Accelerometers, Ground Truthing, and Supervised Learning
Accelerometers are sensitive to movement and the lack of it. They are not sentient and must recognise animal behaviour based on a human observer’s cognition. Therefore, remote recognition of behaviour using accelerometers requires ground truth data which is based on human observation or knowledge. The need for validated behavioural information and for automating the analysis of the vast amounts of data collected today, have resulted in many studies opting for supervised machine learning approaches.
In such approaches, the process of ground truthing involves time-synchronising acceleration signals with simultaneously recorded video, having an animal behaviour expert create an ethogram, and then annotate the video according to this ethogram. This links the recorded acceleration signal to the stream of observed animal behaviours that produced it. After this, acceleration signals are chopped up into finite sections of pre-set size (e.g. two seconds), called windows. From acceleration data within windows, quantities called ‘features’ are engineered with the aim of summarising characteristics of the acceleration signal. Typically, ~15-20 features are computed. Good features will have similar values for the same behaviour, and different values for different behaviours.
The latest issue of Methods in Ecology and Evolution is now online! This month’s issue is a little shorter than our last few. But, as they say, good things come in small packages!
Senior Editor Lee Hsiang Liow has selected six Featured Articles this month. You can find out about all of them below. We’ve also got five Applications articles and a Practical Tools article in the April issue that we’re going to cover. Those six papers are freely available to everyone – no subscription required!
There are many reasons that we might be interested in whether individuals, species or populations overlap in multidimensional space. In ecology and evolution, we might be interested in climatic overlap, morphological overlap, phenological or biochemical overlap. We can use analyses of overlap to study resource partitioning, evolutionary histories and palaeoenvironmental conditions, or to inform conservation management and taxonomy. Even these represent only a subset of the possible cases in which we might want to investigate overlap between entities. Databases such as GBIF, TRY and WorldClim make vast amounts of data publicly available for these investigations. However, these studies require complex multivariate data and distilling such data into meaningful conclusions is no walk in the park.
Artificial intelligence (or AI) is an enormously hot topic, regularly hitting the news with the latest milestone where computers matching or exceeding the capacity of humans at a particular task. For ecologists, one of the most exciting and promising uses of artificial intelligence is the automatic identification of species. If this could be reliably cracked, the streams of real-time species distribution data that could be unlocked worldwide would be phenomenal.
Despite the hype and rapid improvements, we’re not quite there yet. Although AI naturalists have had some successes, they can also often make basic mistakes. But we shouldn’t be too harsh on the computers, since identifying the correct species just from a picture can be really hard. Ask an experienced naturalist and they’ll often need to know where and when the photo was taken. This information can be crucial for ruling out alternatives. There’s a reason why field guides include range maps!
Currently, most AI identification tools only use an image. So, we set out to see if a computer can be taught to think more like a human, and make use of this extra information. Continue reading →
Executive Editor Rob Freckleton has selected six Featured Articles this month. You can find out about all of them below. We’ve also got six Applications articles and five Open Access articles in the February issue – we’ll talk about all of those here too.
On many evenings during spring and fall migration, tens of millions of birds take flight at sunset and pass over our heads, unseen in the night sky. Though these flights have been recorded for decades by the National Weather Services’ network of constantly-scanning weather radars, until recently these data have been mostly out of reach for bird researchers.
Understanding animal movement and population size is a challenge for researchers studying any megafauna species. Sea turtles though, add a whole additional level of complexity. These wide-ranging, swift, charismatic animals spend much of their time underwater and in remote places. When trying to track down and count turtles, this obstacle to understanding population size becomes a full-on barricade.
Mathematicians and conservationists from the UK, Africa and the United States have used machine-learning and citizen science techniques to accurately count wildebeest in the Serengeti National Park in Tanzania more rapidly than is possible using traditional methods.
Evaluating wildebeest abundance is currently extremely costly and time-intensive, requiring manual counts of animals in thousands of aerial photographs of their habitats. From those counts, which can take months to complete, wildlife researchers use statistical estimates to determine the size of the population. Detecting changes in the population helps wildlife managers make more informed decisions about how best to keep herds healthy and sustainable. Continue reading →
For more than a decade, citizen science projects have helped researchers use the power of thousands of volunteers who help sort through datasets that are too large for a small research team. Previously, this data generally couldn’t be processed by computers because the work required skills that only humans could accomplish.
Now, computer machine learning techniques that teach the computer specific image recognition skills can be used in crowdsourcing projects to deal with massively increasing amounts of data—making computers a surprising new partner in citizen science projects.