Classifying the animal behaviour using machine learning algorithms: Investigating the impact of varying overlap period of the window
Keywords:
Classification, Monitoring, Sensor, Acceleration, Behavior, CowAbstract
According to the general trend of applying high technology in practice, high-tech cow breeding is being invested and developed strongly on a global scale. Monitoring the behavior of the cow can be done by using accelerometer sensors. We proposed a behavioral recognition system using machine learning, with the core of using synchronized data from two three-axis accelerometer sensors mounted in the legs and the neck of a cow. This study aims to find out when varying the data window length (corresponding to the number of samples in a record), how the performance of the behavior classification changes, thereby finding the best window length of data. The proposed method was verified on the experimental data set with a real cow.
References
D. N. Tran, T. N. Nguyen, P. C. P. Khanh and D. T. Tran, "An IoT-based Design Using Accelerometers in Animal Behavior Recognition Systems" in IEEE Sensors Journal, (2021), doi: 10.1109/JSEN.2021.3051194.
C. P. K. Phung, D. T. Tran, V. T. Duong, H. T. Nguyen, D. N. Tran, "The new design of cows' behavior classifier based on acceleration data and proposed feature set", Math. Biosci. Eng., Vol. 17 (2020), pp. 2760-2780.
P. Martiskainen, M. Jarvinen, "Cow behavior pattern recognition using a three-dimensional accelerometer and support vector machines", Appl. Anim. Behav. Sci., Vol. 119 (2009), pp. 32–38.
C. P. K. Phung, T. K. Nguyen, D. C. Nguyen, D. N. Tran, D. T. Tran, “Classification of cow’s behaviors based on 3-DoF accelerations from cow’s movements”, Int. J. Electr. Comput. Eng., Vol. 9 (2019), pp. 1656–1662.
Q. T. Hoang, C. P. K. Phung, T. N. Bui, T. P. D. Chu, D. T. Tran, “Cow behavior monitoring using a multidimensional acceleration sensor and multiclass SVM”, Int. J. Mach. Learn. Networked Collab. Eng., Vol. 2 (2018), pp. 110–118.
V. T. Pham et al., “Highly accurate step counting at various walking states using low-cost inertial measurement unit support indoor positioning system”, Sensors, Vol. 18 (2018), pp. 3186.
D. T. Tran. et al., “Optimum design considerations for a 3-DOF micro accelerometer using nanoscale piezoresistors”, IEEE International Conference on Nano/Micro Engineered and Molecular Systems, (2008), pp. 770-773.
D. D. Do et al., “Wireless ad hoc network based on global positioning system for marine monitoring, searching and rescuing (MSnR)”, In Asia-Pacific Microwave Conference 2011, (2011), pp. 1510-1513.
D. T. Tran, D. C. Nguyen, D. N. Tran, D. T. Ta, “Development of a rainfall-triggered landslide system using wireless accelerometer network”, Int. J. Adv. Comput. Technol., Vol. 7 (2015), pp. 14.
D. C. Nguyen, D. T. Tran., D. N. Tran, “Application of compressed sensing in effective power consumption of WSN for landslide scenario”, Asia Pacific Conference on Multimedia and Broadcasting (2015), pp. 1-5.
