognize and adapt to the world, whether in driverless cars or deep-sea mapping robots.

“The goal in general is to enable robots to operate in more challenging environments with high levels of reliability,” he said.

Johnson-Roberson said that U-M has many of the crucial ingredients for success in this area — a deep pool of talented researchers across many disciplines ready to collaborate, flexible and personalized support, and the availability of computing resources that can handle storing the large datasets and heavy computing load necessary for machine learning.

“The people is one of the reasons I came here,” he said. “There’s a broad and diverse set of talented researchers across the university, and I can interface with lots of other domains, whether it’s the environment, health care, transportation or energy.”

“Access to high powered computing is critical for the computing-intensive tasks, and being able to leverage that is important,” he continued. “One of the challenges is the data. A major driver in machine learning is data, and as the datasets get more and more voluminous, so does the storage needs.”

Yuekai Sun, an assistant professor in the Statistics Department, develops algorithms and other computational tools to help researchers analyze large datasets, for example, in natural language processing. He agreed that being able to work with scientists from many different disciplines is crucial to his research.

“I certainly find the size of Michigan and the inherent diversity that comes with it very stimulating,” he said. “Having people around who are actually working in these application areas helps guide the direction and the questions that you ask.”

Sun is also working on analyzing the potential discriminatory effects of algorithms used in decisions like whether to give someone a loan or to grant prisoners parole.

“If you use machine learning, how do you hold an algorithm or the people who apply it accountable? What does it mean for an algorithm to be fair?” he said. “Can you check whether a particular notion of non-discrimination is satisfied?”

Jason Mars, an assistant professor in the Electrical Engineering and Computer Science department and co-founder of a successful spinoff called Clinc, is applying artificial intelligence to driverless car technology and a mobile banking app that has been adopted by several large financial institutions. The app, called Finie, provides a much more conversational interface between users and their financial information than other apps in the field.

“There is going to be an expansion of the number of problems solved and number of contributions that are AI-based,” Mars said. He predicted that more researchers at U-M will begin exploring AI and ML as they understand the potential.

“It’s going to require having the right partner, the right experts, the right infrastructure, and the best practices of how to use them,” he said.

He added that U-M does a “phenomenal job” in supporting researchers conducting AI and ML research.

“The level of support and service is awesome here,” he said. “Not to mention that the infrastructure is state of the art. We stay relevant to the best techniques and practices out there.”

Advanced Research Computing at U-M, in part through resources from the university-wide Data Science Initiative, provides computing infrastructure, consulting expertise, and support for interdisciplinary research projects to help scientists conducting artificial intelligence and machine learning research.

For example, Consulting for Statistics, Computing and Analytics Research, an ARC unit, has several consultants on staff with expertise in machine learning and predictive analysis with large, complex, and heterogeneous data. CSCAR recently expanded capacity to support very large-scale machine learning using tools such as Google’s TensorFlow.

CSCAR consultants are available by appointment or on a drop-in basis, free of charge. See cscar.research.umich.edu or email cscar@umich.edu for more information.

CSCAR also provides workshops on topics in machine learning and other areas of data science, including sessions on Machine Learning in Python, and an upcoming workshop in March titled “Machine Learning, Concepts and Applications.”

The computing resources available to machine learning and artificial intelligence researchers are significant and diverse. Along with the campus-wide high performance computing cluster known as Flux, the recently announced Big Data cluster Cavium ThunderX will give researchers a powerful new platform for hosting artificial intelligence and machine learning work. Both clusters are provided by Advanced Research Computing – Technology Services (ARC-TS).

All allocations on ARC-TS clusters include access to software packages that support AI/ML research, including TensorFlow, Torch, and Spark ML, among others.

ARC-TS also operates the Yottabyte Research Cloud (YBRC), a customizable computing platform that recently gained the capacity to host and analyze data governed by the HIPAA federal privacy law.

Also, the Michigan Institute for Data Science (MIDAS) (also a unit of ARC) has supported several AI/ML projects through its Challenge Initiative program, which has awarded more than $10 million in research support since 2015.

For example, the Analytics for Learners as People project is using sensor-based machine learning tools to translate data on academic performance, social media, and survey data into attributes that will form student profiles. Those profiles will help link academic performance and mental health with the personal attributes of students, including values, beliefs, interests, behaviors, background, and emotional state.

Another example is the Reinventing Public Urban Transportation and Mobility project, which is using predictive models based on machine learning to develop on-demand, multi-modal transportation systems for urban areas.

In addition, MIDAS supports student groups involved in this type of research such as the Michigan Student Artificial Intelligence Lab (MSAIL) and the Michigan Data Science Team (MDST).

(A version of this piece appeared in the University Record.)

Video available from MIDAS Research Forum

By | General Interest, Happenings, News, Research

Video is now available from the MIDAS Research Forum held Dec. 1 in the Michigan League at http://myumi.ch/6vA3V

The forum featured U-M students and faculty showcasing their data science research; a workshop on how to work with industry; presentations from student groups; and a summary of the data science consulting and infrastructure services available to the U-M research community.

NOTE: The keynote presentation from Christopher Rozell of the Georgia Institute of Technology will be available in the near future.

Info sessions on graduate studies in computational and data sciences — Sept. 21 and 25

By | Educational, Events, General Interest, News, Research

Learn about graduate programs that will prepare you for success in computationally intensive fields — pizza and pop provided

  • The Ph.D. in Scientific Computing is open to all Ph.D. students who will make extensive use of large-scale computation, computational methods, or algorithms for advanced computer architectures in their studies. It is a joint degree program, with students earning a Ph.D. from their current departments, “… and Scientific Computing” — for example, “Ph.D. in Aerospace Engineering and Scientific Computing.”
  • The Graduate Certificate in Computational Discovery and Engineering trains graduate students in computationally intensive research so they can excel in interdisciplinary HPC-focused research and product development environments. The certificate is open to all students currently pursuing Master’s or Ph.D. degrees at the University of Michigan.
  • The Graduate Certificate in Data Science is focused on developing core proficiencies in data analytics:
    1) Modeling — Understanding of core data science principles, assumptions and applications;
    2) Technology — Knowledge of basic protocols for data management, processing, computation, information extraction, and visualization;
    3) Practice — Hands-on experience with real data, modeling tools, and technology resources.

Times / Locations:

U-M, SJTU research teams share $1 million for data science projects

By | Data, General Interest, Happenings, News, Research

Five research teams from the University of Michigan and Shanghai Jiao Tong University in China are sharing $1 million to study data science and its impact on air quality, galaxy clusters, lightweight metals, financial trading and renewable energy.

Since 2009, the two universities have collaborated on a number of research projects that address challenges and opportunities in energy, biomedicine, nanotechnology and data science.

In the latest round of annual grants, the winning projects focus on data science and how it can be applied to chemistry and physics of the universe, as well as finance and economics.

For more, read the University Record article.

For descriptions of the research projects, see the MIDAS/SJTU partnership page.

Designing optimal shunts for newborns with heart defects using computational modeling

By | General Interest, Happenings, News, Research

shuntFor babies born with hypoplastic left heart syndrome, several open-heart surgeries are required. During Stage I, a Norwood procedure is performed to construct an appropriate circulation to both the systemic and the pulmonary arteries. The pulmonary arteries receive flow from the systemic circulation, often by using a Blalock-Taussig (BT) shunt between the innominate artery and the right pulmonary artery. This procedure causes significantly disturbed flow in the pulmonary arteries.

A group of researchers led by U-M Drs. Ronald Grifka and Alberto Figueroa used computational hemodynamic simulations to demonstrate its capacity for examining the properties of the flow through and near the BT shunt. Initially, the researchers constructed a computational model which produces blood flow and pressure measurements matching the clinical magnetic resonance imaging (MRI) and catheterization data. Achieving this required us to determine the level of BT shunt occlusion; because the occlusion is below the MRI resolution, this information is difficult to recover without the aid of computational simulations. The researchers determined that the shunt had undergone an effective diameter reduction of 22% since the time of surgery. Using the resulting geometric model, they showed that we can computationally reproduce the clinical data. The researchers then replaced the BT shunt by with a hypothetical alternative shunt design with a flare at the distal end. Investigation of the impact of the shunt design revealed that the flare can increase pulmonary pressure by as much as 7%, and flow by as much as 9% in the main pulmonary branches, which may be beneficial to the pulmonary circulation.

Read more in Frontiers in Pediatrics.

MICDE awards four Catalyst Grants

By | General Interest, News, Research

The Michigan Institute for Computational Discovery and Engineering has awarded its first round of Catalyst Grants, providing $75,000 each to four innovative projects in computational science. The proposals were judged on novelty, likelihood of success, potential for external funding, and potential to leverage ARC’s existing computing resources.

The funded projects are:

Title: From Spiking Patterns to Memory formation — Tools for Analysis and Modeling of Network-wide Cognitive Dynamics of the Brain
Researchers: Sara Aton, Department of Molecular, Cellular and Developmental Biology and Michal Zochowski, Department of Physics, Biophysics Program
Description: The aim of the research is to develop models as well as analysis tools to understand network-wide spatio-temporal patterning underlying experimentally observed neural spiking activity. The research team has developed novel tools to analyze dynamics of neuronal representations across time, before during and after learning. These tools, for the first time, compare the stability of network dynamics before and after memory encoding.

Title: Integral Equation Based Methods for Scientific Computing
Researcher: Robert Krasny, Department of Mathematics
Description: This project expands the application of numerical methods in which the differential equation is first converted into an integral equation by convolution with the Green’s function, followed by discretization and linear solution. Recent advances in numerical analysis and computing resources make this expansion possible, and the research team believes that integral equation-based numerical methods are superior to traditional methods in both serial and parallel computations. The project will attempt to apply these numerical methods to studies of viscous fluid flow, protein/solvent electrostatics, and electronic structure.

Title: Computational Energy Systems
Researchers: Pascal Van Hentenryck, Industrial and Operations Engineering (IOE); E. Byon, IOE; R. Jiang, IOE; J. Lee, IOE; and J. Mathieu, Electrical Engineering and Computer Science
Description: The research team aims to develop new algorithms for the U.S. electrical power grid that integrate renewable energy sources, electrification of transportation systems, the increasing frequency of extreme weather events, and other emerging contingencies.

Title: Black Swans, Dragon Kings, and the Science of Rare Events: Problems for the Exascale Era and Beyond
Researchers: Venkat Raman, Aerospace Engineering; Jacqueline Chen, Sandia National Laboratory; and Ramanan Sankaran, Oak Ridge National Laboratory.
Description: The purpose of the project is to develop the computational frameworks for exploring the tails of distributions, which lead to rare but consequential (and often catastrophic) outcomes. Two such rare events are “Black Swans” (occurring from pre-existing but unencountered events) and “Dragon Kings (occurring due to an external shock to the system). The methods developed are expected to have application in aerospace sciences, power generation and utilization, chemical processing, weather prediction, computational chemistry, and other fields.

Another round of Catalyst Grants will be awarded next year.

U-M, Toyota Research Institute partner in $2.4M battery project

By | General Interest, News, Research

With a $2.4 million investment from the Toyota Research Institute, University of Michigan researchers will develop computer simulation tools to predict automotive battery performance.

The project is part of a four-year, $35 million investment with research entities, universities and companies on research that uses artificial intelligence to help accelerate the design and discovery of advanced materials, TRI has announced.

Initially, the program will aim to help revolutionize materials science and identify new advanced battery materials and fuel cell catalysts that can power future zero-emissions and carbon-neutral vehicles.

“Toyota recognizes that artificial intelligence is a vital basic technology that can be leveraged across a range of industries, and we are proud to use it to expand the boundaries of materials science,” said Eric Krotkov, TRI chief science officer.

“Accelerating the pace of materials discovery will help lay the groundwork for the future of clean energy and bring us even closer to achieving Toyota’s vision of reducing global average new-vehicle CO2 emissions by 90 percent by 2050.”

The project, under the auspices of the Michigan Institute for Computational Discovery and Engineering at U-M, will combine mathematical models of the atomic nature and physics of materials with artificial intelligence.

“At the University of Michigan, we look forward to collaborating with TRI to advance computational materials science using machine learning principles,” said principal investigator Krishna Garikipati, professor of mechanical engineering and mathematics.

Also involved from U-M are Vikram Gavini, associate professor of mechanical engineering and materials science and engineering, and Karthik Duraisamy, assistant professor of aerospace engineering.

“The timing and goals of this program are well-aligned with the paradigm of data-enabled science that we have been promoting via the Michigan Institute for Computational Discovery and Engineering, and the Center for Data-Driven Computational Physics,” Duraisamy said.

The U-M project will use the ConFlux cluster, an innovative, new computing platform that enables computational simulations to interface with large datasets.

In addition to U-M, TRI’s newly funded research projects include collaborations with Stanford University, the Massachusetts Institute of Technology, University at Buffalo, University of Connecticut and the U.K.-based materials science company Ilika. TRI is also in ongoing discussions with additional research partners.

Research will merge advanced computational materials modeling, new sources of experimental data, machine learning and artificial intelligence in an effort to reduce the time scale for new materials development from a period that has historically been measured in decades.

Research programs will follow parallel paths, working to identify new materials for use in future energy systems as well as to develop tools and processes that can accelerate the design and development of new materials more broadly, according to TRI.

In support of these goals, TRI will partner on projects focused on areas including:

  • The development of new models and materials for batteries and fuel cells.
  • Broader programs to pursue novel uses of machine learning, artificial intelligence and materials informatics approaches for the design and development of new materials.
  • New automated materials discovery systems that integrate simulation, machine learning, artificial intelligence or robotics.

Accelerating materials science discovery represents one of four core focus areas for TRI, which was launched in 2015 with mandates to also enhance auto safety with automated technologies, increase access to mobility for those who otherwise cannot drive and help translate outdoor mobility technology into products for indoor mobility.