Please ensure Javascript is enabled for purposes of website accessibility Colloquium | University of West Florida
Skip to main content

Colloquium Schedule

We invite all to participate in our colloquium series, which draws exceptional speakers from around the country. The series also provides our own faculty and students the opportunity to present their own research. All talks are also available via Blackboard Collaborate.


DateSpeaker

 

TBD

 

TBD

 

Past Colloquium Speaker Details and Descriptions
Past Talks

November 19, 2021

Dr. Edgar Ruiz
R Studio

Getting Started with R and Spark: Overview of what Spark is, and how we can use the sparklyr R package as a way to interface to and learn Spark.

October 15, 2021

Dr. Jossy Uvah
University of West Florida

Research and a Quality Technical Report in STEM

September 10, 2021

Dr. Alexander Viguerie
Gran Sasso Science Institute
L'Aquila, Italy

PDE Models of Infectious Disease: validation against data, time-delay formulations, data-driven methods, and future directions

March 12, 2021

Dr. Arthur Baragar
University of Nevada, Las Vegas

Apollonian-like circle packings and smooth rational curves on certain K3 surfaces

February 26, 2021

Dr. Mine Cetinkaya Rundel
Associate Professor of the Practice position at the Department of Statistical  Science at Duke University
Senior Lecturer in the School of Mathematics at University of  Edinburgh,  
Data Scientist and Professional Educator at RStudio

Introductory data science, a fresh look

Abstract: Modern statistics is fundamentally a computational discipline, but too often this fact is not reflected in our statistics curricula. With the rise of data science, it has become increasingly clear that students want, expect, and need explicit training in this area of the discipline. Additionally, recent curricular guidelines clearly state that working with data requires extensive computing skills and that statistics students should be fluent in accessing, manipulating, analyzing, and modeling with professional statistical analysis software. In this talk, we will describe a fresh approach to teaching data science at the introductory level, introduce the design philosophy behind the curriculum, and give examples from course materials as well as from student projects. We will also discuss new directions in assessment and tooling as we scale up the course and move it online.

January 29, 2021

Dr. Raid Amin
University of West Florida

Surveillance of COVID-19 in the contiguous US: UWF graduate students actively doing applied research

January 22, 2021

Dr. Leo Rebholz
Clemson University

Simple and efficient implementation of continuous data assimilation in evolutionary PDEs

Dr. Nicholas Horton

Professor of Technology and Society
Amherst College
Statistics & Data Science

Data acumen and data numeracy: helping students extract meaning from data.

Abstract: Our world is awash in data. How can we prepare students to make sense of it? In this talk, I will argue for a broadening of our statistics courses to incorporate "data acumen" and suggest ways that these capacities can be developed and nurtured. I will outline approaches and techniques that can help students develop a foundation to create and critique sophisticated arguments using data.

Watch the recording of Dr. Nicholas Horton

Dr. Subhash C. Bagui

Distinguished University Professor
University of West Florida
Mathematics and Statistics

Convergence of Known Distributions to Normality or Non-normality and a Few Counter Examples in CLT.

Abstract: This talk presents an elementary technique for deriving the convergence of known discrete/continuous type distributions to limiting normal or non-normal distributions. This technique utilizes the ratio of the pmf/pdf at hand at two consecutive/nearby points. This ratio method is illustrated via a few well-known discrete and continuous distributions, along with discussing counter-examples in CLT. 

Watch the recording of Dr. Subhash C. Bagui

Cecilia Cao, Ph.D

Visiting Assistant Professor 
University of West Florida
Mechanical Engineering

Light and Tough Materials by Design: Mussel Inspired and Machine Learning Realization.

Abstract: Inspiration by the byssal threads found in certain mussels, has led to the design and manufacture of multi-hierarchical structural materials that are both light and tough.

This talk with Dr. Cecilia Cao delved into the research on light and tough materials by design and how the use of updated machine learning techniques and big data systems have been able to give predictions on material properties in high entropy alloys and other structural materials.  

Watch the recording of Dr. Cecilia Cao's talk

Dr. CS Chen

University Professor
University of Southern Mississippi Department of Mathematics

Meshfree Method, PDEs, and 3d Modeling

Abstract: In today’s world, computer graphics are consistently being utilized around us, which has led to the visualization of data and integration of 3D imagery.

Within the last two decades, meshfree methods have become a focal point within the sciences and engineering for solving the interpolation problem and the PDEs problems because of their accuracy.

In this talk, the discussion will be on implicit surfaces (3D images) reconstruction utilizing meshfree methods while reducing human labor in data preparation and computational time.

Watch the recording of Dr.CS Chen's talk

Raid Amin, Ph.D.

Distinguished University Professor
UWF Department of Mathematics & Statistics

Geographic Clusters of Cancer Mortality in the USA: 2000-2014

Abstract: This is a presentation of results that graduate students in STA6912 obtained under my supervision during fall 2017. Cancer mortality data on 29 types of cancers were downloaded from the University of Washington (Institute for Health Metrics and Evaluation). First, we created heat maps showing the cancer mortality rates for each cancer type for the contiguous USA and for the years 1980-2014. The advanced software, ArcGIS was used to create the spatial cluster maps. Then, we reduced the number of cancer types for the cluster analysis to 16 to match what has been studied in the literature on cancer mortality. For each of these 16 cancer types, we did a purely spatial cluster analysis with the modern disease surveillance software SaTScan. Cluster maps were then created with the software ArcGIS. When needed, a second-round analysis of each large-sized cancer cluster was done to identify “hotspots” with SaTScan. To be better able to identify associations between the mortality rates of the 16 cancer types, a principal component analysis was performed on the data, which resulted in having only 5 important principal components, reducing the dimensionality from 16 to 5. The principal components values were then used to be used in purely spatial cluster analysis on each of the first 5 principal components. The mortality incidences were adjusted for 8 covariates with regression analysis, and the resulting residuals were used in the cluster analysis. We also adjusted mortality for each covariate at a time, allowing us to see on the cluster maps the role of each covariate.

Watch the recording of Dr. Amin's talk


Dr. Fang Hu

Associate Professor
Hubei University of Chinese Medicine, China
College of Information Engineering

Optimization Algorithms in Complex Networks and Applications

Abstract: This lecture introduces the concept of a complex network and its characteristics including community structure and node centrality. The experimental process of optimization algorithms in community detection and central node identifying will be demonstrated separately in real-world and computer-generated networks. Furthermore, examples of network modeling and data analysis in traditional Chinese medicine and marine data will be explained.

Bio: Dr. Hu's research interests include complex network modeling, optimization algorithms in community detection, optimization algorithms in node centrality, neural network modeling, optimization algorithms in predictive analytics, network modeling, and data analysis in traditional Chinese medicine data and marine data.

Watch the recording of Dr. Hu's talk


Zhaoxia Wang
Graduate Student
Louisiana State University, Department of Mathematics

Robin Spectrum of Quantum Trees and Orthogonal Polynomials

Abstract: We investigate the spectrum of regular quantum-graph trees, where the edges are endowed with a Schroedinger operator with self-adjoint Robin vertex conditions. It is known that, for large eigenvalues, the Robin spectrum approaches the Neumann spectrum. In this presentation, we compute the lower Robin spectrum. The spectrum can be obtained from the roots of a sequence of orthogonal polynomials involving two variables. As the length of the quantum tree increases, the spectrum approaches a band-gap structure. We find that the lowest band tends to minus infinity as the Robin parameter increases, whereas the rest of the bands remain positive. Unexpectedly, we find that two isolated negative eigenvalues separate from the bottom of the lowest band. Our analysis invokes the interlacing property of orthogonal polynomials. This is joint work with my advisor Professor Stephen Shipman.

Watch the recording of Zhaoxia Wang's talk 


Subhash Bagui, Ph.D.
Distinguished University Professor
UWF Department of Mathematics & Statistics

Statistics: The Hottest Career of the 21st Century

Abstract: Statistics jobs are growing at an astounding rate. By studying Statistics, the science of learning from data, you will be prepared for one of the hottest careers of the 21st century. This talk will discuss the uses of Statistics in various fields and job opportunities for students with statistics training in various sectors (Private or Government). Freshmen, sophomores, juniors as well as seniors are encouraged to attend this talk.

Watch the recording of Dr. Bagui's talk


Samantha Seals, Ph.D.
Visiting Assistant Professor
UWF Department of Mathematics & Statistics

Methods for the Calibration of Longitudinal Data: An Example from the Jackson Heart Study

Abstract: In longitudinal research studies, the devices used to measure participants’ attributes may change throughout follow-up. When a device change occurs, the two devices should be compared to ensure that measurements are comparable; sometimes, calibration of data is necessary. In this talk, we will review methods of calibration and then discuss approaches considered for the calibration of systolic and diastolic blood pressures from the Jackson Heart Study.

Watch the recording of Dr. Seals' talk


Achraf Cohen, Ph.D.
Postdoctoral Teaching/Research Associate
UWF Department of Mathematics & Statistics

Data-Driven Methods for Process Monitoring

Abstract: Data-driven methods have been receiving remarkable attention, especially in the big data era and the fast pace of research in statistical learning theory. Statistical process monitoring methods are essential to understand the variation in a process and to assess its current state. This talk reviews some of the main approaches in the field with a focus on multi-scale methods based on wavelet analysis.

Watch the recording of Dr. Cohen's talk 


Dr. Dawn Kernagis
Research Scientist
Florida Institute for Human and Machine Cognition (IHMC)

NEEMO 21 Mission: Going Undersea to get to Outer Space

Abstract: NEEMO is a NASA mission that sends groups of astronauts, engineers, and scientists to live in Aquarius, the world’s only undersea research station. The Aquarius habitat and its surroundings provide a convincing analog for space exploration and for testing emerging technology and protocol for long-duration space operations. This summer, Dr. Dawn Kernagis had the opportunity to join NEEMO as both a crew member and a researcher, living underwater for 8 days with 5 other crew members. Dawn will provide an overview of the NEEMO 21 mission, including the crew’s training, the experience of living and working underwater, and over a dozen mission objectives ranging from telemedicine to robotics to genetics.

Watch the recording of Dr. Kernagis' talk


Dr. David Banks
Professor
Duke University
Department of Statistical Science

Modern Data Science: A Survey

Abstract: Data Science is a partnership among three disciplines: statistics, computer science (with ECE), and mathematics. This talk reviews the different perspectives and contributions from these fields, and goes into some detail on sparsity (from statistics), boosting (from computer science), and support vector machines (from mathematics).

Watch the recording of Dr. Banks' talk 


Dr. Koray Karabina
Assistant Professor
Florida Atlantic University
Department of Mathematical Sciences

Biometric Authentication Systems: Constructions and their Security

Abstract: In a biometric authentication system, the scanner collects users' biometric images (fingerprint, face, iris, etc.) in the enrollment phase. Distinctive characteristics of the biometric image are then derived during feature extraction; and a digital representation of the feature, called template, is stored in a database. Templates are used during authentication as the basis for comparison. Therefore, biometric templates must be protected from third parties to minimize security and privacy risks. I will survey some challenging problems in the area and demonstrate that assuring the security and privacy of users is highly non-trivial. I will also introduce new cryptographic primitives for biometric authentication and discuss their security.

Watch the recording of Dr. Karabina's talk 


Dr. Jossy Uvah
Professor
University of West Florida
Department of Mathematics & Statistics

Proseminar: Referencing and Good Abstracts

We will discuss the issue of plagiarism, perhaps the most serious crime in academia. We proffer purposeful ways of referencing to avoid this crime. In addition, we discuss elements of a good abstract for a research report. All students currently enrolled in Proseminar are required to attend.

Watch the recording of Dr. Uvah's talk 


Nutan Mishra, Ph.D.

Associate Professor of Statistics
University of South Alabama
Dept of Mathematics & Statistics

Joint Entropy of a Progressively Type-II Censored Sample

Abstract: Consider a life testing experiment with progressive type-II censoring scheme. Shannon entropy, Awad sup entropy, and Renyi entropy for the data collected are computed when the underlying distribution of the lifetime is a Rayleigh distribution with a single parameter. Then we examine the suitability of these three entropies as objective functions to choose an optimal progressive censoring scheme. Also under the same conditions, the suitability of Fisher information and Kullback-Leibler divergence as objective functions are considered.

Watch the recording of Dr. Mishra's talk 


Dr. Jossy Uvah
Professor
University of West Florida
Department of Mathematics & Statistics

A Quality Proseminar

We will discuss all expectations associated with the Proseminar course at the undergraduate and graduate levels. We will also highlight some events that will help you prepare for a successful project. 

Watch the Recording of Dr. Uvah's talk