Category: Publications

Dan Fuhrmann Contributes Paper to Automation Alley’s 2020 Technology in Industry Report

How should companies prepare in 2020 and beyond for the worldwide digital transformation and position themselves for long-term strategic success?

Automation Alley’s 2020 Technology in Industry Report, “Seeing Industry 4.0 Through a 2020 Lens,” recently published, explores this question in a series of new case studies and white papers that explore new trends in Industry 4.0, with the aim of helping businesses stay informed about all things digital. The articles in the report were written in collaboration with academic and industry leaders.

An article contributed by Dan Fuhrmann, interim chair of the Department of Applied Computing, “Michigan Tech Launches New College of Computing,” is included in the report. View and download a PDF of the article below.

Fuhrmann’s paper shares the history and rationale for Michigan Tech’s new College of Computing, and discusses recent College outreach that encourages and facilitates a holistic vision of computing across the disciplines that mirrors the reality of today’s Industry 4.0 workplace.

Download

“I am impressed by Automation Alley’s vision to bring Industry 4.0 thinking to manufacturers in Michigan and the upper Midwest,” notes Fuhrmann. “They have identified eight key technologies that they believe will revolutionize business as we know it: artificial intelligence, big data, cloud computing, cybersecurity, modeling and simulation, robotics, the Internet of Things, and additive manufacturing.” ()

“Many of these topics are being pursued in the College of Computing and elsewhere at Michigan Tech,” Fuhrmann notes. “In fact, Automation Alley has a graphic depicting these technologies that I have ‘borrowed’ liberally for my own presentations about where we are headed.”

“The opportunities associated with Industry 4.0 are enormous,” agrees Adrienne Minerick, dean of Michigan Tech’s College of Computing. “The technological advancements of recent decades provide industry with great opportunities for growth, but this is also a time of profound uncertainty for business leaders and the global workforce as we face new challenges, including the enormous amounts of data we are collecting, disruptive and sophisticated cyber threats, and the impact and fallout of coronavirus, the worst pandemic of our lifetimes.”

The relationship between Michigan Tech and Automation Alley is also important to Michigan Tech’s strategy to expand research and development at the University that enhances and supports the capabilities of the U.S. manufacturing industry, says Jacob Manchester, associate director of corporate research in the Vice President for Research office at Michigan Tech.

“In addition to the potential to solve specific challenges through direct partnerships with Automation Alley membership, the connections to these manufacturers provides valuable networking opportunities for our faculty and researchers,” Manchester explains. “This can be key to building successful collaborations on federal research funding opportunities that address broader societal challenges as we embrace a future manufacturing environment defined by Industry 4.0,”

Fuhrmann says that the COO of Automation Alley, Pavan Muzumdar, visited Michigan Tech in 2019 to help facilitate early conversations about forming the College of Computing. More recently, Automation Alley has expressed interest in serving on a College of Computing external advisory board.

“There are tremendous opportunities for Michigan Tech in engaging with the Automation Alley and their network of small- and medium-sized Michigan manufacturers,” Fuhrmann says. “I will continue to pursue those relationships in my role in Applied Computing and as part of the Tech Forward initiative.

Automation Alley is a World Economic Forum Advanced Manufacturing Hub (MHUB) and a nonprofit Industry 4.0 knowledge center located in Troy, Michigan.

Michigan Tech is a member of Automation Alley.

The full Automation Alley 2020 Technology in Industry Report is available for purchase and download here; an executive summary can be downloaded on the same page.


Tim Havens Co-Author of Article in IEEE Trans. Fuzzy Systems

Timothy Havens (DataS/CC) and Anthony Pinar (DataS/ECE) are co-authors of a paper, written in collaboration with University of Missouri researchers Muhammad Islam, Derek Anderson, Grant Scott, and Jim Keller, that has been published in the July 2020 issue of the journal IEEE Transactions on Fuzzy Systems.

The article is titled, “Enabling explainable fusion in deep learning with fuzzy integral neural networks.” Link to the article here. See the abstract below.

Abstract
Information fusion is an essential part of numerous engineering systems and biological functions, e.g., human cognition. Fusion occurs at many levels, ranging from the low-level combination of signals to the high-level aggregation of heterogeneous decision-making processes. While the last decade has witnessed an explosion of research in deep learning, fusion in neural networks has not observed the same revolution. Specifically, most neural fusion approaches are ad hoc, are not understood, are distributed versus localized, and/or explainability is low (if present at all). Herein, we prove that the fuzzy Choquet integral (ChI), a powerful nonlinear aggregation function, can be represented as a multilayer network, referred to hereafter as ChIMP.

We also put forth an improved ChIMP (iChIMP) that leads to a stochastic-gradient-descent-based optimization in light of the exponential number of ChI inequality constraints. An additional benefit of ChIMP/iChIMP is that it enables explainable artificial intelligence (XAI). Synthetic validation experiments are provided, and iChIMP is applied to the fusion of a set of heterogeneous architecture deep models in remote sensing. We show an improvement in model accuracy, and our previously established XAI indices shed light on the quality of our data, model, and its decisions.

Citation
M. Islam, D. T. Anderson, A. J. Pinar, T. C. Havens, G. Scott and J. M. Keller, “Enabling Explainable Fusion in Deep Learning With Fuzzy Integral Neural Networks,” in IEEE Transactions on Fuzzy Systems, vol. 28, no. 7, pp. 1291-1300, July 2020, doi: 10.1109/TFUZZ.2019.2917124.


Dylan Gaines, Ph.D. Candidate, Computer Science

Written by Karen S. Johnson, Communications Director, College of Computing

Dylan Gaines at ASSETS 2018

Computer Science master’s student and doctoral candidate Dylan Gaines is one of three Michigan Tech students recently awarded a multi-year National Science Foundation (NSF) Graduate Research Fellowship. 

The oldest STEM-related fellowship program in the United States, the prestigious NSF Graduate Research Fellowship Program (GRFP) recognizes exceptional graduate students in science, technology, engineering and mathematics (STEM) disciplines early in their career and supports them through graduate education.

NSF-GRFP fellows are an exceptional group; 42 fellows have gone on to become Nobel Laureates, and about 450 fellows are members of the National Academy of Sciences.

The additional Michigan Tech graduate students who received the fellowship are Greta Colford ’19 (Mechanical Engineering) and Seth Kriz (Chemical Engineering).

The fellowship provides three years of financial support, including a $34,000 annual stipend for each fellow and a $12,000 cost-of-education allowance for the fellow’s institution. In addition to financial support, the GRFP provides opportunities for research in national laboratories and international research.

Read an April 15, 2020, Tech Today article about this here.

Four years, two degrees

Gaines, who arrived as a first-year student in fall 2016, was awarded the Bachelor of Science in Computer Science in spring 2019, also completing a concentration in Game Development. He’s pursuing on his master’s now, which he expects to complete in December 2020. He has also begun working on his Ph.D. in Computer Science at Michigan Tech, which he anticipates completing in spring 2023.

Commenting on Gaines’ award, Department of Computer Science Chair Dr. Linda Ott says, “All of us in the Department of Computer Science are very excited that Dylan is being awarded an NSF Graduate Research Fellowship. This is clear affirmation that Dylan is an excellent student, and that even as an undergraduate he demonstrated strong research skills.”

“I am very thankful for this award, and for everyone that supported me through the application process and helped to review my essays” Gaines says.

Early interest, a first-year research assistant

Ott notes that it is also a tribute to Gaines’s advisor, CS Associate Professor Keith Vertanen who has established a very successful research group in intelligent interactive systems.

“Dr. Ott encouraged the pursuit of research in her CS 1000 class by bringing in faculty like Dr. Vertanen to present what they were working on,” Gaines says. “Because of this, I started doing research with Dr. Vertanen my first semester at Michigan Tech, and he has been nothing but supportive the whole time,” adding, “all of the faculty and staff at Michigan Tech are very supportive of students and make teaching a priority.”

Vertanen recalls that in fall 2017, Gaines approached him following a talk about Vertanen’s research in the CS department’s first-year seminar class.

“I was so impressed by him that I subsequently hired him as an undergraduate research assistant, something I would normally not do with a first-year student,” Vertanen confirms. “Since then, he has been a key contributor to my research group.”

“It became quickly clear to me he was a talented, hard-working, and curious researcher,” Vertanen says. I was pleased to learn NSF recognized this, as well, by awarding him a GRF. I’m excited to see what he’ll accomplish during his Ph.D.”

Text entry techniques

Gaines’s research with Vertanen focuses on text entry techniques for those with visual impairments. His master’s and doctoral research will continue this work. He also plans to develop assistive technologies for use in Augmented Reality. 

His aim is to make smartphones—and technology in general—more accessible for people with visual impairments. Looking ahead, Gaines definitely wants to continue to pursue research, but he’s unsure yet if it will be in academia or in industry. “At this time, I am open to both possibilities,” he says.

In his first two years at Michigan Tech, Gaines was instrumental in research leading to two papers accepted for the 2018 and 2019 ACM Conference on Human Factors in Computing Systems, with acceptance rates of 24% and 26%, respectively. For both papers, Vertanen notes that Dylan helped design and execute the user studies, and also provided careful feedback that improved the submitted papers, the rebuttals, and the final papers. CHI is the flagship conference in human-computer interaction.

During his undergraduate studies, Gaines worked with Vertanen on his NSF project, “CAREER: Technology Assisted Conversations.” In the first year of his PhD, he worked on two NSF projects with Vertanen, “CHS: Small: Rich Surface Interaction for Augmented Environments” and “CHS: Small: Collaborative Research: Improving Mobile Device Input for Users who are Blind or Low Vision.” 

Gaines plans to continue his research in line with the above project, “Improving Mobile Device Input for Users who are Blind or Low Vision,” though now funded by the GRF. See below for more information about the research projects.

“Dylan is one of the strongest and easiest to work with students I have encountered in over ten years of advising undergraduate research students,” Vertanen concludes. “I have no doubt he will produce an exciting and impactful portfolio of research during his Ph.D. studies.”\

An active life

Gaines is an active member of Triangle Fraternity, which he says helped to shape who he is as a person and as a scholar. Triangle is a fraternity of engineers, architects, and scientists that develop balanced men who cultivate high moral character, foster lifelong friendships, and live their lives with integrity, according to the organizations’ website.

As an undergraduate, Gaines was active in the Organization for Information Systems, and he served on the Dean’s Student Advisory Council. He also participated for three years in Husky Game Development (HGD) Enterprise, capping his final year as HGD president and coordinating 66 students on 12 teams. In HGD, student teams design and build video games, often in collaboration with sponsors and alumni.

In summer 2019, he helped with a week-long Computer Science department Summer Youth Program for high school girls, assisting in development of the web API used in their projects, and helping the girls build their mobile apps.

Gaines competed in three seasons for the Huskies as a member of the cross country and track teams, Now, he’s a graduate assistant coach for the team. “I started running cross country about nine years ago,” Gaines affirms. “I ran in the 8k and the 3k steeplechase on the MTU team for three years during my undergrad. I have loved watching the Cross program grow and improve throughout my time here.”

View Gaines’s Michigan Tech Cross Country record here.

Trust, a novel interface, peer mentoring

As a third-year undergrad, Gaines conducted his own research project investigating a novel interface for eye-free text entry, developing an Android application and integrating it with the statistical decoder used in Vertanen’s research group.

“This decoder has evolved over many years and has served as the basis for a variety of projects,” Vertanen explains. “As such, it has a large code base with a complex API. Despite this, Dylan was able to incorporate the decoder into his project with only minimal guidance. He asked questions when stuck, but almost always figured out solutions on his own. His software engineering skills are excellent and he is one of the few students I trust to make changes to the decoder.”

An application programming interface, or API, is a computing interface which defines interactions between multiple software intermediaries. It defines the kinds of calls or requests that can be made, how to make them, the data formats that should be used, the conventions to follow, among other functions.

Upon completing the prototype of his eyes-free text entry interface, Gaines designed and conducted a longitudinal user study. 

“In designing the experimental methodology for his study, he routinely challenged me with probing and insightful questions about how the study should be designed,” Vertanen says. “I felt like I was working with a senior Ph.D. student rather than an undergraduate. I cannot overstate how impressive this is; many students just blindly follow my suggestions, even my bad ones! Now, whenever I design a new user study, I always discuss it with Dylan as this helps refine the design and spot problems.”

Vertanen also asks his other students to pilot their studies with Gaines, as he often provides feedback that improves their studies.

ACM ASSETS 2018

Dylan Gaines, far left, at the ASSETS 2018 Student Research Competition

Gaines’s eyes-free text entry interface work culminated in his solo submission to the ACM ASSETS 2018 Student Research Competition (SRC), “Exploring an Ambiguous Technique for Eyes-Free Mobile Text Entry.” And his related technical paper was accepted by the SRC competition, which had a 50% acceptance rate.

In October 2018, Vertanen and Gaines traveled to Galway, Ireland, where Gaines presented a poster and a talk at ASSETS 2018 about his interface, Tap123. Tap123 offers the potential for faster and easier-to-learn text input for users who are visually impaired. ACM ASSETS is the premier venue for research on assistive technologies and accessible computing.

“His writing skills are excellent; he produced a quality paper with minimal guidance from me,” says Vertanen of Gaines’s ASSETS 2018 participation. “At his poster presentation, he did an excellent job communicating his research and answering questions, and he advanced to the final round, where he gave an excellent talk to the entire conference, winning third-place in the undergraduate category.

Significant impact, contribution

Vertanen reflects that while Gaines is clearly very bright, he also demonstrates an ability to critically assess his understanding of a topic and asked questions whenever he suspects his solutions might be incorrect. 

In his role as Dylan’s research advisor, Vertanen encouraged Dylan, when writing he was writing his research plan, to not only incorporate feedback he received presenting at ASSETS, but also to think about how his work might be relevant in a post-mobile phone world.  I was pleased with the research plan he created,” Vertanen says.

Vertanen predicts that Gaines’s planned work will significantly impact the utility of future AR interfaces for people with visual impairments, adding, “More broadly, his work may also impact everyone, since limitations of device or situation may make audio-only AR an attractive alternative to visual-based AR interaction”

And Gaines has a head start on the publication process. “Throughout his time in my group, he has shown a keen interest in the academic publication process,” Vertanen says of Gaines. “This has already manifested itself; as a first-year Ph.D. student he has one paper in submission and another ready for submission.”

With this publication experience and motivation, Vertanen expects that Gaines’s Ph.D. research will be disseminated widely. Further, this work on interfaces for those with disabilities will provide motivating material in the College of Computing’s ongoing efforts to recruit students who are typically underrepresented in computer science.

NSF Research Projects

CAREER: Technology Assisted Conversations
Sponsor: NSF
PI: Keith Vertanen
Abstract: Face-to-face conversation is an important way in which people communicate with each other, but unfortunately there are millions who suffer from disorders that impede normal conversation. This project will explore new real-time communication solutions for people who face speaking challenges, including those with physical or cognitive disabilities, for example by exploiting implicit and explicit contextual input obtained from a person’s conversation partner.

The goal is to develop technology that improves upon the Augmentative and Alternative Communication (AAC) devices currently available to help people speak faster and more fluidly. The PI will assemble teams of undergraduates to develop the project’s software, and he will host a summer youth program on the technology behind text messaging, offering scholarships for women, students with disabilities, and students from underrepresented groups. Funded first-year research opportunities will further help retain undergraduates, particularly women, in computing.

CHS: Small: Rich Surface Interaction for Augmented Environments
Sponsor: NSF
PI: Keith Vertanen
Co-PI: Scott Kuhl
The preliminary data for this project was developed through an Institute of Computing and Cybersystems faculty seed grant funded by Michigan Tech alumnus Paul Williams. Read a blog post about this research here.
Abstract: Virtual Reality (VR) and Augmented Reality (AR) head-mounted displays are increasingly being used in different computing related activities such as data visualization, education, and training. Currently, VR and AR devices lack efficient and ergonomic ways to perform common desktop interactions such as pointing-and-clicking and entering text. 

The goal of this project is to transform flat, everyday surfaces into a rich interactive surface. For example, a desk or a wall could be transformed into a virtual keyboard. Flat surfaces afford not only haptic feedback, but also provide ergonomic advantages by providing a place to rest your arms. This project will develop a system where microphones are placed on surfaces to enable the sensing of when and where a tap has occurred. Further, the system aims to differentiate different types of touch interactions such as tapping with a fingernail, tapping with a finger pad, or making short swipe gestures. This project will investigate different machine learning algorithms for producing a continuous coordinate for taps on a surface along with associated error bars.

CHS: Small: Collaborative Research: Improving Mobile Device Input for Users who are Blind or Low Vision. 
Sponsor: NSF
PI: Keith Vertanen
Abstract: Smartphones are an essential part of everyday life. But for people with visual impairments, basic tasks like composing text messages or browsing the web can be prohibitively slow and difficult. The goal of this project is to develop accessible text entry methods that will enable people with visual impairments to enter text at rates comparable to sighted people. This project will design new algorithms and feedback methods for today’s standard text entry approaches of tapping on individual keys, gesturing across keys, or dictating via speech.

Publications by Dylan Gaines

Vertanen, K., ​Gaines, D.​, Fletcher, C., Stanage, A., Watling, R., Krisstensson, P.O. 2019. VelociWatch: Designing and Evaluating a Virtual Keyboard for the Input of Challenging Text. In ​Proceedings of The ACM Conference on Human Factors in Computing Systems (CHI ‘19)​.

Gaines, D., Exploring an Ambiguous Technique for Eyes-Free Mobile Text Entry. 2018. In ​Proceedings of the 20t​ h​ International ACM SIGACCESS Conference on Computers and Accessibility Student Research Competition​ ​(ASSETS ‘18)​.

Vertanen, K., Fletcher, C., ​Gaines, D.​, Gould, J., Kristensson, P.O. 2018. The Impact of Word, Multiple Word, and Sentence Input on Virtual Keyboard Decoding Performance. In ​Proceedings of the ACM Conference on Human Factors in Computing Systems​ ​(CHI ‘18)​.

More Background

The Deans’ Student Advisory Council, College of Business, serves to foster effective communication among the Dean’s Office, faculty, and students, and provide advice to the Dean on matters relating to undergraduate business education and the College community.

Husky Game Development Enterprise (HGD). The mission of HGD is to design and develop games for business, education, and fun. We work as an interdisciplinary, student-run enterprise that fosters productivity, creativity, and effective business practices. Our goal is to create quality software that will attract and satisfy industry sponsors.

The Institute of Computing and Cybersystems (ICC) is the research arm of the Michigan Tech College of Computing. It leads and promotes opportunities for faculty and students to work across organizational boundaries to create an environment that is a reflection of the contemporary technological innovation that mirrors today’s industry and society.

The National Science Foundation (NSF) is an independent federal agency created by Congress in 1950 “to promote the progress of science; to advance the national health, prosperity, and welfare; to secure the national defense.

The NSF Graduate Research Fellowship Program (GRFP) recognizes and supports individuals early in their graduate training in Science, Technology, Engineering, and Mathematics (STEM) fields.

The Organization for Information Systems (OIS) is a student organization focused on the technical and professional development of its members.

Triangle Fraternity was founded in 1907 by sixteen engineers at the University of Illinois.  From the start, it was meant to be a place where men of similar majors could socialize, support each other’s academic pursuits and better prepare themselves for successful careers.  Since that time, our membership has grown and expanded to include mathematics and the physical sciences as well as architecture, making us STEM long before the term was coined in 2001. Today, we continue to provide a unique social, academic and professional experience for STEM majors.


Undergraduate Tyler Marenger Earns University Honors

Written by Karen S. Johnson, Communications Director, College of Computing

Tyler Marenger’s career goals include constantly improving himself, facing and overcoming the challenges he encounters along the way. The Michigan Tech Software Engineering undergraduate is making sure he’s prepared.

This spring, Marenger was awarded Michigan Tech University Honors, which recognizes the academic excellence of undergraduates.

Since his enrollment as a first-year student in fall 2017, Marenger, from Gladstone, Mich., has appeared multiple times on the 4.0 Deans’ List and the Deans’ List. In fall 2020 (December), he expects to complete his Bachelor of Science in Software Engineering and a minor in Mathematical Sciences.

Marenger says this recognition on the University Honors list encourages him as he continues on his academic journey and pursues his life goals.

“It is an incredible honor to have such a prestigious University recognize and commemorate me on my accomplishments,” Marenger says. “I also truly appreciate the words of recognition and encouragement from the College of Computing and the Computer Science department. I am proud to say that I am a Michigan Tech Husky.”

University Honors are reserved for degree-seeking students who rank in the top 2 percent of their class and maintain at least a 3.50 cumulative GPA while carrying 12 credits or more for both the fall and spring semesters.

More accolades

In addition to University Honors, Marenger has three times received the Department of Mathematics’ Certificate of Merit for Outstanding Academic Achievement for his performance in the courses MA  2160, Calculus II; MA 3160, Calculus III; and MA 2720, Statistical Methods. For one semester, Marenger was a teaching assistant for MA 3160, Calculus III, grading mathematical essays (write-ups) and student coursework.

Marenger is a three-semester member of the Husky Game Development Enterprise, working with his teammates on the game, “Lost in Mazie Mansion,” which won Honorable Mention honors at this spring’s Design Expo. His primary role on the team is software development, and he also contributes to the design and layout of the game. His team plans to continue development of the game in the fall 2020 semester.

Making time for personal pursuits

Marenger says that by breaking tasks into manageable pieces, he feels he can better manage his time, meet his goals, and make time for personal pursuits. 

“I have found that breaking up my work/studying in order to exercise helps promote a high level of energy and encourages me to complete my workload,” he notes. “Dedicating specific time slots to reduce my workload helps me get done in a timely manner. That way, I can enjoy my personal time exploring my interests or spending time with my friends.”

Marenger identifies his most substantial hobby as fitness, and says he enjoys pushing himself towards self-improvement. He is an avid weightlifter, constantly setting new goals and spending countless hours at the gym. He enjoys outdoor and recreational activities, as well, including jet skiing, dirt biking, hiking, skiing, camping, and fishing. 

Supportive faculty mentors

Both Associate Professor Ali Ebnenasir, Computer Science, and Elizabeth Reed, a former senior lecturer in Michigan Tech’s Department of Mathematics, have been especially supportive regarding Marenger’s academic work, he says.

After finishing his MA 2720, Statistical Methods, course in fall 2018—with an outstanding final grade—and earning the Mathematics department’s Certificate of Merit—Marenger shares that in an email Reed extended congratulations and best wishes, encouraging Marenger to seek a minor in Mathematical Sciences and offering to write a reference letter.

And shortly after completing the senior-level CS 4710, Model-Driven Software Development class in spring 2020, Marenger recalls that Ebnenasir both congratulated him on his performance in that class, and encouraged him to consider continuing his education beyond the bachelor of science.  CS 4710 focuses on mathematical methods for the design and verification of software systems. Marenger has since shared his resume with Ebnenasir, and earlier this summer they discussed Michigan Tech’s Computer Science Ph.D. program and funding and research opportunities.

“In spring 2020, Tyler demonstrated excellent performance in solving individual assignments, as well as professionalism in group projects,” Ebnenasir confirms, noting Marenger’s positive attitude towards learning new topics.

“Tyler is meticulous and hardworking, and I also I am sure that he will be a star if he maintains and improves his outstanding self-discipline and perseverance,” Ebnenasir says. “Good luck Tyler, and we hope to see you back for your Ph.D. at Michigan Tech in the future!”

Collaborations in software development

Marenger clearly excels at learning and mastering the ideas and content in his Computer Science courses. He says he especially enjoyed CS 4760, User Interface Design and Implementation, for which he and his CS 4760 team developed an application for use with the Micro:bit Web USB Grapher device, part of a teaching tool and curriculum aid already widely used for computing-related learning by K-12 teachers and students.

Marenger and his team reasoned that since the Micro:bit pocket-sized computer can record data through a variety of sensors, this capability, along with its board sensors and its extensibility, could also be used to augment classroom science demonstrations.

“Our application is designed to take the data that the pocket-sized Micro:bit provides and display it on one or more graphs,” Marenger explains. “The application graphs, manipulates, and saves data collected on the Micro:bit, which will help expose K-12 students to computing and programming principles while they learn about a wide variety of scientific phenomena.”

The team’s development and deployment of their React.js application was accomplished in collaboration with the Michigan Tech Humanities department, the Michigan Tech Graduate School, and Bill Siever, a teaching professor in the Computer Science and Engineering department at Washington University of St. Louis, Mo.

Building the future

Looking forward, Marenger says he will continue furthering his education and building his software development skills. 

“I plan to constantly educate myself on new and upcoming technologies so that I can pursue advancements in the field of computer science,” he confirms. “I want to gather as much industry knowledge as I can so that one day, I can take on project leadership roles or develop a product of my own that I can manage and promote.”


Sergeyev, Students Earn ASEE Conference Awards

Professor Aleksandr Segeyev, Applied Computing, and a group of Michigan Tech students presented two papers at the 2020 American Society for Engineering Education (ASEE) Gulf-Southwest Annual conference, which was conducted online April 23-24, 2020. Both papers received conference awards.

The Faculty Paper Award

“Pioneering Approach for Offering the Convergence MS Degree in Mechatronics and Associate Graduate Certificate”
by Sergeyev, Professor and Associate Chair John Irwin (MMET), and Dean Adrienne Minerick (CC).

The Student Paper Award

“Efficient Way of Converting outdated Allen Bradley PLC-5 System into Modern ControlLogix 5000 suit”, by Spencer Thompson (pictured), Larry Stambeck, Andy Posa, Sergeyev, and Lecturer Paniz Hazaveh, Applied Computing.

Founded in 1893, the American Society for Engineering Education is a nonprofit organization of individuals and institutions committed to furthering education in engineering and engineering technology.


Nathir Rawashdeh Publishes Paper in BioSciences Journal

A paper co-authored by Assistant Professor Nathir Rawashdeh, Applied Computing, on Skin Cancer Image Feature Extraction, has been published this month in the EurAsian Journal of BioSciences.

View the open access article, “Visual feature extraction from dermoscopic colour images for classification of melanocytic skin lesions,” here.

Additional authors are Walid Al-Zyoud, Athar Abu Helou, and Eslam AlQasem, all with the Department of Biomedical Engineering, German Jordanian University, Amman, Jordan.

Citation: Al-Zyoud, Walid et al. “Visual feature extraction from dermoscopic colour images for classification of melanocytic skin lesions”. Eurasian Journal of Biosciences, vol. 14, no. 1, 2020, pp. 1299-1307.

Rawashdeh’s interests include unmanned ground vehicles, electromobility, robotics, image analysis, and color science. He is a senior member of the IEEE.


Bo Chen, Grad Students Present Posters at Security Symposium

College of Computing Assistant Professor Bo Chen, Computer Science, and his graduate students presented two posters at the 41st IEEE Symposium on Security and Privacy, which took place online May 18 to 21, 2020.

Since 1980, the IEEE Symposium on Security and Privacy has been the premier forum for presenting developments in computer security and electronic privacy, and for bringing together researchers and practitioners in the field.

Chen leads the Security and Privacy (SnP) lab at Michigan Tech. He is a member of Michigan Tech’s Institute of Computing and Cybersystems (ICC) and its Center for Cybersecurity (CyberS).

His research focuses on applied cryptography and data security and he investigates novel techniques to protect sensitive data in mobile devices/flash storage media and cloud infrastructures. Chen is also interested in designing novel techniques to ensure security and privacy of big data.

Chen will serve as general chair for the First EAI International Conference on Applied Cryptography in Computer and Communications (AC3), which will be held in Xiamen, China, in May 2021.

Visit Chen’s faculty website here.

Poster: A Secure Plausibly Deniable System for Mobile Devices against Multi-snapshot Adversaries
Authors: Bo Chen, Niusen Chen
Abstract: Mobile computing devices have been used broadly to store, manage and process critical data. To protect confidentiality of stored data, major mobile operating systems provide full disk encryption, which relies on traditional encryption and requires keeping the decryption keys secret. This however, may not be true as an active attacker may coerce victims for decryption keys. Plausibly deniable encryption (PDE) can defend against such a coercive attacker by disguising the secret keys with decoy keys. Leveraging concept of PDE, various PDE systems have been built for mobile devices. However, a practical PDE system is still missing which can be compatible with mainstream mobile devices and, meanwhile, remains secure when facing a strong multi- snapshot adversary. This work fills this gap by designing the first mobile PDE system against the multi-snapshot adversaries.

Poster: Incorporating Malware Detection into Flash Translation Layer
Authors: Wen Xie, Niusen Chen, Bo Chen
Abstract: OS-level malware may compromise OS and obtain root privilege. Detecting this type of strong malware is challeng- ing, since it can easily hide its intrusion behaviors or even subvert the malware detection software (or malware detector). Having observed that flash storage devices have been used broadly by computing devices today, we propose to move the malware detector to the flash translation layer (FTL), located inside a flash storage device. Due to physical isolation provided by the FTL, the OS-level malware can neither subvert our malware detector, nor hide its access behaviors from our malware detector.

The 41st IEEE Symposium on Security and Privacy was sponsored by the IEEE Computer Society Technical Committee on Security and Privacy in cooperation with the International Association for Cryptologic Research. The Symposium was May 18-20, 2020, and the Security and Privacy Workshops were May 21, 2020.


Havens, Yazdanparast Publish Article in IEEE Transactions on Big Data

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.


Article by Tim Havens in IEEE Transactions on Fuzzy Systems

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 Is Co-author of Article in IEEE Transactions on Fuzzy Systems

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