Electrical and Computer Engineering Newsblog

ECE graduate student Aliaksei Petsiuk coauthored an article with Joshua Pearce (MSE/ECE) titled, “Low-cost open source ultrasound-sensing based navigational support for visually impaired,” published in the journal Sensors.
https://doi.org/10.3390/s19173783

Low-Cost Open Source Ultrasound-Sensing Based Navigational Support for the Visually Impaired

Abstract

Nineteen million Americans have significant vision loss.

Over 70% of these are not employed full-time, and more than a quarter live below the poverty line. Globally, there are 36 million blind people, but less than half use white canes or more costly commercial sensory substitutions. The quality of life for visually impaired people is hampered by the resultant lack of independence.

To help alleviate these challenges this study reports on the development of a low-cost, open-source ultrasound-based navigational support system in the form of a wearable bracelet to allow people with the lost vision to navigate, orient themselves in their surroundings and avoid obstacles when moving.

The system can be largely made with digitally distributed manufacturing using low-cost 3-D printing/milling. It conveys point-distance information by utilizing the natural active sensing approach and modulates measurements into haptic feedback with various vibration patterns within the four-meter range. It does not require complex calibrations and training, consists of the small number of available and inexpensive components, and can be used as an independent addition to traditional tools.

Sighted blindfolded participants successfully demonstrated the device for nine primary everyday navigation and guidance tasks including indoor and outdoor navigation and avoiding collisions with other pedestrians.

Read the Open Access article at Sensors.

West Baton Rouge solar plant with 197,000 panels begins construction: Entergy Louisiana to purchase its power

Some 197,000 solar panels capable of powering thousands of homes are going into one of the largest solar plants to be built in Louisiana on a 560-acre site near Port Allen.

“The economies of scale has finally kicked in,” said Joshua Pearce, director of the Michigan Tech Open Sustainability Technology lab. “Utilities are actively putting in large-scale solar farms because it’s now a low enough cost. When costs first came down, large industry jumped on it first and now utilities are catching up.”

Read more at The Advocate, by Kristen Mosbrucker.

Floating Solar Panels Are Helping This Mining Company Save Water

Las Tórtolas is a 4.1 square mile reservoir nestled in the sunny, arid mountains of Chile, about 40 miles north of the capital city of Santiago. But it’s not the kind of place you’d want to go swimming. The water in the reservoir is actually the waste (also known as tailings) from the nearby Los Bronces copper mine, and floating on top are 256 photovoltaic solar panels, each one capable of producing about 330 watts of electricity.

“It’s like putting a plastic sheet over the whole lake, or the whole tailings pond,” explains Joshua Pearce, a Professor of Materials Science and Engineering at Michigan Tech. Pearce has worked extensively in the emerging field of floatovoltaic technology (FVT), or the overlap of solar energy systems and water use. He says that the presence of solar panels over a body of water can provide enough shade to consistently reduce evaporation by 70-80%. That’s precisely what Anglo-American has achieved since the Las Tórtolas array went online in March 2019.

Read more at The Weather Channel, by Thom Dunn.

America’s richest could afford this important investment to help fight climate change, scientist says

The technology exists to “green” America’s electricity grid to fight climate change — and together, the country’s richest people have enough money to pay for it. In fact, they could even make a profit on the investment.

That’s according to a 2019 research paper on solar energy led by Joshua Pearce, a professor of materials science and engineering at Michigan Technological University.

Read more at CNBC Make It, by Catherine Clifford.

Amid energy transition in Michigan’s Upper Peninsula, what is solar’s role?

The Upper Peninsula Power Co., which has some of the highest electric rates in the continental U.S., is looking to buy power from a large-scale solar project it says would help reduce costs for its customers.

UPPCO’s case reflects trends elsewhere in Michigan where utilities are pursuing large-scale projects while at the same time being accused of limiting small, customer-owned projects.

“It’s much more acute and much more divisive here than it is downstate,” said Joshua Pearce, an engineering professor at Michigan Technological University in Houghton. “[UPPCO] hates distributed generation, but they love making money.”

Read more at Energy News Network, by Andy Balaskovitz.

Timothy Havens (CC/ICC) was General Co-Chair of the 2019 IEEE International Conference on Fuzzy Systems in New Orleans, LA, June 23 to 26. At the conference, Havens presented his paper, “Machine Learning of Choquet Integral Regression with Respect to a Bounded Capacity (or Non-monotonic Fuzzy Measure),” and served on the panel, “Publishing in IEEE Transactions on Fuzzy Systems.” Three additional papers authored by Havens were published in the conference’s proceedings: “Transfer Learning for the Choquet Integral,” “The Choquet Integral Neuron, Its PyTorch Implementation and Application to Decision Fusion,” and “Measuring Similarity Between Discontinuous Intervals – Challenges and Solutions.”

Zhuo Feng (ECE/ICC) is Principal Investigator on a project that has received a $500,000 research and development grant from the National Science Foundation. This potential three-year project is titled, “SHF: Small: Spectral Reduction of Large Graphs and Circuit Networks.”

Extract

Spectral methods are playing increasingly important roles in many graph and numerical applications. This research plan will investigate a truly-scalable yet unified spectral graph reduction approach that allows reducing large-scale, real-world directed and undirected graphs with guaranteed preservation of the original graph spectra.

The success of the proposed research will significantly advance the state of the arts in spectral graph theory, electronic design automation (EDA), data mining, machine learning, as well as scientific computing, leading to the development of much faster numerical and graph-based algorithms.

The algorithms and methodologies to be developed will be disseminated to leading technology companies such as EDA software and network companies for potential industrial adoptions. Spectral graph reduction algorithms/software packages will also be made available to other researchers through collaborations.

Read more at the National Science Foundation.

Timothy Havens (ECE/ICC) and Anthony Pinar (ECE) coauthored the article, “Enabling Explainable Fusion in Deep Learning with Fuzzy Integral Neural Networks,” which was accepted this month for publication in the journal IEEE Transactions on Fuzzy Systems.

DOI: 10.1109/TFUZZ.2019.2917124

Extract

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.

Herein, we prove that the fuzzy Choquet integral (ChI), a powerful nonlinear aggregation function, can be represented as a multi-layer network, referred to hereafter as ChIMP. An additional benefit of ChIMP/iChIMP is that it enables eXplainable AI (XAI).