ZOOLOGICAL SOCIETY OF LONDON (ZSL) WHIPSNADE ELEPHANT LISTENING PROJECT
- Custom data acquisition and complicated signal processing simplified and translated into an accessible, easy to read and informative visitor display.
- Delivered consultation and system design to develop a new innovative data sharing application.
- Completed a high profile technical challenge within tight timescales and budget.
- Harnessing technology to deliver new insights and understanding.
- The new system aligns with the overall Zoo strategy to promote scientific understanding and education of worldwide animals and their behaviours.
- The display was met with Royal interest as part of the official unveiling.
- National Instrument NI-9181 cDAQ 1 Slot Chassis
- National Instruments NI-9250 24-bit C Series Sound and Vibration Input (IEPE)
Founded in 1826, the Zoological Society of London (ZSL) is an international scientific, conservation and educational charity whose mission is to promote and achieve the worldwide conservation of animals and their habitats.
As part of the unveiling of a new £2m centre for elephant care at the Zoo’s Whipsnade site, ZSL wanted to further enhance the public’s understanding of these magnificent creatures by installing a demonstration that illustrates how elephants communicate. Much of elephant communication is made through a number of grunts and grumbles, most fascinatingly only some of which are audible to the human ear. Many of these noises take place within the infrasound spectrum that elephants with their sensitive hearing range can pick up but people cannot.
The Zoo wished to create an innovative display that allowed the public to experience the elephants’ communication noises. The Austin Consultants team met with the ZSL to understand the requirements for the visitor experience and, in consultation with the Zoo, it was agreed to use a sensitive microphone capable of capturing sound down to 1-2Hz in order to capture the noises being made by the elephants. This data would then be translated onto a visual display projected alongside the viewing platform in the centre that explained these noises to visitors.
In addition to displaying live data captured when the elephants were inside the centre and within range of the microphone, the need to display recorded data was also identified, to ensure visitors who entered the centre when the elephants were out of range of the microphone could also understand and experience the elephants’ range of sound production.
The project delivery was under additional constraint with a deadline of a Royal visit to officially unveil the elephants’ £2m home by HM The Queen, accompanied by HRH The Duke of Edinburgh.
Most off-the-shelf microphones do not record anything below 20Hz, as normally there is no point as it can’t be audibly heard, so it was important to work with sensor manufacturers to find a suitable microphone. The chosen IEPE microphone from PCB Piezotronics not only had a working range that dropped below 20Hz, but it was important that it also has flat frequency response over this “infrasound” range, making analysis a little easier in the short timescales.
The data acquisition and microphone were mounted in the elephant centre (keeping acquisition close to the source to reduce additional electrical noise) and this was used to capture the noises being used made by the elephants. The signals from which were acquired at a sample rate of 25kHz, fully utilising the anti-aliasing filtering and differential inputs of the NI-9250. Using software developed in LabVIEW this data was processed and logged using an industrial Windows PC positioned in a plant room within the elephant centre close to the display.
ZSL Elephant Voices Visitor Experience Display
At the design stage there were still many unknowns: Do they elephants communicate much at the infrasound level in a zoo environment? What other factors affect signals at this low-frequency range? How sensitive does the acquisition equipment need to be to record these sounds? How close? As a result, we worked closely with ZSL to iterate down to a solution that met both our initial goals.
Our user experience and web design consultants worked with ZSL to understand the requirements for the display interface to ensure it fulfilled not only the educational and informational requirements but also the accessibility and cognitive needs of the wide range of visitors to the Zoo.
After reviewing many interface options and designs, including more abstract pulsating and colour changing objects, a real-time frequency spectrum with ~10 seconds of history moving from right to left was identified as the most effective and interesting. It gives the ability for the public to hear audible noises, then turn and look at the display to identify if inaudible sounds were being made at the same time. The final visual solution itself runs within a full-screen chromium browser and harnesses cutting-edge web technology including 3D WebGL rendering and visualisation engines.
There are a number of challenges with such a system, not only working in a niche area of the audio spectrum (even for acoustic engineers), but also distilling complex information into a user-friendly, exciting and inspiring display. Many people have commented on how interesting it is to just stand and watch the display!
The infrasound region is full of other noises such as the movement of buildings, low-end engine noise, air conditioning systems etc. Our processing helps remove some of these distracting noises, but deliberately not all, to give the public reference even when the elephants are feeling a little shy!
The informative display captures the communication sounds being made by the elephants and displays both the human audible noises and the inaudible infrasound as an easy to understand colourful spectrum for visitors to view when visiting the centre for elephant care.
The new system has allowed ZSL to harness technology to deliver new insights and understanding, and promote scientific understanding and education of the elephants and their behaviour.
As part of the royal visit to officially unveil the centre HRH The Duke of Edinburgh was ‘very interested’ to learn about the technology used.*
Applying Machine Learning to Interpret the Elephant Noises
To further understand the elephant noises, the Austin Consultants machine learning team are currently working to develop an algorithm that can identify certain types of calls, patterns, and maybe even specific individual elephants. The longer-term ambition of this exciting project is to attempt to interpret these calls, for example, by associating them with activities and behaviours. Maybe, with the help of machine learning, one day we can even improve the welfare of elephants in captivity, for example, by determining when an elephant is ill, but not displaying any visible symptoms.
This also has wide applications for industry. For example, we can apply machine learning algorithms to condition monitoring and predictive maintenance of industrial equipment. By analysing typical models of operation, we can use changes that fall outside normal parameters to provide an early indication of a potential fault; thus, highlighting a maintenance requirement before the equipment fails, reducing downtime, and cutting costs.