RESEARCH

Providing direct support for AI and ML research

CARTE capitalizes on Toronto's position as a world-class research powerhouse in analytics and artificial intelligence (A/AI) and its location in close proximity to a wide range of industry clusters, from biomedical technology to advanced manufacturing.

We support basic research in analytics and artificial intelligence (A/AI) methodologies that may have broad application, by driving collaborative research between technical A/AI experts and those in other domains. We seed small-scale research projects and catalyze the launch of large-scale multi-investigator initiatives.

In addition, our in-house AI and ML expert directly collaborates with faculty at the university to accelerate research in these areas.

CARTE Research Support: Selected Publications

CARTE directly supports faculty engaging in AI and ML research by fostering collaboration with our in-house AI/ML expert. The following papers are published collaborations involving CARTE Research Associate Alex Olson and our faculty affiliates.

Faculty interested in new research support opportunities can contact Alex here.

  • Guven, G., Arceo, A., Bennett, A., Tham, M., Olanrewaju, B., McGrail, M., Isin, K., Olson, A.W. and Saxe, S., 2022. A construction classification system database for understanding resource use in building construction. Scientific Data9(1), pp.1-12.
  • Huang, W., Olson, A., Khalil, E., & Saxe, S. (2022, June 29–July 1). Image-based Prediction of House Attributes with Deep Learning [Poster]. ACM SIGCAS Conference on Computing and Sustainable Societies, Seattle, WA.
  • Raju, S., Olson, A., Deghan, S., Eisenberg, N., Chan, T.C.Y., and Roche-Nagle, G. (2022, August 18-21). Utilizing machine learning algorithms to evaluate sex-based differences in preoperative hemoglobin thresholds in open vascular surgery [Poster]. SVS 2021 Annual Vascular Meeting, San Diego, CA.

CARTE Seed: Selected Publications

The primary goal of CARTE Seed is to bring together a pair of faculty researchers with complementary expertise within FASE to build a high-impact project that will eventually secure large-scale external research funding. CARTE Seed funded projects are substantial initiatives co-funded by the Departments of the respective researchers.

2021 CARTE Seed Recipients

  1. Exploring the Applications of Natural Language Processing in Engineering Education Research

    Chirag Variawa (Institute for Studies in Transdisciplinary Engineering Education and Practice)
    Sinisa Colic (Department of Mechanical and Industrial Engineering)

  2.  Analysis of Computer-Aided Design Data: Applying Software Development Principles to Physical Product Design
    Alison Olechowski (Department of Mechanical and Industrial Engineering)
    Shurui Zhou (Department of Electrical and Computer Engineering)
  3. Analytics for Selective Mining using Sensor-based Data
    Kamran Esmaeili (Department of Civil & Mineral Engineering and Lassonde Institute of Mining)
    Mariano Consens (Department of Mechanical and Industrial Engineering)
  4. Enabling Combined Planning and Reinforcement Learning Robot Behaviours to Automate Structured Tasks
    Jonathan Kelly (University of Toronto Institute for Aerospace Studies)
    Florian Shkurti (University of Toronto Mississauga Computer Science)

2020 CARTE Seed Recipients

  1. Autonomous additive manufacturing system (AAMS): a novel in-situ monitoring and closed-loop control process using machine learning
    Chi-Guhn Lee (Department of Mechanical and Industrial Engineering)
    Yu Zou (Department of Materials Science and Engineering)
  2. Closed-loop artificially intelligent fiber-selective peripheral nerve interface for neuroprosthetic applications
    Roman Genov (Department of Electrical and Computer Engineering)
    José Zariffa (Institute of Biomaterials and Biomedical Engineering)
  3. Giving robots a sense of touch: Safe, high-performance robot manipulation combining novel skin-like sensors with high-rate, learning-based feedback control
    Xinyu Liu (Department of Mechanical and Industrial Engineering)
    Angela Schoellig (University of Toronto Institute for Aerospace Studies)

Projects awarded CARTE Seed funding and co-funded by the Centre for Healthcare Engineering

  1. Imitation and reinforcement learning for gait training of lower-limb prosthesis users
    Fae Azhari (Department of Mechanical and Industrial Engineering; Department of Civil & Mineral Engineering)
    Josh Taylor (Department of Electrical and Computer Engineering)

Selected Publications of CARTE Seed Projects

  • Xing, W., Lyu, T., Chu, X., Rong, Y., Lee, C.G., Sun, Q. and Zou, Y., 2021. Recognition and classification of single melt tracks using deep neural network: A fast and effective method to determine process windows in selective laser melting. Journal of Manufacturing Processes68, pp.1746-1757.
  • Xing, W., Chu, X., Lyu, T., Lee, C.G., Zou, Y. and Rong, Y., 2022. Using convolutional neural networks to classify melt pools in a pulsed selective laser melting process. Journal of Manufacturing Processes74, pp.486-499.
  • M. ElAnsary, J. Xu, J.S. Fihlo, G. Dutta, L. Long, C. Tejeiro, A. Shoukry, C. Tang, E. Kilinc, J. Joshi, P. Sabetian, S. Unger, J. Zariffa, P. Yoo, R. Genov, “Bidirectional peripheral nerve interface with 64 2nd-order opamp-less ∆∑ ADCs and fully-integrated wireless power/data transmission”, IEEE Journal of Solid-State Circuits, 56(11): 3247-3262, 2021.
  • M. El Ansary, J. Xu, J. Sales Filho, G. Dutta, L. Long, A. Shoukry, C. Tejeiro, C. Tang, E. Kilinc, J. Joshi, P. Sabetian, S. Unger, J. Zariffa, P. Yoo, R. Genov, “Multi-Modal Peripheral Nerve Active Probe and Microstimulator with On-Chip Dual-Coil Power/Data Transmission and 64 2nd-Order Opamp-Less ΔΣ ADCs”, International Solid-State Circuits Conference, February 13-22 2021, virtual.
  • R. Zuo, Z. Zhou, B. Ying, and X.Y. Liu, “A soft robotic gripper with anti-freezing ionic hydrogel-based sensors for learning-based object recognition,” IEEE International Conference on Robotics and Automation (ICRA’21), Xi’an, China, May 30-June 5, 2021.
  • Y. E. Hwang, R. Genov, J. Zariffa, "Reducing convolutional neural network architectures for selective peripheral nerve recording on implantable devices", Society for Neuroscience Annual Meeting, Nov, 8-11, 2021 (virtual).

© 2020 Faculty of Applied Science & Engineering