Advanced methods for intelligent monitoring of fetal wellbeing
Project Leader: Marimuthu Palaniswami
Staff: Emerson Keenan
Collaborators: Fiona Brownfoot (Mercy Hospital for Women), Yoshitaka Kimura (Tohoku University) Chandan Karmakar (Deakin University) Ahsan Khandoker (Khalifa University)
Primary Contact: Marimuthu Palaniswami (email@example.com)
Keywords: artificial intelligence; Internet of Things (IoT); machine learning; signal processing; wearable devices
Disciplines: Electrical & Electronic Engineering
Research Centre: ARC Research Network on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP)
Stillbirth, defined as the loss of life after 28 weeks gestation, affects almost 3 million families across the globe and ends over 2000 Australian pregnancies each year. Sadly in Australia, half of all stillbirths occur after 37 weeks gestation with the incidence of stillbirth rising drastically with each week. This is particularly devastating, given the baby could often have been safely delivered, if only fetal distress were identified.
In this project we seek to develop new signal processing and machine learning methods to intelligently monitor fetal wellbeing using wearable devices. This will consist of developing computationally efficient algorithms suitable for operation in an Internet-of-Things (IoT) framework. This work continues over a decade of research our group has undertaken developing signal processing techniques and models to better understand maternal-fetal physiology, and builds upon collaborations with The University of Oxford, Tohoku University and The Mercy Hospital for Women.
We are currently seeking a postgraduate research (PhD) student for this project.