Abstract
In this paper, the dairy cattle movement detecting technology based on 3-axis acceleration sensor information fusion is presented. For they show ideal performance in generalization and optimization, Support vector machines are used to build an information fusion model for dairy cattle’s behavior classification. The data feature of the support vector machine fusion model is derived from 3-axis acceleration data. RBF function is used as the model’s kernel function. The genetic algorithm is used to optimize the parameters of the kernel function. The training and testing results show that using genetic algorithm for kernel function parameter searching has good ability to optimize the fusion model.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Paula, M., Mikko, J.: Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines. J. Applied Animal Behaviour Science 119, 32–38 (2009)
Yoshioka, H., Ito, M., Tanimoto, Y.: Effectiveness of a Real-time Radiotelemetric Pedometer for Estrus Detection and Insemination in Japanese Black Cows. J. Journal of Reproduction and Development 56, 351–355 (2010)
Ungar, E., Schoenbaum, I., Henkin, Z.: Inference of the Activity Timeline of Cattle Foraging on a Mediterranean Woodland Using GPS and Pedometry. J. Sensors 11, 362–383 (2011)
van Eerdenburg, F.J.C.M.: The pedometer, an automated aid in the detection of estrous. J. Veterinary Quarterly 30, 49–57 (2008)
Cristianini, N., Shawe-Taylor, J.: Methodology of support vector machine. Machine press, Beijing (2005)
Hairong, W., Dongmei, L., Yun, W., Weiguo, Y.: Fire Detecting Technology of Information Fusion using Support Vector Machines. In: 2010 International Conference on Artificial Intelligence and Computational Intelligence, pp. 194–198 (2010)
Liu, X.W., Wang, H.: Multiclass Support Vector Machines Theory and Its Data Fusion Application in Network Security Situation Awareness. In: 3rd International Conference on Wireless Communications, Networking and Mobile Computing, ShangHai, pp. 6349–6352 (2007)
Zhao, M., Shi, Z.: Human Activity Recognition with User-Free Acceleration in the Sensor Networks. In: 2005 International Conference on Neural Networks and Brain, BeiJing, pp. 1212–1217 (2005)
Guraliuc, A.R., Serra, A.A., Nepa, P., Manara, G., Potorti, F.: Detection and classification of human arm movements for physical rehabilitation. In: 2010 Antennas and Propagation Society International Symposium, pp. 1–4 (2010)
Joohyun, H., Namjin, K., Eunjong, C., Taesoo, L.: Classification Technique of Human Motion Context based on Wireless Sensor Network. In: 27th IEEE Engineering in Medicine and Biology Annual Conference, ShangHai, pp. 5201–5202 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Zhou, H., Yin, L., Liu, C. (2012). Dairy Cattle Movement Detecting Technology Using Support Vector Machine. In: Sénac, P., Ott, M., Seneviratne, A. (eds) Wireless Communications and Applications. ICWCA 2011. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 72. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29157-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-29157-9_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29156-2
Online ISBN: 978-3-642-29157-9
eBook Packages: Computer ScienceComputer Science (R0)