Mohamed El Banani

I am a Ph.D. student in computer science at the University of Michigan where I am working with John Laird and Jason Corso as part of the Artificial Intelligence Laboratory.

Prior to coming to Michigan, I got my undergraduate degree at Georgia Tech, where I worked with Maithilee Kunda in computer science, and with Omer Inan and Todd Sulchek in biomedical engineering.

Email  /  CV  /  Google Scholar  /  GitHub  /  LinkedIn

News

  • 02/2018: ArXiv paper on learning which question to ask in human-guided viewpoint estimation: Adviser Networks.
  • 09/2017: I released a PyTorch implementation of Clickhere CNN and Render For CNN . (code)
  • 06/2017: I gave a talk at the 37th Soar workshop on my current research project. (slides)
  • 06/2016: I gave a talk at the 36th Soar workshop on the block design task project. (slides)
  • 07/2016: I presented a poster at CogSci 2016. (paper)

Research

Adviser Networks: Learning What Question to Ask for Human-In-The-Loop Viewpoint Estimation
Mohamed El Banani and Jason J. Corso
arXiv
paper / code

We define the Adviser problem as the problem of finding the query that would best improve the performance of a hybrid-intelligence system. We formulate a solution to the adviser problem using a deep convolutional neural network and apply it to the task of viewpoint estimation where the question asks for the location of a specific keypoint in the input image. We show that by using the keypoint guidance from the Adviser Network and the human, the model is able to outperform the previous hybrid-intelligence state-of-the-art by 3.27%, and outperform the computer-only state-of-the-art by 10.44%.

A Computational Exploration of Problem-Solving Strategies and Gaze Behaviors on the Block Design Task
Maithilee Kunda, Mohamed El Banani, and James M. Rehg
38th Annual Conference of the Cognitive Science Society, 2016
paper / code

We present a computational architecture that is used to compare different models of problem-solving on the block design task and to generate detailed behavioral predictions for each different strategy. We describe the results of three different modeling experiments and discuss how these results provide greater insight into the analysis of gaze behavior and error patterns on the block design task.

A Pilot Study of a Modified Bathroom Scale to Monitor Cardiovascular Hemodynamic in Pregnancy
Odayme Quesada, Mohamed El Banani, James Heller, Shire Beach, Mozziyar Etemadi, Shuvo Roy, Omer Inan, Juan Gonzalez, and Liviu Klein
Meeting of the American College of Cardiology, 2016
paper

We showed that the ballistocardiogram (BCG) signal - the heart beat induced repetitive movements of the body due to acceleration of blood as it is ejected into the large vessels - can be measured using a modified bathroom scale. We used the scale to acquire serial measurements of BCG waveforms during pregnancy to assess maternal cardiovascular adaptation , including changes in cardiac output (CO), cardiac contractility (CC) and heart rate (HR).

Three-Dimensional Particle Tracking in Microfluidic Channel Flow using In and Out of Focus Diffraction
Bushra Tasadduq, Gonghao Wang, Mohamed El Banani, Wenbin Mao, Wilbur Lam, Alexander Alexeev, and Todd Sulchek
Journal of Flow Measurement and Instrumentation, 2015
paper

Three-dimensional particle tracking is important to accurately understand the motion of particles within complex flow fields. We show that three-dimensional trajectories of particles within microfluidic flow can be extracted from two-dimensional bright field video microscopy. The method utilizes the defocusing that occurs as particles move out of the objective focal plane when viewed through a high numerical aperture objective lens.


(this guy makes a nice wesbite)