Top photo


Shah rokh Valaee

Professor


Department of Electrical and Computer Engineering
University of Toronto
10 King's College Road
Toronto, ON, Canada, M5S 3G4




UofT Crest


I am a professor in the Department of Electrical and Computer Engineering at the University of Toronto. I am a member of the Communications Group, and my research is on Signal Processing and Wireless Networks. There are three major themes in my research:

 



OUR RESEARCH

Machine Learning with Unbalanced Data

In many practical applications, datasets used for training neural networks are highly unbalanced or scarce in volume. Examples can be found in medical imaging, where data from common diseases are significanlty more than that of rare diseases, or in financial transactions with much more healthy transactions than fradulent ones, or in the analysis of network traces with hackers traffic constituting only a small amount of communications. Training deep neural networks with unbalanced data tends to bias the network towards the classes that contain more data. In our research, we address these shortcomings by data augmentation:

  • Data augmentation via radial transformation
    • Salehinejad H, Valaee S, Dowdell T, Barfett J., "Image Augmentation using Radial Transform for Training Deep Neural Networks", IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2018. Link to Arxiv
    • Salehinejad H, Naqvi S, Colak E, Barfett J, Valaee S., "Unsupervised Semantic Segmentation of Kidneys Using Radial Transform Sampling on Limited Images," IEEE Global Conference on Signal and Information Processing (IEEE GlobalSIP), California, USA, 2018.
    • Salehinejad H, Naqvi S, Colak E, Barfett J, Valaee S. "Cylindrical Transform: 3D Semantic Segmentation of Kidneys with Limited Annotated Images," IEEE Global Conference on Signal and Information Processing (IEEE GlobalSIP), California, USA, 2018.

    Radial Transformed Images

  • Data Augmentation via Generative Adversarial Networks
    • Salehinejad H, Valaee S, Dowdell T, Colak E, Barfett J. "Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks", IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2018. Link to Arxiv
    • Salehinejad H, Dowdell T, Colak E, Barfett J, Valaee S., "Synthesizing Chest Radiograph Pathology for Training Deep Convolutional Neural Networks", Accepted in IEEE Transactions on Medical Imaging, 2018.

    Synthesized Chest Xray

    X-Ray Generation



Complexity reduction of Deep Neural Networks

Scarcity of data is a challenge in training large neural networks. Training large networks with small data might result in overfitting. Drop-out has been proposed to address this problem by removing some of the neurons during the training phase. In our research on drop-out, we represent the neural net with a graphical model and minimize the Ising energy to identify the neurons that should be dropped during the training and also during inference. In our approach, neurons that operate in the saturated region of the sigmoid function are prone to be dropped.

Dropping Saturated Neurons


Localization of Wireless Terminals

We have developed an accurate location estimation technique for indoor environment using compressive sensing. The proposed algorithm has been developed on HP PDA and Android devices and tested in Bahen Centre at the University of Toronto, Bayview Village shopping mall in North Toronto, and the Canadian National Institute for Blind (CNIB). Currently, we are using machine learning and channel state information for location estimation.

Indoor Localization

Localization Accuracy



Vehicular Networks

Our research in vehicular networks focuses on interference management in wireless channel. The research includes both 802.11p Wireless Access in Vehicular Environment (WAVE), and C-V2X. We have shown that 802.11p suffers from significant interference that limits the number of vehicles that can participate in the network. Using the concept of Pseudo Orthogonal Codes (POC), we have designed effective distributed schedulers that are applicable to both 802.11p and C-V2X. Currently, we are working on scheduling sidelinks in device-to-device (D2D) and LTE-V2X technology. We have designed effective resource management schemes for multichannel operation of V2X and D2D.

Contiguous Scheduling in C-V2X


News




  • Professor Valaee gave the Keynote Speech at the 20th International Conference on Network-Based Information Systems (NBiS-2017), entitled "Cooperative Self-driving Vehicles."

  • "Cooperative Self-driving Vehicles," IEEE Toronto - Communication Society Chapter, COM-SOC Tutorial, Nov 2017.

  • Professor Valaee gave a Tutorial at VTC Fall 2017 on "Connected Vehicles".

  • Professor Valaee gave an invited talk at the 3rd International Workshop Research Advancements in Future Internet Architectures (RAFNET), in conjunction with IEEE VTC Fall 2017, entitled "User Localization in Next Generation Wireless Networks".

  • Professor Valaee gave an invited talk at IEEE Toronto Chapter of Measurement-Instrument, Robotics and Automation, Ryerson University, Toronto, 2015, entitled "Connected Cars for Smart Cities".

  • Professor Valaee gave the Keynote Speech at EAI International Conference on Smart Urban Mobility Services, October 2015, entitled "Connected Cars for Smart Urban Mobility".

  • Professor Valaee gave the Plenary Speech at CSI Computer Conference, and Artificial Intelligence Workshop, Mashhad, Iran, 2015, entitled "Localization of Wireless nodes".



OUR TEAM

We have a vibrant group that concentrates on tackling difficult engineering problems. Our researchers are among the best with strong technical background and great programming skills. We use advanced signal processing and wireless networking techniques to solve challenging problems with a focus on mixing theory and practice. Our analytical strengths span a wide range that includes machine learning, compressive sensing, and network coding. We implement our machine learning algorithms on GPU hardware, and our localization algorithms on the Android planform.








© copyright Hojjat Salehinejad, Shahrokh Valaee