Category: Research

Nathir Rawashdeh Comments on Bad Weather Driving Project

Nathir A. Rawashdeh
Nathir A. Rawashdeh

Nathir Rawashdeh was quoted by Digital Engineering 24/7 in a story about artificial intelligence and simulation software helping engineers test autonomous vehicles’ driving in bad weather.

Rawashdeh is assistant professor in the Department of Applied Computing, an affiliated assistant professor in the Department of Electrical and Computer Engineering, and a member of the Institute of Computing and Cybersystems (ICC).

Rainmakers for Autonomous Driving

Nature presents a major obstacle when engineers test autonomous driving in bad weather. You cannot invoke a snowy, rainy or sunny day on demand; nor can you summon up a thunderstorm at your engineering team’s convenience—at least you can’t in the real world. But you can in the virtual world where you control the pixels. This has now become a growing business segment for simulation software makers.

“Sensor and computing technologies are rapidly evolving and changing in an engineering sense, which requires continuous updating of noise simulation and sensor degradation models to serve the ADAS community of engineers and researchers,” Rawashdeh says.

Read more at Digital Engineering 24/7, by Kenneth Wong.

Lucas and Whitaker Place in Computing[MTU] Showcase Poster Session

Evan Lucas
Evan Lucas
Steven Whitaker
Steven Whitaker

The Institute of Computing and Cybersystems has announced the winners of the first Computing[MTU] Showcase Poster Session. Among the winners were electrical and computer engineering graduate students Evan Lucas and Steven Whitaker for “Active learning with binary feedback on multiclass problems,” who were tied for second place with Suresh Pokharel of Computer Science.

Active learning with binary feedback on multiclass problems

An active learning approach is often used for multiclass classification problems, where predictions are made on new data and a human user is used to determine if the predictions are correct. Typical approaches may ask a human to select the correct class if the prediction is incorrect. This work attempts to use a binary feedback on the predicted classes to save time and allow maximal use of a negative prediction on a partly trained model.

Anindya Ghoshroy Joins the Field of Compressed Ultrafast Photography

Anindya Ghoshroy
Anindya Ghoshroy

Dr. Anindya Ghoshroy (PhD ’20) begins the new year with a postdoctoral researcher position at California Institute of Technology. Ghoshroy will be working under the direction of Dr. Lihong Wang, a world-renowned researcher in the imaging field, and the inventor of the fastest optical technology in the world, called compressed ultrafast photography (CUP), capable of 10 trillion frames per second.

Wang and Ghoshroy are interested in the next big step – investigating the near field implementations of ultrafast photography, and the resolution of nanoscale transient scenes. An integration of the CUP framework with “active convolved illumination” (ACI), an image-capturing technology that Ghoshroy and his PhD advisor Dr. Durdu Guney have been developing, and will potentially lead to a significant first step towards this direction.

ACI, being immune to “noise” will potentially enable imaging of live cells, virus, and bacteria with fine details, not accessible with the state-of-the-art imaging systems.

Set of ACI images.
Ground truth, Raw data, ACI futuristic illustration of SARS CoV2, ACI OFF, ACI ON with 3 nm scale bar, and ACI ON as a 3D model.

Christopher Middlebrook Awarded Device from Gentec-EO Laser Lab

Device with laser beam and software display.

Chris Middlebook (ECE) was one of the winners of the Gentec-EO Laser Lab Awards. Middlebrook won a Beamage-4M laser beam profiler.

The Gentec-EO Laser Lab Awards contest aims to support optics laboratories in universities and colleges in the United States. Its goal is to ensure students have access to the same quality measurement instruments that are used today in the industry.

MTU Team Among Winners of TiM$10K Challenge

Group of five team members.
L-R: Brian Parvin, Paul Allen, David Brushaber, Alex Kirchner, and Kurtis Alessi

A Michigan Tech team is among the winners of the SICK Inc. TiM$10K Challenge. For the second year, students from universities around the country were invited to participate in the challenge, designed to support innovation and student achievement in automation and technology.

For the competition, teams were supplied with a 270-foot SICK LiDAR sensor and accessories, and challenged to solve a problem, create a solution or bring a new application to any industry that utilizes the SICK LiDAR.

The Tech team members — Brian Parvin, Kurtis Alessi, Alex Kirchner, David Brushaber and Paul Allen — earned Honorable Mention (fourth place overall) for their project, Evaluating Road Markings (the Road Stripe Evaluator). The innovative product aims to help resolve issues caused by poor road markings while reducing maintenance costs and improving motorist safety.

Each team was asked to submit a video and paper for judging upon completion of its project. A panel of judges decided the winning submissions based on creativity and innovation, ability to solve a customer problem, commercial potential, entrepreneurship of the team, and reporting.

“This was a unique project in that the team was required to identify a problem and develop a solution to it that is based on SICK’s TiM LiDAR — most teams are handed a problem and asked to create a solution,” said team advisor Tony Pinar, senior design coordinator in the Department of Electrical and Computer Engineering. “I think this format allowed the team to exercise even more innovation than a ‘typical’ project.”

Pinar said the team was well organized and demonstrated an excellent work ethic from day one. “It was exciting to watch them identify a salient problem and develop a functional proof-of-concept solution despite the setbacks that affected us all after spring break,” he said.

SICK is one of the world’s leading manufacturers of sensors, safety systems, machine vision, encoders and automatic identification products for industrial applications.

Soft Community Detection

Sakineh “Audrey” Yazdanparast (ECE), Timothy C. Havens (CC), and Mohsen Jamalabdollahi have authored “Soft Overlapping Community Detection in Large-Scale Networks via Fast Fuzzy Modularity Maximization,” which is available under the “Early Access” area on IEEE Xplore.

Extract

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.

Citation

S. Yazdanparast, T. C. Havens and M. Jamalabdollahi, “Soft Overlapping Community Detection in Large-Scale Networks via Fast Fuzzy Modularity Maximization,” in IEEE Transactions on Fuzzy Systems.

DOI: 10.1109/TFUZZ.2020.2980502

Jeremy Bos on the Wild West of Automotive Lidar

Photonics Focus cover with infrared photo of a car.

THE CITY OF HOUGHTON is in the far north of Michigan’s upper peninsula, along the southern shore of Lake Superior. It’s famous for two things: the notable engineering school, Michigan Technical[sic] University, and being two miles past the end of the Earth. It’s more than 200 miles away from the closest freeway, and averages 250 inches of snowfall per year.

Jeremy Bos, assistant professor of electrical and computer engineering at Michigan Tech, finds this environment ideal for research on autonomous vehicles (AV).

Read more at SPIE Photonics Focus, by Gwen Weerts.

Pearce Group on Solar Systems

Renewable EnergyECE student Trevor Peffley co-authored an article with Joshua Pearce (MSE/ECE) titled: “The Potential for Grid Defection of Small and Medium Sized Enterprises Using Solar Photovoltaic, Battery and Generator Hybrid Systems“, which was published in Renewable Energy.

https://doi.org/10.1016/j.renene.2019.12.039

Based on the results of this study it is clear that it is already technically and economically viable for all scales of commercial utility customers to install a solar, battery and natural gas hybrid electricity generation system.

In the News

Joshua Pearce’s (MSE/ECE) research on bifacial solar photovoltaic (PV) performance in the snow was covered by PV Magazine.

Joshua Pearce (MSE/ECE) is quoted in “2020 energy trends affecting consumers” published in Save.

In Print

Joshua Pearce (MSE/ECE) coauthored a study “Performance of Bifacial Photovoltaic Modules on a Dual-Axis Tracker in a High-Latitude, High-Albedo Environment” published in the Conference Proceedings of the IEEE Photovoltiac Specialists Conference (PVSC). 

New Funding

Joshua Pearce (MSE/ECE/IMP) is the principal investigator on a project that has received a $182,580 research and development cooperative agreement with the U.S. Department of Energy.

The project is entitled, “The Energizer Bunny: Dual-Use Photovoltaic and Pasture-Raised Rabbit Farms.”

Chelsea Schelly (SS/IMP )is the Co-PI on this potential 15-month project.

Synchrophasor Data Project Funding for Chee-Wooi Ten

Chee-Wooi Ten
Chee-Wooi Ten

Chee-Wooi Ten (ECE/AIM) is the principal investigator on a project that has received a $99,732 research and development cooperative agreement with the University of California Riverside. The project is entitled, “Discovery of Signatures, Anomalies, and Precursors in Synchrophasor Data with Matrix Profile and Deep Recurrent Neural Networks.” This is a 17-month project.

By Sponsored Programs.

Havens Discusses Artificial Intelligence in Plain Terms

Timothy Havens
Timothy Havens

Cognitive scientist and Dartmouth professor John McCarthy coined the term artificial intelligence (AI) in 1955 when he began his exploration of whether machines could learn and develop formal reasoning like humans. More than 60 years later, AI is the hottest tech topic of the day, from the boardroom to the breakroom.

“AI is a mathematical and algorithmic model that allows computers to learn to do tasks without being explicitly programmed to do those tasks.” –Timothy Havens, the William and Gloria Jackson Associate Professor of Computer Systems in the College of Computing at Michigan Technological University and director of the Institute of Computing and Cybersystems.

For those who prefer analogies, Havens likens the way AI works to learning to ride a bike: “You don’t tell a child to move their left foot in a circle on the left pedal in the forward direction while moving your right foot in a circle… You give them a push and tell them to keep the bike upright and pointed forward: the overall objective. They fall a few times, honing their skills each time they fail,” Havens says. “That’s AI in a nutshell.”

Read more at The Enterprisers Project, by Stephanie Overby.