An evaluation of machine learning classifiers for next-generation, continuous-ethogram smart trackers

Abstract

Background Our understanding of movement patterns and behaviours of wildlife has advanced greatly through the use of improved tracking technologies, including application of accelerometry (ACC) across a wide range of taxa. However, most ACC studies either use intermittent sampling that hinders continuity or continuous data logging relying on tracker retrieval for data downloading which is not applicable for long term study. To allow long-term, fine-scale behavioural research, we evaluated a range of machine learning methods for their suitability for continuous on-board classification of ACC data into behaviour categories prior to data transmission. Methods We tested six supervised machine learning methods, including linear discriminant analysis (LDA), decision tree (DT), support vector machine (SVM), artificial neural network (ANN), random forest (RF) and extreme gradient boosting (XGBoost) to classify behaviour using ACC data from three bird species (white stork Ciconia ciconia, griffon vulture Gyps fulvus and common crane Grus grus) and two mammals (dairy cow Bos taurus and roe deer Capreolus capreolus). Results Using a range of quality criteria, SVM, ANN, RF and XGBoost performed well in determining behaviour from ACC data and their good performance appeared little affected when greatly reducing the number of input features for model training. On-board runtime and storage-requirement tests showed that notably ANN, RF and XGBoost would make suitable on-board classifiers. Conclusions Our identification of using feature reduction in combination with ANN, RF and XGBoost as suitable methods for on-board behavioural classification of continuous ACC data has considerable potential to benefit movement ecology and behavioural research, wildlife conservation and livestock husbandry.

Perspectives in machine learning for wildlife conservation

“…For example, on-board processing solutions can use data from low-cost sensors to identify behaviors of interest and engage resource-intensive sensors only when these behaviors are being performed 66 . Other on-board algorithms classify raw data into behavioral states to reduce the volume of data to be transmitted 67 . Various supervised ML methods have shown their potential in automating behavior analysis from accelerometer data 68,69 , identifying behavioral state from trajectories 70 , and predicting animal movement 71 .…”

R package for animal behavior classification from accelerometer data—rabc

“…Secondly, rather than offering a “black‐box” training process, the visualization tools within rabc assist users in building an understanding of the behavior classification process and why some behaviors can be better classified than others, providing avenues to modify or improve the behavior classification model. Finally, the classification model trained in rabc can be exported and used on‐board of trackers as for instance used in (Yu et al., 2021 ). It is worth noting that the features calculated in the rabc package can be further extended if deemed necessary.…”

“…In a comparison with three other supervised machine learning methods (support vector machine, artificial neural network, and random forest models), XGBoost classified behavior from ACC data similarly well to the alternative methods. However, XGBoost had the fastest runtime and the second smallest memory usage (Yu et al., 2021 ). The default limit to the number of features (no_features) is 5 but can be user defined.…”

“…Note that for four hyperparameters, a set of alternative values are provided which will be optimized in this procedure (nrounds = c(5, 10, 50, 100), max_depth = c(2, 3, 4, 5, 6), eta = c(0.01, 0.1, 0.2, 0.3), gamma = c(0, 0.1, 0.5)), while for three hyperparameters we fixed the setting (colsample_bytree = 1, min_child_weight = 1, subsample = 1). The settings for these seven hyperparameters are based on our previous experience with a range of different ACC datasets (Yu et al., 2021 ). For details on the function of the hyperparameters, please refer to https://xgboost.readthedocs.io/en/latest/parameter.html .…”

“…To help biologists translate ACC data into behaviors, this package uses XGBoost, which is currently one of the most promising supervised machine learning methods for this specific purpose (Yu et al., 2021 ). Unlike the web‐based tool “AcceleRater” (Resheff et al., 2014 ), our rabc package does not focus on providing a “one‐stop service” turning ACC data into behaviors.…”