Category: News

Husky Games Takes 1st in Design Expo ’21 Enterprise Awards

As we’ve come to expect, the judging for Design Expo 2021 was VERY CLOSE, but the official results are in. The College of Engineering and the Pavlis Honors College have announced the award winners.

The Husky Game Development Enterprise (Team 115) has come out on top in Enterprise Awards category of Design Expo 2021. The student organization is advised by Scott Kuhl, Computer Science.

Husky Games is led by students Gabe Oetjens, Computer Science, and Keira Houston, Civil Engineering. The group is sponsored by Sponsored by: the Pavlis Honors College’s Enterprise Program.

Read more about Husky Games, view their Design Expo video submission, and explore all 2021 entries here: mtu.edu/expo.

More than 1,000 students in Enterprise and Senior Design showcased their hard work April 15 at Michigan Tech’s second-ever fully virtual Design Expo.

Teams competed for cash awards totaling nearly $4,000. Judges for the event included corporate representatives, community members and Michigan Tech staff and faculty.

Download and play the game here: www.huskygames.com.

Watch the video below:

115 Husky Game Development

ENTERPRISE AWARDS (Based on video submissions)

First Place
Husky Game Development (Team 115)
Advisor Scott Kuhl, College of Computing
Video

Second Place
Aerospace Enterprise (Team 106)
Advisor L. Brad King, Mechanical Engineering-Engineering Mechanics
Video

Third Place: 
Innovative Global Solutions (Team 116)
Advisors Radheshyam Tewari, ME-EM and Nathan Manser, Geological and Mining Engineering and Sciences
Video

Honorable Mention: 
Consumer Product Manufacturing (Team 111)
Advisor Tony Rogers, Chemical Engineering
Video

See all categories and awards here: mtu.edu/expo.


Volunteers Needed for Augmented Reality Study

by Department of Computer Science

We are looking for volunteers to take part in a study exploring how people may interact with future Augmented Reality (AR) interfaces. During the study, you will record videos of yourself tapping on a printed keyboard. The study takes approximately one hour, and you will be paid $15 for your time. You will complete the study at your home.

To participate you must meet the following requirements:

  • You must have access to an Android mobile phone
  • You must have access to a printer
  • You must be a fluent speaker of English
  • You must be 18 years of age or older
  • You must live in the United States

If you would like to take part, please contact rhabibi@mtu.edu


Dr. Qun Li to Present Lecture April 23, 3 pm


The Department of Computer Science will present a lecture by Dr. Qun Li on Friday, April 23, 2021, at 3:00 p.m. Dr. Li is a professor in the computer science department at William and Mary university. The title of his lecture is, “Byzantine Fault Tolerant Distributed Machine Learning.”

Lecture Title

Byzantine Fault Tolerant Distributed Machine Learning

Lecture Abstract

Training a deep learning network requires a large amount of data and a lot of computational resources. As a result, more and more deep neural network training implementations in industry have been distributed on many machines. They can also preserve the privacy of the data collected and stored locally, as in Federated Deep Learning.

It is possible for an adversary to launch Byzantine attacks to a distributed or federated deep neural network training. That is, some participating machines may behave arbitrarily or maliciously to deflect the training process. In this talk, I will discuss our recent results on how to make distributed and federated neural network training resilient to Byzantine attacks. I will first show how to defend against Byzantine attacks in a distributed stochastic gradient descent (SGD) algorithm, which is the core of distributed neural network training. Then I will show how we can defend against Byzantine attacks in Federated Learning, which is quite different from distributed training.


Article by Sidike Paheding in Elsevier’s Remote Sensing of Environment


An article by Dr. Sidike Paheding, Applied Computing, has been accepted for publication in the Elsevier journal, Remote Sensing of Environment, a top journal with an impact factor of 9.085. The journal is ranked #1 in the field of remote sensing, according to Google Scholar.

The paper, “Estimation of root zone soil moisture from ground and remotely sensed soil information with multisensor data fusion and automated machine learning,” will be published in Volume 260, July 2021 of the journal. Read and download the article here.

Highlights

  • A machine learning approach to estimation of root zone soil moisture is introduced.
  • Remotely sensed optical reflectance is fused with physical soil properties.
  • The machine learning models well capture in situ measured root zone soil moisture.
  • Model estimates improve when measured near-surface soil moisture is used as input.

Paheding’s co-authors are:

  • Ebrahim Babaeian, Assistant Research Professor, Environmental Science, University of Arizona, Tucson
  • Vijay K. Devabhaktuni, Professor of Electrical Engineering, Department Chair, Purdue University Northwest, Hammond, IN
  • Nahian Siddique, Graduate Student, Purdue University Northwest
  • Markus Tuller, Professor, Environmental Science, University of Arizona

Abstract

Root zone soil moisture (RZSM) estimation and monitoring based on high spatial resolution remote sensing information such as obtained with an Unmanned Aerial System (UAS) is of significant interest for field-scale precision irrigation management, particularly in water-limited regions of the world. To date, there is no accurate and widely accepted model that relies on UAS optical surface reflectance observations for RZSM estimation at high spatial resolution. This study is aimed at the development of a new approach for RZSM estimation based on the fusion of high spatial resolution optical reflectance UAS observations with physical and hydraulic soil information integrated into Automated Machine Learning (AutoML). The H2O AutoML platform includes a number of advanced machine learning algorithms that efficiently perform feature selection and automatically identify complex relationships between inputs and outputs. Twelve models combining UAS optical observations with various soil properties were developed in a hierarchical manner and fed into AutoML to estimate surface, near-surface, and root zone soil moisture. The addition of independently measured surface and near-surface soil moisture information to the hierarchical models to improve RZSM estimation was investigated. The accuracy of soil moisture estimates was evaluated based on a comparison with Time Domain Reflectometry (TDR) sensors that were deployed to monitor surface, near-surface and root zone soil moisture dynamics. The obtained results indicate that the consideration of physical and hydraulic soil properties together with UAS optical observations improves soil moisture estimation, especially for the root zone with a RMSE of about 0.04 cm3 cm−3. Accurate RZSM estimates were obtained when measured surface and near-surface soil moisture data was added to the hierarchical models, yielding RMSE values below 0.02 cm3 cm−3 and R and NSE values above 0.90. The generated high spatial resolution RZSM maps clearly capture the spatial variability of soil moisture at the field scale. The presented framework can aid farm scale precision irrigation management via improving the crop water use efficiency and reducing the risk of groundwater contamination.


Remote Sensing of Environment (RSE) serves the Earth observation community with the publication of results on the theory, science, applications, and technology of remote sensing studies. Thoroughly interdisciplinary, RSE publishes on terrestrial, oceanic and atmospheric sensing. The emphasis of the journal is on biophysical and quantitative approaches to remote sensing at local to global scales.


PhD Student Daniel Byrne, CS, Awarded Finishing Fellowship


by Karen S. Johnson, Communications Director, College of Computing

The Graduate Dean Awards Advisory Panel and dean have awarded a Summer 2021 Finishing Fellowship to PhD student Daniel Byrne, Computer Science. Byrne will receive full support for the semester, which includes three research credit hours and a stipend.

“The panel was impressed with your research, publication record, and contribution to the mission of Michigan Tech,” says the award letter. “The intent of this fellowship is to allow you to focus your time on your dissertation so that you can complete your degree requirements during the fellowship period.”

Byrne’s research centers around the modeling and optimization of memory systems, which are found in today’s datacenters. He explains that data caching helps improve the speed and efficiency of front-end cloud applications, such as websites and video streaming.


In collaboration with researchers at the University of Rochester, Byrne has developed a new data caching system. “Our system uses intelligent data replication and allocation across multiple memory devices to maximize performance while reducing overall operating costs,” Byrne says.

“Specifically, we focus on utilizing new memory technologies to lower operational costs while meeting performance targets,” Byrne adds. “Even small increases in performance and energy savings have significant impact over an entire deployment of servers.”

His improvements to caching systems have already been adopted outside the lab, into a widely-used open-source caching system called “memcached.”

“Daniel’s research focuses on modeling and designing a hybrid memory system where the conventional DRAM (faster, but more expensive) and the emerging non-volatile memory (NVM, cheaper but slower) are combined to host a key-value store,” says Dr. Zhenlin Wang, Computer Science, Byrne’s faculty advisor, along with Dr. Nilufer Onder, associate professor in the CS department.

Wang expects that Byrne’s research will have a long term impact on design and implementation of a hybrid key-value store. “His work explores the theoretical properties of and interactions between inclusive and exclusive caches, a design space which has never been investigated before,” Wang says.

Byrne began his Michigan Tech PhD studies in computer science in Fall 2016. “I am grateful for the amount of support from my advisors, the Computer Science department, and the Graduate School during my PhD program,” he says.

“I am also incredibly grateful for my PhD committee’s support as I finish my dissertation over the summer. It has been a wonderful journey, and I have greatly enjoyed my time as a graduate student, especially my tenure as GSG vice president.”

“I extend my sincere gratitude to the Graduate School for this support during the final period of completing and defending my dissertation,” he adds.

“I also would like to thank the College of Computing for its efforts in creating a strong research environment and a supportive community of graduate students and faculty.”

Recipients of the fellowship are expected to finish during the semester for which funding is provided, maintain good academic and conduct standing, publish their work in internationally recognized peer review journals, among other requirements.

Byrne served as vice president of the Michigan Tech Graduate Student Government from Summer 2019 to Spring 2020. He says he is happy to have had the opportunity to advocate for graduate students and achieve increased support for health care, an initiative he championed during his tenure.

In Spring 2019 he received a Graduate Student Service Award, which is awarded by the Graduate Student Government Executive Board. The Service Award recognizes outstanding contributions to the graduate community at Michigan Tech. See the April 5, 2019, announcement in Tech Today here.

View Byrne’s Github page here.