Classifying behavior by tracking acceleration has received increased interest lately. Here, we evaluated the performance of three commercial activity trackers in differentiating seven dog behaviors. Adult companion dogs (N = 70) performed still (lying, sitting, standing) and dynamic (walking, sniffing, trotting, playing) tasks, while wearing ActiGraph GT9X Link, Kaunila and FitBark devices placed on the neck collar and ActiGraph GT9X Link placed on the back. Each task was performed for 3 min within a session and repeated in two sessions; the behaviors were confirmed from video recordings. Activity scores of devices were calculated as median values for behavioral differentiation, and as minute-based values for inter-device correlations and cutoff analysis. Measurements of all devices correlated with each other, and median activity scores of all devices - unaffected by dog age, weight or sex - differentiated the still from dynamic behaviors. Dynamic behaviors were also differentiated from each other, with exception of walking vs. sniffing by back-placed ActiGraph GT9X and Kaunila. The definition of cutoffs between behaviors varied from moderate to high accuracy; defined cutoffs for standing and walking were the least accurate. The classification performance of the cutoffs had an accuracy of 80% in all the devices; thus, they performed reasonably well in classifying these behaviors.

Movement sensor data from seven static and dynamic dog behaviors (sitting, standing, lying down, trotting, walking, playing, and (treat) searching i.e. sniffing) was collected from 45 middle to large sized dogs with six degree-of-freedom movement sensors attached to the collar and the harness. With 17 dogs the collection procedure was repeated. The duration of each of the seven behaviors was approximately three minutes. The order of the tasks was varied between the dogs and the two repetitions (for the 17 dogs). The behaviors were annotated post-hoc based on the video recordings made with two camcorders during the tests with one second resolution. The annotations were accurately synchronized with the raw movement sensors data. The annotated data was originally used for training behavior classification machine learning algorithms for classifying the seven behaviors. The developed signal processing and classification algorithms are provided together with the raw measurement data and reference annotations. The description and results of the original investigation that the dataset relates to are found in: P. Kumpulainen, A. Valldeoriola Cardó, S. Somppi, H. Törnqvist, H. Väätäjä, P. Majaranta, Y. Gizatdinova, C. Hoog Antink, V. Surakka, M. V. Kujala, O. Vainio, A. Vehkaoja, Dog behavior classification with movement sensors placed on the harness and the collar, Applied Animal behavior Science, 241 (2021), 105,393.

Leaving a dog home alone is part of everyday life for most dog owners. Previous research shows that dog-owner relationship has multifarious effects on dog behavior. However, little is known about the interplay between dog-owner relationship, physical activity of the dog, and affective experiences at the time of the owner leaving home and reunion when the owner comes home. In this paper, we explored how the general (daily, home alone, and over the 2-week study period) physical activity of the dog, and owner's perceptions of the dog's affective state were correlated at those particular moments. Nineteen volunteer dog owners had their dogs (N = 19) wear two activity trackers (ActiGraph wGT2X-GT and FitBark2) for 2 weeks 24 h/day. Prior to the 2-week continuous physical activity measurement period, the owners filled in questionnaires about the dog-owner relationship and the dog behavior. In daily questionnaires, owners described and assessed their own and their perception of the emotion-related experiences of their dog and behavior of the dog at the moment of separation and reunion. The results indicated that the dog-owner relationship has an interplay with the mean daily and weekly physical activity levels of the dog. An indication of strong emotional dog-owner relationship (especially related to the attentiveness of the dog, continuous companionship, and time spent together when relaxing) correlated positively with the mean daily activity levels of the dog during the first measurement week of the study. Results also suggest that the mean daily and over the 2-week measurement period physical activity of the dog correlated the affective experiences of the dog and owner as reported by the owner when the dog was left home alone. More research is needed to understand the interplay between affect, physical activity of the dog, dog-owner relationship, and the effects of these factors on, and their interplay with, the welfare of dogs.

Dog owners' understanding of the daily behaviour of their dogs may be enhanced by movement measurements that can detect repeatable dog behaviour, such as levels of daily activity and rest as well as their changes. The aim of this study was to evaluate the performance of supervised machine learning methods utilising accelerometer and gyroscope data provided by wearable movement sensors in classification of seven typical dog activities in a semi-controlled test situation. Forty-five middle to large sized dogs participated in the study. Two sensor devices were attached to each dog, one on the back of the dog in a harness and one on the neck collar. Altogether 54 features were extracted from the acceleration and gyroscope signals divided in two-second segments. The performance of four classifiers were compared using features derived from both sensor modalities. and from the acceleration data only. The results were promising; the movement sensor at the back yielded up to 91 % accuracy in classifying the dog activities and the sensor placed at the collar yielded 75 % accuracy at best. Including the gyroscope features improved the classification accuracy by 0.7-2.6 %, depending on the classifier and the sensor location. The most distinct activity was sniffing, whereas the static postures (lying on chest, sitting and standing) were the most challenging behaviours to classify, especially from the data of the neck collar sensor. The data used in this article as well as the signal processing scripts are openly available in Mendeley Data, https://doi.org/10.17632/vxhx934tbn.1.

Respiration is vital to land-dwelling mammals; besides, salient information is encoded in the respiratory rate. Objective assessment of the respiratory rate is difficult in dogs; in particular, if the unobtrusive measurement is desired. The goal of this work was to develop and evaluate a method for unobtrusive sensing of respiratory rate in dogs. For this, the “FlexPock” multisensor system, originally developed for unobtrusive estimation of heart rate and respiratory rate in humans via magnetic impedance; accelerometry; and optical measurements, was used to assess canine respiratory rate. In a proof-of-concept study with 10 healthy dogs of different breeds and sizes, a total of 240 minutes of data was recorded in the phases standing, sitting, lying down, and walking. An algorithm was developed that estimates the respiratory rate by fusing the information from multiple sensors for increased accuracy and robustness. To discard unusable data, a simple yet effective signal quality metric was introduced. Impedance pneumography recorded using adhesive electrodes was used as a reference. Analysis of the raw FlexPock data revealed that the magnetic impedance and accelerometry were the best individual sensing modalities and fusion of these data further increased the accuracy. Using leave-one-dog-out cross-validation, the average estimation error was 9.5% at a coverage of 50.1%. However, strong variation between dogs and phases was observed. During the walking phase, neither reference nor unobtrusive sensor reported usable results, while the sitting phase exhibited the best performance. In conclusion, the fusion of magnetic impedance and accelerometry can be used for unobtrusive respiratory rate estimation in stationary dogs.

The functionality of three dry electrocardiogram electrode constructions was evaluated by measuring canine heart rate during four different behaviors: Standing, sitting, lying and walking. The testing was repeated (n = 9) in each of the 36 scenarios with three dogs. Two of the electrodes were constructed with spring-loaded test pins while the third electrode was a molded polymer electrode with Ag/AgCl coating. During the measurement, a specifically designed harness was used to attach the electrodes to the dogs. The performance of the electrodes was evaluated and compared in terms of heartbeat detection coverage. The effect on the respective heart rate coverage was studied by computing the heart rate coverage from the measured electrocardiogram signal using a pattern-matching algorithm to extract the R-peaks and further the beat-to-beat heart rate. The results show that the overall coverage ratios regarding the electrodes varied between 45–95% in four different activity modes. The lowest coverage was for lying and walking and the highest was for standing and sitting.

Dog owners are highly motivated in understanding behavior and physiology of their pets and monitoring their wellbeing. Monitoring with a commercially available activity trackers reveals levels of daily activity and rest but recognizing the behavior of the dog would provide additional information, especially when the dog is not under supervision. In this study, a performance of a 3D accelerometer movement sensor placed on the dog collar was evaluated in classifying seven activities during semi-controlled test situation with 24 dogs. Various features were extracted from the acceleration time series signals. The performance of two classifiers was evaluated with two feature scenarios: using all computed features and the ones given by forward selection algorithm. The highest overall classification accuracy for the seven behaviors was 76%. The results are promising pro improving classification of specific behaviors by relatively simple algorithms.