Design of real-time cow behavior monitoring system based on wireless sensor networks and K-Mmeans clustering algorithm

Abstract

Introduction: The present article is the product of the research whose code CS20.04, carried out during 2020. This work was supported by the Institute of Information Technology (IOIT), Vietnam Academy of Science and Technology (VAST).
 Problem: Animal monitoring is a significant problem in the agricultural sector. The primary purpose is to monitor the health of animals regularly. Consequently, animal welfare and product quality could be improved, leading to an improvement in profit. Cow behavior recognition system was considered as the right solution for cow monitoring. The requirements for this kind of system are economical, high performance, and real-time.
 Objective: The research objective is to design a real-time cow monitoring system based on wireless sensor networks and the K-means clustering algorithm.
 Methodology: A wireless sensor node was designed to measure the collar-mounted acceleration data using an accelerometer. Firstly, the collected data were classified into three classes based on the VeDBA (Vector of Dynamic Body Acceleration) feature using the K-means algorithm. Then, the thresholds for VeDBA in the previous step were used to classify new data.
 Results: Three behaviors (including feeding, lying, and standing) were classified in real-time with the accuracy of classification about 89%.
 
 Conclusion: The proposed system could be adapted in monitoring cow in real-time, the behavior classification could be implemented on the microcontroller. The results confirmed the reliability of the proposed system.
 Originality: The behavior classification could be implemented on the microcontroller for the first time in monitoring cow.
 Limitations: Only three behaviors were classified in the experiment.