Shayan Fazeli

Shayan Fazeli

Ph.D. Candidate in Computer Science

University of California, Los Angeles

Biography

I am a Computer Science Ph.D. Candidate at the University of California, Los Angeles. My research is focused on the intersection of machine learning and health informatics. I like to design, improve, and utilize deep learning inference pipelines, especially for practical problems in the medical domain and advancing healthcare systems.

Interests

  • Artificial Intelligence
  • Machine Learning
  • Health Informatics
  • Data Science

Education

  • Ph.D. in Computer Science

    University of California, Los Angeles

  • M.Sc. in Computer Science, 2020

    University of California, Los Angeles

  • B.Sc. in Computer Science, 2017

    Sharif University of Technology

  • B.Sc. in Electrical Engineering, 2017

    Sharif University of Technology

Education

 
 
 
 
 

Ph.D. | Computer Science

University of California, Los Angeles

Sep 2017 – Present Los Angeles

Graduate Student Researcher in eHealth and Data Analytics lab, focusing on deep representation learning and healthcare AI

  • Selected Research

    • Public Health: OLIVIA, ReFOCUS, BREATHE
    • Trends and Time-series: ECG recognition, Infering stress from multi-modal physiological readings, Anxiety recognition from longitudinal smartphone usage data, rehabilitation exercise tracking, Learning electronic health records
    • Medical Imaging: Bone-marrow Pathology, CT-Scan Brain Hemorrhage localization
    • Graph Representation Learning: Humo-Lumo gap prediction for Molecules via heterogeneous ensemble of deep models (2nd place - OGBLSC@NeurIPS2022)
  • Teaching

    • CS180: Algorithms and Complexity
    • CSM152A: FPGA Lab - Introduction to Digital Design
 
 
 
 
 

M.Sc. | Computer Science

University of California, Los Angeles

Sep 2017 – Mar 2020 Los Angeles

Major: Artificial Intelligence

Minor 1: Data Science Computing

Minor 2: Computer Vision

Selected Coursework: Deep Learning Topics (A+), Machine Learning in Natural Language Processing (A), Bayesian Networks (A), Probabilistic Programming and Relational Learning (A), Probabilistic Graphical Models (A), Learning from Text (A)

 
 
 
 
 

Double Major B.Sc. | Electrical Engineering / Computer Science

Sharif University of Technology

Sep 2012 – Jun 2017 Tehran

Computer Science Thesis: Semi-supervised Indoor Layout Estimation using Fully Convolutional Neural Networks

  • I was a researcher at the Computer Vision Lab - Mathematical Sciences Department

Electrical Engineerinng Thesis: Cuffless Blood Pressure Estimation using iPPG and Eulerian Video Magnification and Constrained Local Neural Fields

Selected Coursework: Statistics (A+), Computer Vision (A+), Image Processing (A+), Stochastic Processes (A), Information Theory (A+), Cryptography (A+), Data Structures (A+), Algorithm Design (A+)

Accomplish­ments

UCLA Graduate Fellowship Recipient

Member of Exceptional Talents Organization

Member of Iran National Elites Foundation

Ranked 12th in the National University Entrance Examination

Experience

Data Science / AI Research Intern

Unsupervised Universal Patient Representation:

  • Unsupervised and Semi-supervised Representation Learning
  • Interpretable Inference Model Design
  • Attention for Electronic Health Records

Data Science / AI Research Intern

Clinical Note Generation and Representation: Task-specific Representation Learning and Generative Modeling for Radiology Reports

Visualization and Monitoring Dashboard: Interactive Visualizations and Statistical Analysis of High-Dimensional Data and Exploring Task Metric Spaces with Neural Network

Graduate Research Student / Teaching Associate

Research

  • eHealth and Data Analytics Lab

Teaching

  • CS152A: Digital Design Lab
  • CS180: Algorithms

UCLA Graduate Fellowship

  • University fellowship
  • Researching at the eHealth and Data Analytics lab - Computer Science Department

Volunteering

Event Coordinator

CS Department Open House Ambassador

Recent Videos

Recent Publications

Unsupervised Acute Intracranial Hemorrhage Segmentation With Mixture Models

Intracranial hemorrhage occurs when blood vessels rupture or leak within the brain tissue or elsewhere inside the skull. It can be caused by physical trauma or by various medical conditions and in many cases leads to death. The treatment must be started as soon as possible, and therefore the hemorrhage should be diagnosed accurately and quickly. The diagnosis is usually performed by a radiologist who analyses a Computed Tomography (CT) scan containing a large number of cross-sectional images throughout the brain. Analysing each image manually can be very time-consuming, but automated techniques can help speed up the process. While much of the recent research has focused on solving this problem by using supervised machine learning algorithms, publicly-available training data remains scarce due to privacy concerns. This problem can be alleviated by unsupervised algorithms. In this paper, we propose a fully-unsupervised algorithm which is based on the mixture models. Our algorithm utilizes the fact that the properties of hemorrhage and healthy tissues follow different distributions, and therefore an appropriate formulation of these distributions allows us to separate them through an Expectation-Maximization process. In addition, our algorithm is able to adaptively determine the number of clusters such that all the hemorrhage regions can be found without including noisy voxels. We demonstrate the results of our algorithm on publicly-available datasets that contain all different hemorrhage types in various sizes and intensities, and our results are compared to earlier unsupervised and supervised algorithms. The results show that our algorithm can outperform the other algorithms with most hemorrhage types.

Contact