Monitoring and classifying animal behavior using ZigBee-based mobile ad hoc wireless sensor networks and artificial neural networks

Animal welfare is an issue of great importance in modern food production systems. Because animal behavior provides reliable information about animal health and welfare, recent research has aimed at designing monitoring systems capable of measuring behavioral parameters and transforming them into their corresponding behavioral modes. However, network unreliability and high-energy consumption have limited the applicability of those systems. In this study, a 2.4-GHz ZigBee-based mobile ad hoc wireless sensor network (MANET) that is able to overcome those problems is presented. The designed MANET showed high communication reliability, low energy consumption and low packet loss rate (14.8%) due to the deployment of modern communication protocols (e.g. multi-hop communication and handshaking protocol). The measured behavioral parameters were transformed into the corresponding behavioral modes using a multilayer perceptron (MLP)-based artificial neural network (ANN). The best performance of the ANN in terms of the mean squared error (MSE) and the convergence speed was achieved when it was initialized and trained using the Nguyen-Widrow and Levenberg-Marquardt back-propagation algorithms, respectively. The success rate of behavior classification into five classes (i.e. grazing, lying down, walking, standing and others) was 76.2% (@s"m"e"a"n=1.06) on average. The results of this study showed an important improvement regarding the performance of the designed MANET and behavior classification compared to the results of other similar studies.

[1]  Peter I. Corke,et al.  Virtual fences for controlling cows , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[2]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[3]  Esmaeil S. Nadimi,et al.  Original paper: Energy generation for an ad hoc wireless sensor network-based monitoring system using animal head movement , 2011 .

[4]  T B Mepham,et al.  The role of food ethics in food policy , 2000, Proceedings of the Nutrition Society.

[5]  Ole Green,et al.  Monitoring and modeling temperature variations inside silage stacks using novel wireless sensor networks , 2009 .

[6]  Alsmadi M.Kh.S.,et al.  Back Propagation Algorithm: The Best Algorithm Among the Multi-layer Perceptron Algorithm , 2009 .

[7]  L D King,et al.  Spatial and time distribution of dairy cattle excreta in an intensive pasture system. , 2001, Journal of environmental quality.

[8]  Mac Schwager,et al.  Robust classification of animal tracking data , 2007 .

[9]  Norbert Jankowski,et al.  NEW NEURAL TRANSFER FUNCTIONS , 2007 .

[10]  Deborah Estrin,et al.  Habitat monitoring with sensor networks , 2004, CACM.

[11]  Andreas Willig,et al.  Protocols and Architectures for Wireless Sensor Networks , 2005 .

[12]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[13]  Diane J. Cook,et al.  Smart environments - technology, protocols and applications , 2004 .

[14]  Thomas Bak,et al.  ZigBee-based wireless sensor networks for classifying the behaviour of a herd of animals using classification trees , 2008 .

[15]  Daniel Roviras,et al.  Adaptive Predistortions Based on Neural Networks Associated with Levenberg-Marquardt Algorithm for Satellite Down Links , 2008, EURASIP J. Wirel. Commun. Netw..

[16]  Ian F. Akyildiz,et al.  Wireless sensor networks , 2007 .

[17]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[18]  Ivan Stojmenovic,et al.  Localized Sensor Area Coverage with Low Communication Overhead , 2008, IEEE Trans. Mob. Comput..

[19]  H. Søgaard,et al.  ZigBee-based wireless sensor networks for monitoring animal presence and pasture time in a strip of new grass , 2008 .

[20]  S. Manikandan,et al.  Prediction of biosorption efficiency for the removal of copper(II) using artificial neural networks. , 2008, Journal of hazardous materials.

[21]  Margit Bak Jensen,et al.  The need for lying time in high producing dairy cows , 2005 .

[22]  Ning Wang,et al.  Review: Wireless sensors in agriculture and food industry-Recent development and future perspective , 2006 .

[23]  Eugene D. Ungar,et al.  Inference of Animal Activity From GPS Collar Data on Free-Ranging Cattle , 2005 .

[24]  Abdolreza Moghadassi,et al.  A New Approach Based on Artificial Neural Networks for Prediction of High Pressure Vapor-liquid Equilibrium , 2009 .

[25]  Walter Lang,et al.  Spatial temperature profiling by semi-passive RFID loggers for perishable food transportation , 2009 .

[26]  K. Sällvik,et al.  Automatic identification and determination of the location of dairy cows. , 2005 .

[27]  G. Zervas,et al.  Sustainability of small ruminant organic systems of production , 2004 .

[28]  R. Dobos,et al.  Spectral Analysis of Feeding and Lying Behavior of Cattle Kept Under Different Feedlot Conditions , 2005, Journal of applied animal welfare science : JAAWS.

[29]  Esmaeil S. Nadimi,et al.  Observer Kalman filter identification and multiple-model adaptive estimation technique for classifying animal behaviour using wireless sensor networks , 2009 .

[30]  A. H. Ipema,et al.  Pilot study to monitor body temperature of dairy cows with a rumen bolus , 2008 .

[31]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[32]  Peter Corke,et al.  Networked Cows : Virtual fences for controlling cows , 2004 .