Sana Arastehfar

SKILLS

Languages

Python, SQL, Matlab, C++

Soft Skills

Project Ownership
Collaboration
Innovative Problem Solving
Strategic Thinker

Frameworks & Cloud Platform

Scipy, Scikit-Learn, PyTorch, PyTorch Geometric, Numpy, Pandas, AWS SageMaker, Azure ML

Version Control

Git, Docker

Data Visualization

Streamlit, Plotly, Power BI

WORK EXPERIENCE

Machine Learning Engineer - University of Alberta, Darkhorse Analytics

2024 till present

Mitacs project on the Residential Fire Prediction project under supervision of Nooshin Salari in collaboration with Darkhorse Analytics. Developing and deploying machine learning models to predict residential fire risks across Chicago, using SQL, Python, and PyTorch.
Conducted comprehensive time-series analysis and forecasting to identify high-risk areas, enabling proactive fire prevention strategies and effective resource allocation.
Created user-friendly dashboards using Streamlit to facilitate data-driven decision-making.
Presented findings and insights to stakeholders, effectively communicating complex technical concepts to non-technical audiences.

Summer Geometry Initiative Research Fellow - MIT

2023

Gained research experiences related to applied geometry and geometry processing under the direction of Justin Solomon.
Participated in projects such as “Tangible NeRFs: Geometry-guided NeRF Exploration” supervised by Ilke Demir, and “Intrinsic Mollification” under Keenan Crane, etc.

Machine Learning Engineer - Hermes Capital Tehran (Startup)

2020 till 2022

Developed ML algorithms to forecast the short term return values of the stock in the Iran stock market using Python and various methods in PyTorch.
Presented complex data insights and model outcomes to stakeholders through clear, compelling presentations.
Successfully integrated ML solutions into trading strategies.

Co-founder and COO - Zist Abzar Pars Engineers (Signals Origin Startup)

2015 till 2020

Production of bio signals recording devices such as Electromyography (EMG), Electrocardiography (ECG), Ambulatory ECG, SnapECG.
Co-founded and managed operations of a biomedical startup specializing in bio signal recording devices.
Oversaw all aspects from product development to market launch, leading a team of engineers in designing high-quality biomedical devices.

RESEARCH

Intrinsic Mollification - SGI MIT

2023

This project was conducted under supervision of Keenan Crane, where we investigate maintaining triangle quality in geometry processing algorithms without altering mesh connectivity. GitHub

Tangible NeRFs: Geometry-guided NeRF Exploration - SGI MIT

2023

This project was conducted under supervision of Ilke Demir based on recent scene understanding and editing approaches using the combination of Diffusion Models and NeRFs. This project is based on enhancing NeRFs performance through stabilizing the output using geometry and text guidance. GitHub

Single Agent Behavior Prediction Using Linear Temporal Logic (LTL) in Soccer

2023

Master’s thesis in sport analytics under supervision of professors Muise and Pfaff. The goal of this research is to predict a single soccer player's behavior by extracting the Linear Temporal Logic (LTL) formula. Taking advantage of BayesLTL, a modern tool for extracting LTL formulas in a Bayesian and contrastive framework, we extract a player’s longstanding behavior in different situations (such as before and after losing ball possession, before and after receiving a goal, and etc.) in the form of interpretable human-readable LTL formulas. GitHub

Visual Representation Learning of Colorectal Cancer in Histology Images Using Contrastive Learning

2022

Implementation of Simple Contrastive Learning, Self-supervised learning with BYOL and Supervised Contrastive Learning for the first time on CRC100k dataset. The purpose of this work is to assess the effects of contrastive loss on medical datasets, specifically in a supervised setting. GitHub

Smart Meter Data Analysis for Prediction of Residential Energy Consumption

2020 till 2021

Final project of Bachelor’s degree under the supervision of Professor Mohammadreza Jabbarpour. The goal of the project is to propose a novel deep learning method for estimation and forecasting the consumption loads using smart meter data. Our proposed method consists of employing Graph Neural Network and LSTM networks to capture both temporal and spatial information. GitHub

AWARDS

Vector Scholarship In Artificial Intelligence - 2022
UTSPAN Scholarship for pre-CASSIS workshop - 2022
Canadian Statistical Science Institution (CANSSI) sport analysis grant - 2022
Awarded a certificate by the Vice Presidency for Science and Technology for participating in National Laboratory Equipment & Chemical Exhibition - 2018
EMG (Electromyograph) device of Signals Origin is currently online at Universitat Politecnica de Catalunya BarcelonaTech (UPC) in CREB lab - 2018
Design and implementation of Ambulatory Electrocardiography and Electromyography- 2014

Sana Arastehfar

Machine Learning Engineer

About Me

SKILLS

Languages

Soft Skills

Frameworks & Cloud Platform

Version Control

Data Visualization

WORK EXPERIENCE

Machine Learning Engineer - University of Alberta, Darkhorse Analytics

Summer Geometry Initiative Research Fellow - MIT

Machine Learning Engineer - Hermes Capital Tehran (Startup)

Co-founder and COO - Zist Abzar Pars Engineers (Signals Origin Startup)

RESEARCH

Intrinsic Mollification - SGI MIT

Tangible NeRFs: Geometry-guided NeRF Exploration - SGI MIT

Single Agent Behavior Prediction Using Linear Temporal Logic (LTL) in Soccer

Visual Representation Learning of Colorectal Cancer in Histology Images Using Contrastive Learning

Smart Meter Data Analysis for Prediction of Residential Energy Consumption

PUBLICATIONS

AWARDS

Teaching Assistant