eCite Digital Repository

Bag of Class Posteriors, a new multivariate time series classifier applied to animal behaviour identification

Citation

Smith, D and Dutta, R and Hellicar, A and Bishop-Hurley, G and Rawnsley, R and Henry, D and Hills, J and Timms, G, Bag of Class Posteriors, a new multivariate time series classifier applied to animal behaviour identification, Expert Systems With Applications, 42, (7) pp. 3774-3784. ISSN 0957-4174 (2015) [Refereed Article]

Copyright Statement

Copyright 2014 Elsevier Ltd

DOI: doi:10.1016/j.eswa.2014.11.033

Abstract

Class Posteriors (BOCP) and the Bag of Class Posterior with Ordering (BOCPO). The models propose a new multi-scale feature representation where the class posterior estimates of contiguous local patterns are aggregated over longer time scales. The models are employed as part of an animal behaviour monitoring system that are comprised of sensors, which are fitted to the animals, and a classifier that translates sensor data into knowledge of the animalís behaviour.

Animal monitoring systems are commonly developed to infer a small number of behaviours with relevance to a specific application. To investigate if a standard monitoring system with an Inertial Measurement Unit (IMU) can be reused for different management applications, a set of ten cattle behaviours relevant to different management applications were classified with the proposed models. Results indicate that the multi-scale BOCP and BOCPO models were far more capable of classifying the cow behaviours offering a 43% to 77% improvement over benchmark time interval classifiers with fixed time resolution. In addition, the BOCPO model was shown to offer a far more efficient feature representation than the related multi-scale Bag of Features (BOF) classifier (up to 200 times smaller) making it better suited to deploy upon monitoring devices fitted to animals in the field.

Item Details

Item Type:Refereed Article
Keywords:precision cattle management, inertial measurement unit, dairy, grazing behaviour, time series classification, class posterior estimates
Research Division:Agricultural and Veterinary Sciences
Research Group:Animal Production
Research Field:Animal Management
Objective Division:Animal Production and Animal Primary Products
Objective Group:Livestock Raising
Objective Field:Dairy Cattle
Author:Rawnsley, R (Dr Richard Rawnsley)
Author:Hills, J (Dr James Hills)
ID Code:102412
Year Published:2015
Web of Science® Times Cited:9
Deposited By:Tasmanian Institute of Agriculture
Deposited On:2015-08-19
Last Modified:2017-11-01
Downloads:0

Repository Staff Only: item control page