Charles C Onu

Charles-Onu_blackwhite

PhD student, Computer Science, McGill University
charles.onu { at } mail.mcgill.ca

I conduct my research at the intersection of artificial intelligence and medicine at Mila and the Reasoning and Learning (RL) lab at McGill. I work under the supervision of  Prof. Doina Precup, co-director of RL lab and director of the DeepMind lab in Montreal. My research interests are around the issues of representation learning, multi-modal fusion, few-shot learning, and transfer learning.

I am the founder of Ubenwa, a social venture aiming to save newborn lives through low-cost, cry-based diagnostic technology powered by AI. Our work is funded by generous grants from Mila, Ministère de l’Économie, Science et Innovation (MESI) de Québec, and District 3.

New: I was featured in the AI for Good episode of The AI Element podcast by Element AI.

New: I was invited to This Week in ML and AI (TWiML & AI) where I dicussed Classical Machine learning for Infant Medical Diagnosis.

Conferences and Papers

* Co-first authors

2018

  1. From keyword spotting in adult speech to pathology detection in infant cry: a neural transfer learning approach (in submisssion) preprint
    Onu C. C., Bhattacharya G.,  Precup D.
    Neural Information and Processing Systems (NIPS), Workshop on Interpretability and robustness in Audio, Speech and Language, 2018
  2. Undersampling and Bagging of Decision Trees in the Analysis of
    Cardiorespiratory Behavior for the Prediction of Extubation
    Readiness in Extremely Preterm Infants (Link)
    Kanbar L. J.*, Onu C. C.*, Shalish W., Brown K., Sant’Anna G. M., Kearney R. E., Precup D.
    40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), 2018
  3. Saving Newborn lives at Birth Using Machine Learning
    Onu C C, Udeogu I, Ndiomu E, Kengni U , Precup D , Sant’anna G M , Alikor E , Opara P
    UNESCO Chair in Technologies for Development (Tech4Dev), 2018
  4. Bringing diversity of experience into decision-making about surgery: developing an app for that (Link)
    Ilja Ormel, Susan Law, Michel Lortie, Charles C Onu, Donna Tataryn
    International Journal of Whole Person Care, Vol 5 No 1, 2018

2017

  1. Ubenwa: Cry-based Diagnosis of Birth Asphyxia (Link)
    Onu C C, Udeogu I, Ndiomu E, Kengni U , Precup D , Sant’anna G M , Alikor E , Opara P
    NIPS 2017 Workshop on Machine Learning for the Developing World
  2. Predicting Extubation Readiness in Extreme Preterm Infants based on Patterns of Breathing (Link)
    Onu C. C., Kanbar L. J., Shalish W., Brown K., Sant’Anna G. M., Kearney R. E., Precup D.
    10th IEEE Symposium Series on Computational Intelligence (SSCI), 2017
  3. Visualizing Research Productivity in Sub-Saharan Africa: The Case of Computer Science
    Meikleham, A.; Negro, L. M.; Onu, C. C.; Harsh, M.; Bal, R.
    15th International Globelics Conference, 2017
  4. A Semi-Markov Chain Approach to Modeling Respiratory Patterns Prior to Extubation in Preterm Infants (Link)
    Onu C. C.*, Kanbar L. J.*, Shalish W., Brown K., Sant’Anna G. M., Kearney R. E., Precup D.
    39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), 2017

2015

  1. SVM Approach to Cry-based diagnosis of Birth Asphyxia
    Charles C Onu, Innocent Udeogu, Eyenimi Ndiomu
    Award! Best Paper, Workshop on Machine Learning in Healthcare
    Neural Information and Processing Systems (NIPS), 2015

2014

  1. Harnessing Infant Cry for Swift, Cost-effective Diagnosis of Perinatal Asphyxia in Low Resource Settings
    Charles C Onu
    International Humanitarian Technology Conference (IHTC), 2014
    Paper on IEEE Explore
  2. Harnessing Mobile Technology in the Diagnosis of Perinatal Asphyxia
    Charles C Onu
    UNESCO Chair in Technologies for Development (Tech4Dev), 2014

 

Projects

  1. EmbedKB
    Developed with Zafarali Ahmed, a tensorflow-based framework for rapid implementation of knowledge base embedding models and evaluation on natural language processing tasks.
  2. APEX
    An interdisciplinary project amongst researchers in McGill’s departments of Computer Science, Biomedical Engineering and Neonatology. The Apex project is aimed at developing (ml-based) methodologies for predicting extubation readiness in extremely preterm newborns.
  3. Health Experiences Canada
    Meeting information, social and psychological needs of patients preparing for breast cancer surgery. Involves development of machine-learning based recommender system for delivery of care videos.
  4. Ubenwa
    Cry-based diagnosis of birth asphyxia.

 

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s