You are now in the main content area

Dr. Soosan Beheshti

Soosan Beheshti
Program Director, Electrical Engineering
BSc, MASc, PhD, PEng

Areas of Academic Interest

Statistical signal processing

Statistical learning theory and generalization

Machine learning

Information theory

Data denoising

Data compression

System modelling and control


Year University Degree
2002 Massachusetts Institute of Technology  PhD
1996 Massachusetts Institute of Technology  MASc
1991 Isfahan University of Technology BSc

Courses Taught

Course Code Course
EE 8102 Statistical Inference
ELE 532/BME 532

Signals and Systems I



A childhood passion for math, philosophy, electromagnetic waves, and problem-solving led Soosan Beheshti to become an electrical engineer. Her early research and studies on communication systems design piqued her curiosity and led her to consider a range of questions on data modelling for the purpose of prediction and control. This area would become the foundation of Beheshti’s research, and her models can be adapted to a broad number of machine learning applications, from medical imaging to data clustering. 

For Beheshti, simpler is better. “That’s modelling,” she says. In her research on statistical signal and data processing, Beheshti harnesses data for parametric modelling. To get to the underlying structure of a set of observed data, she turns to Occam’s razor law of parsimony philosophy, a 14th-century problem-solving principle that argues, “Entities should not be multiplied without necessity.” 

“How much we trust the data dictates the complexity of the model structure that we consider,” says Beheshti. As more data is gathered that requires a faster modelling process, her research will continue to focus on meeting the challenges related to model complexity, validity, and reliability.


Soosan Beheshti

"Data modeling should be a transformation of the knowledge to applicable structures with ultimate consistency and reliable confidence."

  • Dean’s Teaching Award, Faculty of Engineering and Architectural Science, Toronto Metropolitan University, 2010
  • EECS Carlton E. Tucker Award for Teaching Excellence, Massachusetts Institute of Technology, 1998
  • S. Beheshti, E. Nidoy, and F. Rahman “K-MACE and Kernel K-MACE clustering”, IEEE Access, vol. 8, pp. 17390-17403, 2020.  
  • Y. Sadat-Nejad and S. Beheshti, “Efficient High Resolution sLORETA in Brain Source Localization”,  Journal of Neural Engineering, 2020. 
  • E. Naghsh, M. F. Sabahi, and S. Beheshti, “Joint Preprocessing of Multiple Datasets to Enhance Source Separation”, IEEE Signal Processing Letters, vol. 26, no. 12, pp. 1917-1921, 2019.  
  • S. Beheshti and S. Sedghizadeh, “Number of Source Signal Estimation by Mean Squared Eigenvalue Error (MSEE)”, IEEE Transactions on Signal Processing, vol. 66, no. 21, pp. 5694-5704, 2018.   (MATLAB Code) (external link) 
  • T. Yousefi, S. Beheshti, M. Shamsi, and S. Eftekharifar, “ECG signal compression and denoising via optimum sparsity order selection in compressed sensing framework”, Biomedical Signal Processing and Control, Elsevier, vol. 41, pp. 161-171, 2018.  
  • Y. Naderahmadian, S. Beheshti, and M. Tinati, “Correlation Based Online Dictionary Learning Algorithm”, IEEE Transactions on Signal Processing, vol. 64, no.3, pp. 592-602, 2016.  
  • Signal and Information Processing (SIP) Lab
  • Associate Editor, Signal, Image and Video Processing (SIVP)
  • Associate Editor, IET Signal Processing
  • Senior Member, IEEE