Through our research we continue to answer new questions about the nature of the infant cry, while also designing and developing efficient signal-processing and machine-learning algorithms for analysis.
Our clinical studies with partners in Nigeria and Canada are aimed at acquiring a large database of clinically-annotated infant cries and further validating the Ubenwa algorithm in a real setting. Our goal is to acquire up to 10,000 cries from 2,500 patients within 2 years. This will ensure that we have the right amount and diversity of data to demonstrate the efficacy of Ubenwa.
CC Onu, J Lebensold, WL Hamilton, D Precup “Neural Transfer Learning for Cry-based Diagnosis of Perinatal Asphyxia”, 20th Annual Conference of the International Speech Communication Association INTERSPEECH 2019. View Paper
CC Onu, I Udeogu, E Ndiomu, U Kengni, D Precup, GM Sant'anna, EAD Alikor, P Opara, “Ubenwa: Cry-based Diagnosis of Birth Asphyxia”, Machine Learning for Development workshop, 31st Conference on Neural Information Processing Systems 2017 View Paper
CC Onu, I Udeogu, E Ndiomu, “SVM Approach to the Cry-based Diagnosis of Birth Asphyxia,” Machine Learning for Healthcare workshop, 29th Conference on Neural Information Processing Systems, 2015. Best Paper Award (Nvidia Titan X GPU)
CC Onu, “Harnessing infant cry for swift, cost-effective diagnosis of perinatal asphyxia in low-resource settings,” IEEE International Humanitarian Technology Conference (IHTC), 2014 View Paper