Also In This Section
  • Categories

  • Recent Posts

  • Archives

  • Category: Research

    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.”

    Join the virtual lecture here.

    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.


    AI, Mobile Security Grad-level Research Assistant Needed

    Dr. Xiaoyong (Brian) Yuan and Dr. Bo Chen are seeking an hourly paid graduate research assistant to work in the areas of artificial intelligence and mobile security. The project is expected to begin Summer 2021 (5/10/2021).

    Preferred Qualifications:
    1.     Passion for research in artificial intelligence and mobile security.
    1.     Familiar with Android OS and Android app development.
    2.     Basic knowledge of machine learning and deep learning.
    3.     Solid programming skills in Java, Python, or related programming languages. 
    4.     Experience with popular deep learning frameworks, such as Pytorch and Tensorflow is a plus.

    To Apply: Please send a resume and a transcript to Dr. Yuan (xyyuan@mtu.edu).


    ECE Master’s Defense: Chinmay Rajaram Kondekar

    by Electrical and Computer Engineering

    Electrical Engineering Master’s candidate Chinmay Kondekar (advisor: Aleksandr Sergeyev), will present his master’s defense at 11 a.m. Tuesday (April 13) via Zoom

    The title of his presentation is “Integration of Robotic and Electro-Pneumatic Systems Using Advanced Control and Communication Schemes.” 


    Graduate Research Colloquium 2021

    by Graduate Student Government

    This year’s Graduate Research Colloquium organized by the Graduate Student Government was hosted virtually due to COVID restrictions. There were in total 48 presentations — 17 poster presenters and 31 oral presenters.

    Poster presentations took place in a pre-recorded video style and the oral sessions were hosted live via Zoom. You can watch all the poster videos and recordings for the oral sessions here. Each presentation was scored by two judges from the same field of research.

    Participants were able to gain valuable feedback from these judges before presenting their research at an actual conference. It was stiff competition amongst all presenters. Following are the winners for each of these sessions.

    Of the many presentations were the following by two graduate students affiliated with the College of Computing.

    Simulating the Spread of Infectious Diseases
    Meara Pellar-Kosbar, Data Science

    This simulation is designed to show how a fictional viral illness could spread among people in a virtual room. Over the course of the virtual simulation, a number of automatic simulated people called subjects will move about an adjustable virtual grid. During this time, subjects will come into contact with each other and with item cells in the virtual room. Subjects will be exposed to this fictional virus via contact with other subjects, items, and via the air when within a certain distance of a contagious subject. The viral counts of each subject will be tracked and shown as the simulation runs, showing how the actions of the subjects’ affects their viral counts.

    Cultural Competence Effects of Repeated Implicit Bias Training
    Karen Colbert, Social Sciences

    Karen Colbert is a PhD student in the Computational Sciences and Engineering department.

    Abstract: Diversity training literature suggests that mandatory and recurrent sessions should maximize training efficacy, but research has primarily focused on single, brief training sessions that are often voluntary. Michigan Tech is one of few universities to implement required and repeated diversity training for all faculty who serve on search, tenure, and promotion committees. The goal of this study is to evaluate the training’s effectiveness, as well as to fill the gap in research on mandatory recurring diversity training. To do this, we anonymously surveyed faculty members on their knowledge, attitudes, and skills related to content from the Diversity Literacy program and scored responses to create a single composite score for each participant. We hypothesized that composite Cultural Competency Score (CCS) would be higher for faculty who 1) have taken more refresher trainings, and 2) completed training more recently. This study included 130 total respondents (large sample), 69 of whom provided their Diversity Literacy completion information anonymously through Human Resources (small sample). Composite CCS did not differ significantly by frequency of training, H(2)=3.78, p=.151. CCS did differ significantly by years since last training, F(2,63)=4.436, p=.016. Results from both large and small groups showed no statistical significant relationship between CCS and faculty committee service. CCS was negatively correlated with years employed at Tech in both the large (r=-0.363, p=0.002) and small (r = -0.258, p=0.01) samples. This relationship between low CCS and longer employment at Tech may additionally be related to the Diversity Literacy program’s implementation in 2010. Qualitative responses were also collected regarding training material that faculty found most memorable (N=102) and most confident to put into practice (N=93).

    View all the Research Colloquium abstracts here.