top of page

Sana Arastehfar

Master of Computer Science

Queen's University, at Kingston

About Me

​

I am a Machine Learning Engineer with extensive experience in research and applied machine learning. My expertise spans time-series analysis, predictive modeling, and computer vision, with over 8 years of experience in the startup ecosystem, I bring a unique blend of technical expertise and entrepreneurial spirit. I was a co-founder of a biomedical startup specializing in developing signal recording devices. My background demonstrates a strong ability to innovate, solve complex problems, and adapt to new challenges.

 

I am passionate about continuous learning and thrive in environments where I can explore cutting-edge technologies and deliver impactful solutions.

Skills

SKILLS

Languages​

​

Python, SQL, Matlab, C++, PDDL, RDDL

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

Data Visualization​

​

Streamlit, Plotly, Power BI

Version Control​

​

Git, Docker

work expeience

WORK EXPERIENCE

Machine Learning Engineer - University of Alberta, Darkhorse Analytics

2024 till present

  • This mitacs project is on the Residential Fire Prediction project under supervision of Nooshin Salari in collaboration with Darkhorse Analytics. We are developing and deploying machine learning models to predict residential fire risks across Chicago, using tools such as SQL, Python, and PyTorch. W conducted comprehensive time-series analysis and forecasting to identify high-risk areas, enabling proactive fire prevention strategies and effective resource allocation. Additionally, we created user-friendly dashboards using Streamlit, which facilitated data-driven decision-making. Throughout the project, we presented findings and insights to stakeholders and external partners, effectively communicating complex technical concepts to non-technical audiences.

​

​

Summer Geometry Initiative Research Fellow - Massachusetts Institute of Technology(MIT)

2023

  • This research program is directed by Justin Solomon, during which we gained research experiences related to applied geometry and geometry processing. My participated projects are as follows: "Tangible NeRFs: Geometry-guided NeRF Exploration Under supervision of "Ilke Demir", Intrinsic Mollification under supervision of "Keenan Crane", and Probing Learned Quasimetric Representation for Control under supervision of "Tongzhou Wang". GitHub

​

Machine Learning Engineer -  Hermes Capital Tehran (Startup)

2020 till 2022

  • Developing Machine Learning based algorithms to forecast the short time return values of the stock in Iran stock market. The project was conducted using Python and different learning based and statistical methods were devoloped in PyTorch. We presented complex data insights and model outcomes to stakeholders through clear and compelling presentations, facilitating informed investment decisions. In collaboration with data scientists, analysts, and financial experts, we helped integrate machine learning solutions into trading strategies. The project was successful in the sense of long term profit making. 

​

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 the production of bio signal recording devices, overseeing all aspects from product development to market launch. Led a team of engineers in designing high-quality biomedical devices, ensuring compliance with industry standards and regulatory requirements. Managed financial planning, budgeting, and fundraising efforts. By fostering a culture of innovation and continuous improvement, we drove the development of cutting-edge biomedical technologies, which ultimately led to the creation of SnapECG, expanding the company’s product portfolio.​

​

UI/UX Developer - Sharif University of Technology Accelerator (Tamin Online Startup)

2017

  • Designed and developed a B2B e-commerce website for selling industrial equipment using HTML, CSS, AngularJS, and UX/UI best practices to create intuitive and responsive web interfaces, ensuring seamless navigation and accessibility across various devices. Collaborated with product managers and stakeholders to gather requirements and translate business needs into functional and aesthetically pleasing web designs. Conducted user research and usability testing to identify areas for improvement, implementing iterative design changes to enhance the site's functionality.

​

​​

​

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

​

Implementation of Personal Library for Classic Machine Learning Method

2019

  • Implementation of classic Machine Learning methods such as Regression, KNN, Decision Trees, Naïve Bayes… in Octave/Matlab. GitHub

​​

Researcher - Biomedical Engineering Research Center at Universitat Politecnica de Catalunya

2018 till 2019

  • Working remotely on a surface EMG recording system (WaveQuest) developed by Zist Abzar Pars Engineers.

​

Heart Attack Prediction & Implementation of Portable ECG

2015 till 2019

  • Under supervision of Professor Hamid Reza Marateb, and together with my colleagues in “Zist Abzar Pars,” a healthcare startup co-founded by me, we worked on heart attack prediction using patients Electrocardiography signal profiles. We processed and classified signals for ECG using Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) methods for arrhythmia detection. Our effort manifested itself in designing and implementing an innovative portable ECG. The ultimate achievement of this project was introducing the SnapECG wearable device, with the capability to store patients’ heart signals. â€‹

​

​

​

PUBLICATIONS

S. Arastehfar, C. Muise, C. Pfaff, A Linear Temporal Logic Framework for Single Player Behavior Extraction in Soccer. Under review.

S. Arastehfar, M. Matinkia, M. Jabbarpour, Short-Term Residential Load Forecasting Using Graph Convolutional Recurrent Neural Network, in Elsevier Engineering Application of Artificial Intelligence, 2022

Reseach
Publication
key

AWARDS & HONORS

  • 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

TEACHER ASSISTANT

Elements of Data Analytics - (Bachelor’s Course) - 2023

​

Engineering Mathematics - (Bachelor’s Course) - 2019

​

Algorithm Design - (Bachelor’s Course) - 2019

​

Computer Architecture - (Bachelor’s Course) - 2019

​

Logic Circuits - (Bachelor’s Course) - 2018

​

bottom of page