Hi this is


Ph.D. Student at University of Toronto & Co-Founder of Veebar Tech

About Me

I am passionate about transitional research, challenging questions, and moon shots.
An academic researcher by day, an entrepreneur by night.

Download Cv

My Experience

University of Toronto

Ph.D. Student

I am a researcher at Autism Research Center (ARC). My research is focused on using graph neural netowrk (GNN) clustering to find clinically relavant labels for individuals diagnosed with ASD and ADHD.

Co-Founder and CTO

Veebar Tech Inc. is a Canadian start-up company which aims to develop smart-home systems to support independent aging adults at home. Starting from 2018, the company has been working closely with seniors and senior community centres to understand their pain in order to serve them better.

Humber College


Course Title: Elements of Product Design - ELIC105
Course Level: College
The course focuses on the process of developing electronic-based products with considerations on hardware encapsulation (SOLIDWORKS) and user interface (HTML&CSS).

Head Teacher Assistant

Under the supervision of Dr.Soosan Beheshti, I worked as the head teacher assistant for the course of Signals and Systems I (BME 532). In addition to my task as a TA, I helped to develope online open-source platform for the course. Including 13 graphical user interfaces (GUIs) that help with the undrestanding of the course.

Volunteer Work


Institute of Electrical and Electronics Engineers (IEEE), Instrumentation and Robotic Automation Chapter

Journal Reviewer

Springer SIVP
(10 Journals)

IET Signal Processing
(2 Journals)

Student Theme Lead

Healthcare AI and Analytics (HAA) at iBEST ST.Michael`s Hostpital


Occasionally get invited as a guest speaker for technology / health related conferences

Selected Publications

Higher Resolution sLORETA (HR-sLORETA) in EEG Source Imaging
sLORETA is one of the well-established EEG source localization methods that is popular for its satisfactory estimation, simplicity, and fast computation. However, the method has a low-resolution and requires manual postprocessing thresholding to provide a sparser solution with acceptable resolution in source detection. Here we propose a subspace based thresholding that results in a higher resolution brain imaging based on minimizing a desired least square source detection error. Simulation results show the proposed method, denoted by HR-sLORETA, provides stable and high resolution solution in terms of Percentage of Undetected Sources (PUS) and Spatial Dispersion (SD) compared to the existing manual thresholding approaches as well as Otsu thresholding approach. It is shown that HR-sLORETA outperforms Otsu, which is the only other available automatic thresholding method, in scenarios with three or more sources

Efficient Blinking Component Estimation in Subspace-Based EEG and MEG Analysis
Removing EyeBlink (EB) artifact is often an essential preprocessing step of EEG/MEG analysis. Subspace-based methods such as Independent Component Analysis (ICA) and Signal Source Projection (SSP) are well-known methods of EB artifact removal. However, these methods require preknowledge of the number of components (NoC) involved in the blinking segments which is unknown and estimated by visual inspection. Here, we provide a reliable and efficient method for estimating the NoC of EB. The method utilizes an SVD denoising approach denoted by Number of Source Eigenvalue Error (NoSEE). The proposed method performance is examined by synthetic EEG, and is validated by real MEG data. Root Mean Square Error (RMSE) is used to evaluate the performance while visual inspection on real MEG data is used to validate the algorithms results. In both cases, the proposed method provides optimum NoC in the sense of MSE minimization and consistency with the real data. The method provides more accurate results compared to manual methods. In addition, the low computational complexity of the algorithm results in much less processing time for this automatic NoC calculator compared to the trial and error procedure of the manual methods which enables the algorithm to be used in online EEG analysis.

Automated EEG Source Error Thresholding (AESET) in L2-Regularization Inverse Problems
Brain source localization techniques aim to provide high spatial resolution for EEG data which are known to have a high temporal resolution. Yet, this task is very challenging and limited due to the influence of volume conduction effect. Most popular inverse solutions which provide a reasonable estimate for the location of the source while being simple and computationally fast, such as the L2 -Regularization based category of solutions, tends to provide low resolution and blurred estimated. Here we present a probabilistic approach for automating the thresholding of the L2-based inverse solutions that will result in a more reliable solution. The approach utilizes Minimum Noiseless Description Length (MNDL) thresholding. Addition of this method to the result of the inverse solutions confines the need for manual thresholding. The method‘s performance is evaluated in a series of synthetic simulations with the change in parameters such as Signal-to-Noise Ratio (SNR) and the number of source patches. Mean Square Error (MSE) and Percentage of Undetermined Source (PUS) are used to evaluate the performance of the thresholding method, and the results illustrate the advantage of this automatic thresholding over the manual thresholding.


By: Younes Jul 23, 2020

Graph Theory - small-world phenomenon

Here is a short story on how I used graph theory and twitter, to find a direct path from Elon Musk account to my account [...]

By: Veebar Tech Aug 15, 2020

Veebar Tech Won developement-stage award

My company (Veebar Tech) just recieved third stage Norman Esch Engineering Innovation & Entrepeneurship Award [...]

By: Younes Aug 17, 2020

GPT3- Open AI

GPT-3 is a new deep learning model from Open AI that performs text-in/text-out tasks. In short, it is google search on streroid. But you can read the longer version here [...]

Join My Email Contact List

If you enjoy receiving a short email once in a month on books, podcasts, scientific papers, and apps that I have found interesting, please consider signing up with your email: