Also In This Section
  • Categories

  • Recent Posts

  • Archives

  • Category: Grad Students

    Smart Start Seminar Today, Weds., Jan. 20

    New graduate students at Michigan Tech are invited to our virtual Smart Start. In Smart Start, we’ll introduce students to resources and policies to assist them to have a successful start to their graduate careers. It will be especially useful for students in their first year, but all students are welcome to attend.

    The seminar will be recorded for any students who cannot attend the zoom meeting. The seminar will be held at 2 p.m. today (Jan. 20) via Zoom. Please register online to receive streaming information and reminders to attend. It will be taped and available online for those unable to attend at that time.


    Summer 2021 Finishing Fellowship Nominations Open

    by Debra Charlesworth, Graduate School

    Applications for Summer 2021 finishing fellowships are being accepted and are due no later than 4 p.m., March 3, 2021 to the Graduate School. Please email applications to gradschool@mtu.edu.

    Instructions on the application and evaluation process are found online. Students are eligible if all of the following criteria are met:

    1. Must be a PhD student
    2. Must expect to finish during the semester supported as a finishing fellow
    3. Must have submitted no more than one previous application for a finishing fellowship
    4. Must be eligible for candidacy (tuition charged at Research Mode rate) at the time of application
    5. Must not hold a final oral examination (“defense”) prior to the start of the award semester

    Finishing Fellowships provide support to PhD candidates who are close to completing their degrees. These fellowships are available through the generosity of alumni and friends of the University. They are intended to recognize outstanding PhD candidates who are in need of financial support to finish their degrees and are also contributing to the attainment of goals outlined in

    The Michigan Tech Plan. The Graduate School anticipates funding up to 10 fellowships with support ranging from $2,000 to full support (stipend + tuition). Students who receive full support through a Finishing Fellowship may not accept any other employment. For example, students cannot be fully supported by a Finishing Fellowship and accept support as a GTA or GRA.


    VPR Research Series: Funding Graduate Students

    Meet the VPR Sponsored Operations Team and VPR Staff

    by Office of the Vice President of Research

    Join VPR team members and other members of the Michigan Tech research community from noon to 1 p.m. tomorrow (Jan. 12) for presentations and discussion to help you and your team as you pursue funding for your research and other externally supported programs.

    This month’s discussion will be led by Will Cantrell, associate provost and dean of the Graduate School. Cantrell will describe how researchers can work with graduate students to provide the best learning experience while achieving research goals, followed by a question and answer session.

    Session attendees will also have a chance to meet the Sponsored Programs Operations Team and VPR Staff. Attendees will have the chance to ask presentation and general VPR-related questions at the end. Join this virtual session via Zoom.


    Master’s Defense: Taylor Morris, CS, Tues., Jan. 5

    Computer Science graduate student Taylor Morris will present a Master’s Defense on Tuesday, January 5, from 6:00 to 7:00 p.m.

    Presentation Title: “Using Text Mining and Machine Learning Classifiers to Analyze Stack Overflow.”

    Advisor: Associate Professor Laura Brown, Computer Science

    Link to the Michigan Tech Events Calendar entry here.

    Join the Zoom meeting here. (michigantech.zoom.us/j/83033288850)


    Celebrate Husky Innovation January 25-29

    Husky Innovate is organizing Innovation Week, a series of innovation themed events the week of January 25 to 29, 2020. Our goal is to provide opportunities for students, faculty and alumni to meet virtually to engage around the topic of innovation.

    We will host panel discussions, alumni office hours and the Bob Mark Business Model Pitch Competition from 5:30 to 7:30 p.m. on Thursday, January 28.

    We will celebrate entrepreneurship, innovative research and projects on campus and within our extended MTU community.

    If you are interested in hosting an innovation tour, participating in a panel discussion, leading a workshop or something else, sign-up here.

    Faculty and staff are invited to celebrate innovation week with an innovation themed learning module or student activity.


    Siva Kakula to Present PhD Defense Dec. 21, 3 pm

    Graduate student Siva Krishna Kakula, Computer Science, will present his PhD defense, “Explainable Feature- and Decision-Level Fusion,” on Monday, December 21, 2020, from 3:00 to 5:00 p.m. Kakula is advised by Dr. Timothy Havens, College of Computing.

    Link to the virtual lecture here.

    Siva Kakula earned his master of science in computer engineering at Michigan Tech in 2014, and completed a bachelor of technology in civil engineering at IIT Guwahati in 2011. His research interests include machine learning, pattern recognition, and information fusion.

    Download the informational flier below.

    Lecture Abstract

    Information fusion is the process of aggregating knowledge from multiple data sources to produce more consistent, accurate, and useful information than any one individual source can provide. In general, there are three primary sources of data/information: humans, algorithms, and sensors. Typically, objective data—e.g., measurements—arise from sensors. Using these data sources, applications such as computer vision and remote sensing have long been applying fusion at different “levels” (signal, feature, decision, etc.). Furthermore, the daily advancement in engineering technologies like smart cars, which operate in complex and dynamic environments using multiple sensors, are raising both the demand for and complexity of fusion. There is a great need to discover new theories to combine and analyze heterogeneous data arising from one or more sources.

    The work collected in this dissertation addresses the problem of feature- and decision-level fusion. Specifically, this work focuses on Fuzzy Choquet Integral (ChI)-based data fusion methods. Most mathematical approaches for data fusion have focused on combining inputs relative to the assumption of independence between them. However, often there are rich interactions (e.g., correlations) between inputs that should be exploited. The ChI is a powerful aggregation tool that is capable modeling these interactions. Consider the fusion of N sources, where there are 2N unique subsets (interactions); the ChI is capable of learning the worth of each of these possible source subsets. However, the complexity of fuzzy integral-based methods grows quickly, as the fusion of N sources requires training 2N-2 parameters; hence, we require a large amount of training data to avoid the problem of over-fitting. This work addresses the over-fitting problem of ChI-based data fusion with novel regularization strategies. These regularization strategies alleviate the issue of over-fitting while training with limited data and also enable the user to consciously push the learned methods to take a predefined, or perhaps known, structure. Also, the existing methods for training the ChI for decision- and feature-level data fusion involve quadratic programming (QP)-based learning approaches that are exorbitant with their space complexity. This has limited the practical application of ChI-based data fusion methods to six or fewer input sources. This work introduces an online training algorithm for learning ChI. The online method is an iterative gradient descent approach that processes one observation at a time, enabling the applicability of ChI-based data fusion on higher dimensional data sets.

    In many real-world data fusion applications, it is imperative to have an explanation or interpretation. This may include providing information on what was learned, what is the worth of individual sources, why a decision was reached, what evidence process(es) were used, and what confidence does the system have on its decision. However, most existing machine learning solutions for data fusion are “black boxes,” e.g., deep learning. In this work, we designed methods and metrics that help with answering these questions of interpretation, and we also developed visualization methods that help users better understand the machine learning solution and its behavior for different instances of data.