Timothy Havens, the William and Gloria Jackson Associate Professor of Computer Systems, has co-authored a paper recently published in The Journal of the Acoustical Society of America, Volume 50, Issue 1.
The paper is titled, “Recurrent networks for direction-of-arrival identification of an acoustic source in a shallow water channel using a vector sensor.” Havens’s co-authors are Steven Whitaker (EE graduate student), Andrew Barnard (ME-EM/GLRC), and George D, Anderson, US Naval Undersea Warfare Center (NUWC)-Newport.
The work described in the paper was funded by the United States Naval Undersea Warfare Center and Naval Engineering Education Consortium (NEEC) (Grant No. N00174-19-1-0004) and the Office of Naval Research (ONR) (Grant No. N00014-20-1-2793). This is Contribution No. 76 of the Great Lakes Research Center at Michigan Technological University.
Conventional direction-of-arrival (DOA) estimation algorithms for shallow water environments usually contain high amounts of error due to the presence of many acoustic reflective surfaces and scattering fields. Utilizing data from a single acoustic vector sensor, the magnitude and DOA of an acoustic signature can be estimated; as such, DOA algorithms are used to reduce the error in these estimations.
Three experiments were conducted using a moving boat as an acoustic target in a waterway in Houghton, Michigan. The shallow and narrow waterway is a complex and non-linear environment for DOA estimation. This paper compares minimizing DOA errors using conventional and machine learning algorithms. The conventional algorithm uses frequency-masking averaging, and the machine learning algorithms incorporate two recurrent neural network architectures, one shallow and one deep network.
Results show that the deep neural network models the shallow water environment better than the shallow neural network, and both networks are superior in performance to the frequency-masking average method.
Department of Computer Science faculty and students presented two posters, a paper, and chaired a session at the 26th Annual Conference on Innovation and Technology in Computer Science Education (ITiCSE), conducted online June 26 to July 1, 2021.
“A Visualization for Teaching Integer Coercion,” a poster presented by James Walker with Steven Carr, Ahmed Radwan, Yu-Hsiang Hu, Yu Chin Cheng, Jean Mayo, and Ching-Kuang Shene, was one of three posters that received the conference’s Best Poster Award.
The poster describes the Expression Evaluation (EE) visualization tool. The tool is designed to aid students in understanding type conversions that take place implicitly in C. Understanding type conversions is essential to avoid Integer errors in C which continue to be a source of security vulnerabilities.
An additional paper and poster were presented at the conference, below. Dr. Linda Ott chaired a conference session on Students: Diversity.
Poster: Modeling the Growth and Spread of Infectious Diseases to Teach Computational Thinking by Meara Pellar-Kosbar, Dylan Gaines, Lauren Monroe, Alec Rospierski, Alexander Martin, Ben Vigna, Devin Stewart, Jared Perttunen, Calvin Voss, Robert Pastel and Leo Ureel II
The poster discusses a simulation model developed to teach middle school students about the spread of infectious diseases augmented with affordances to help students develop computational thinking skills. The simulation was partially developed as a Citizen Science project in the courses CS4760 and CS5760, User Interface Design and Human Computer Interaction.
This position paper describes a fundamental difference in attitudes toward the use of analogy in the computer science education community versus other STEM education communities. Additionally, it provides suggestions for how to address concerns in the CS education research community in order to advance research into the use of analogy in computing education
The 26th annual conference on Innovation and Technology in Computer Science Education (ITiCSE) was sponsored by ACM, the ACM Special Interest Group on Computing Education (SIGCSE), the ACM Europe Council, and Informatics Europe.
by Graduate Student Government
The Graduate Student Government (GSG) is pleased to announce a hybrid poster presentation session at Alumni Reunion 2021, which will be held Aug. 6.
Due to the ongoing pandemic, GSG has decided to combine physical posters with prerecorded presentations from participants. This has been decided to keep in mind the health and safety of everyone who is going to be a part of this event, since the COVID-19 pandemic is still ongoing.
The Alumni Reunion poster presentation session is a continued tradition designed to increase interaction between graduate students and MTU alumni. It is a unique opportunity for graduate students to share their research work and expand network connections. This event is also a great opportunity for students to work on their presentation skills and prepare for upcoming conferences. Alumni will be able to give valuable insight and feedback on the videos that appeal to them.
Participation is open to graduate students from all departments. The event will consist of elevator-pitch-style poster presentations, with physical posters and prerecorded presentations by participants. This hybrid setup will allow alumni to take a closer look at the physical posters and everyone to view the video presentations for the respective posters. Registration closes on July 16 at 11:59 p.m. Limited seats only. Don’t wait — register today.
Detailed instructions and guidelines for recording your presentation will be sent out to you once you have registered. Alternatively, you will also be able to find the instructions on the GSG website. The deadline for participants to submit their presentation videos is July 30.
For more information, please contact Shreya Joshi at firstname.lastname@example.org.
by Pasi Lautala
Thomas Oommen (GMES, ICC), Ricardo Eiris, (CEGE, ICC), and Beth Veinott (CLS, ICC) are among eight Michigan Tech researchers who have submitted a a record number of eight concept papers for proposed research projects with the Federal Railroad Administration.
The Federal Railroad Administration (FRA) requested that Michigan Tech submit a record number of eight concept papers for proposed research projects as part of their 2021 Broad Agency Announcement.
In addition, Tech is a subcontractor for two more concept paper proposals. The paper submittal was coordinated by the Rail Transportation Program and the range of topics speaks to the diversity of Michigan Tech’s expertise applicable to the rail transportation. The PIs are looking forward to FRA decisions on how many of these papers advance to full proposals.
Each of the 10 projects had a different principal investigator (PI), representing six university departments/institutes and several more co-PIs.
The project titles and their PIs include:
- Hyper- and Multi-spectral Sensing and Deep Learning for Automated Identification of Roadbed Condition, (PI, Thomas Oommen, GMES).
- Wire Arc Additive Manufacturing (WAAM) for Weld Enhanced Cast Steel Coupler Knuckles (PI, Paul Sanders, MSE).
- IoT Assisted Data-analytics Framework Enables Assessment of Location Based Ride Quality (LBRQ) (PI, Sriram Malladi, MEEM).
- RailStory: Using Web-based Immersive Storytelling to Attract the Next Generation of Young Women in Rail (PI, Ricardo Eiris, CEGE).
- A Risk Informed Decision-Making Framework for Coastal Railroad System Subjected to Storm Hazards and Sea Level Rise (PI, Yousef Darestani, CEGE).
- Rail Corridor Life-Cycle Assessment (LCA) Framework, Factors and Models to Support Project Evaluation and Multi-Modal Comparisons (PI, Pasi Lautala, CEGE).
- Development of Infrared Thermography for Effective Rail Weld Inspection (PI, Qingli Dai, CEGE).
- Enabling Longer-distance, AI-enabled Drone-based Grade Crossing Assessment in Potentially GPS Denied Environments (PI, Colin Brooks).
- Multi-Site Simulation to Examine Driver Behavior Impact of Integrated Rail Crossing Violation Warning (RCVW) and In-Vehicle Auditory/Visual Alert (IVAA) System (PI, Elizabeth Veinott, subcontract with Virginia Tech).
- Evaluation of Non-traditional Methods of Reducing Emissions in Short Line Railroad Operations (PI, Jeremy Worm, subcontract with ASLRRA).
On May 18, 2021, Dr. Guy Hembroff, Applied Computing, presented an invited talk at a meeting of Michigan’s Health Information Management Systems Society (HIMSS). Dr. Hembroff discussed his work developing a trusted framework architecture designed to improve population health management and patient engagement.
The talk demonstrated his team’s work in the development of accurate geo-tagged pandemic prediction algorithms, which are used to help coordinate medical supply chains to care for patients most vulnerable to COVID-19, an innovation that can be extended to help improve general population health management.
The framework of the pandemic prediction architecture, which aggregates longitudinal patient health data, including patient generated health data and social determinants of health, is a holistic and secure mHealth community model. The model can help Michigan residents overcome significant barriers in healthcare, while providing healthcare agencies with improved and coordinated population management and pandemic prediction.
The architecture’s machine learning algorithms strategically connect residents to community resources, providing customized health education aimed to increase the health literacy, empowerment and self-management of patients. The security of the architecture includes development of unique health identifiers and touch-less biometrics capable of large-scale identity management.
Dr. Guy Hembroff is an associate professor in the Applied Computing department of the Michigan Tech College of Computing, and director of the Health Informatics graduate program. His areas of expertise are network engineering, medical/health informatics, biometric development, intelligent medical devices, data analytics, and cybersecurity.
The event was sponsored by HIMSS and Blue Cross Blue Shield of Michigan (BCBSM).
A mission-driven non-profit, the Healthcare Information and Management Systems Society, Inc. (HIMSS) is a global advisor and thought leader supporting the transformation of the health ecosystem through information and technology, according to the organization’s website.