000265153 001__ 265153
000265153 005__ 20190517053813.0
000265153 0247_ $$2doi$$a10.1111/2041-210X.13172
000265153 02470 $$a10.1111/2041-210X.13172$$2DOI
000265153 037__ $$aARTICLE
000265153 245__ $$aA novel biomechanical approach for animal behaviour recognition using accelerometers
000265153 260__ $$c2019-04-02
000265153 269__ $$a2019-04-02
000265153 336__ $$aJournal Articles
000265153 520__ $$a1. Data from animal-borne inertial sensors are widely used to investigate several aspects of an animal's life, such as energy expenditure, daily activity patterns and behaviour. Accelerometer data used in conjunction with machine learning algorithms have been the tool of choice for characterising animal behaviour. Although machine learning models perform reasonably well, they may not rely on meaningful features, nor lend themselves to physical interpretation of the classification rules. This lack of interpretability and control over classification outcomes is of particular concern where different behaviours have different frequency of occurrence and duration, as in most natural systems, and calls for the development of alternative methods. Biomechanical approaches to human activity classification could overcome these shortcomings, yet their full potential remains untapped for animal studies. 2. We propose a general framework for behaviour recognition using accelerometers, and develop a hybrid model where (a) biomechanical features characterise movement dynamics, and (b) a node-based hierarchical classification scheme employs simple machine learning algorithms at each node to find feature-value thresholds separating different behaviours. Using triaxial accelerometer data collected on 10 wild Kalahari meerkats, and annotated video recordings of each individual as groundtruth, this hybrid model was validated in three scenarios: (a) when each behaviour was equally represented (EQDIST), (b) when naturally imbalanced datasets were considered (STRAT) and (c) when data from new individuals were considered (LOIO). 3. A linear-kernel Support Vector Machine at each node of our classification scheme yielded an overall accuracy of >95% for each scenario. Our hybrid approach had a 2.7% better average overall accuracy than top-performing classical machine learning approaches. Further, we showed that not all models with high overall accuracy returned accurate behaviour-specific performance, and good performance during EQDIST did not always generalise to STRAT and LOIO. 4. Our hybrid model took advantage of robust machine learning algorithms for automatically estimating decision boundaries between behavioural classes. This not only achieved high classification performance but also permitted biomechanical interpretation of classification outcomes. The framework presented here provides the flexibility to adapt models to required levels of behavioural resolution, and has the potential to facilitate meaningful model sharing between studies.
000265153 542__ $$fCC BY-NC
000265153 6531_ $$aaccelerometer, animal behaviour recognition, biomechanics, machine learning, meerkat, movement intensity, movement periodicity, posture
000265153 700__ $$aChakravarty, Pritish
000265153 700__ $$aCozzi, Gabriele
000265153 700__ $$aOzgul, Arpat
000265153 700__ $$aAminian, Kamiar
000265153 773__ $$tMethods in Ecology and Evolution
000265153 790__ $$whttps://doi.org/10.5061/dryad.7q294p8$$2url
000265153 8560_ $$fpritish.chakravarty@epfl.ch
000265153 8564_ $$uhttps://infoscience.epfl.ch/record/265153/files/Chakravarty_et_al_2019_MEE.pdf$$zPOSTPRINT$$s1392018
000265153 909C0 $$zMarselli, Béatrice$$xU10303$$pLMAM$$mkamiar.aminian@epfl.ch$$0252052
000265153 909CO $$qGLOBAL_SET$$pSTI$$particle$$ooai:infoscience.epfl.ch:265153
000265153 960__ $$apritish.chakravarty@epfl.ch
000265153 961__ $$afantin.reichler@epfl.ch
000265153 973__ $$aEPFL$$sPUBLISHED$$rREVIEWED
000265153 980__ $$aARTICLE
000265153 981__ $$aoverwrite