Bats are considered to be a good indicator species, reflecting the general health of the natural environment – so a healthy bat population suggests a healthy biodiversity in the local area. In this project we are exploring bat activity in one of the most iconic and high profile of London’s regeneration areas, the Queen Elizabeth Olympic Park. A network of bat monitors will be installed across the park in early 2017, as the bats wake up from winter hibernation.
How will it work?
Each bat monitoring device works like “Shazam for bats”. It captures the soundscape of its surroundings through an ultrasonic microphone, then processes this data, turning it into an image called a spectrogram. Machine learning algorithms, developed by the UCL researchers, then scan the spectrogram image, identifying possible bat calls and returning the species most likely to have made the call.
What’s the technology innovation?
Measuring bat activity in the QEOP provides a very interesting real-world use case that involves large amounts of sensor data – in this case acoustic data. Rather than sending all of this data to the cloud for processing, each device will process the data itself on its own chip, removing the cost of sending large amounts of data to the cloud – we call this high frequency processing at the edge.