基于IMU的细粒度奶牛行为判别

针对奶牛行为判别自动化水平不足、准确率低的问题,采用惯性测量单元(IMU)和卷积神经网络(CNN),对细粒度奶牛行为判别进行研究.结果表明:1)在KNN、SVM、BPNN、CNN和LSTM 5个模型中,CNN模型在奶牛行为分类测试集上的准确率最高.2)含有三轴加速度计、陀螺仪和磁力计的IMU更加适用于奶牛行为分类,其分...     

宁夏地区荷斯坦牛产奶量和产犊间隔影响因素分析

为探讨影响宁夏地区荷斯坦牛产奶量和产犊间隔的非遗传因素,以宁夏某奶业有限公司2012—2016年间6 236头健康中国荷斯坦牛产奶性能记录和繁殖记录为研究材料,以305d产奶量和产犊间隔为研究对象,运用SAS8.1软件,采用多因素方差分析法分析场、胎次、初产月龄、产犊年份及产犊季节对荷斯坦牛305d产奶量和产犊间隔的影响。结果表明:场、胎次、产犊年份、产犊季节和产犊间隔均对荷斯坦牛305d产奶量有极显著影响(P0.01),初产月龄对305d产奶量有显著影响(P0.05);场、胎次、产犊季节和产奶量对产犊间隔有极显著影响(P0.01)。研究发现胎次、初产月龄、产犊季节和产犊间隔是影响荷斯坦奶牛305d产奶量的重要因素,胎次、产犊季节和产奶量是影响奶牛产犊间隔的重要因素。     

过瘤胃甜菜碱对奶牛泌乳性能和生产性能的影响

实验选取黑龙江省大庆市某集约化奶牛场年龄、胎次、体况及泌乳量相近的健康奶牛40头,随机分为4组,每组10头,Ⅰ、Ⅱ、Ⅲ组日粮中每头每天添加5、10和20 g过瘤胃甜菜碱,Ⅳ组为过瘤胃甜菜碱对照组。试验期从产前14 d至产后42 d,通过对试验奶牛产后乳蛋白（LP）、乳脂率（BF）、乳糖（SL）的分析,研究过瘤胃胆碱和甜...     

奶牛头胎产犊日龄与305d泌乳量的相关分析

[目的]探讨奶牛头胎产犊日龄对其产奶量的影响。[方法]以宁夏平吉堡奶牛场一分场系谱资料比较完整的50头奶牛头胎产犊记录为资料,对奶牛头胎产犊日龄与305 d泌乳量进行相关分析。[结果]50头奶牛头胎产犊日龄与305 d泌乳量的相关系数为0.4482,达显著水平(P<0.05),即奶牛头胎产犊日龄与305 d泌乳量呈中等正相关。305 d泌乳量(y)与产犊日龄(x)之间的回归方程为y=8.173x+11.460。在744~887 d之间产犊的奶牛,其305 d泌乳量随头胎产犊日龄的增加而增大,可以预测该时期内奶牛的产奶量。[结论]奶牛头胎产犊日龄对其305 d泌乳量有较大影响。     

孕牛血清中可溶性白细胞介素2受体水平的变化

应用酶标双搞体夹心法分别测定未孕牛、妊娠早期（＜１００ｄ）、妊娠中期（１００～２００ｄ）和妊娠后期（＞２００ｄ）的黑白花奶牛各１０头的血清可溶性白细胞介素２受体水平的变化，结果表明，不同妊娠阶段各组与未孕牛差异不显著（Ｐ＞０．０５），这就说明了妊娠时母体外周血清中１Ｌ－２Ｒ阳性表达细胞无显著变化，从而抑制机体对胚胎或胎儿的排斥反应     

Effect of Hypoglycemia on Performances, Metabolites, and Hormones in Periparturient Dairy Cows

In this research work, 24 multiparous holstein cows were used to evaluate the effect of hypoglycemia on periparturient metabolism and lactation performance. The cows were arranged into two groups of hypoglycemia （L） and normal plasma glucose （N） based on plasma glucose level. The same diets were fed ad libitum from 28 days before expected calving date to 28 days after calving. The parameters relative to energy balance, such as dry matter intake （DMI）, body weight （BW）, milk yield （MY）, and concentrations of plasma glucose, nonesterified fatty acids （NEFA）, β-hydroxybutyric acid （BHBA）, insulin （INS）, glucagons （GLN）, leptin （LP）, neuropeptide Y （NPY） in plasma were measured at regular intervals. Incidence of hypoglycemia was higher prepartum than that of postpartum （88% vs. 50%）, and the recurrence of hypoglycemia was reversed （31% vs. 100%）. Hypoglycemia did not affect feed intake before and after calving. With the increase of postpartum feed intake, incidence of hypoglycemia decreased rapidly, even disappeared at 28 days of postpartum. Hypoglycemia had no impact on prepartum BW, but BW in L group was lower than that of cows in N group at 1 day and 14 days of postpartum （P〈0.05）. Milk yield was not affected by hypoglycemia. Cows in L group had higher plasma NEFA concentration than cows in N group. It reached a peak （1442 μmol L^-1 vs. 1052 μmol L^-1） at day 1 of postpartum （P〈0.05）. Plasma BHBA concentration of cows in L group was higher than that in N group, which reached a peak （2.01 mmol L^-1 vs. 1.34 mmol L^-1） at 14 days of postpartum （P〈0.05）. Plasma concentration of INS and GLN was unaffected by treatment, but postpartum plasma GLN concentration obviously increased, especially in L group. Plasma concentration of LP and NPY before calving was unaffected by treatment, but postpartum LP level in L group was slightly lower than that in N group, and NPY level in L group was significantly higher than that in N group （P〈0.05）. Overall, periparturient dairy cows are easy to develop hypoglycemia, which stimulates lipid metabolism. Adaptive changes of some metabolites and hormones, such as NEFA, BHBA, INS, GLN, LP, NPY are of benefit to increase feed intake and recovery of NEB in periparturient period, but there still are some issues on interaction of those endocrine factors in the energy balance of periparturient cows to be understood further.     

Detection of cows with insemination problems using selected classification models

In the present study, the detection of cows with artificial insemination (AI) difficulties using selected statistical and machine learning methods is presented. Cows were divided into two classes: those that conceived after one or two services (“GOOD”) and those that required more than two services per conception (“POOR”). The best performance was exhibited by one of the artificial neural networks (ANN) and the multivariate adaptive regression spline (MARS) method (AIC, BIC, RMS and accuracy); whereas logistic regression (LR) and classification functions (CF) were of somewhat lower quality. The detection of cows with AI difficulties, performed on the basis of the test set comprising new instances, showed that the ANN and MARS were more precise in comparison with the statistical methods. Sensitivity and specificity were over 85% for the perceptron with two hidden layers (MLP2) and MARS and approximately 80% or lower for LR and CF. From among variables determining the AI category, the average calving interval and cow body condition index were the most important. Other significant variables were lactation number, pregnancy length, sex of calf from previous calving and cow age. The prognoses obtained using ANN and MARS can be used for the appropriate preparation of cows for AI.     

产后乏情奶牛的诱导发情研究

 本研究用奶牛初乳、新斯的明、孕激素和孕马血清促性腺激素(PMSG)处理产后乏情奶牛,测定处理后24头奶牛乳汁中孕酮(P₄)和17β-雌二醇(17β-E₂)水平变化。结果表明:初乳对产后乏情奶牛的诱导发情作用,可能与处理后乳汁17β-E₂/P₄增加有关;注射初乳时,配合用新斯的明能提高发情率;产后乏情奶牛,用初乳十新斯的明+LRH-A₂方法处理,可有效地诱导发情,且受胎率较高。     

围产期奶牛血清中阴阳离子状况的分析

为了解围产期奶牛机体主要阴阳离子水平及其变化,在黑龙江某3个集约化奶牛场分别选取荷斯坦经产奶牛8头,分别在产前21 d、14 d,7 d、分娩当天、产后7 d、14 d、21 d尾静脉采血,并测定Cl、Na、K、Mg、Ca、P等离子血清浓度.结果显示围产期奶牛血清Cl、Na、K、P含量在分娩后呈现降低趋势;Ca含量呈分...     

Elimination of ceftiofur hydrochloride residue in postpartum cows' milk after intramammary infusing at dry-off

The purpose of this study was to investigate the residue elimination of ceftiofur hydrochloride in milk of postpartum cows after intramammary infusing at dry-off. An ultra-high performance liquid chromatography-tandem mass spectrometry(UPLC-MS/MS) method was developed and validated to detect ceftiofur hydrochloride residue in milk. Through preprocessing, ceftiofur hydrochloride was derivatized into a more stable compound dedfuroyl ceftiofur acetamide(DCA) for further analysis. The linear range of DCA was 0.1 to 50 μg kg~(-1). Average recoveries of DCA were 82.52~(-1)05.86%. The intra-day and interday coefficients of variation(CV) were 2.95–9.82 and 6.41–7.43%, respectively. The limit of detection(LOD) and limit of quantitation(LOQ) scores were 0.05 and 0.1 μg kg~(-1), respectively. These parameters showed this method was reliable and valid. Twelve cows were administrated 10 m L ceftiofur hydrochloride by intramammary infusion(corresponding to 500 mg ceftiofur) to each udder after the last milking before the dry-off period. Milk was collected from each udder of cow at 12, 24, 36, 48, 60 and 72 h after calving and was mixed for each time point and each cow, then subjected to UPLC-MS/MS analysis. The results showed, the DCA concentrations in all milk samples were less than LOQ and the maximum residue limit(MRL) 100 μg kg~(-1), which suggested the withdrawal time of ceftiofur hydrochloride intramammary infusion used for preventing and curing mastitis in dry cows was 0 day. The study provided guidance for the clinical applications of ceftiofur hydrochloride intramammary infusion(dry cow).     

Peripheral Concentration of Hydroxyprolineand 3-methyl-histidine in Postpartum Cow

1　Introduction　　 It has been show in rat(Harkness and Harkness,1 95 4) ,human(Montford and PereaTamayo,1 96 1 ) and cattle (Kaidi,1 989) that the increase in the weight of the uterus duringpregnancy is associated with an increase in the collagen content of the uterus.Themechanisms involved in timulating collagen synthesis are unknown.Atthe same time there ishypertrophy and hyperplasia of the smooth muscle fibers of the myometrium.In the post-partum period,the involutionary changes of the…     

奶牛及黄牛脂肪肝发病率及肝脂肪浸润程度的研究

试验在３个荷斯坦牛场，１个娟珊牛场和１个黄牛场对１７０头经产的围产期牛和８６头青年母牛脂肪肝发病率及肝脂肪浸润程度进行了调查和研究．结果表明，牛脂肪肝主要发生在围产期，从第１产（娟珊牛）、第２产（荷斯坦牛）以后，下次产前１周肝实质出现少量脂肪浸润（０．２％～１．９％）；各品种牛在产后第１周内肝出现明显脂肪浸润（２．８％～３８．１％）；第７周后降低到较低水平（０％～３．５％）．各品种牛脂肪肝的发病率分别为：娟珊牛６４％；荷斯坦牛４８％；黄牛６．６％；各品种青年母牛４．８％．肝脂肪浸润的严重程度和产后体质下降相关（ｒ＝０．２８．Ｐ＜０．０１），但和分娩时牛的体况以及产奶量无关．     

产犊月份对荷斯坦牛产奶量的影响

以西安草滩第二牛场的荷斯坦牛为研究对象,选择2～4胎产奶量记录完整的健康母牛共587头,其中2胎217头,3胎196头,4胎174头,主要探讨产犊月份对产奶量的影响。将所有产奶数据校正到305d产奶量,用Excel进行统计分析,做出全年产奶量的整体分布曲线。对12个月份和4个季节的产奶量分别采用单因素方差分析,确定各月份和不同季节的影响效果。结果表明,冬季12、1、2月份和早春的3月份产犊的母牛305d产奶量最高,显著或极显著高于其他月份,属高产奶量月份;夏季6、7、8月份产犊的母牛305d产奶量最低,显著或极显著低于其他月份,属低产奶量月份;春季4、5月份和秋季9、10、11月份产犊的母牛305d产奶量处于中等水平,显著或极显著低于冬季和早春,但显著或极显著高于夏季,属中等产奶量月份。产犊月份对产奶量的影响效果表明,在保证全年牛奶供求基本平衡的前提下,适当调整在高产月份产犊,对提高奶牛群体产奶量具有重要意义。     

Simplify the interpretation of alert lists for clinical mastitis in automatic milking systems

Based on sensor measurements, an automatic milking system (AMS) generates mastitis alert lists indicating cows which are likely to have clinical mastitis (CM). Because of the general assumption of equal probabilities of developing CM for all cows, all alerts on the list have the same success rate. As a consequence, it is not possible to rank-order the alerts in terms of their likelihood of CM. In practice, the performance of a CM detection system is not only based on the sensitivity (SN) and specificity (SP) of the system, but is also influenced by the prior probability of a cow having CM. This study illustrates the idea of using cow-specific prior probabilities of CM, based on non-AMS information, to provide a rank-order on the alerts from an AMS. A tree-augmented naive Bayesian network was trained from available data to determine these cow-specific prior probabilities for CM. The graphical structure of the network and the probability tables for its variables in the network were based on data from 274 Dutch dairy herds that recorded each case of CM over an 18-month period. The final data set contained information on a total of 5363 CM cases derived from 28,137 lactations and 22,860 cows. The available prior cow information (parity, days in milk, season of the year, somatic cell count history and CM history) was included as variables in the network. By combining the cow-specific prior probabilities of CM with the SN and SP of the detection system of the AMS, the computed success rates can be used to discriminate between CM alerts. Our illustrations indicate that the success rate might range from 3 to 84%, while assuming an equal overall probability would result in a success rate of 21%. Using the computed success rates, the CM alerts on an alert list can be rank-ordered, thereby providing the dairy farmer information about which cows have the highest priority for visual inspection for CM.     

Automatic detection of lameness in dairy cattle—Vision-based trackway analysis in cow's locomotion

The occurrence of lameness in dairy cattle is of increasing importance in herd health management and herd productivity. Current practice, involves visual observation by human experts to score cow's locomotion in order to estimate the lameness in the herd. The trackway defined as “hind hoof compared to fore hoof position” is one of the main components to score the locomotion. However, because of the time-consuming observation method, lame cows are undiagnosed until the problem has become severe. Up till now there is no automatic (visual) method for detecting lameness in dairy cattle. The objective of our study was to make an automatic system for continuous on-farm detection and prediction of lameness in the farm by using vision techniques. The current focus was on demonstrating the possibility of capturing cow's hoof locations by vision and strong correlation between automatically calculated hoof trackway and visual locomotion scores. Fifteen selected lactating cows were scored visually by four trained observers at the Gent University Research Farm. Scoring varied from 1 (normal walking) to 5 (extremely lame). Side-view images with resolution of 1024 × 768 pixels were recorded when cows passed an experimental set-up freely. Recorded videos were split into sequences of bitmap images. After background subtraction, binary image operations, calibration and hoof separation, the trackway information containing hoof location in the real world and its related time in the video was calculated. The accuracy of automatically captured results was checked by comparing with the output from manually labeled hoof locations. The mean correlation coefficient of all measurements was 94.8%. Hence, the results suggest that the automatic method by vision analysis is feasible to present the cows’ real locomotion situations. The first result showed a positive linear relationship between cows’ trackways overlap and locomotion scores by human visualization. This research proved that vision techniques have great potential to be used for continuous quantification of lameness in cows.     

Detection of cows with insemination problems using selected classification models

In the present study, the detection of cows with artificial insemination (AI) difficulties using selected statistical and machine learning methods is presented. Cows were divided into two classes: those that conceived after one or two services (“GOOD”) and those that required more than two services per conception (“POOR”). The best performance was exhibited by one of the artificial neural networks (ANN) and the multivariate adaptive regression spline (MARS) method (AIC, BIC, RMS and accuracy); whereas logistic regression (LR) and classification functions (CF) were of somewhat lower quality. The detection of cows with AI difficulties, performed on the basis of the test set comprising new instances, showed that the ANN and MARS were more precise in comparison with the statistical methods. Sensitivity and specificity were over 85% for the perceptron with two hidden layers (MLP2) and MARS and approximately 80% or lower for LR and CF. From among variables determining the AI category, the average calving interval and cow body condition index were the most important. Other significant variables were lactation number, pregnancy length, sex of calf from previous calving and cow age. The prognoses obtained using ANN and MARS can be used for the appropriate preparation of cows for AI.     

立体栖架散养蛋鸡行为加速度信号降噪方法比较分析

针对采用姿态传感器监测散养蛋鸡行为过程中存在加速度信号易受噪声干扰,不同行为加速度信号特征尚不清晰的问题,以立体栖架散养蛋鸡的三维空间行为为目标,在构建蛋鸡穿戴式行为监测系统,获取不同行为加速度信号的基础上,研究小波阈值、CEEMDAN、CEEMDAN结合小波阈值对加速度信号的降噪效果,分析蛋鸡6种典型行为活动的加速度信号特征。结果表明:1)小波史坦无偏似然估计(Rigrsure)阈值的降噪效果更好,降噪后信号的信噪比(SNR)为17.613 2,均方根误差(RMSE)为0.045 0;2)根据X、Y轴加速度标准差分布特征,可将蛋鸡三维空间行为活动强度由低到高分为趴卧和站立、采食和饮水、行走、跳跃4类,各类行为活动的加速度信号标准差差异极显著(P<0.001)。本研究表明,小波Rigrsure阈值法在对蛋鸡空间行为活动加速度信号进行降噪的同时可以保留更多的有效信息,可根据加速度标准差对蛋鸡典型行为的活动水平进行分类识别。     

口服理囊散治疗卵泡囊肿奶牛B超影像学研究

旨在研究口服理囊散对卵泡囊肿奶牛卵巢和子宫形态学指标变化的影响,探讨理囊散治疗卵泡囊肿的作用机理。通过直肠检查结合B超对卵泡囊肿奶牛做出诊断后,对囊肿奶牛口服理囊散,运用B超每3d测量1次囊肿卵泡直径、卵巢长、卵巢宽、子宫角纵径和子宫颈纵径,并与灌药前进行对比。结果显示,32头卵泡囊肿奶牛口服理囊散后,治疗有效者28头,治疗有效率为87.5%;囊肿卵泡直径在口服理囊散的第4天显著减小(P<0.05),灌药后第7天达到正常,部分奶牛发情并排卵;囊肿卵巢的长宽和口服理囊散前相比差异不显著(P>0.05),但均达到正常卵巢大小;子宫角纵径在口服理囊散后第16天下降显著P<0.05),其余时间不显著(P>0.05);子宫颈纵径在口服理囊散后变化不显著(P>0.05),但均低于灌药前。说明B超是诊断卵泡囊肿的有效手段,理囊散对卵泡囊肿奶牛卵巢和子宫形态学变化具有一定的作用,对治疗卵泡囊肿奶牛也有明显效果。     

Real-time automatic lameness detection based on back posture extraction in dairy cattle: Shape analysis of cow with image processing techniques

In this paper results on utilizing image analysis techniques towards early lameness detection in dairy cattle are presented. Data from two different dairy farms in Belgium were gathered. Preprocessing on raw data is required because of non-predictable behaviours of cows such as stopping for a while in front of the camera or non-uniform walking behaviour during experiments. Prelocalization of cow in each frame has been done based on two steps separation: (1) A coarse estimation of moving objects was obtained through background subtraction, (2) second statistical analysis of intensities in gray-scale image along with binarization was utilized to detect moving object in video. A common problem in on-farm collected videos is the similarity of the background and the cow's body colour since the use of classic algorithms for segmentation purposes does not work. Here a hierarchy background/foreground exaggeration is proposed to segment the cow in each frame and track it in video. The combination of logarithm and exponential, background subtraction as well as statistical filtering are used to find the accurate shape of the cow. Furthermore, the back posture of each cow during standing and walking was extracted automatically. It was done by detecting the arc of back posture and fitting a circle through selected points on the spine line. The average inverse radius of four frames displaying the hind hoofs in contact with the ground (two frames for each hoof in a row) was assigned to the cow. Based on this curvature value, a score representing the status of lameness in the individual cow was given automatically. Experimental results from two different databases show promising results in automatic lameness detection based on back posture information.     

Comparison of segmentation algorithms for cow contour extraction from natural barn background in side view images

Computer vision techniques are a means to extract individual animal information such as weight, activity and calving time in intensive farming. Automatic detection requires adequate image pre-processing such as segmentation to precisely distinguish the animal from its background. For some analyses such as gait analysis, a side view perspective is recommended. When using a side view angle however, the background is more difficult to control – moving objects, such as other animals may negatively impact successful image segmentation. The objective of this research was to evaluate five different background segmentation algorithms on side view images when taken against a static background (a solid transportable wall) and a dynamic background (open air, without a wall).The experiments were conducted on a commercial robotic-milking dairy farm in Israel with a herd size of 70 Israeli Holstein cows. A side view image of cow’s gait was recorded after milking when the cows exited the milking area and returned to the cowshed. From the recording database, a random selection was made of 35 frames containing a static background (solid wall) and 20 frames containing a dynamic background (natural barn environment with other cows).Five segmentation algorithms were chosen and adapted from literature to extract the cow shape from the image. The output of three algorithms gave the cow’s full body shape two identified only the contour of the cow’s body. The algorithms were compared on their ability to correctly identify the cow’s back contour line. The performance of each algorithm was quantified by comparing its outputs to a golden standard of manually labelled cow pixels in the image.The introduction of a physical wall behind the cows (static background) significantly improved the foreground segmentation results (Mean Absolute Error (MAE) = 6.7 ± 5.7 pixels vs. 19.7 ± 9.1 pixels). The fourth algorithm, based on an edge detection on the background difference frame, gave the best cow back contour line segmentation results (b₀ = −0.4 ± 15.5 and b₁ = 1.00 ± 0.07). The fifth algorithm which is based on consecutive frame differences was less accurate than the other four methods which are based on the background frame differences (MAE = 16.0 ± 5.9 pixels vs. 4.1 ± 2.2 pixels, 4.3 ± 2.2 pixels, 5.6 ± 2.8 pixels and 3.7 ± 1.4 pixels respectively for the other four algorithms). The results show that the applied algorithms were not robust enough to work on side view images with dynamic backgrounds.