Real-time classification of cattle behavior using Wireless Sensor Networks

Abstract

The detection of activity and behavioral patterns using accelerometers in humans has been a longstanding research. Progress in this field has been successfully transferred to the study of animal behavior thanks to the emergence of new Internet of Things (IoT) technologies such as Wireless Sensor Networks (WSNs) and the need for more complex behavioral information. All the systems proposed by the scientific community have been evaluated in terms of classification performance. However, not many studies consider the potential loss of accuracy undergone when these systems are deployed in WSNs, given the low computational capacities of their nodes and the need for a low energy consumption. This paper proposes a behavioral pattern classification system for four types of animal behavior in free-range grazing cattle along with an optimal and a restricted configuration thereof. The evaluation of this system takes into account its classification performance and its expected accuracy under the limited resources that WSNs can offer. The results show that the optimal configuration improves the performance of its alternatives by an average of 9% and the restricted configuration by an average of 6%. Moreover, as part of a WSN, the results demonstrate a flawless accuracy in the optimal and restricted configurations for walking (100% and 100%), almost perfect for grazing (98.39% and 98.59%), and acceptable for lying (79.03% and 69.01%) and standing (75.81% and 70.42%). In conclusion, the proposed system represents a powerful tool for analyzing complex behaviors in cattle through the use of WSNs.