Work performed by Computer Systems Engineering student Michael Shanta for his 3rd year project, supervised by Dr. Marina Cole and Dr. Siavash Esfahani in the School of Engineering, was written up in a paper that was recently accepted for presentation at the IEEE Sensors 2020 Conference.

For his 3rd year project Michael worked on developing machine learning techniques for an Electronic Nose in order to classify odours based on the sensor responses. The system aims to detect incontinence incidents, allowing alerts to be sent to relevant personnel from an IoT network via a cloud server.

The current trend of smart devices, is causing a revolution of the world we know where all things physical and digital are connected, monitoring the environment, and performing computation autonomously. One such use of this technology is in healthcare.

Urinary Incontinence is estimated to affect up to six million people in the United Kingdom, with sufferers often reporting having a lower quality of life. The project aimed to reduce the burdens associated with this condition for both sufferers and healthcare workers by designing a wearable, IoT-connected Electronic Nose (E-Nose). E-noses are devices which directly replicate the stages of human olfaction; delivery, detection and processing. The e-nose would be used to monitor the air and send alerts when an incontinence incident occurs by detecting the presence of urine odour.

Commercially proven metal oxide gas sensors for Volatile Organic Compound detection were used as well as custom-designed sensors developed at the Microsensors and Bioelectronics laboratory at the University of Warwick. An artificial neural network was used to solve the classification problem of identifying urine from other odours based on the sensor responses.

The paper titled “Wearable IoT Electronic Nose for Urinary Incontinence Detection” will be presented at the IEEE Sensors 2020 conference in October.