AI at Johns Hopkins combines the intuition and understanding of human intelligence with the raw power of empirical AI to transform discovery.


Submit Research/Proposal

coming soon



Related Institutes

Emily Mower-Provost (University of Michigan) “Automatically Measuring Emotion from Speech: New Methods to Move from the Lab to the Real World”

Maryland Hall 110 @ 3400 N. Charles Street, Baltimore, MD 21218
12:00 pm / 1:15 pm
December 6
Emotion has intrigued researchers for generations. This fascination has permeated the engineering community, motivating the development of affective computing methods. However, human emotion remainsnotoriously difficult to accurately detect. As a result, emotion classification techniques are not always effective when deployed.  This is a problem because we are missing out on the potential that emotion recognition provides: the opportunity to automatically measure an aspect of behavior that provides critical insight into our health and wellbeing, insight that is not always easily accessible.  In this talk, I will discuss our efforts in developing emotion recognition approaches that are effective in natural environments and demonstrate how these approaches can be used to support mental health.


Emily Mower Provost is an Associate Professor in Computer Science and Engineering and Toyota Faculty Scholar at theUniversity of Michigan. She received her Ph.D. in Electrical Engineering from the University of Southern California (USC), Los Angeles, CA in 2010. She has been awarded a National Science Foundation CAREER Award (2017), the Oscar Stern Award for Depression Research (2015), a National Science Foundation Graduate Research Fellowship (2004-2007). She is a co-author on the paper, ?Say Cheese vs. Smile: Reducing Speech-Related Variability for Facial Emotion Recognition,? winner of Best Student Paper at ACM Multimedia, 2014, and a co-author of the winner of the Classifier Sub-Challenge event at the Interspeech 2009 emotion challenge. Her research interests are in human-centered speech and video processing, multimodal interfaces design, and speech-based assistive technology. The goals of her research are motivated by the complexities of the perception and expression of human behavior.
Read More
Related Institutes
3:00 pm / 5:00 pm
December 7
Join us for a seminar with Mark J. Schmitt of Los Alamos National Laboratory, titled ?The Quest for Inertial Confinement Fusion using Large Directly Driven Targets with 1, 2 or 3 Concentric Shells?.
The seminar will begin at 3pm ET on December 7, 2021.
Please contact Rachel Wise for connection information.
Recent progress has been made assessing the use of large directly-driven spherical targets consisting of 1, 2 or 3 shells to achieve ignition on the NIF using both single shell and double shell polar direct drive (PDD) implosions. The fundamental goals of these experiments is to validate the outer ablator shell hydro-efficiency, kinetic energy transfer efficiency between concentric shells, and adequate drive symmetry to compress the inner DT fuel. It is shown that large capsules driven at low intensity with the existing NIF laser can provide an extremely high coupling efficiency to the target with virtually no degradation from laser-plasma instabilities. For example, the Revolver triple-shell ignition target requires high (>90%) coupling of direct-drive laser energy to its large 5-6 mm outer shell to demonstrate high hydro-efficiency (~10%) of PDD laser energy into inward kinetic energy for small laser-beam-to-capsule radius ratios (~1/3). Moreover, high implosion kinetic energy transfer efficiency between the outer two colliding shells (>50%) is needed. Recent experiments employing 5 mm outer shells were measured using both x-ray self-emission imaging and x-ray backlit radiography. The post-collision inner shell trajectory was measured with backlighting showing good agreement with simulation. Diagnostic measurements indicate scattered light levels less than 2%. More recently, simulations of large single shell target using a similar polar direct drive configuration to ablate mainly the liquid DT fuel to drive the implosion have shown nuclear yields approaching 100 MJ for laser drive energies of 1.5 MJ. Details of these concepts will be discussed.
Research supported under LANL's LDRD Program projects 20180051DR, 20200765ER and the US Department of Energy under contract 89233218CNA000001.
Dr. Schmitt received his PhD from UCLA and is currently a staff member in the Plasma Theory and Applications Group of the Computational Physics Division at Los Alamos National Laboratory. Mark has a broad background in the simulation of laser related applications including inertial confinement fusion (ICF), free-electron lasers (FELs), laser-plasma instabilities, short-pulse laser ion generation, laser-induced plasma discharge channels, laser-driven flyer plates, laser propagation and laser remote sensing. He most recently was the Principle Investigator for the Revolver direct-drive triple-shell project and the current polar direct drive double shell experiments on National Ignition Facility (NIF). Over his career at Los Alamos he has held many technical leadership roles for multi-disciplinary teams including projects to design high-power FELs, laser remote sensing systems, and ICF implosion experiments at both the Omega laser and the NIF. His ICF team executed the largest Be capsule implosions on NIF, conducted the first direct-drive CH capsule implosions on NIF, obtained the first 2D backlit images of direct-drive capsules on NIF and were the first to perform polar direct drive implosions of double shell targets on the NIF. Mark has mentored many students and post-docs during his tenure at LANL. He is a member of the APS and the Eta Kappa Nu Honor Society and is a Senior Member of the IEEE. He has well over 100 publications.
Read More
Related Institutes
3:00 pm / 5:00 pm
December 14
Storytelling in Science
Todd Hufnagel
Professor, Department of Materials Science and Engineering
Johns Hopkins University
December 14, 2021
3-5:00 PM ET
Registration link
There are more opportunities than ever for us to communicate our science: Talks, papers, and posters, of course, but also social media and blogs. Effective communication is particularly important for students, not only to make their work more influential but also as advertising to potential employers and collaborators. But how many times have you watched a scientist ramble through an interminable series of slides and wondered, ?What is the point of all of this??
Don't be that speaker. Learn how to give a great talk (or write a great paper) by using the basic building blocks of storytelling ? momentum, conflict, and resolution ? to craft a compelling narrative for your work. Using techniques described by Randy Olson in his book Houston, We Have a Narrative: Why Science Needs Story, we'll learn to tell the difference between good and bad scientific storytelling and use that understanding to develop narrative structures that will capture an audience's attention.
This virtual workshop will be hosted on Zoom.
Note: The workshop is limited to 25 participants, and advance registration is required. All participants will receive a copy of the book in either Kindle or paperback form ahead of the workshop.
Instructor: Todd Hufnagel has a long-standing interest in helping students learn to communicate their work through effective speaking and writing. He is Professor of Materials Science and Engineering and Mechanical Engineering, Associate Director of the Materials Science in Extreme Environments University Research Alliance and a fellow of the Hopkins Extreme Materials Institute.
Read More
Related Institutes
11:00 am / 12:00 pm
January 13
Details forthcoming.
Speaker information here.
Read More