Research article

The new design of cows' behavior classifier based on acceleration data and proposed feature set

  • Received: 05 January 2020 Accepted: 02 March 2020 Published: 11 March 2020
  • Monitor and classify behavioral activities in cows is a helpful support solution for livestock based on the analysis of data from sensors attached to the animal. Accelerometers are particularly suited for monitoring cow behaviors due to small size, lightweight and high accuracy. Nevertheless, the interpretation of the data collected by such sensors when characterizing the type of behaviors still brings major challenges to developers, related to activity complexity (i.e., certain behaviors contain similar gestures). This paper presents a new design of cows' behavior classifier based on acceleration data and proposed feature set. Analysis of cow acceleration data is used to extract features for classification using machine learning algorithms. We found that with 5 features (mean, standard deviation, root mean square, median, range) and 16-second window of data (1 sample/second), classification of seven cow behaviors (including feeding, lying, standing, lying down, standing up, normal walking, active walking) achieved the overall highest performance. We validated the results with acceleration data from a public source. Performance of our proposed classifier was evaluated and compared to existing ones in terms of the sensitivity, the accuracy, the positive predictive value, and the negative predictive value.

    Citation: Phung Cong Phi Khanh, Duc-Tan Tran, Van Tu Duong, Nguyen Hong Thinh, Duc-Nghia Tran. The new design of cows' behavior classifier based on acceleration data and proposed feature set[J]. Mathematical Biosciences and Engineering, 2020, 17(4): 2760-2780. doi: 10.3934/mbe.2020151

    Related Papers:

  • Monitor and classify behavioral activities in cows is a helpful support solution for livestock based on the analysis of data from sensors attached to the animal. Accelerometers are particularly suited for monitoring cow behaviors due to small size, lightweight and high accuracy. Nevertheless, the interpretation of the data collected by such sensors when characterizing the type of behaviors still brings major challenges to developers, related to activity complexity (i.e., certain behaviors contain similar gestures). This paper presents a new design of cows' behavior classifier based on acceleration data and proposed feature set. Analysis of cow acceleration data is used to extract features for classification using machine learning algorithms. We found that with 5 features (mean, standard deviation, root mean square, median, range) and 16-second window of data (1 sample/second), classification of seven cow behaviors (including feeding, lying, standing, lying down, standing up, normal walking, active walking) achieved the overall highest performance. We validated the results with acceleration data from a public source. Performance of our proposed classifier was evaluated and compared to existing ones in terms of the sensitivity, the accuracy, the positive predictive value, and the negative predictive value.



    加载中


    [1] G. Mattachini, E. Riva, C. Bisaglia, J. C. A. M. Pompe, G. Provolo, Methodology for quantifying the behavioral activity of dairy cows in free-stall barns, J. Anim. Sci., 10 (2013), 4899-4907.
    [2] A. Rahmana, D.V. Smitha, Cattle behaviour classification from collar, halter, and ear tag sensors, Inf. Process. Agric., 5 (2018), 124-133.
    [3] S. M. C. Porto, C. Arcidiacono, Localization and identification performances of a real-time system based on ultra wide band technology for monitoring and tracking dairy cow behavior in semi-open free-stall barn, Comput. Electro. Agric., 108 (2014), 221-229. doi: 10.1016/j.compag.2014.08.001
    [4] M. R. Borchers, Y. M. Chang, A validation of technologies monitoring dairy cow feeding, ruminating, and lying behaviors, J. Dairy Sci., 999 (2016), 7458-7466.
    [5] G. M. Pereira, J. H. Bradley, I. E. Marcia, Validation of an eartag accelerometer sensor to determine rumination, eating, and activity behaviors of grazing dairy cattle, J. Dairy Sci., 101 (2018), 2492-2495. doi: 10.3168/jds.2016-12534
    [6] H. C. Weigele, L. Gygax, A. Steiner, B. Wechsler, J. B. Burla, Moderate lameness leads to marked behavioral changes in dairy cows, J. Dairy Sci., 3101 (2018), 2370-2382.
    [7] F. Mahmoud, B. Christopher, A. Maher, H. Jürg, S. Alexander, S. Adrian, H. Gaby, Prediction of calving time in dairy cattle, Anim. Reprod. Sci., 187 (2017), 37-46.
    [8] N. Bareille, F. Beaudeau, S. Billon, A. Robert, P. Faverdin, Effects of health disorders on feed intake and milk production in dairy cows, Livest. Prod. Sci., 83 (2003), 53-62.
    [9] J. A. V. Diosdado, Z. E. Barker, Classification of behavior in housed dairy cows using an accelerometer-based activity minitoring system, Anim. Biotelemetry, 3 (2015), 1-14. doi: 10.1186/s40317-014-0021-8
    [10] K. M. Abell, M. E. Theurer, R. L. Larson, B. J. White, D. K. Hardin, R. F. Randle, Predicting bull behavior events in a multiple-sire pasture with video analysis, accelerometers, and classification algorithms, Comput. Electro. Agric., 136 (2017), 221-227. doi: 10.1016/j.compag.2017.01.030
    [11] M. E. Theurer, D. E. Amrine, B. J. White, Remote noninvasive assessment of pain and health status in cattle, Vet. Clin. Food Anim., 29 (2013), 59-74. doi: 10.1016/j.cvfa.2012.11.011
    [12] C. W. Maina, IoT at the Grassroots-Exploring the Use of Sensors for Livestock Monitoring. Ist-Africa Week Conference, 2017, 1-8.
    [13] N. Zehner, C. Umstatter, System specification and validation of a noseband pressure sensor for measurement of ruminating and eating behavior in stable-fed cows, Comput. Electro. Agric., 136 (2017), 31-41. doi: 10.1016/j.compag.2017.02.021
    [14] J. Wang, Z. He, J. Ji, K. Zhao, H. Zhang, IoT-based measurement system for classifying cow behavior from tri-axial accelerometer, Cienc. Rural, 49 (2019), 1-13.
    [15] E. S. Nadimi, H. T. Sø gaard, Observer Kalman flter identifcation and multiple-model adaptive estimation technique for classifying animal behaviour using wireless sensor networks, Comput. Electro. Agric., 68 (2009), 9-17. doi: 10.1016/j.compag.2009.03.006
    [16] K. O'Driscoll, L. Boyle, A brief note on the validation of a system for recording lying behavior in dairy cows, Appl. Anim. Behav. Sci., 111 (2008), 195-200. doi: 10.1016/j.applanim.2007.05.014
    [17] M. S. Shahriar, D. Smith, Detecting heat events in dairy cows using accelerometers and unsupervised learning, Comput. Electro. Agric., 128 (2016), 20-26. doi: 10.1016/j.compag.2016.08.009
    [18] J. M. Talavera, L. E. Tobón, J. A. Gómez, M. A. Culman, J. M. Aranda, D. T. Parra, et al., Review of IoT applications in agro-industrial and environmental fields, Comput. Electro. Agric., 142 (2017), 283-297.
    [19] C. Arcidiacono, S. M. Porto, M. Mancino, G. Cascone, A threshold-based algorithm for the development of inertial sensor-based systems to perform real-time cow step counting in free-stall barns, Biosyst. Eng., 153 (2017), 99-109. doi: 10.1016/j.biosystemseng.2016.11.003
    [20] J. Wang, Z. He, Development and validation of an ensemble classifier for real-time recognition of cow behavior patterns from accelerometer data and location data, PLoS One, 13 (2018).
    [21] B. Robert, B. J. White, D. G. Renter, R. L. Larson, Evaluation of three-dimensional accelerometers to monitor and classify behavior patterns in cattle, Comput. Electro. Agric., 67 (2009), 80-84. doi: 10.1016/j.compag.2009.03.002
    [22] B. D. Robért, B. J. White, D. G. Renter, R. L. Larson, Determination of lying behavior patterns in healthy beef cattle by use of wireless accelerometers, Am. J. Vet. Res., 72 (2011), 467-473. doi: 10.2460/ajvr.72.4.467
    [23] L. Atallah, B. Lo, R. King, G. Yang, Sensor positioning for activity recognition using wearable accelerometers, IEEE Trans. Biomed. Circ. Syst., 5 (2011), 320-329. doi: 10.1109/TBCAS.2011.2160540
    [24] J. Krause, S. Krause, Reality mining of animal social system, Trends Ecol. Evol., 28 (2013), 541-551. doi: 10.1016/j.tree.2013.06.002
    [25] J. C. Davila, A. M. Cretu, M. Zaremba, Wearable sensor data classification for human activity recognition based on an iterative learning framework, Sensors, 17 (2017), 1287. doi: 10.3390/s17061287
    [26] R. Muller, L. Schrader, A new method to measure behavioral activity levels in dairy cows, Appl. Anim. Behav. Sci., 83 (2003), 247-258. doi: 10.1016/S0168-1591(03)00141-2
    [27] M. Sugiyama, M. Kawanabe, Machine learning in Non-Stationary Environments, MIT Press, 2012.
    [28] P. Martiskainen, M. Jarvinen, Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines, Appl. Anim. Behav. Sci., 119 (2009), 32-38. doi: 10.1016/j.applanim.2009.03.005
    [29] C. Arcidiacono, S. M. C. Porto, M. Mancino, G. Cascone, Development of a threshold-based classifier for real-time recognition of cow feeding and standing behavioural activities from accelerometer data, Comput. Electro. Agric., 134 (2017), 124-134. doi: 10.1016/j.compag.2017.01.021
    [30] S. Bhattacharya, A. M. Krishna, D. Lombardi, A. Crewe, N. Alexander, Economic MEMS based 3-axis water proof accelerometer for dynamic geo-engineering applications, Soil Dyn. Earthq. Eng., 36 (2012), 111-118. doi: 10.1016/j.soildyn.2011.12.001
    [31] M. Alsaaod, J. J. Niederhauser, G. Beer, N. Zehner, G. S. Regula, A. Steiner, Development and validation of a novel pedometer algorithm to quantify extended characteristics of the locomotor behavior of dairy cows, J. Dairy Sci., 98 (2015), 6236-6242. doi: 10.3168/jds.2015-9657
    [32] M. Janidarmian, A. R. Fekr, K. Radecka, Z. Zilic, A comprehensive analysis on wearable acceleration sensors in human activity recognition, Sensors, 17 (2017), 1-26. doi: 10.1109/JSEN.2017.2761499
    [33] N. Twomey, T. Diethe, A comprehensive study of activity recognition using accelerometers, Informatics, 5 (2018), 1-37.
    [34] 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., 9 (2019), 1656-1662.
    [35] 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., 2 (2018), 110-118. doi: 10.30991/IJMLNCE.2018v02i03.003
  • Reader Comments
  • © 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Metrics

Article views(7332) PDF downloads(677) Cited by(12)

Article outline

Figures and Tables

Figures(7)  /  Tables(11)

/

DownLoad:  Full-Size Img  PowerPoint
Return
Return

Catalog