Dog's life

Ladha, Cassim; Hammerla, Nils Y.; Hughes, Emma; Olivier, Patrick; Ploetz, Thomas

doi:10.1145/2493432.2493519

Cited by 83 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After training, the classifier can classify unlabeled raw data-samples into the learned activity categories. Recently, various studies utilized IMUs for AAR regarding: wildlife [3][4][5][6][7][8][9], livestock [1,2,[10][11][12][13][14][15][16][17][18], and pets [19][20][21].…”

Section: Discussionmentioning

confidence: 99%

Horsing Around—A Dataset Comprising Horse Movement

Kamminga

Janßen

Meratnia

et al. 2019

Data

View full text Add to dashboard Cite

Movement data were collected at a riding stable over seven days. The dataset comprises data from 18 individual horses and ponies with 1.2 million 2-s data samples, of which 93,303 samples have been tagged with labels (labeled data). Data from 11 subjects were labeled. The data from six subjects and six activities were labeled more extensively. Data were collected during horse riding sessions and when the horses freely roamed the pasture over seven days. Sensor devices were attached to a collar that was positioned around the neck of horses. The orientation of the sensor devices was not strictly fixed. The sensors devices contained a three-axis accelerometer, gyroscope, and magnetometer and were sampled at 100 Hz.

show abstract

Section: Discussionmentioning

confidence: 99%

Horsing Around—A Dataset Comprising Horse Movement

Kamminga

Janßen

Meratnia

et al. 2019

Data

View full text Add to dashboard Cite

show abstract

“…As such, while energy expenditures may have been greater for pruritic atopic dogs, specific behaviors were neither identifiable nor attempted to be recorded. A recent attempt to identify specific behaviors in dogs using a small number of dogs ( n = 13) did not specify accuracy for individual behaviors making it difficult to understand the positive predictive value of results [ 6 ].…”

Section: Discussionmentioning

confidence: 99%

“…Three-dimensional movement detection and continuous sampling were not possible with this system. One previously-reported study attempted to classify specific behaviors using a multidimensional sensor [ 6 ]. This study evaluated the ability of a collar-based sensor to correctly identify behaviors in a small population of dogs ( n = 13).…”

Section: Introductionmentioning

confidence: 99%

Wearable sensor shown to specifically quantify pruritic behaviors in dogs

Griffies¹,

Zutty

Sarzen³

et al. 2018

BMC Vet Res

View full text Add to dashboard Cite

BackgroundWearable technology is an exciting new field in humans and animals. In dogs activity monitors have helped to provide objective measurement tools where pet owner observation had been the only source of information. Previous research has focused on measuring overall activity versus rest. This has been relatively useful in determining changes in activity in orthopedic disease or post-surgical cases [Malek et al., BMC Vet Res 8:185, 2012, Yashari et al., BMC Vet Res 11:146, 2015]. Assessment of pruritus via changes in activity, however, requires an assumption that increased activity is due to scratching or other pruritic behaviors. This is an inaccurate method with obvious flaws as other behaviors may also register as greater activity. The objective of this study was to validate the ability of a multidimensional high frequency sensor and advanced computer analysis system, (Vetrax®, AgLogica Holdings, Inc., Norcross, GA, USA) to specifically identify pruritic behaviors (scratching and head shaking). To establish differences between behaviors, sensor and time stamped video data were collected from 361 normal and pruritic dogs. Video annotations were made by two observers independently, while blinded to sensor data, and then evaluated for agreement. Annotations that agreed between the two were used for further analysis. The annotations specified behaviors at specific times in order to compare with sensor data. A computer algorithm was developed to interpret and differentiate between these behaviors. Test subject data was then utilized to test and score the system’s ability to accurately predict behaviors.ResultsResults for prediction of head shaking behavior included sensitivity and specificity of 72.16% and 99.78% respectively. Analysis of scratching produced sensitivity and specificity of 76.85% and 99.73% respectively. These results illustrate the ability of the system to accurately report both scratching and head shaking with an overall accuracy of 99.24% and 99.56% respectively.ConclusionsThis study validates the use of this system to accurately and objectively report scratching and head shaking in dogs. While a small portion of scratching or head shaking behaviors may be missed, as indicated by the sensitivity, when detected, the confidence that these behaviors occurred is extremely high. These factors make this system a very useful tool for objective assessment of pruritus in clinical and research settings.

show abstract

“…However, these systems are only capable of indicating if the dog was resting or moving and do not differentiate between different activities which involve movement. In (Ladha, Hammerla, Hughes, Olivier, & Ploetz, 2013), Author versión -Please cite as: Patricia Pons, Javier Jaén, Alejandro Catalá. Assessing machine learning classifiers for the detection of animals' behavior using depth-based tracking.…”

Section: Wearable Tracking Systemsmentioning

confidence: 99%

Assessing machine learning classifiers for the detection of animals’ behavior using depth-based tracking

Pons

Jaén

Catalá

2017

Expert Systems with Applications

View full text Add to dashboard Cite

There is growing interest in the automatic detection of animals' behaviors and body postures within the field of Animal Computer Interaction, and the benefits this could bring to animal welfare, enabling remote communication, welfare assessment, detection of behavioral patterns, interactive and adaptive systems, etc. Most of the works on animals' behavior recognition rely on wearable sensors to gather information about the animals' postures and movements, which are then processed using machine learning techniques. However, non-wearable mechanisms such as depth-based tracking could also make use of machine learning techniques and classifiers for the automatic detection of animals' behavior. These systems also offer the advantage of working in setups in which wearable devices would be difficult to use. This paper presents a depth-based tracking system for the automatic detection of animals' postures and body parts, as well as an exhaustive evaluation on the performance of several classification algorithms based on both a supervised and a knowledge-based approach. The evaluation of the depth-based tracking system and the different classifiers shows that the system proposed is promising for advancing the research on animals' behavior recognition within and outside the field of Animal Computer Interaction. Highlights: • Animal Computer Interaction studies could benefit from automatic behavior detection • Cats' body postures and orientation can be determined using depth-based information • Depth-based trackers offer promising accuracy rates classifying cats' postures

show abstract

Dog's life

Cited by 83 publications

References 10 publications

Horsing Around—A Dataset Comprising Horse Movement

Horsing Around—A Dataset Comprising Horse Movement

Wearable sensor shown to specifically quantify pruritic behaviors in dogs

Assessing machine learning classifiers for the detection of animals’ behavior using depth-based tracking

Contact Info

Product

Resources

About