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.

The original random forests algorithm has been widely used and has achieved excellent performance for the classification and regression tasks. However, the research on the theory of random forests lags far behind its applications. In this paper, to narrow the gap between the applications and theory of random forests, we propose a new random forests algorithm, called random Shapley forests (RSFs), based on the Shapley value. The Shapley value is one of the well-known solutions in the cooperative game, which can fairly assess the power of each player in a game. In the construction of RSFs, RSFs uses the Shapley value to evaluate the importance of each feature at each tree node by computing the dependency among the possible feature coalitions. In particular, inspired by the existing consistency theory, we have proved the consistency of the proposed random forests algorithm. Moreover, to verify the effectiveness of the proposed algorithm, experiments on eight UCI benchmark datasets and four real-world datasets have been conducted. The results show that RSFs perform better than or at least comparable with the existing consistent random forests, the original random forests and a classic classifier, support vector machines.

Although tremendous advancement regarding the highly stable metal halide perovskite nanocrystals (PNCs) has been achieved, previous studies were primarily focused on green light-emitting PNCs (i.e., bromine-based PNCs). The stability of chlorine-based PNCs with a violet or blue emission property was still lagging behind that of their bromine-based counterparts. Herein, a nondemanding and versatile strategy for in situ encapsulating allinorganic chlorine-based PNCs with multifold exceptionally high stabilities was presented. Wellordered mesoporous silica enabled the confined growth of PNCs in its pores followed by the porosity sealing by tetramethyl orthosilicate hydrolysis, thereby rendering full encapsulation of chlorine-based PNCs in dense silica that originated from high-temperature calcination. This judiciously designed structure imparted enclosed violet/blue emitting PNCs impart with outstanding long-term stability (>1.5 year) with high photoluminescence quantum yield (i.e., 30.4%) in pure water as the result of complete isolation of PNCs from detrimental stimuli, eventually leading to the application in the white light-emitting diode device.

The continuous development and improvement of tracking devices has enabled researchers to study animal movement ecology, physiology and behaviours in ever-increasing detail (Williams et al., 2019;Wilson et al., 2019). In addition to positional data, various micro-sensors on-board of tracking devices enable the monitoring of different aspects of the wildlife tracked as well as their environment (Ropert-Coudert & Wilson, 2005). Accelerometer (ACC) data is one such feature measured with micro-sensors that is increasingly used to study animal behaviours and energetics (e.g. Williams et al., 2014).

Increasingly animal behaviour studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviours requires the development of classifiers. Here, we present the “rabc” package to assist researchers with the interactive development of such animal-behaviour classifiers based on datasets consisting out of accelerometer data with their corresponding animal behaviours. Using an accelerometer and a corresponding behavioural dataset collected on white stork (Ciconia ciconia), we illustrate the workflow of this package, including raw data visualization, feature calculation, feature selection, feature visualization, extreme gradient boost model training, validation, and, finally, a demonstration of the behaviour classification results.

Background Biologgers have contributed greatly to studies of animal movement, behaviours and physiology. Accelerometers, among the various on-board sensors of biologgers, have mainly been used for animal behaviour classification and energy expenditure estimation. However, a general principle for the combined sampling duration and frequency for different taxa is lacking. In this study, we evaluated whether Nyquist–Shannon sampling theorem applies to accelerometer-based classification of animal behaviour and energy expenditure approximation. To evaluate the influence of accelerometer sampling frequency on behaviour classification, we annotated accelerometer data from seven European pied flycatchers (Ficedula hypoleuca) freely moving in aviaries. We also used simulated data to systematically evaluate the combined effect of sampling duration and sampling frequency on the performance of estimating signal frequency and amplitude. Results We found that a sampling frequency higher than Nyquist frequency at 100 Hz was needed to classify fast, short-burst behavioural movements of pied flycatcher, such as swallowing food with a mean frequency of 28 Hz. In contrast, high frequency movements with longer durations such as flight could be characterized adequately using much lower sampling frequency of 12.5 Hz. To identify rapid transient prey catching manoeuvres within these flight bouts, again a high frequency sampling at 100 Hz was needed. For both the experimental data of the flycatchers and the simulated data, the combination of sampling frequency and sampling duration affected the accuracy of signal frequency and amplitude estimation. For long sampling durations, the sampling frequency equal to the Nyquist frequency was adequate for accurate signal frequency and amplitude estimation. Accuracy declined with decreasing sampling duration, especially for signal amplitude estimation with up to 40% standard deviation of normalized amplitude difference. To accurately estimate signal amplitude at low sampling duration, a sampling frequency of four times the signal frequency was necessary (two times the Nyquist frequency). Conclusions The appropriate sampling frequency of accelerometers depends on the objective of the specific study and the characteristics of the behaviour. For studies with no constraints on device battery and storage, a sampling frequency of at least two times the Nyquist frequency will achieve relative optimal representative of signal information (i.e., frequency and amplitude). For classification and energy expenditure estimation of short-burst behaviours, 1.4 times the Nyquist frequency of behaviour is required.

Increasingly, animal behavior studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviors requires the development of classifiers. Here, we present the “rabc” (r for animal behavior classification) package to assist researchers with the interactive development of such animal behavior classifiers in a supervised classification approach. The package uses datasets consisting of accelerometer data with their corresponding animal behaviors (e.g., for triaxial accelerometer data along the x, y and z axes arranged as “x, y, z, x, y, z,…, behavior”). Using an example dataset collected on white stork (Ciconia ciconia), we illustrate the workflow of this package, including accelerometer data visualization, feature calculation, feature selection, feature visualization, extreme gradient boost model training, validation, and, finally, a demonstration of the behavior classification results.

In this paper, in order to improve the precision of the short-term load forecasting, we propose a power load forecasting method combined principal component analysis (PCA) with least squares support vector machine (LS-SVM). Firstly PCA extracts the feature of the influence factors for power load, and then LS-SVM constructs a training model with a new variables extracted by PCA. After using PCA-LS-SVM model this paper proposed to forecast power load of one area, the results show that this method can effectively eliminate the redundant information among influential factors, reduce the input dimension of the prediction model, simplify the structure of the network, increase the learning speed and improve the power load forecasting accuracy. So this method is effectively feasible.