Also In This Section
  • Topics

  • Author: karenjoh

    The Michigan Tech College of Computing offers a full range of undergraduate and graduate degrees in the Computing disciplines.

    Sidike Paheding, Applied Computing, Publishes Paper in IEEE Access

    A paper co-authored by Sidike Paheding, Applied Computing, has been published in the journal, IEEE Access. “Trends in Deep Learning for Medical Hyperspectral Image Analysis,” was available for early access on March 24, 2021.

    The paper discusses the implementation of deep learning for medical hyperspectral imaging.

    Co-authors of the paper are Uzair Khan, Colin Elkin, and Vijay Devabhaktuni, all with the Department of Electrical and Computer Engineering, Purdue University Northwest.

    Abstract

    Deep learning algorithms have seen acute growth of interest in their applications throughout several fields of interest in the last decade, with medical hyperspectral imaging being a particularly promising domain. So far, to the best of our knowledge, there is no review paper that discusses the implementation of deep learning for medical hyperspectral imaging, which is what this work aims to accomplish by examining publications that currently utilize deep learning to perform effective analysis of medical hyperspectral imagery.

    This paper discusses deep learning concepts that are relevant and applicable to medical hyperspectral imaging analysis, several of which have been implemented since the boom in deep learning. This will comprise of reviewing the use of deep learning for classification, segmentation, and detection in order to investigate the analysis of medical hyperspectral imaging. Lastly, we discuss the current and future challenges pertaining to this discipline and the possible efforts to overcome such trials.

    DOI: 10.1109/ACCESS.2021.3068392

    IEEE Access is a multidisciplinary, applications-oriented, all-electronic archival journal that continuously presents the results of original research or development across all of IEEE’s fields of interest. Supported by article processing charges, its hallmarks are a rapid peer review and publication process with open access to all readers.


    Our Stories: Dr. Robert Pastel, Assoc. Prof., Computer Science

    This is part of a series of short introductions about College students, faculty, and staff that we would like to include in the Weekly Download. Would you like to be featured? Send a photo and some background info about yourself to computing@mtu.edu.

    Dr. Robert Pastel, Associate Professor of Computer Science

    • Advisor to Humane Interface Design Enterprise (HIDE)
    • Has been teaching at Michigan Tech for about 20 years, and teaching for 30 years.
    • Researcher with the Human-Centered Computing group of the Institute of Computing and Cybersystems (ICC)

    Education

    • PhD, University of New Mexico, Physics
    • MS, Computer Science, Michigan Tech

    Faculty Profile


    Classes Dr. Pastel teaches: 
    o    CS5760 – Human-Computer Interaction – Usability Evaluation and Testing 
    o    CS4791 and CS4792 – Senior Design
    o    ENT1960 – ENT5960 – Humane Interface Design Enterprise

    The “coolest” class you teach, and why: All my classes are “cool” because they all involve making applications that will be used by people. The “coolest” class is CS4760 – User Interface – Design and Implementation where students work with scientists across the world to make citizen science applications.

    The importance of your class topics to the overall understanding of Computing and your discipline: In all my classes, students learn to design and implement usable applications for people.

    Your teaching philosophy: My teaching philosophy is that students learn best by experience and working with others. Consequently students work in teams on project for clients. 

    Research projects in which students are assisting: 

    • StreamCLIMES – Large collaborative project studying bio diversity of intermittent streams. I’m responsible for developing a web applications monitoring the stream.
    • FloodAware – Large collaborative project recording and modelling flooding in urban areas. I’m responsible for developing the citizen science effort.
    • KeTT – Keweenaw Time Traveler – Historical geospatial information citizen science website for user to record region’s history and explore the maps and stories. 

    Interests beyond teaching and research: The outdoors: skiing, biking and hiking. Every summer, he takes a one-month backpacking trip. 


    Human Factors Grad Student Wins Hackathon, Cites Pandemic for Opportunity

    One Michigan Tech graduate student found a silver lining of the pandemic-driven shift to remote study: the ability to gain experiences previously prevented by distance. And “gained experience” is an understatement, as Brooke Poyhonen recently was on the winning team in the Texas Health Care Challenge, an online hackathon that sought solutions to problems in health care.

    The winning project, from Team WatsonCares, focused on women’s postpartum health and proposed a suite of services for new mothers:

    • A natural-language chatbot, powered by IBM Watson’s AI, to answer patient questions about both mental and physical health
    • A community feature allowing postpartum women to support one another
    • Deep informational and support resources

    Poyhonen said the team came together because after hearing initial “problem pitches,” in which existing teams outline the projects they want to tackle, some were uninterested in the originally pitched ideas. So they created their own team. “Ideally, we want the chatbot to be personalized to the patient’s history,” she said. “And we wanted to create a safe space for women to talk to each other.”

    Poyhonen will complete her accelerated M.S. in applied cognitive science and human factors this spring. She earned a B.S. in psychology from Michigan Tech in 2020. Both degrees are offered by the Cognitive and Learning Sciences department in the University’s College of Sciences and Arts.

    The Texas challenge is normally on-site only, and she appreciated the chance to participate and urges other students to seek out similar opportunities. “It was great to meet people from around the country and work with a team on a real-world goal,” Poyhonen said. “It’s a great networking opportunity and gives me a concrete project to discuss in interviews. It was just so rewarding.”

    The team’s prize included $120,000 in credits toward IBM products and services, a smaller cash award, and temporary office space with a Dallas venture capital firm. Poyhonen is working with team members on the project as a start-up while also pursuing other opportunities.

    She got her first taste of hackathons over the winter in the Work Related Musculoskeletal Disorders Grand Challenge, run by the American Registry for Diagnostic Medical Sonography. The challenge was to help the up to 90% of sonographers who develop disorders such as occupational overuse syndrome. Her team, which included a sonography mentor, an engineering student and two sonography students, created the Air Buddy, a device to help sonographers apply pressure to a probe with reduced physical stress. Poyhonen’s team won first place after judges deliberated for an entire week after the month-long window for teams to work on the problem.

    Kelly Steelman, interim chair of the Cognitive and Learning Sciences Department, said hackathons are great supplements to classroom experiences. “I commend Brooke for taking the initiative to seek out design challenges as a way to build her portfolio of experiences and hone the skills she’s learned in our program,” Steelman said. “Brooke took advantage of opportunities through outside organizations, but we also offer hack-a-thons right here on campus.”

    She said Husky Innovate is currently planning their inaugural hack-a-thon as part of an initiative to grow the human-centered design community at Michigan Tech. For more information on this, contact Lisa Casper.

    Dr. Steelman is a member of the Human-Centered Computing research group of the Institute of Computing and Cybersystems (ICC).

    Michigan Tech’s graduate program in Applied Cognitive Science and Human Factors teaches students how to apply principles of psychology to the design and evaluation of human-technological systems. Steelman said Beth Veinott, director of the Center for Human-Centered Computing, frequently reinforces for students that, “If you get the psychology right first, you design the right system, it is easier to train, and people are more likely to adopt it.”


    PhD Defense: Jinxiang Liu, Monday, April 2, 1-3 pm

    PhD candidate Jinxiang Liu, Computer Science, will present his PhD Defense on Monday, April 12, 2021, from 1:00 to 3:00 p.m.

    The title of Liu’s dissertation is, “Prediction of Coincident Peak Days in Electricity System: A Case Study for Classification on Imbalanced Data.”

    Dissertation Abstract

    To guarantee sufficient electricity supply for its highest demands, many regional organizations surcharge their customers during coincident peaks (CPs), a time of highest demand across the system or region of interest. Therefore, the accurate prediction of these coincident peaks would be helpful not only for companies to ensure sufficient generation is available, but also for customers who may try to avoid electricity consumption and consequent additional cost.

    This dissertation focuses on the prediction of the top five coincident peak days (5CPs) in a year. We used classification models to solve this imbalanced prediction problem (around 1.3\% for positive cases) by classifying the next day as 5CP days or non-5CP days.

    We analyze six sets of actual historical data from different regions of Canada and the United States. We explore the effect of forecast accuracy on 5CP days prediction through four cases: I – knowing tomorrow’s power demand and weather condition exactly (an oracle), II & III – knowing some information about tomorrow (an oracle + increasing noise), and IV – no knowledge of future.

    We proposed a three-phase model to predict 5CP days: first, clustering is applied to filter some negative cases, second, an all convolutional neural network that estimates the probability of being a 5CP day for the remaining cases is learned, and third, an adaptive method is used determines thresholds.

    This three-phase model exhibits promising performances with the highest mean recall of 1.00, mean precision of 0.56, and mean F1 score of 0.72. Finally, we explored the use of a few-short learning framework to this problem. A triplet network is implemented for the 2-way-5-shot classifications. The prediction results have the highest mean recall of 1.00, mean precision of 0.67, and mean F1 score of 0.79.


    Register for Michigan Tech’s Design Expo, Thursday, April 15

    by Pavlis Honor College

    Now’s the time to register to attend Virtual Design Expo, the annual Enterprise and Senior Design project showcase at Michigan Tech.

    Once again, for the second time ever in its 21-year history, Design Expo will take place virtually. We’ve excitedly taken lessons learned from last year’s first virtual Expo and fused it with new ways of connecting to make the 2021 Design Expo more engaging and safe to attend in real-time!

    Design Expo puts our undergraduate student innovators and their corporate and community sponsors and faculty advisors front and center.

    Every year, teams showcase their solutions to complex, real-world and life-changing challenges. Teams compete for thousands of dollars in cash awards—and receive priceless, well-deserved recognition. 

    Guests and judges will need to register in order to attend by April 9. 

    This year’s event will happen in multiple segments online via Zoom and Gatherly. 

    Monday, April 12

    • Noon — Remote, asynchronous viewing and judging of team videos opens on the Design Expo website, mtu.edu/expo.

    Thursday, April 15

    • 11 to 11:30 a.m. — Opening remarks via live Zoom webinar
    • 11:30 a.m. to 1:30 p.m. — Synchronous event with student teams begins: take part in real-time interaction/Q&A with students using Gatherly
    • 3 to 3:30 p.m. — Presentation of Awards via Zoom live webinar
    • 3:30 p.m. — Virtual Design Expo 2021 concludes

    Spring Celebration Update

    In light of recent changes to Michigan’s COVID-19 epidemic orders that increase the size of allowable group gatherings, Michigan Technological University has modified its graduation celebration planned for April 30, 2021 to allow families and guests to participate alongside their graduate.

    As announced in an earlier email to students, the University will host a graduation walk through campus to celebrate this significant milestone. Students may now invite up to six guests to walk with them. Details, including the start times, are still being worked out. Graduates who would like to participate will be asked to sign up prior to the celebration. A signup link will be emailed to all eligible graduates on March 22.

    As a reminder, Michigan Tech remains committed to the health and safety of our campus community. All guests and graduates will be required to wear a face mask at all times and practice social distancing during the event. Please be sure to check www.mtu.edu/commencement for the latest information.

    Congratulations, Huskies—you did it! The pride you feel now will only grow stronger with time. Your Michigan Tech family and our community joins you and your loved ones in celebrating your completion of this journey. 

    Regalia Update

    Regalia is encouraged, but not required at the outdoor event. Regalia can be ordered through Herff Jones with direct delivery to the graduate. If you have questions regarding your order, contact Michele Nash from Herff Jones at mnash@herffjones.com or 248-667-9018. 

    Class of 2021, you’ve done an amazing job! If you have any questions, contact commencement@mtu.edu.

    Please Note

    Neither participation in the commencement ceremony nor inclusion in the program constitutes official completion of degree requirements or the attainment of honors or other recognitions.

    Graduates do not receive their diploma at the commencement ceremony. Diplomas are mailed to the graduate approximately six weeks after degree requirements are met.



    CyberCorps SFS Program: Info Session #1 Is March 22, 7 pm

    Monday, March 22, 2021 6-7 p.m.

    An exciting scholarship opportunity has been announced for Michigan Tech students who wish to pursue cybersecurity-related degrees and work for government agencies after graduation.

    Two informational sessions will be presented, on March 22 and March 30, both from 6:00 to 7:00 p.m. EST, to help students complete the application process for the CyberCorps: Scholarship for Service (SFS) Program.

    Both sessions will provide the same information. Prior registration is required. Following, you will receive a confirmation email and instructions for joining the session.

    View the blog post here: https://blogs.mtu.edu/computing/2021/02/19/info-sessions-for-cybercorps-scholarship-are-march-22-march-30/

    More info about the SFS Program: https://www.mtu.edu/sfs/


    SASE at Michigan Tech Is Newest Student Organization

    A new student organization has been officially approved through the office of Student Leadership and Involvement

    The mission of the Society of Asian Scientists and Engineers (SASE) at Michigan Tech is to support and promote the personal and professional development of Asian/Asian-American students and their friends.

    Any and all interested students (including all majors and identities) are welcome to join SASE at Michigan Tech. Faculty and staff are also welcome to be involved as honorary members of the RSO.

    Find more info and contact the SASE at Michigan Tech on the group’s Involvement Link webpage.

    An APIDA (Asian Pacific Islander Desi American) subcommittee will plan activities centered specifically around the Asian American experience,. Sudent leaders are working to officially affiliate the group as a national SASE chapter, in addition to its status as a Registered Student Organization (RSO) at the University.

    The SASE group is co-advised by Distinguished Professor of Transportation Engineering Dr. Zhanping You (CEE) and Liz Fujita, Academic Advisor and Outreach Specialist in the Electrical and Computer Engineering department.

    Information about the national work of SASE can be found here.



    Physics Colloquium Today, March 18, 4 pm

    The next Physics Colloquium will be held at 4 p.m. today (March 18) via Zoom. Alice Allen will present “Schrödinger’s code: Opening the computational box.”

    Allen is a faculty specialist in the Astronomy Department at the University of Maryland (College Park) and editor-in-chief of the Astrophysics Source Code Library (ASCL). Her abstract and bio can be viewed here.

    If you haven’t registered for the weekly Physics Colloquium series in the past, please register in advance for this event.