Skip to main content

data-analysis

Mentors and Regional Facilitators
Name Region Skills Interests
Andrew Fullard Campus Champions
Alana Romanella Campus Champions
Balamurugan Desinghu ACCESS CSSN, Campus Champions, CAREERS, Northeast
diana Trotman CAREERS
Daniel Sierra-Sosa Campus Champions
Fernando Garzon ACCESS CSSN
Georgia Stuart TRECIS
Craig Gross Campus Champions
Iman Rahbari Campus Champions, ACCESS CSSN
Jason Yalim Campus Champions
Katia Bulekova ACCESS CSSN, Campus Champions, CAREERS, Northeast
Laura Christopherson Campus Champions
shuai liu ACCESS CSSN
Michael Puerrer Campus Champions, Northeast
Maryam Taeb
Mahmoud Parvizi Campus Champions
Paul Rulis Campus Champions
Rebecca Belshe Campus Champions, CCMNet
Russell Hofmann ACCESS CSSN
Xiaoqin Huang ACCESS CSSN
Suhong Li CAREERS, ACCESS CSSN
Swabir Silayi Campus Champions
Yun Shen CAREERS, Northeast, ACCESS CSSN
Users
There are no Users associated with this topic. View All People.
Projects
There are no projects associated with this topic. Please check back often as more projects are added regularly, or view All Projects.
Blog Entries
There are no Blog Entries associated with this topic.

Affinity Groups

There are no Affinity Groups associated with this topic. View All Affinity Groups.

Upcoming Events & Trainings

Title Date
Throughput Computing 2024 7/08/24

Topics from Ask.CI

Loading topics from Ask.CI ...

Engagements

Investigation of robustness of state of the art methods for anxiety detection in real-world conditions
University of Illinois at Urbana-Champaign

I am new to ACCESS. I have a little bit of past experience running code on NCSA's Blue Waters. As a self-taught programmer, it would be interesting to learn from an experienced mentor. 

Here's an overview of my project:

Anxiety detection is topic that is actively studied but struggles to generalize and perform outside of controlled lab environments. I propose to critically analyze state of the art detection methods to quantitatively quantify failure modes of existing applied machine learning models and introduce methods to robustify real-world challenges. The aim is to start the study by performing sensitivity analysis of existing best-performing models, then testing existing hypothesis of real-world failure of these models. We predict that this will lead us to understand more deeply why models fail and use explainability to design better in-lab experimental protocols and machine learning models that can perform better in real-world scenarios. Findings will dictate future directions that may include improving personalized health detection, careful design of experimental protocols that empower transfer learning to expand on existing reach of anxiety detection models, use explainability techniques to inform better sensing methods and hardware, and other interesting future directions.

Status: Complete

People with Expertise

Balamurugan Desinghu

Rutgers, the State University of New Jersey

Programs

ACCESS CSSN, Campus Champions, CAREERS, Northeast

Roles

mentor, researcher/educator, research computing facilitator, cssn, Consultant

Bala Desinghu Photo

Expertise

+84 more tags

Kyle Randall

Programs

ACCESS CSSN

Roles

student-facilitator

NASA Langley Picture

Expertise

Frédéric Chevalier

Texas Biomedical Research Institute

Programs

Campus Champions

Roles

researcher/educator, domain champion

Expertise

People with Interest

Adedeji Adekunle

Rutgers University, Camden

Programs

CAREERS

Roles

student-facilitator

Interests

Steve Spicklemire

University of Indianapolis

Programs

Campus Champions

Roles

research computing facilitator

Placeholder headshot

Interests

Katia Bulekova

Boston University

Programs

ACCESS CSSN, Campus Champions, CAREERS, Northeast

Roles

mentor, research computing facilitator

image of Katia Bulekova

Interests