Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Estimation of Body Core Temperature of Cow using Neck Sensor based on Machine Learning

목부착형 센서를 이용한 기계학습 기반 소 심부체온 예측방안

  • Lee, Woongsup (Department of Information and Communication Engineering, Gyeongsang National University) ;
  • Ryu, Jongyeol (Department of Information and Communication Engineering, Gyeongsang National University) ;
  • Ban, Tae-Won (Department of Information and Communication Engineering, Gyeongsang National University) ;
  • Kim, Seong Hwan (Department of Information and Communication Engineering, Gyeongsang National University) ;
  • Kang, Sang Kee (Graduate School of International Agricultural Technology, Seoul National University) ;
  • Ham, Young Hwa (Agrirobotec Corporation) ;
  • Lee, Hyun June (Institute of Green Bio Science & Technology, Seoul National University)
  • Received : 2018.10.15
  • Accepted : 2018.10.29
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The body temperature of livestock is directly related to the health of livestock such that it changes immediately when there exists health problem. Accordingly, the monitoring of livestock's temperature is one of most important tasks in farm management. However, the temperature of livestock is usually measured using skin-attached sensor which is significantly affected by the outside temperature and the condition of attachment which results in the inaccurate measurement of temperature. Herein we have proposed new scheme which estimates the body core temperature of cow based on measured data from neck-attached smart sensor. Especially, we have considered both schemes which estimate the exact temperature and which detect the unusually high temperature based on machine learning. We have found that the occurrence of high temperature can be detected accurately. The proposed scheme can be used in monitoring of health condition of cow and improving the efficiency of farm management.

체온은 가축의 건강상태와 직접적으로 연관되어있어서 건강에 문제가 발생하였을 때 체온이 즉각 변화한다. 따라서 정확한 체온 측정은 스마트 축사 관리에서 중요하다. 하지만 현재 가축의 체온을 측정하기 위해서 주로 사용되는 표피 부착형 센서의 경우 외기 및 센서의 부착상태에 따라 측정되는 체온 값이 크게 변화하고, 측정되는 체온이 가축의 실제 심부체온과 다른 경우가 많다. 본 연구에서는 목 부착형 센서를 이용하여 소의 심부체온을 예측하는 방안을 개발하였다. 특히 심부체온을 정확하게 예측하는 회귀방안과 특정온도 이상으로 체온이 올라가는 것을 감지하는 분류방안을 다양한 기계학습방안을 이용하여 개발하였다. 이를 통해 높은 정확도로 소의 심부체온 이상여부를 예측할 수 있음을 보였다. 제안 방안을 통해서 소의 건강상태를 정확하게 파악하고 축사관리의 효율성을 향상시킬 수 있다.

Keywords

HOJBC0_2018_v22n12_1611_f0001.png 이미지

Fig. 1 Wearable sensor to measure temperature of cow.

HOJBC0_2018_v22n12_1611_f0002.png 이미지

Fig. 2 CIDR sensor to measure body core temperature.

HOJBC0_2018_v22n12_1611_f0003.png 이미지

Fig. 3 Comparison of measured body skin temperature and body core temperature.

HOJBC0_2018_v22n12_1611_f0004.png 이미지

Fig. 4 Hexagonal graph of body skin temperature and body core temperature.

HOJBC0_2018_v22n12_1611_f0005.png 이미지

Fig. 5 Performance comparison of regression algorithms for body core temperature prediction.

HOJBC0_2018_v22n12_1611_f0006.png 이미지

Fig. 6 Performance comparison of classification algorithms for body core temperature prediction (39℃).

HOJBC0_2018_v22n12_1611_f0007.png 이미지

Fig. 7 Performance comparison of classification algorithms for body core temperature prediction (39.5℃).

Table. 1 Attribute of data for cow.

HOJBC0_2018_v22n12_1611_t0001.png 이미지

Table. 2 Accuracy of regression algorithms for body core temperature prediction.

HOJBC0_2018_v22n12_1611_t0002.png 이미지

Table. 3 Accuracy of classification algorithms for body core temperature prediction.

HOJBC0_2018_v22n12_1611_t0003.png 이미지

References

  1. S. Neethirajan, S, "Recent Advances in Wearable Sensors for Animal Health Management," Sensing and Bio-Sensing Research, vol. 12, no. 1, pp. 15-29, Feb. 2017. https://doi.org/10.1016/j.sbsr.2016.11.004
  2. C. T. Kadzere, M. R Murphy, N. Silanikove, and E. Maltz, "Heat Stress in Lactating Dairy Cows: A Review," Livestock production science, vol. 77, no. 1, pp. 59-91, Oct. 2002. https://doi.org/10.1016/S0301-6226(01)00330-X
  3. A. E. Adams, F. J. Olea-Popelka, and I. N. Roman-Muniz, "Using Temperature-sensing Reticular Boluses to Aid in The Detection of Production Diseases in Dairy Cows," Journal of Dairy Science, vol. 96, no. 3, pp. 1549-1555, Mar. 2013. https://doi.org/10.3168/jds.2012-5822
  4. D. D. Soerensen, and L. J. Pedersen, "Infrared Skin Temperature Measurements for Monitoring Health in Pigs: A Review," Acta Veterinaria Scandinavica, vol. 57, no. 5, pp. 59-91, Feb. 2015. https://doi.org/10.1186/s13028-015-0143-x
  5. A. Madureira, B. Silper, T. Burnett, L. Polsky, L. Cruppe, D. Veira, J. Vasconcelos, and R. Cerri, "Factors Affecting Expression of Estrus Measured by Activity Monitors and Conception Risk of Lactating Dairy Cows," Journal of Dairy Science, vol. 98, no. 10, pp. 7003-7014, Oct. 2015. https://doi.org/10.3168/jds.2015-9672
  6. A. Castro-Costa, A. A. K. Salama, X. Moll, J. Aguilo, and G. Caja, "Using Wireless Rumen Sensors for Evaluating The Effects of Diet and Ambient Temperature in Non-lactating Dairy Goats," Journal of Dairy Science, vol. 98, no. 7, pp. 4646-4658, Jul. 2015. https://doi.org/10.3168/jds.2014-8819
  7. W. Lee, S. Kim, J. Ryu, and T. Ban, "Fast Detection of Disease in Livestock based on Deep Learning," Journal of the Korea Institute of Information and Communication Engineering, vol. 21, no. 5, pp. 1009-1015, May 2017. https://doi.org/10.6109/JKIICE.2017.21.5.1009
  8. K. Han, W. Lee, and K. Sung, "Development of a Model to Analyze The Relationship Between Smart Pig-farm Environmental Data and Daily Weight Increase Based on Decision Tree," Journal of Korea Institute of Information and Communication Engineering, vol. 20, no. 12, pp. 2348-2354, Dec. 2016. https://doi.org/10.6109/jkiice.2016.20.12.2348
  9. W. Lee, J. Ryu, T. Ban, S. Kim, and H. Choi, "Prediction of Water Usage in Pig Farm based on Machine Learning," Journal of Korea Institute of Information and Communication Engineering, vol. 21, no. 8, pp. 1560-1566, Aug. 2017. https://doi.org/10.6109/JKIICE.2017.21.8.1560
  10. I. H. Witten, E. Frank, M. A. Hall, and C. J. Pal, Data Mining: Practical Machine Learning Tools and Techniques. 4th ed. Burlington, MI: Morgan Kaufmann, 2016.