Institute of Computing and Cybersystems (ICC) Blog

An article by Audrey Yazdanparast (2019, PhD, Electrical Engineering) and Dr. Timothy Havens, “Linear Time Community Detection by a Novel Modularity Gain Acceleration in Label Propagation,” has been accepted for publication in the journal, IEEE Transactions on Big Data.

The paper presents an efficient approach for detecting self-similar communities in weighted graphs, with applications in social network analysis, online commodity recommendation systems, user clustering, biology, communications network analysis, etc.

Paper Abstract: Community detection is an important problem in complex network analysis. Among numerous approaches for community detection, label propagation (LP) has attracted a lot of attention. LP selects the optimum community (i.e., label) of a network vertex by optimizing an objective function (e.g., Newman’s modularity) subject to the available labels in the vicinity of the vertex. In this paper, a novel analysis of Newman’s modularity gain with respect to label transitions in graphs is presented. Here, we propose a new form of Newman’s modularity gain calculation that quantifies available label transitions for any LP based community detection.

The proposed approach is called Modularity Gain Acceleration (MGA) and is simplified and divided into two components, the local and global sum-weights. The Local Sum-Weight (LSW) is the component with lower complexity and is calculated for each candidate label transition. The General Sum-Weight (GSW) is more computationally complex, and is calculated only once per each label. GSW is updated by leveraging a simple process for each node-label transition, instead of for all available labels. The MGA approach leads to significant efficiency improvements by reducing time consumption up to 85% relative to the original algorithms with the exact same quality in terms of modularity value which is highly valuable in analyses of big data sets.

Timothy Havens is director of Michigan Tech’s Institute of Computing and Cybersystems (ICC), the associate dean for research for the College of Computing , and the William and Gloria Jackson Associate Professor of Computer Systems.

View the article abstract here.

Imagine if your car could tell you when you are passing by an area occupied by rare migratory birds, or it could listen to roads and bridges to determine when infrastructure repairs need to be made.

A recent gift from Mobility Research at Ford Motor Company recently provided a $149,518 gift to fund research that could make this possible.

Dr. Timothy Havens, Institute of Computing and Cybersystems, and Dr. Andrew Barnard, Great Lakes Research Center, will lead an exploration of how future connected vehicles could use AI and acoustics to detect, classify, and localize external sound events, and evaluate and monitor transportation infrastructure.

The gift will fund a Ph.D. student fellowship, a team of undergraduate students in the SENSE Enterprise, and build and develop a mobile acoustics test bed that will allow students, Havens, and Barnard to conduct cutting-edge research in AI and acoustics.

Michigan Tech would like to thank Chad Esselink (’94, Computer Science) and Tavan Eftekhar at Ford Mobility Research for making this possible.

The Institute of Computing and Cybersystems (ICC) is the research arm of the College of Computing at Michigan Tech. The ICC provides faculty and students the opportunity to work across organizational boundaries to create an environment that is a reflection of contemporary technological innovation. This collaboration allows for a convergence in communication, control and computing that mirrors today’s industry and society.

The Great Lakes Research Center (GLRC) provides state-of-the-art laboratories to support research on a broad array of topics. Faculty members from many departments across Michigan Technological University’s campus collaborate on interdisciplinary research, ranging from air–water interactions to biogeochemistry to food web relationships.

Faculty/Researcher Profile: Weihua Zhou, Multi-Disciplinary Digital Healthcare Solutions

By Karen Johnson, Communications Director, College of Computing and Institute of Computing and Cybersystems

How can the cost-effectiveness of healthcare be improved, especially for complicated chronic diseases? This is the overarching question Dr. Weihua Zhou is seeking to answer with his research. The multi-disciplinary solutions he is investigating merge the fields of medical imaging and informatics, computer vision, and machine learning. 

An assistant professor in Michigan Tech’s Health Informatics program, and an affiliated associate professor in the Biomedical Engineering department, Zhou is working with students on a number of research projects in Michigan Tech’s Medical Imaging and Informatics Lab, which he directs. He is a member of the Institute of Computing and Cybersystems’s Center for Data Science.

Zhou says his research is driven by clinical significance, and he is especially interested in developing practical solutions to improve the cost-effectiveness of treating complicated chronic diseases, such as coronary artery disease, heart failure and senile dementia. 

He is excited about his career, his international research, and his work at Michigan Tech. “We have a very productive team, including dedicated Ph.D. students, self-motivated graduate and undergraduate students, and a lot of experienced clinical and technical collaborators,” he says of his colleagues and collaborators at Michigan Tech and around the world.

Zhou feels that he can be dedicated to both his research and teaching at Michigan Tech. “I joined the Health Informatics program at Michigan Tech, both because health informatics is my research focus, and because Michigan Tech’s leading reputation among engineering schools opens opportunities to find new and respected technical collaborators. 

Zhou often calls himself a salesman. “I sell techniques to our clinical collaborators and ask them to design the projects with me, provide the patient data, and test our tools,” he explains. “I also sell my ideas about clinical problems to technical collaborators and ask them to work with us to solve the important clinical problems.”

And when he communicates with his Ph.D. students, “sometimes I also consider them as my buyers and let them appreciate my ideas so that they can be really inspired.”

Primary Research

Zhou identifies two of his research projects of as primary. 

“This first is exploring image-guided approaches to improving the treatment of heart failure, which has been supported by AHA grants, and is now being supported by a new faculty startup grant,” Zhou says. “The second main project is seeking to employ machine learning to improve the risk stratification for osteoporosis, which is supported by a National Institutes of Health (NIH) subcontract award from Tulane University.”

On the NIH grant, awarded in December 2019, Zhou is working with internationally renowned researcher and educator Dr. Hong-Wen Deng, an endowed chair and professor in the School of Public Health and Tropical Diseases at Tulane University, New Orleans, La. Zhou and Deng are studying trans-omics integration of multi-omics studies for male osteoporosis.

Zhou is also co-PI with Jinshan Tang, professor of Applied Computing at Michigan Tech, on a Portage Health Foundation Infrastructure Enhancement Grants titled, “High Performance Graphics Processing Units.” The project is focused on building big data computing capabilities toward advancing research and education. Several additional proposals are under review and revision. Zhou’s past research support includes an American Heart Association award, which studied a new image-guided approach for cardiac resynchronization therapy.

Teaching and Mentoring

Zhou, who started at Michigan Tech in fall 2019, instructed Introduction to Health Informatics in the fall semester, and Applied Artificial Intelligence in Health this spring.  He says that in the Medical Informatics program, the subjects he teaches are very practical.

“I believe the following strategies are very important and I practice them in my classes every day: 1) Make the class interactive; 2) Make the assignments and projects practical; 3) Emphasize the learning process; and 4) Keep the teaching materials up to date,” Zhou says.

Zhou supervises two Ph.D. candidates in the Department of Applied Computing, and a Health Informatics master’s student.

Applied Computing Ph.D. candidate Zhuo He’s primary research project concerns information fusion between electrical signal propagation and mechanical motion to improve the treatment of heart failure. Ph.D. candidate Chen Zhao’s primary research concerns using image fusion and computer vision to improve interventional cardiology. And Zhou’s Health Informatics master’s student, Rukayat Adeosun, is studying nuclear image-guided approaches to improving cardiac resynchronization therapy.

Education and Post-Doc

Zhou was awarded his Ph.D. in computer engineering by the Department of Electrical and Computer Engineering at Southern Illinois University Carbondale in 2012; his dissertation is titled, “Image reconstruction and imaging configuration optimization with a novel nanotechnology enabled breast tomosynthesis multi-beam X-ray system.”

Following, Zhou was a post-doctoral researcher in the Department of Radiology and Imaging Sciences at Emory University, Atlanta, Georgia, then he was appointed a Nina Bell Suggs Endowed Professor at University of Southern Mississippi, where he was a tenure-track assistant professor. Zhou also completed an MSc.-Ph.D. in computer science (2007) and a B.E. in computer science and technology (2003), both at Wuhan University, China.

Achievement

Zhou received the USM College of Arts and Sciences Scholarly Research Award in March 2019, participated in the AHA Research Leaders Academy of the American Heart Association in September 2017 and August 2018, and received the USM Butch Oustalet Distinguished Professorship Research Award in April 2018.

University and Professional Service

Zhou serves on Michigan Tech’s Review Committee for Graduate Dean’s Awards Advisory Committee, and in October 2019 he served on the Review Committee for Research Excellence Fund (REF) – Research Seed Grants (RS).

He was an invited speaker at the Machine Learning in SPECT MPI Applications session at the Annual Scientific Session of the American Society of Nuclear Cardiology in Washington, D.C., in 2009.

Zhou is a member of the American Heart Association (AHA) and the American Society of Nuclear Cardiology (ASNC).

Peer-Review

Since Zhou joined Michigan Tech in August 2019, he has published five scholarly papers, in Journal of Nuclear Cardiology and the IEEE Journal of Translational Engineering in Health and Medicine. Two additional articles are under revision with Journal of Nuclear Cardiology and the journal Medical Physics, and one is under review by the Medical Image Computing and Computer Assisted Intervention (MICCAI) Conference 2020.

Since 2007, he has published more than 80 peer-reviewed journal and conference papers and book chapters in publications including JACC: Journal of The American College of Cardiology: Cardiovascular Imaging, Journal of Nuclear Cardiology, and IEEE Journal of Translational Engineering in Health and Medicine.

Zhou is a translator of featured papers and abstracts for the Journal of Nuclear Cardiology, and a paper reviewer for the Journal of Nuclear Cardiology, JACC: Journal of The American College of Cardiology, and JACC: Cardiovascular Imaging. He is a reviewer for American Heart Association data science grants. 

Commercial Success

Zhou holds a number of patents and invention disclosures, including new methods to 1) diagnose apical hypertrophic cardiomyopathy from gated single-photon emission computed tomography (SPECT), and 2) measure right-ventricular and interventricular mechanical dyssynchrony from gated single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI); and 3) the integration of fluoroscopy venogram and myocardial perfusion SPECT image with left-ventricular contraction sequence and scar distribution to guide the real-time surgery of cardiac resynchronization therapy. 

He and his colleagues have developed a number of software tools, some of which are being used in hospitals for research purposes, and he believes that the tools can be successfully validated and become commercially available. For example, Zhou’s nuclear image-guided software toolkit to improve cardiac resynchronization therapy is being validated by a large clinical trial. 

A personal note.

Zhou loves independent thinking, facts and exact numbers, and he values persistence, all of which express themselves in his teaching and research, and his life.

Follow Weihua Zhou on Twitter: @LabMiil

The College of Computing’s Department of Applied Computing officially starts on July 1, 2020. The new department will replace the CMH Division.

The U.S. Department of Defense, Office of Naval Research, has awarded Michigan Tech faculty researchers a $249,000 grant that supports the creation of an ROTC undergraduate science and engineering research program at Michigan Tech. The primary goal of the program is to supply prepared cadets to all military branches to serve as officers in Cyber commands.

The principal investigator (PI) of the project is Andrew Barnard, Mechanical Engineering-Engineering Mechanics. Co-PIs are Timothy Havens, College of Computing; Laura Brown , Computer Science, and Yu Cai, Applied Computing. The title of the project is, “Defending the Nation’s Digital Frontier: Cybersecurity Training for Tomorrow’s Officers.”

The curriculum will be developed over the summer, and instruction associated with the award will begin in the fall 2020 semester. Cadets interested in joining the new program are urged to contact Andrew Barnard.

Initially, the program will focus on topics in cybersecurity, machine learning and artificial intelligence, data science, and remote sensing systems, all critical to the The Naval Science and Technology (S&T) Strategic Plan and the Navy’s Force of the Future, and with equal relevance in all branches of the armed forces.

The plan of work focuses on on engaging ROTC students in current and on-going Cyber research, and supports recruitment of young ROTC engineers and scientists to serve in Navy cybersecurity and cyber-systems commands. The program will compel cadets to seek positions within Cyber commands upon graduation, or pursue graduate research in Cyber fields.

“Our approach develops paid, research-based instruction for ROTC students through the existing Michigan Tech Strategic Education Naval Systems Experiences (SENSE) program,” said principal investigator Andrew Barnard, “ROTC students will receive one academic year of instruction in four Cyber domains: cybersecurity, machine learning and artificial intelligence (ML/AI), data science, and remote sensing systems.”

Barnard says the cohort-based program will enrich student learning through deep shared research experiences. He says the program will be designed with flexibility and agility in mind to quickly adapt to new and emerging Navy science and technology needs in the Cyber domain. 

Placement of officers in Cyber commands is of critical long-term importance to the Navy (and other DoD branches) in maintaining technological superiority, says the award abstract, noting that technological superiority directly influences the capability and safety of the warfighter.

Also closely involved in the project are Michigan Tech Air Force and Army ROTC officers Lt. Col. John O’Kane and LTC Christian Thompson, respectively.

“Unfortunately, many ROTC cadets are either unaware of Cyber related careers, or are unprepared for problems facing Cyber officers,” said Lt. Col. O’Kane. “This proposal aims to provide a steady flow of highly motivated and trained uniformed officers to the armed-services, capable of supporting the warfighter on day-one.”

Andrew Barnard is director of Michigan Tech’s Great Lakes Research Center, an associate professor of Mechanical Engineering-Engineering Mechanics, and faculty advisor to the SENSE Enterprise.

Tim Havens is director of the Institute of Computing and Cybersystems, associate dean for research, College of Computing, and the William and Gloria Jackson Associate Professor of Computer Systems.

Laura Brown is an associate professor, Computer Science, director of the Data Science graduate program, and a member of the ICC’s Center for Data Sciences.

Yu Cai is a professor of Applied Computing, an affiliated professor of Computational Science and Engineering, a member of the ICC’s Center for Cybersecurity, and faculty advisor for the Red Team, which competes in the National Cyber League (NCL).

The Great Lakes Research Center (GLRC) provides state-of-the-art laboratories to support research on a broad array of topics. Faculty members from many departments across Michigan Technological University’s campus collaborate on interdisciplinary research, ranging from air–water interactions to biogeochemistry to food web relationships.

The Army and Air Force have active ROTC programs on Michigan Tech’s campus.

The Office of Naval Research (ONR) coordinates, executes, and promotes the science and technology programs of the United States Navy and Marine Corps.

An article co-authored by Tim Havens, associate dean for research, College off Computing, “Soft Overlapping Community Detection in Large-Scale Networks via Fast Fuzzy Modularity Maximization,” was published in the March 2020 issue of IEEE Transactions on Fuzzy Systems.

Havens’s co-authors are Audrey Yazdanparast (ECE) and Mohsen Jamalabdollahi of Cisco Systems.

Article Abstract: Soft overlapping clustering is one of the notable problems of community detection. Extensive research has been conducted to develop efficient methods for non-overlapping and crisp-overlapping community detection in large-scale networks. In this paper, Fast Fuzzy Modularity Maximization (FFMM) for soft overlapping community detection is proposed.

FFMM exploits novel iterative equations to calculate the modularity gain associated with changing the fuzzy membership values of network vertices. The simplicity of the proposed scheme enables efficient modifications, reducing computational complexity to a linear function of the network size and the number of communities. Moreover, to further reduce the complexity of FFMM for very large networks, Multi-cycle FFMM (McFFMM) is proposed.

The proposed McFFMM reduces complexity by breaking networks into multiple sub-networks and applying FFMM to detect their communities. Performance of the proposed techniques are demonstrated with real-world data and the Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks. Moreover, the performance of the proposed techniques is eval- uated versus some state-of-the-art soft overlapping community detection approaches. Results show that the McFFMM produces a remarkable performance in terms of overlapping modularity with fuzzy memberships, computational time, number of detected overlapping nodes, and Overlapping Normalized Mutual Informa- tion (ONMI).

View more info here.

Tim Havens, associate dean for research, College of Computing, and director of the Institute of Computing and Cybersystems, was quoted in the article, “Data science vs. machine learning: What’s the difference?” published March 10, 2020, in the online publication, The Enterprisers Project.

Havens’s quotation concerns machine learning models, which the article explains are only as good as the quality of the data they learn from. Havens says, “Luckily, there are many types of problems for which lots of data exist.”

Link to the article here.

The Enterprisers Project is a community and online publication built to discuss the evolving role of the CIO and how IT leaders drive business value in a digital world. It is a collaborative effort between Harvard Business Review and Red Hat that delivers daily analysis and advice on topics ranging from emerging technologies to IT talent. Articles in the publication are written by CIOs, for CIOs and other IT executives, who share lessons learned from innovating in true partnership with the business. 

Timothy Havens, director of the Institute of Computing and Cybersystems (ICC), is co-author of the article, “A Similarity Measure Based on Bidirectional Subsethood for Intervals,” published in the March 2020 issue of IEEE Transactions on Fuzzy Systems.

Havens’s co-authors are Shaily Kabir, Christian Wagner, and Derek T. Anderson.

Havens is also associate dean for research, College of Computing, and the William and Gloria Jackson Associate Professor of Computer Systems.

Christian Wagner, an affiliated member of the ICC, was an ICC donor-sponsored visiting professor at Michigan Tech in the 2016-17 academic year. He is now with the School of Computer Science at University of Nottingham.

Shaily Kabir is with the School of Computer Science, University of Nottingham. Derek T. Anderson is with the Electrical Engineering and Computer Science Department, University of Missouri, Columbia.

S. Kabir, C. Wagner, T. C. Havens and D. T. Anderson, “A Similarity Measure Based on Bidirectional Subsethood for Intervals,” in IEEE Transactions on Fuzzy Systems.

https://ieeexplore.ieee.org/document/9019656

Chee-Wooi Ten, associate professor, Electrical and Computer Engineering, and member of the ICC’s Center for Cyber-Physical Systems, was recently awarded a 6 month, $25K contract from the nonpartisan advisory panel, Protect Our Power. The title of the project is, “Consulting for Utilities on Cyber Risk Management.”

The activities Ten will undertake for the project include identifying security vendors for industrial harden security hardware and software, and conducting a survey of each of the identified security vendors to enumerate their strengths and weaknesses.

Ten will talk with vendors and utilities to understand their needs, identify product niches, and prepare a conclusion report that discusses the pros and cons of each vendor product and how each niche will contribute to general solutions for deploying security solutions for U.S. power utilities.

Project deliverables include a literature review, vendor discovery search, criteria identification and definition, comparative analysis matrix, and best practices conclusion paper.

Protect Our Power is a nonpartisan advisory panel with the single focus of strengthening the nation’s electrical power grid. The panel is composed of experts from industry, the physical and cyber defense communities, and finance and government. Its mission is to build consensus among key stakeholders and public policy influencers to launch a coordinated and adequately funded effort to make the nation’s electric grid and the country’s more than 3,000 utility companies prepared and protected against all cyberthreats.

The Michigan Tech Institute of Computing and Cybersytems (ICC) has announced a search for an Assistant Director, Research Development, an administrative position.

The new position will support ICC researchers as they collectively work to create and implement activities to grow and support ICC-affiliated research and graduate programs.

By collaborating with, coaching/mentoring, and supporting the work of researchers at all levels, this individual will be integral to the business development and outreach of the ICC. The successful candidate will provide pre- and post-award support to institute members, assist with the financial processes for the institute, and help lead daily administrative functions.

View the complete position description here.