Assistant Professor Sidike Paheding, Applied Computing, will present his lecture, “Deep Neural Networks for UAV and Satellite Remote Sensing Image Analysis,” on Dec. 11, 2020, at 3:00 p.m. via online meeting.
Paheding’s research focuses on the areas of computer vision, machine learning, deep learning, image/video processing, and remote sensing.
Remote sensing data can provide non-destructive and instantaneous estimates of the earth’s surface over a large area, and has been accepted as a valuable tool for agriculture, weather, forestry, defense, biodiversity, etc. In recent years, deep neural networks (DNN), as a subset of machine learning. for remote sensing has gained significant interest due to advances in algorithm development, computing power, and sensor systems.
This talk will start with remote sensing image enhancement framework, and then primarily focuses on DNN architectures for crop yield prediction and heterogeneous agricultural landscape mapping using UAV and satellite imagery.
Paheding is an associate editor of the Springer journal Signal, Image, and Video Processing, ASPRS Journal Photogrammetric Engineering & Remote Sensing, and serves as a guest editor/reviewer for a number of reputed journals. He has advised students at undergraduate, M.S., and Ph.D. levels, and authored/coauthored close to 100 research articles.
Bo Chen, Computer Science, has been awarded a Fall 2020 REF Research Seed Grant (REF-RS) for his project, “Towards Secure and Reliable Decentralized Cloud Storage.” Funding for the 12-month, $25,800 award begins on January 1, 2021.
“This grant will provide significant help to advance my current research,” says Chen. “This is really exciting news for me.”
As a recipient of the REF seed grant, which is awarded by the Michigan Tech Office of the Vice President for Research, Chen will participate in review and feedback for the next round of REF proposals. View the full list of Fall 2020 REF award recipients here.
A decentralized cloud storage system eliminates the need of dedicated computing infrastructures by allowing peers which have spare storage space to join the network and to provide storage service. Compared to the conventional centralized cloud storage system, it can bring significant benefits including cheaper storage cost, better fault tolerance, greater scalability, as well as more efficient data storing and retrieval, making it well fit the emerging Internet of things (IoT) applications.
While bringing immense benefits, the decentralized cloud storage system also raises significant security concerns, since the storage peers are much less reputable than the traditional data centers and may more likely misbehave.
This project thus aims to build a secure and reliable decentralized cloud storage system which can serve as the cloud infrastructure for future IoT applications. The project will actively investigate two fundamental security issues faced by the decentralized cloud storage system: 1) How can we prevent the malicious storage peers from stealing the data? 2) How can we ensure that once the data are stored into the system, they are always retrievable even if the storage peers misbehave?
To address the aforementioned issues in an untrusted p2p environment, the PI will integrate efficient integrity checking with the blockchain, as well as the broadly equipped secure hardware like Intel SGX. The PI will also broaden the educational impact of the proposed project by actively involving both graduate and undergraduate students from the MTU cybersecurity programs.
The Vice President for Research Office announces the Fall 2020 REF awards. Thanks to the individual REF reviewers and the REF review panelists, as well as the deans and department chairs, for their time spent on this important internal research award process.
Darrell Robinette (ME-EM/APSRC) is the principal investigator on a project that has received a $1,348,109 research and development co-op/joint agreement from the Department of Energy.
The project is entitled, ” Energy Optimization of Light and Heavy Duty Vehicle Cohorts of Mixed Connectivity, Automation and Propulsion System Capabilities via Meshed V2V-V2I and Expanded Data.”
Jeff Naber (ME-EM/APSRC), Bo Chen (ME-EM/APSRC), Jung Yun Bae (ME-EM/APSRC) and Chris Morgan (PHC/APSRC) are Co-PI’s on this potential 2.3-year project. Bo Chen is a researcher with the ICC’s Cyber-Physical Systems research group.
Senior Research Scientist Joel LeBlanc of Michigan Tech Research Institute (MTRI) will present his lecture, “Testing the Validity of Physical (Software) Models in Inverse Problems,” on Friday, December 4, 2020, at 3:00 p.m. via online meeting.
LeBlanc has a Ph.D. in Statistical Signal Processing. His areas of expertise include statistical signal processing, applied nonconvex optimization, EO/IR imaging, and Synthetic Aperture Radar (SAR) imaging. His research interests are in information theoretic approaches to inverse-imaging, computational techniques for solving large inverse problems, and fundamental limits of sensing.
Numerical simulations are the modern analog of the “physical system” referenced by Rosenblueth and Wiener in their 1945 paper “The Role of Models in Science.” This talk will introduce the inverse-problem approach for making inferences about the physical world and discuss how the Maximum Likelihood (ML) principle leads to both performant estimators and algorithm agnostic bounds on performance. The resulting estimators and associated bounds are only valid when global convergence is achieved, so I will present new results on global convergence testing that I believe are widely applicable. Finally, I will discuss some of my ongoing research interests: optimal resource allocation and testing for adversarial behavior through model relaxation.
Michigan Tech Research Institute focuses on technology development and research to sense and understand natural and human-made environments. Through innovation, education, and collaboration, the Institute supports meaningful solutions to critical global issues, from infrastructure to invasive species, national security to public health.
Briana Bettin’s research interests are many. They include user experience, human factors, human-computer interactions, mental models, information representation, rural digital literacy, education, engagement, retention, and digital anthropology. Her Ph.D. dissertation aims to better understand how novice programmers approach learning programming, and how their construction of programming ideas might be better facilitated.
“I delve into mental models research and explore theories for how students might construct knowledge,” she explains. “Specifically, the major studies in my dissertation explore how prior applicable knowledge might allow for transfer to programming concepts, which can feel very novel to students who have never programmed before.”
Bettin is also exploring methods for designing programming analogies, testing their application in the classroom, and observing how their use may impact student understanding of specific topics. “I take a very user experience-oriented approach, and work to apply methods and ideas from user-experience research in the CS classroom space,” she says.
Creative energy, insight, and humanity.
With Computer Science department faculty members Associate Professor Charles Wallace and Assistant Professor Leo Ureel, Bettin has worked on projects studying how novice programmers communicate. She and Ureel also worked on several ideas in the introductory CS classrooms, including exploring pair programming obstacles in the classroom and in research.
“I got to know Dr. Wallace during my Ph.D., and I love getting his perspective on research ideas,” Bettin says. “He has so many interesting ideas, and he’s so fun to talk to!”
“Briana brings loads of creative energy, insight, and humanity to everything she does,” says Wallace. “We are very fortunate to have her with us.”
Passionate about Computing Education.
Other research collaborators include Lecturer Nathan Manser, Geological and Mining Engineering and Sciences, and Senior Lecturer Michelle Jarvie-Eggart, Engineering Fundamentals, College of Engineering, with whom Bettin has explored topics in technology acceptance across engineering and computer science.
“Briana has been an enthusiastic addition to our research group,” Jarvie-Eggart says, who is working with Steelman and Wallace on improving engineering students’ acceptance of programming. “She really is amazing!”
Jarvie-Eggart sat in on Bettin’s Intro to Programming class in fall 2019, and noted that Bettin’s. approach of teaching algorithmic thinking and logic—before students begin programming—helps make programming more accessible to all.
“It builds foundational knowledge from the ground up,” she says. “Our research team is very excited about using her progressive CS education approaches to teach engineers programming.”
“Stefka Hristova, in Michigan Tech Humanities, has always been supportive, helping me cultivate an interdisciplinary research vision and voice,” Bettin says. “Dr. Robert Pastel has also been so valuable in helping me approach my research with strong design. He has given me a lot of insight and I am so appreciative!”
“Briana is passionate about Computing Education, and she is invested in infusing equity and diversity into the STEM field,” Hristova says.
In Part III of this article, to be published soon, Briana Bettin talks about peer mentors and friends … and they say a few words, too.
Read the first installment of this article, ‘Briana Bettin, Asst. Prof., Part I: Neopets, HTML, Early Success Part I”, here.
A Chemistry Seminar will be presented Friday, September 13, 2020, at 3:00 p.m., via online meeting.
Dr. Sangyoon Han will present his lecture, “Toward Discovery of the Initial Stiffness-Sensing Mechanism by Adherent Cells.” Han is an Assistant Professor in Biomedical Engineering, an Affiliate Assistant Professor in Mechanical Engineering-Engineering Mechanics, and advisor for the Korean Student Association. Han is a member of the ICC’s Center for Data Science.
The stiffness of the extracellular matrix (ECM) determines nearly every aspect of cellular/tissue development and contributes to metastasis of cancer. Adherent cells’ stiffness-sensing of the ECM triggers intracellular signaling that can affect proliferation, differentiation, and migration of the cells. However, biomechanical and molecular mechanisms behind this stiffness sensing have been largely unclear. One critical early event during the stiff-sensing is believed to be a force transmission through integrin-based adhesions, changing the molecular conformation of the molecules comprising the adhesions that link the ECM to the cytoskeleton. To understand this force transmission, my lab develops experimental and computational techniques, which include soft-gel-based substrates, live-cell imaging, computer-vision-based analysis, and inverse mechanics, etc. In this talk, I will talk about how we use soft-gel to quantify the spatial distribution of mechanical force transmitted by a cell, how we use light microscopy and computer vision to analyze the focal adhesions, and how these techniques are related to stiffness sensing. In particular, I will show you new data where cells can transmit different levels of traction forces in response to varying stiffness, even when the activity of the major motor protein, myosin, is inhibited. At the end of the talk, potential molecules responsible for the differential transmission will be discussed.
Sangyoon Han received his Ph.D. in Mechanical Engineering at the University of Washington (UW) in 2012 and did postdoctoral training with Dr. Gaudenz Danuser in the Department of Cell Biology at Harvard Medical School and the University of Texas Southwestern Medical Center for five years until 2017. Before the Ph.D., he received B.S and M.S. degree from Mechanical Engineering at Seoul National University, Seoul, Korea in 2002 and 2004.
He joined Michigan Tech, Biomedical Engineering from fall 2017, and started Mechanobiology Laboratory. His lab’s interests are in understanding the dynamic nature of force modulation occurring across cell adhesions and cytoskeleton that regulate cells’ environmental sensing. His lab develops a minimally-perturbing experimental approach and computational techniques, including soft-gel fabrication, nano-mechanical tools, live-cell microscopy, and image data modeling, to capture the coupling between force modulation and cellular molecular dynamics.
A research paper by Assistant Professor Sidike Paheding, Applied Computing, is to be published in the November 2020 issue of the journal, Expert Systems and Applications.
An in-press version of the paper, “Binary Chemical Reaction Optimization based Feature Selection Techniques for Machine Learning Classification Problems,” is available online.
A chemical reaction optimization (CRO) based feature selection (FS) technique is proposed.
The proposed CRO based FS technique is improvised using particle swarm optimization.
Performance evaluation of proposed techniques on benchmark datasets gives promising results.
Feature selection is an important pre-processing technique for dimensionality reduction of high-dimensional data in machine learning (ML) field. In this paper, we propose a binary chemical reaction optimization (BCRO) and a hybrid binary chemical reaction optimization-binary particle swarm optimization (HBCRO-BPSO) based feature selection techniques to optimize the number of selected features and improve the classification accuracy.
Three objective functions have been used for the proposed feature selection techniques to compare their performances with a BPSO and advanced binary ant colony optimization (ABACO) along with an implemented GA based feature selection approach called as binary genetic algorithm (BGA). Five ML algorithms including K-nearest neighbor (KNN), logistic regression, Naïve Bayes, decision tree, and random forest are considered for classification tasks.
Experimental results tested on eleven benchmark datasets from UCI ML repository show that the proposed HBCRO-BPSO algorithm improves the average percentage of reduction in features (APRF) and average percentage of improvement in accuracy (APIA) by 5.01% and 3.83%, respectively over the existing BPSO based feature selection method; 4.58% and 3.12% over BGA; and 4.15% and 2.27% over ABACO when used with a KNN classifier.
Expert Systems With Applications, published by Science Direct/Elsevier, is a refereed international journal whose focus is on exchanging information relating to expert and intelligent systems applied in industry, government, and universities worldwide. The journal’s Impact factor is 5.4.