A computer vision-based approach for behavior recognition of gestating sows fed different fiber levels during high ambient temperature
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.
Abstract
The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.
참고문헌 (24)
- Edith J Mayorga, "Heat stress adaptations in pigs", Animal Frontiers, 9(1), pp.54~61 (2019), Oxford University Press (OUP)[DOI]
- Robert J. Collier, "Thermal Biology of Domestic Animals", Annual Review of Animal Biosciences, 3(1), pp.513~532 (2015), Annual Reviews[DOI]
- Lucy MC, "Heat stress in pregnant sows: thermal responses and subsequent performance of sows and their offspring", Mol Reprod Dev, 84, pp.946~956 (2017)[DOI]
- KwangYeol Kim, "Evaluation of high nutrient diets and additional dextrose on reproductive performance and litter performance of heat‐stressed lactating sows", Animal Science Journal, 90(9), pp.1212~1219 (2019), Wiley[DOI]
- H.Q. Sun, "Effects of different amounts of konjac flour inclusion in gestation diets on physio-chemical properties of diets, postprandial satiety in pregnant sows, lactation feed intake of sows and piglet performance", Anim Reprod Sci, 152, pp.55~64 (2015), Elsevier BV[DOI]
- Oliviero C, "Feeding sows with high fibre diet around farrowing and early lactation: impact on intestinal activity, energy balance related parameters and litter performance", Res Vet Sci, 86, pp.314~319 (2009)[DOI]
- J. A. de Leeuw, "Effects of dietary fibre on behaviour and satiety in pigs", Proceedings of the Nutrition Society, 67(4), pp.334~342 (2008), Cambridge University Press (CUP)[DOI]
- Zverina LR, "A Pilot study : behavior and productivity of gestating sows in width-adjustable stalls", Austin J Vet Sci Anim Husb, 2, pp.1012~ (2015)
- Stephen G. Matthews, "Early detection of health and welfare compromises through automated detection of behavioural changes in pigs", The Veterinary Journal, 217, pp.43~51 (2016), Elsevier BV[DOI]
- Aqing Yang, "Automated video analysis of sow nursing behavior based on fully convolutional network and oriented optical flow", Computers and Electronics in Agriculture, 167, pp.105048~ (2019), Elsevier BV[DOI]
- "Fully convolutional networks for semantic segmentation" (2015)[URL]
- Chan Zheng, "Automatic recognition of lactating sow postures from depth images by deep learning detector", Computers and Electronics in Agriculture, 147, pp.51~63 (2018), Elsevier BV[DOI]
- Ren S, "Faster r-cnn : towards real-time object detection with region proposal networks", Neural Inf Process Syst, 39, pp.91~99 (2015)
- Chen Chen, "Recognition of aggressive episodes of pigs based on convolutional neural network and long short-term memory", Computers and Electronics in Agriculture, 169, pp.105166~ (2020), Elsevier BV[DOI]
- Behnke S, "Hierarchical neural networks for image interpretation" (2003), Springer
- Simard PY, "Best practices for convolutional neural networks applied to visual document analysis", Proceedings of the Seventh International Conference on Document Analysis and Recognition (2003)
- Deng J, "Imagenet: a large-scale hierarchical image database", 2009 IEEE conference on computer vision and pattern recognition, pp.248~255 (2009)
- "Very deep convolutional networks for large-scale image recognition" (2014)[URL]
- Ming-yue Zhang, "Effects of confinement duration and parity on behavioural responses and the degree of psychological fear in pregnant sows", Applied Animal Behaviour Science, 193, pp.21~28 (2017), Elsevier BV[DOI]
- MeGlone JJ, "Produetivity and behaviour of sows in level vs sloped farrowing pens and crates", J Anim Sci, 68, pp.82~87 (1990)
- T A Hicks, "Behavioral, endocrine, immune, and performance measures for pigs exposed to acute stress", Journal of Animal Science, 76(2), pp.474~483 (1998), Oxford University Press (OUP)[DOI]
- Severine P. Parois, "Effect of Floor Cooling on Behavior and Heart Rate of Late Lactation Sows Under Acute Heat Stress", Frontiers in Veterinary Science, 5, pp.223~ (2018), Frontiers Media SA[DOI]
- A. Sapkota, "Including dietary fiber and resistant starch to increase satiety and reduce aggression in gestating sows1,2", Journal of Animal Science, 94(5), pp.2117~2127 (2016), Oxford University Press (OUP)[DOI]
- Ramonet Y, "The effect of dietary fibre on energy utilisation and partitioning of heat production over pregnancy in sows", Brit J Nutr, 84, pp.85~94 (2000)