Category: Research

Tony Pinar (ECE), Tim Havens (ECE/CS) and Joe Rice’s (CS) paper, titled “Efficient Multiple Kernel Classification Using Feature and Decision Level Fusion,” in IEEE Transactions on Fuzzy Systems was one of two papers from the transactions featured in IEEE Computational Intelligence Magazine as a CIS Publication Spotlight.

DOI: 10.1109/TFUZZ.2016.2633372

Extract: Kernel methods for classification is a well-studied area in which data are implicitly mapped from a lower-dimensional space to a higher dimensional space to improve classification accuracy. However, for most kernel methods, one must still choose a kernel to use for the problem. Since there is, in general, no way of knowing which kernel is the best, multiple kernel learning (MKL) is a technique used to learn the aggregation of a set of valid kernels into a single (ideally) superior kernel.

Read more at III Xplore Digital Library.

Joshua Pearce (MSE/ECE) gave an invited talk for the University of Lorraine entitled “Will you 3D print your next lab? : Leveraging Improvements in Distributed Manufacturing for Open Source Scientific Hardware” at the Lorraine Fab Living Lab in Nancy, France.

The visit was covered by the regional newspaper L’Est Republicain(circulation >123,000).

In Print

Joshua Pearce (MSE/ECE) authored the chapter “Open-source 3D Printing” in “Managing Humanitarian Innovation: The cutting edge of aid.” Editors: Eric James and Abigail Taylor, 2018, Practical Action Publishing.

eISBN: 978-178044-953-1 | ISBN: 978-185339-953-4 doi:https://doi.org/10.3362/9781780449531.021

Joshua Pearce (MSE/ECE) authored “Expanding the Consumer Bill of Rights for material ingredients,” in Materials Today.

In the News

Joshua Pearce (MSE/ECE), John Gershenson (MEEM), and alumni Tobias J. Mahan and Benjamin L. Savonen are mentioned in the article “Researchers Develop the Kijenzi 3D Printer to Respond to Humanitarian Crises,” in 3DPrint.com.

Research by Joshua Pearce (MSE/ECE), was featured in the story “Solar Microgrids for National Security: Study Finds 17 GW Could Fortify US Military Bases,” originally posted in May, 2017. The story was referenced recently in Microgrid Knowledge.

On the Road

Joshua Pearce (MSE/ECE) gave an invited talk, “Production for the People: How open source hardware design and 3D printing enable real distributed manufacturing,” at the 20th Finnish Rapid Prototyping Association Conference and Nordic3DExpo last Thursday (April 19) in Espoo, Finland.

Husam Sweidan, PhD student in Electrical and Computer Engineering, and Timothy Havens (ECE), published an article entitled, “Sensor Relocation for Improved Target Tracking,” in the April, 2018, volume of IET Wireless Sensor Systems.

DOI: 10.1049/iet-wss.2017.0037 , Print ISSN 2043-6386, Online ISSN 2043-6394

Extract: In the first phase, the wireless sensor network tracks the targets based on the initial deployment. The second phase uses the location estimates from phase 1 to form a region of interest (ROI). The last phase carries out the sensor relocation to the ROI.

Sumit Paudyal (ECE) is the principal investigator on a project that has received $500,000 from the National Science Foundation. The project is entitled “CAREER: Operation of Distribution Grids in the Context of High-Penetration Distributed Energy Resources and Flexible Loads.”

This is a five-year project.

Abstract

The number of distributed energy resources (DERs) and flexible loads such as photovoltaic (PV) panels, electric vehicles (EVs), and energy storage systems (ESSs) are rapidly growing at the consumer end. These small distributed devices connect to low voltage power distribution grids via power electronic interfaces that can support bi-directional power flows. Despite being small in size, if aggregated, these devices a provide significant portion of the energy and ancillary services (e.g., reactive power support, frequency regulation, load following) necessary for reliable and secure operation of electric power grids. In future distribution grids, with numerous such small active devices, real-time control and aggregation will entail computational challenges. The computational challenges further increase when the aggregation requires coordination with legacy grid control actions which involve integer decision variables, such as load tap changers, capacitor banks, and network switches. This CAREER project concentrates around solving operational and computational issues for distribution grids with large penetration of DERs and flexible loads.

Read more at the National Science Foundation.

Tonight’s viewers of AlphaGo will get the opportunity to learn more on the research and application of artificial intelligence (AI) happening today, here at Michigan Tech and beyond. A panel discussion with Dr. Timothy Havens (ECE/CS), Dr. Laura Brown (CS), Dr. Steven Goldsmith (MEEM/ECE), Dr. Scott Marratto (HU), and Josh Manela (ECE alumnus) of Ford subsidiary Argo AI will follow the screening.

AlphaGo: 7:30 p.m. Friday, November 3, Rozsa Center for the Performing Arts

AlphaGo is featured in this year’s 41 North Film Festival hosted by the Rozsa Center for the Performing Arts. Directed by Greg Kohs, the documentary chronicles a journey from the halls of Cambridge, through the backstreets of Bordeaux, past the coding terminals of DeepMind in London, and, ultimately, to the seven-day tournament in Seoul. As the drama unfolds, more questions emerge: What can artificial intelligence reveal about a 3000-year-old game? What can it teach us about humanity?

Saeid Nooshabadi (ECE/ICC) is the principal investigator on a project that has received $349,988 from the National Science Foundation for the project, “Collaborative Research: ACI-CDS&E: Highly Parallel Algorithms and Architectures for Convex Optimization for Realtime Embedded Systems (CORES).” This is a three-year project.

By Sponsored Programs.

Abstract

Embedded processors are ubiquitous, from toasters and microwave ovens, to automobiles, planes, drones and robots and are typically very small processors that are compute and memory constrained. Real-time embedded systems have the additional requirement of completing tasks within a certain time period to accurately and safely control appliances and devices like automobiles, planes, robots, etc. Convex optimization has emerged as an important mathematical tool for automatic control and robotics and other areas of science and engineering disciplines including machine learning and statistical information processing. In many fields, convex optimization is used by the human designers as optimization tool where it is nearly always constrained to problems solved in a few hours, minutes or seconds. Highly Parallel Algorithms and Architectures for Convex Optimization for Realtime Embedded Systems (CORES) project takes advantage of the recent advances in embedded hardware and optimization techniques to explore opportunities for real-time convex optimization on the low-cost embedded systems in these disciplines in milli- and micro-seconds.

Read more at the National Science Foundation.

Chee-Wooi Ten (ECE) is the lead principal investigator on a project that has received a $348,866 research and development grant from the National Science Foundation (NSF). Yeonwoo Rho (Math/ICC) is the Co-PI on the project “CPS:Medium: Collaborative Research: An Actuarial Framework of Cyber Risk Management for Power Grids.” This is a three-year project.

There are two investigators from University of Wisconsin-Milwaukee.

The total for both universities is $700,975.

Abstract

As evidenced by the recent cyberattacks against Ukrainian power grids, attack strategies have advanced and new malware agents will continue to emerge. The current measures to audit the critical cyber assets of the electric power infrastructure do not provide a quantitative guidance that can be used to address security protection improvement. Investing in cybersecurity protection is often limited to compliance enforcement based on reliability standards. Auditors and investors must understand the implications of hypothetical worst case scenarios due to cyberattacks and how they could affect the power grids. This project aims to establish an actuarial framework for strategizing technological improvements of countermeasures against emerging cyberattacks on wide-area power networks.

Read more at the National Science Foundation.