• EI
    • CSA
    • CABI
    • 卓越期刊
    • CA
    • Scopus
    • CSCD
    • 核心期刊

奶牛乳房炎自动检测技术研究进展

初梦苑, 刘晓文, 曾雪婷, 王彦超, 刘刚

初梦苑，刘晓文，曾雪婷，等. 奶牛乳房炎自动检测技术研究进展[J]. 农业工程学报，2023，39（11）：1-12. DOI: 10.11975/j.issn.1002-6819.202303143
引用本文: 初梦苑，刘晓文，曾雪婷，等. 奶牛乳房炎自动检测技术研究进展[J]. 农业工程学报，2023，39（11）：1-12. DOI: 10.11975/j.issn.1002-6819.202303143
shu
CHU Mengyuan, LIU Xiaowen, ZENG Xueting, et al. Research advances in the automatic detection technology for mastitis of dairy cows[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(11): 1-12. DOI: 10.11975/j.issn.1002-6819.202303143
Citation: CHU Mengyuan, LIU Xiaowen, ZENG Xueting, et al. Research advances in the automatic detection technology for mastitis of dairy cows[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2023, 39(11): 1-12. DOI: 10.11975/j.issn.1002-6819.202303143
shu

奶牛乳房炎自动检测技术研究进展

  • 1.

    中国农业大学智慧农业系统集成研究教育部重点实验室，北京 100083

  • 2.

    中国农业大学农业农村部农业信息获取技术 重点实验室，北京 100083

基金项目: 国家重点研发计划项目（2021YFD1300502）
详细信息
    作者简介:

    初梦苑，博士生，研究方向为基于机器视觉的奶牛健康养殖应用。Email：cmy@cau.edu.cn

    通讯作者:

    刘刚，博士，教授，博士生导师，研究方向为电子信息技术在农业中的应用。Email：pac@cau.edu.cn

  • 中图分类号: S818;S811.2;S24

Research advances in the automatic detection technology for mastitis of dairy cows

  • 1.

    Key Laboratory of Smart Agriculture Systems Integration, Ministry of Education, China Agricultural University, Beijing 100083, China

  • 2.

    Key Laboratory of Agricultural Information Acquisition Technology, Ministry of Agriculture and Rural Affairs, China Agricultural University, Beijing 100083, China

HTML全文

    摘要
  • 摘要:

    奶牛乳房炎是影响奶牛健康的主要疾病之一，发病率高、发病范围广、经济损失严重。目前奶牛乳房炎的检测大多是采集奶牛乳汁进行理化性质检测，该方法对检测环境有着较高要求，且检测周期长。随着信息技术的迅速发展，奶牛乳房炎的自动检测技术取得了较好的研究成果。该研究根据数据的传感器类型，从视觉传感器、自动挤奶系统与其他传感器3个方面阐述了奶牛乳房炎自动检测的研究进展。基于视觉传感器的奶牛乳房炎自动检测方法包括基于乳房热红外图像和基于乳汁图像的检测方法，该方法较大程度上保障了动物福利，但检测精度有待提升；基于自动挤奶系统（automatic milking systems, AMS）的奶牛乳房炎自动检测方法利用AMS获取乳汁信息，然后构建乳房炎检测模型，该方法检测误差较小，但成本较高；基于其他传感器的奶牛乳房炎检测方法采用独立研发的传感器获取乳汁数据，预测乳房炎发病情况，该方法操作简便，但使用不同传感器构建的检测模型精度差异较大。该文还探讨了目前奶牛乳房炎自动检测领域存在的精度低、实时性差、自动化不足等问题，并展望了该领域未来的发展趋势，以期为开展奶牛乳房炎自动检测技术与方法研究提供参考。

    Abstract:

    Cow mastitis is one of the most serious diseases in the healthy development of dairy farming, due to the high incidence and wide range of characteristics. Mastitis in dairy cows can also reduce milk production and quality, leading to human health and herd turnover costs. Dairy cows with clinical mastitis vary greatly in the abnormal changes in their udders and milk. In the case of subclinical mastitis, there is no outstanding appearance in the udder and milk, where the economic loss is more severe than before. Physical and chemical property testing has been widely used to collect the milk for the diagnosis of mastitis in dairy cows at present. However, the testing environment and the long testing period cannot fully meet the demand for the rapid and real-time diagnosis of mastitis in dairy cows. Fortunately, advanced electronic information technology and equipment have been widely used in the field of agriculture in recent years. The automatic detection of dairy cow mastitis has achieved better research for the high requirements. In this review, the current research progress was introduced into the automatic detection of dairy cow mastitis, according to the different types of sensors in the data acquisition. Three aspects were also included: the visual sensor, the automatic milking system (AMS), and the rest sensors. Firstly, the automatic detection of dairy cow mastitis with the vision sensor was divided into the detection with the udder thermal infrared and the milk images. Automatic detection was achieved in mastitis in dairy cows without damage and stress. Especially, the mastitis detection with the thermal infrared images shared the animal welfare, but the detection accuracy needed to be improved during this time. Mastitis detection with the milk images was achieved with high accuracy during lactation somatic cell count (SCC) detection. But it was still lacking in the test trials on the accuracy of mastitis detection in dairy cows. Secondly, the AMS was often used to collect milk information in the automatic detection of dairy cow mastitis. The local data or manually recorded individual information of dairy cows were then combined to construct the detection model of dairy cow mastitis using machine learning classification. The automation and efficiency of mastitis detection were greatly improved, as well as the accuracy of detection. However, the AMS was easy to cause injury to the dairy cow's udder during milking, even to the animal welfare and the high cost. Finally, a sensor or multi-sensor system was developed using the rest sensors. A mastitis detection model was constructed using machine learning. The milk or udder data was also obtained to verify, according to the mastitis characteristics and the changes in milk physical and chemical properties. The detection can be expected to fully meet the harsh needs of the rapid and accurate detection of mastitis in dairy cows, due to the low cost and simple operation. Different types of sensors were used to detect mastitis in dairy cows, where the accuracy was quite different. As such, a critical review was proposed on the current progress of accuracy, real-time, and sufficient automation in the detection of mastitis in dairy cows. The future trend was also given to important technical support for future research on the automatic detection of mastitis in dairy cows.

    • HTML全文

  • 0.   引　言

    随着人民生活水平的不断提高，乳制品的需求日益增长[1-2]。而乳房炎、子宫内膜炎、口蹄疫与跛足等奶牛疾病的发生，不仅降低产奶量、损害牛奶质量，还影响人类身体健康、增加牛群更替成本[3]。其中，乳房炎发病率高、发病范围广，是造成养殖场经济损失较为严重的疾病之一[4-5]。奶牛乳房炎最常用的分类方法由美国国家乳房炎委员会（American national mastitis committee, ANMC）提出，该方法根据奶牛乳房及乳汁有无肉眼可见变化，将乳房炎分为临床型乳房炎（clinical mastitis, CM）与非临床型乳房炎（nonclinical or subclinical mastitis, SCM），即隐性乳房炎[6-7]。根据临床症状与乳汁变化程度，CM又可分为最急性、急性、亚急性和慢性乳房炎[8]。根据国际奶业联合会的统计，世界上所有存栏奶牛中至少有1/3患有各类乳房炎，奶牛临床型乳房炎发病率是2%，隐性乳房炎发病率为50%[9-12]。国内临床型乳房炎头发病率约为5.38%，乳区发病率约为1.65%；隐性乳房炎头发病率约为59.36%，乳区发病率约为31.62%[13-18]。全球每年因乳房炎造成的经济损失高达350亿美元，仅美国的损失就达20亿美元[19-24]。奶牛乳房炎发病原因主要有病原微生物感染、环境与管理不当、奶牛自身因素等[25-27]。临床型乳房炎主要根据奶牛乳房和乳汁是否出现肉眼可见的异常变化进行诊断，如乳房红肿坚硬、产奶量下降、乳汁稀薄且混有絮状物[28]。而隐性乳房炎乳房和乳汁在外观上肉眼不可见，因此经济损失更为严重[29]。目前养殖场诊断奶牛隐性乳房炎的方法主要有乳汁体细胞计数（somatic cell count, SCC）[30-31]、加州乳房炎试验（California mastitis test, CMT）[32]、乳汁pH值检查[33]、乳汁电导率检查[34]、乳汁酶学检查与病原学诊断等[35]。上述检测方法虽然能较准确地筛查奶牛乳房炎，但通常工作量大，检测周期长，且奶样对检测环境有着较高的要求，难以满足养殖场快速实时诊断奶牛乳房炎的需求。

    近年来，随着信息技术的迅速发展，先进的电子信息技术装备被广泛应用于工业、农业、医疗与制造业等领域[36]。在农业信息化领域，智慧养殖是指利用各种传感器技术、人工智能技术、环境监测技术、环境控制技术、无线通讯技术与大数据技术等，集成畜禽生理疾病信息的智能监测与预警、畜禽行为智能监测、精准饲喂与智能环境控制等于一体的养殖系统[37]。智慧养殖能够为畜禽打造健康、舒适、安全的生活环境，为养殖者提供高效、可靠和综合的管理手段，全面提升养殖数字化与智能化水平[38]。奶牛乳房炎自动检测技术一般指利用红外热成像技术、机器视觉技术、传感器技术、机器学习技术或数据分析技术等，对获取的奶牛热图像、奶样、乳房信息、奶牛个体信息等进行综合分析与处理，诊断奶牛是否患有乳房炎以及患病程度的过程[39-41]。

    目前已有较多国内外研究学者对奶牛乳房炎进行自动化检测，并取得了丰硕成果。奶牛乳房炎自动检测研究利用传感器或多传感器系统，采集奶牛乳房或乳汁信息，使用数据分析与机器学习方法，构建乳房炎检测模型。根据奶牛乳房炎自动检测所采用的传感器类型，本文主要从基于视觉传感器、自动挤奶系统和其他传感器的奶牛乳房炎自动检测技术3个方面展开介绍，分析当前阶段奶牛乳房炎自动检测面临的主要技术问题与挑战，并展望未来研究的重点与发展趋势，以期为开展奶牛乳房炎自动检测技术与方法研究提供参考。

    1.   基于视觉传感器的奶牛乳房炎检测技术

    机器视觉一般指使用非接触式光学传感设备，采集被测目标的图像信息，并对图像信息进行分析、处理与计算，得到被测目标的形态、颜色、纹理等特征数据，进而根据特征数据进行判断与决策[42-43]。基于视觉传感器的奶牛乳房炎自动检测技术通常是借助热像仪、显微镜、可见光相机等数据采集设备，获取奶牛乳房区域热图像、奶样体细胞图像或奶样pH测试纸图像，再利用机器视觉等技术，对原始图像数据进行分析处理，最后对奶牛乳房炎患病情况进行诊断，如图1所示。近年来较为典型的基于视觉传感器的奶牛乳房炎自动检测技术相关研究成果如表1所示。

    图  1  基于视觉传感器的奶牛乳房炎检测技术示意图
    Figure  1.  Sketch map of mastitis detection technology in dairy cow based on visual sensors
    下载: 全尺寸图片 幻灯片
    表  1  基于视觉传感器的奶牛乳房炎检测技术
    Table  1.  Researches on mastitis detection technology in dairy cow based on visual sensors
    年份
    Year    		采集设备
    Collecting equipment    		技术方法
    Technical methods    		特征
    Features    		研究结果
    Research results    		文献
    Literature
    2019FLIR A615热像仪数字图像处理眼乳温差临床型乳房炎检测准确率87.5%，隐性乳房炎准确率33.3%[44]
    2019ThermaCAM B20 HSV热像仪数字图像处理乳房温度乳房炎检测敏感性93.75%，特异性94.96%[45]
    2020FLIR A615热像仪数字图像处理
    深度学习    		眼乳温差乳房炎检测准确率83.33%[46]
    2021FLIR A615热像仪深度学习眼乳温差乳房炎检测精度77.3%[47]
    2021MAG62热像仪数字图像处理
    深度学习    		眼乳温差临床型乳房炎检测准确率91.4%， 隐性乳房炎检测准确率85.3%[48]
    2022Fotric-625c热像仪数字图像处理
    数据分析    		乳区温度分布
    拟合线斜率    		健康乳区识别精度76%，患病乳区识别精度75%[49]
    2022Guide C400M热像仪数字图像处理
    数据分析    		乳房温度−[50]
    2022FLIR A310热像仪深度学习眼乳温差
    双乳温差    		乳房炎检测准确率87.62%[51]
    2023FLIR A310热像仪深度学习热图像纹理、
    色彩、结构    		乳房炎检测准确率88.4%[52]
    2015显微镜数字图像处理体细胞数与人工SCC相比，乳房炎检测准确率99.7%[53]
    2017Logitech5000 USB相机、pH试纸数字图像处理体细胞数与高精度SCC相比，乳房炎检测平均相对误差为3.67%[54]
    2020数码显微镜数字图像处理体细胞数与高精度SCC相比，乳房炎检测最大偏差低于8%[55]
    下载: 导出CSV 
    | 显示表格

    1.1   基于乳房热红外图像的奶牛乳房炎检测

    红外热成像（infrared thermography, IRT）技术可探测物体发出的中长波红外辐射，并将其转换为温度数据，从而生成物体热分布可视化的数字图像或视频。目前，越来越多的学者利用IRT技术，评估农场牲畜的生育能力、新陈代谢、疼痛以及疾病监测[56-58]。奶牛乳房炎是当乳腺受到病原体侵袭以及理化因素刺激时，乳房区域所发生的炎症反应[59]。奶牛乳房区域存在炎症时，血流会发生相应变化，炎症区域皮肤表面温度升高。因此，较多研究借助热像仪测量奶牛乳房表面温度，并观测其温度变化，从而进行奶牛乳房炎的检测。

    有些研究通过观测奶牛乳房皮肤表面温度以及变化，来检测乳房炎发病情况。WATZ等[45]将大肠杆菌注入健康奶牛体内诱发乳房炎，然后利用热像仪从奶牛后侧拍摄热红外数据，使用图像识别软件自动检测奶牛后侧乳房区域，并计算热图像中乳区最大温度。该研究利用IRT技术，根据奶牛乳房最大温度自动检测乳房炎，敏感性为93.75%，特异性为94.96%。郭艳娇等[49]提出了一种基于热图像的奶牛乳房温度分布测量与乳房炎检测方法。该方法可自动识别奶牛左右后乳区，通过线剖法建立奶牛乳区温度分布拟合方程，根据温度拟合线斜率的正负进行奶牛乳房炎的识别，与CMT真值相比，健康乳区识别精度为76%，患病乳区识别精度为75%。该研究首次将奶牛乳区温度分布拟合线斜率作为乳房炎特征，取得了较好的检测效果，为基于乳房图像的乳房炎检测提供了新思路。KHAKIMOV等[50]利用IRT研究了奶牛乳房炎，与产奶量和乳房皮肤表面温度之间的关系。研究结果表明，患乳房炎乳区的皮表温度与产奶量之间显著相关（线性皮尔逊相关系数（linear Pearson correlation coefficient, LPCC）为−0.96），健康乳区皮表温度与产奶量之间没有显著关系（LPCC为0.16）。该研究还将皮表温度范围为32～36 °C的乳区判定为健康乳区，皮表温度为36.1～39 °C范围内的乳区判定为患病乳区，该方法证实了根据奶牛乳房皮表温度快速评估牛群乳房炎感染情况的可行性。但是，只根据奶牛乳房皮表温度及变化诊断是否患有乳房炎，结果易受养殖场环境、季节、奶牛个体特异性等因素影响。

    此外，奶牛患乳房炎时，患病乳房局部区域温度升高，奶牛体核温度不变，而奶牛眼睛温度可以较好地反映直肠温度。因此，奶牛眼睛与乳房温度之间的差异在一定程度上可以反映奶牛患病情况。张旭东等[44]利用传统数字图像处理方法进行奶牛眼睛与乳房的自动定位，然后根据奶牛眼乳温差判断奶牛是否患有乳房炎。在奶牛眼乳定位研究中，该研究基于热图像中HSV（hue, saturation, value）颜色特征与骨架特征，自动检测奶牛眼睛位置。利用基于骨架特征的支持向量机（support vector machine, SVM）分类技术，自动检测奶牛乳房位置。预测结果与SCC检测结果进行对比，CM检测准确率为87.5%，SCM准确率为33.3%。随着人工智能的快速发展，深度学习技术越来越多地应用于畜牧自动监测领域。ZHANG等[46]提出了一种基于热图像双边滤波增强的深度学习网络EFMYOLOv3（enhanced fusion mobileNetV3 YOLOv3）[60]，用于自动检测热图像中奶牛眼睛与乳房位置，如图2所示。在定位奶牛热图像中眼睛与乳房之前，使用基于灰度直方图的双边滤波图像增强算法增强热图像细节，提高了前景与背景之间的对比度，最后根据热图像中自动提取的奶牛眼乳温差来判断奶牛是否患有乳房炎，并将诊断结果与SCC结果对比。该乳房炎分类算法准确率、敏感性和特异性分别为83.33%、92.31%和76.47%。王彦超等[47]为提高奶牛乳房炎检测精度，在YOLOv3-tiny网络中增加了4个残差结构和3个压缩激励（squeeze and excitation，SE）模块，并对激活函数进行改进，利用改进后的YOLOv3-tiny网络进行奶牛眼睛与乳房的定位，根据自动检测的奶牛眼乳温差来判定是否患有乳房炎，奶牛乳房炎的检测精度为77.3%。宋子琪[48]使用YOLOv4模型进行奶牛眼睛与乳房部位的自动检测，眼睛检测平均精度（Average precision, AP）比使用传统图像处理方法提高了3.6%，乳房检测AP值提高了12.65%。根据奶牛眼乳温差进行乳房炎的分级，奶牛CM检测准确率为91.4%，特异性为80%，敏感性为93.3%。用奶牛眼睛与乳房温度差值检测乳房炎，虽在一定程度上避免了奶牛个体特异性对检测结果的影响，但奶牛眼睛温度与体核温度仍有一定差距，用奶牛眼睛温度代替直肠温度，容易造成乳房炎检测误差累积。

    图  2  基于IRT与深度学习的奶牛关键部位检测[46]
    Figure  2.  Key parts detection of dairy cows based on IRT (infrared thermo graphy) and deep learning[46]
    下载: 全尺寸图片 幻灯片

    METZNER等[61]将大肠杆菌注入奶牛右后肢诱发乳房炎，并利用IRT技术观测奶牛左右乳房温差。由热红外图像可以检测到诱发乳房炎的乳区与未感染乳房炎的乳区，且最大温度差异显著。因此，可以根据奶牛两侧乳房温差来检测乳房炎。但是当奶牛左右两侧乳房同时患有乳房炎时，两侧乳房温度差异较小，可能造成乳房炎的误诊。因此，WANG等[51]提出了一种基于热图像的奶牛乳房炎综合检测新方法，该方法使用YOLOv5深度学习网络[62]自动获取奶牛眼睛与乳房位置信息，并提取眼区与乳区最大温度，综合对比奶牛左右两侧乳房皮表温差与眼乳温差，从而进行乳房炎的诊断。结果表明，该研究检测奶牛乳房炎准确性、特异性和敏感性分别为87.62%、84.62%和96.30%，该方法可有效减少环境、个体特异性等因素的干扰。

    随着深度学习在机器视觉领域的快速发展，有研究者将图像分类技术应用于奶牛乳房炎的自动检测，实现了“一步式”奶牛乳房炎检测。张倩等[52]拼接奶牛眼睛与乳房热红外图像，并基于融合数据增强方法提升检测模型鲁棒性，最后改进ResNet34网络用于奶牛乳房炎分类模型的构建，检测准确率为88.4%。该方法不仅提高了奶牛乳房炎的检测精度，还缩短了分类时间，有效避免了前人研究中“多步式”造成的误差累积。但该研究未深入探明ResNet34网络用于热图像中乳房炎检测所使用的特征，后续研究应详细分析网络机理，提取更丰富的乳房炎特征，以提高乳房炎检测精度。

    基于热红外图像的奶牛乳房炎检测方法可以无接触、无应激地检测奶牛乳房患病情况，并且可以实时获取检测结果，较大程度地保障了动物福利。但是，利用热像仪拍摄的奶牛乳房热图像，仅反映了乳区皮肤表面温度分布，而皮表温度容易受到环境干扰，造成乳房炎检测精度不高。

    1.2   基于乳汁图像的奶牛乳房炎检测

    基于乳汁图像的奶牛乳房炎检测主要是指对奶牛乳汁的显微图像、pH试纸图像等进行分析与处理，然后构建奶牛乳汁SCC预测模型，根据自动计算的乳汁中体细胞数评估奶牛乳房炎患病情况[63]。

    在基于乳汁显微图像的奶牛乳房炎检测方面，DE MELO等[53]将奶牛乳汁原始RGB显微图像改为Lab颜色空间，应用K均值聚类算法去除图像中碎片与其他背景，通过分水岭变换分离剩余的边界细胞，然后对图像中体细胞进行计数。所提方法与人工计数对比，该方法能够以99.7%的准确率自动计算显微镜载玻片图像中细胞数量。GAO等[55]为快速测定奶牛乳汁中体细胞数，开发了一种基于视觉的乳汁体细胞计数仪。该仪器能够自动获取载玻片的显微图像，并使用霍夫变换对显微图像进行校准，然后建立离散优化模型确定图像分割阈值，最后采用最小二乘圆法检测乳汁体细胞圆度，通过递归算法实现体细胞的自动计数。该细胞计数仪与丹麦FossMatic 5000高精度乳汁SCC仪的检测结果进行对比，最大偏差低于8%，验证了该仪器的适用性。

    在基于乳汁pH试纸图像的奶牛乳房炎检测方面，蔡一欣等[54]为解决奶牛隐性乳房炎难以防治等问题，提出利用可见光相机采集奶牛乳汁pH试纸图像，融合颜色特征与形态学处理方法，分割试纸中化学反应区并获取RGB值，最后使用幂回归法建立RGB值与乳汁SCC的预测模型，并基于Android技术在便携式移动终端开发了奶牛乳房炎快速检测系统。根据养殖场实测的20组乳汁SCC进行对比，该估测方法平均相对误差为3.67%，标准差为1.88%，可满足养殖场奶牛隐性乳房炎的快速检测。

    基于乳汁图像的奶牛乳房炎检测相关研究，通常检测乳汁SCC精度较高，但大多研究没能将所提方法用于实际养殖环境中的奶牛乳房炎检测，即乳房炎检测精度未知。未来研究应注重方法的实际应用，将设计的奶牛乳汁SCC预测模型应用于乳房炎检测，实现奶牛乳房炎的快速精准检测。

    综上所述，基于视觉传感器的奶牛乳房炎检测技术，可以无损无应激地实现奶牛乳房炎的检测，尤其是基于热红外图像的乳房炎检测方法，直接对无接触获取的奶牛乳房热图像进行分析检测，较大程度地保障了动物福利，但基于IRT检测奶牛乳房炎精度通常不高。基于乳汁图像的奶牛乳房炎检测技术，在乳汁SCC检测中取得了较高精度，但大多研究缺少实际检测奶牛乳房炎的相关试验。相较于AMS和其他传感器获取奶牛乳房炎数据，该方法主要优势在于无接触无应激地采集数据，保障了动物福利。但获取的数据较为单一，且图像分析过程增加了误差积累，检测精度不高。

    2.   基于自动挤奶系统的奶牛乳房炎检测技术

    基于自动挤奶系统的奶牛乳房炎检测技术，通常是利用养殖场AMS采集奶牛乳汁信息，并结合本地数据或人工记录的奶牛个体信息，使用机器学习分类方法，构建奶牛乳房炎检测模型，并通过养殖场实际测试，逐步优化检测模型[64-65]。近年来较为典型的基于自动挤奶系统的奶牛乳房炎自动检测技术相关研究成果如表2所示。

    表  2  基于自动挤奶系统的奶牛乳房炎检测技术
    Table  2.  Researches on mastitis detection technology in dairy cow based on AMS (automatic milking systems)
    年份
    Year    		特征
    Features    		技术方法
    Technical methods    		研究结果
    Research results    		文献
    Literature
    2001电导率（electric conductivity, EC）、产奶量线性回归乳房炎检测特异性98%，敏感性100%[66]
    2008EC、RGB、产奶量线性回归−[67]
    2009前奶EC线性回归乳房炎检测敏感性68%～88%[68]
    2010产次、产奶天数、季节、体细胞数等贝叶斯网络−[69]
    2010EC、RGB、警报原因、警报次数等朴素贝叶斯网络临床型乳房炎假阳警报减少35%[70]
    2013泌乳等级、产奶量、EC、季节等支持向量机乳房炎检测敏感性89%，特异性92%[71]
    2014产奶量变化协同控制临床型乳房炎检测敏感性63%[72]
    2019氧浓度混合线性模型隐性乳房炎检测敏感性84%，特异性46%[73]
    2020EC、奶牛活动量、反刍、产次逻辑混合模型隐性乳房炎检测ROC曲线下方面积（area under curve, AUC）0.92[74]
    2022体细胞数、EC、产次、产奶量等梯度增强慢性乳房炎检测准确率88.8%[75]
    2022EC、产奶量等广义线性混合模型临床型乳房炎检测敏感性最高78%，特异性最高97%[76]
    下载: 导出CSV 
    | 显示表格

    AMS是乳品行业中最关键技术之一[77]。AMS不仅可以代替人工挤奶与传统挤奶系统，还是管理奶牛健康、提升生产效率的一种通用方法[78]。2020年全球AMS使用数量约5万个，主要集中在欧洲（90%）、加拿大（9%）以及其他国家（1%）[79-80]。AMS作业时，内部嵌入的乳汁传感器可以自动检测乳汁中体细胞数、电导率、乳糖与脂肪等成分的含量，这些数据都是奶牛乳房炎检测的重要指标[81]。由于AMS可以自动、快速、准确地获取乳汁中关键信息，较多研究学者利用AMS获取奶牛乳汁信息构建乳房炎检测模型。

    基于AMS的奶牛乳房炎检测在研究初期多采用简单的线性回归方法，根据SCC、EC与产奶量等常规指标进行奶牛乳房炎患病状况的预测[82]。DEMOL等[66]基于AMS设计了一个奶牛乳房炎自动检测模型，该模型主要包括牛奶产量和EC两个变量的时间序列，通过线性回归更新参数值和残差方差。当残差超出设定置信区间时，模型发出乳房炎警报。使用构建的最优乳房炎检测模型，测试25头奶牛的29 033次挤奶样本，特异性为98%，敏感性达到100%。该模型检测精度较高，但测试的奶牛样本数量较少，无法验证该方法在实际乳房炎检测中的普适性与准确性。KAMPHUIS等[67]分析来自AMS中的传感器数据，包括乳汁EC、RGB值以及牛奶产量，通过计算相关系数和信息增益比评估各项参数在预测异常乳汁和CM中的重要性。经测试与计算，最重要的参数为乳汁EC、蓝色与绿色通道值，该研究将上述参数作为奶牛乳房炎与异常乳汁检测的潜在预测变量，但并未利用潜在预测变量构建乳房炎检测模型。CLAYCOMB等[68]在AMS下方约1.5 m处长奶管中安装单个传感器测量奶牛前奶EC，通过控制常规集群内单个乳头的脉动，实现4个乳房之间乳汁的有序分离，使用4个乳房乳汁的EC值作为奶牛乳房炎患病状态判断的主要指标。经现场试验测试，1000次挤奶样本中乳房炎检测敏感性范围为68%～88%。

    随着人工智能的快速发展，基于AMS的奶牛乳房炎检测研究使用SVM、贝叶斯网络等机器学习方法对奶牛乳房炎进行诊断[83-85]。MAMMADOVA等[71]使用SVM技术，根据来自AMS的奶牛数据（泌乳等级、产奶量、EC、平均挤奶时间、季节），计算奶牛乳汁中SCC，并依据SCC值预测奶牛是否感染乳房炎[86]。该方法对奶牛乳房炎检测的敏感性为89%，特异性为92%。HUYBRECHTS等[72]提出将协同控制概念引入奶牛乳房炎检测中，协同控制可以对多传感器输出数据进行实时建模并减小建模值残差。该研究基于产奶量变化数据，开发并测试了协同控制模型用于奶牛乳房炎的早期检测，检测CM敏感性为63%。该研究首次将协同控制技术应用于奶牛乳房炎检测，但检测精度不高，后续研究可以融合多模态数据构建多特征的奶牛乳房炎检测模型。BONESTROO等[75]开发了一种基于传感器和梯度增强分类器的奶牛慢性乳房炎检测模型，该模型使用SCC、EC、乳汁中血液含量、产次、乳汁分流、挤奶间隔时间、产奶量和产奶天数预测奶牛慢性乳房炎，其中SCC、EC与乳汁中血液含量数据来自AMS。该模型利用7个奶牛养殖场的传感器数据进行训练，利用其他7个养殖场的数据对模型性能进行测试。试验结果表明，该模型对奶牛慢性乳房炎检测的准确率为88.8%，马修斯相关系数（Matthew’s correlation coefficient, MCC）为71.2%，AUC为96.4%。BAUSEWEIN等[76]指出不同制造商开发的AMS检测奶牛CM精度不同，以德国南部巴伐利亚奶牛群作为试验对象，当地AMS检测CM敏感性在31%～78%之间，特异性在79%～97%之间。

    上述研究都是根据AMS的乳汁SCC、EC、产奶量与产次等数据对乳房炎患病进行预测。还有一些研究提出使用奶牛活动量、乳汁氧浓度等指标检测乳房炎，也取得了较高检测精度[87-88]。WITTEK等[73]提出利用乳汁中氧浓度（oxygen concentrations, OC）预测奶牛乳房炎感染情况。根据氧浓度预测乳房炎的依据是，奶牛乳汁中细胞会消耗氧气，SCC的增加将导致OC降低。因此，该研究通过分析乳汁OC与SCC的关系，验证OC检测SCM的可行性。经过对690份奶牛乳汁样本的分析与检测，发现OC随着SCC的增加而降低，而EC显著增加。利用OC检测奶牛SCM敏感性为84%，特异性为46%，AUC为0.72。KHATUN等[74]为确定养殖场中自动挤奶系统检测奶牛SCM的可行性，根据乳汁EC，与使用热量和反刍-长距离标签记录的每日活动和每日反刍相对变化预测当季SCM。研究表明，结合奶牛乳汁EC、活动变化、SCM发生前反刍变化和产次所构建的联合模型，SCM预测性能最优，平均AUC为0.92。

    上述基于AMS进行奶牛乳房炎检测的研究，都能够较好地为养殖户提供乳房炎预警数据，即筛选出养殖场中可能患有乳房炎的奶牛。但预警数据中，所有奶牛患乳房炎的概率相同，无法从列表中判断奶牛患病优先级[89]。因此，STEENEVELD等[69]根据奶牛个体信息（产次、产奶天数、季节、SCC历史数据以及乳房炎病史等数据），结合AMS检测奶牛乳房炎的敏感性和特异性，构建基于贝叶斯网络的奶牛乳房炎警报列表排序模型。该模型的构建对目前基于AMS的奶牛乳房炎检测技术提供了新的研究方法与思路。同时，STEENEVELD等[70]在上述研究基础上，根据奶牛个体信息与来自AMS的警报信息（乳汁EC、警报原因、乳汁颜色是否异常、与预期产奶量的偏差以及96小时内警报次数），基于朴素贝叶斯网络，区分来自AMS警报列表中的真阳数据与假阳数据[90]。试验结果表明，奶牛乳房炎警报列表上的假阳警报有效减少了35%。

    综上所述，基于AMS的奶牛乳房炎检测技术，利用集成式AMS挤奶同时自动检测并分析乳汁中各成分含量及理化指标，乳房炎检测的自动化程度和精度较高[91]。当检测到奶牛乳汁异常时，可及时对异常牛奶进行分流处理，并预警患病奶牛信息。目前国内奶牛养殖主要以小规模的散户饲养为主，大型化、规模化的养殖场较少，而AMS成本较高，国内虽有少数大型养殖场引入AMS，但仍未见基于AMS的奶牛乳房炎检测相关研究的报道。此外，AMS挤奶完成后，通过拉力作用从奶牛身上抽出，容易造成奶牛乳房皮肤损伤，从而导致乳房出血、产奶量降低、乳房炎发生等问题，损害动物福利[92-93]。

    3.   基于其他传感器的奶牛乳房炎检测技术

    除了借助视觉传感器与AMS检测奶牛乳房炎的方法外，还有较多研究者根据奶牛乳房炎发病特征与乳汁理化性质变化，研发了专门用于奶牛乳房炎检测的传感器或多传感器系统。基于其他传感器的奶牛乳房炎检测方法，根据传感器采集的奶牛个体数据，利用机器学习分类算法构建奶牛乳房炎检测模型，如图3所示。相比于AMS，该类传感器或系统一般检测方法较为简单，成本也更低。近年来基于其他传感器的奶牛乳房炎自动检测技术相关研究成果如表3所示。

    图  3  基于其他传感器的奶牛乳房炎检测技术示意图
    Figure  3.  Sketch map of mastitis detection technology in dairy cow based on other sensors
    下载: 全尺寸图片 幻灯片

    有些研究根据奶牛乳房炎发病后乳汁理化性质的变化，设计了用于乳汁分析的传感器，并根据乳汁EC、pH、蛋白质以及乳糖等特征信息构建乳房炎检测模型。李晋阳等[94]根据奶牛感染乳房炎后乳汁EC与pH值的变化，研发了一种基于单片机的奶牛乳房炎自动检测仪。该仪器可以安装在AMS中，在挤奶过程中在线监测奶牛患病情况，也可以独立使用，能够实现快速且低成本的奶牛乳房炎检测。当pH阈值设置为6.9，电导率阈值设置为6.5 mS/cm时，CM检测准确率为94%，SCM检测准确率67%。MOTTRAM等[95]设计了一种化学传感器系统以提高奶牛乳房炎检测性能，该传感器系统由一系列化学传感器和数据处理传感器阵列组成，根据被感染腺体与健康腺体乳汁分泌物的差异判断奶牛是否患有乳房炎。利用该传感器系统检测奶牛CM，敏感性和特异性分别为93%和96%。KAMPHUIS等[96]探讨了奶牛乳汁EC和在线复合体细胞计数（in-line composite somatic cell count, ISCC）传感器[102]，在挤奶过程中检测CM。试验结果表明，仅使用EC作为奶牛乳房炎检测工具，检测错误率最高为7.8%，仅使用ISCC检测乳房炎错误率最高为3.7%，而使用模糊逻辑算法结合EC与ISCC检测CM，错误率最高仅为2.1%，检测性能较优。FOSGATE等[97]基于贝叶斯分类模型，利用手持式乳汁电导率仪检测奶牛乳房炎，当EC值超过临界点25 mO/cm时，模型估计奶牛患有乳房炎，奶牛乳房炎检测的敏感性与特异性分别为89.9%和86.8%。ALTAY等[99]使用分类与回归树（classification and regression tree, CART）、卡方自动交互检测（chi-squared automatic interaction detection, CHAID）、穷举卡方自动交互检测（exhaustive chi-squared automatic interaction detection, Ex-CHAID）、快速无偏有效统计树（quick, unbiased, efficient, statistical tree, QUEST）与MARS数据挖掘算法，根据潜在预测因子（包括哺乳次数、产奶天数、乳糖、乳汁颜色与明度、脂肪含量、蛋白质含量、密度、pH值与EC等），预测奶牛乳房炎患病情况。结果表明，CART和MARS算法在区分患病奶牛与健康奶牛时具有较好的分类性能。与CMT结果相比，CART分类方法敏感性为71.6%，特异性为83.9%，准确率为75%，AUC为0.742。MARS分类方法敏感性85.7%，特异性80.9%，准确率83%，AUC0.869。

    表  3  基于其他传感器的奶牛乳房炎检测技术
    Table  3.  Researches on mastitis detection technology in dairy cow based on other sensors
    年份
    Year    		传感器类型
    Sensor type    		特征
    Features    		技术方法
    Technical methods    		研究结果
    Research results    		文献
    Literature
    2007单片机EC、pH值阈值CM检测准确率94%，SCM检测准确率67%[94]
    2007化学传感器乳汁分泌物主成分分析与交叉验证CM检测敏感性93%，特异性96%[95]
    2008体细胞计数仪EC、SCC模糊逻辑CM检测错误率最高2.1%[96]
    2013手持式乳汁电导率仪EC贝叶斯网络乳房炎检测敏感性89.9%，特异性86.8%[97]
    2017测力传感器双侧乳区硬度差异阈值CM检测敏感性62.5%，特异性96.7%[98]
    2022超声波乳汁分析仪脂肪、蛋白质、乳糖、pH值、EC等多元回归自适应样条
    （Multivariate Adaptive
    Regression Splines, MARS）    		乳房炎检测准确率83%[99]
    2022GPS奶牛运动轨迹与社会行为物联网乳房炎预测结果与SCC一致[100]
    2023榨奶系统、项圈、声波传感器产奶量、EC、活动量、反刍时间随机森林乳房炎检测准确率88%[101]
    下载: 导出CSV 
    | 显示表格

    此外，还有研究根据奶牛乳房炎发病前后乳房和个体特征变化，借助相关传感器对奶牛乳房炎患病情况进行预测。REES等[98]使用测力传感器对45头患CM奶牛和95头健康奶牛的乳房硬度进行了客观测定。分析乳房硬度数据发现，相较于上下测量点，奶牛乳房中间测量点硬度最高。而且患有严重CM的奶牛比健康奶牛的乳房硬度更高，患有CM的乳区相较于其他乳区硬度更高。该研究根据奶牛两后腿之间乳房硬度的差异构建奶牛乳房炎检测模型。当硬度差异阈值置为0.425 kg时，AUC为0.817，敏感性为62.5%，特异性为96.7%。FENG等[100]设计了一个基于物联网的奶牛社会行为感知框架模拟奶牛乳房炎的传播，并推断奶牛感染乳房炎的风险。该研究首先为养殖场中每头奶牛安装了便携式GPS，以追踪奶牛活动轨迹。其次，根据奶牛时空接触信息，绘制有向加权的奶牛社会行为图，如图4所示。最后构建奶牛乳房炎传播概率模型，估测奶牛患乳房炎概率。结果表明，该研究根据奶牛患病概率优先级预测结果与SCC一致，验证了所提方法的有效性。赵紫瑄等[101]采用转盘式挤奶系统记录奶牛产奶量数据，通过项圈测定奶牛活动量，并利用声波传感器监测奶牛反刍时间。根据上述奶牛个体数据，通过决策树、随机森林、eXtreme Gradient boosting等机器学习算法，预测奶牛是否患有乳房炎。结果表明，该研究中随机森林算法对乳房炎预测效果最优，产奶量、活动量与反刍时间可作为奶牛乳房炎预测因子。

    图  4  基于物联网的奶牛社会行为感知框架[100]
    注：A～F为奶牛ID，t为时刻，p为患病概率
    Figure  4.  Dairy cow social behavior perception framework based on Internet of things[100]
    Note: A～F are dairy cow’s ID, t is the moment, p is the probability of illness.
    下载: 全尺寸图片 幻灯片

    与基于AMS的奶牛乳房炎检测方法相比，使用独立传感器基本能够满足快速、精准检测奶牛乳房炎的需求，而且成本更低，操作简便。但使用不同类型的传感器检测奶牛乳房炎，精度差异较大，这是由于传感器类型的限制，导致所获取的奶牛乳房及乳汁特征通常较为单一，所构建的乳房炎检测模型性能差异也较大，不利于奶牛乳房炎的高精度检测。因此，后续研究应采用多传感器系统，采集多模态数据，增加特征维度，以提高奶牛乳房炎检测精度。

    4.   讨　论

    4.1   当前主要挑战

    近年来，虽然国内外研究学者在奶牛乳房炎自动检测领域已做出大量的改进与创新，取得了丰硕的研究成果，但奶牛乳房炎自动检测技术的实时性、准确性以及自动化程度仍有待提高。因此，进行奶牛乳房炎自动检测技术的研究时，仍需着重考虑以下问题：

    1）基于乳房热红外图像的奶牛乳房炎检测技术，虽然较大程度上保障了动物福利，能够无接触、无应激地实现奶牛乳房炎的自动检测。但由于乳房皮肤表面温度易受环境、季节等外界因素影响，因此该方法检测乳房炎精度较低；

    2）基于乳汁图像的奶牛乳房炎检测技术，在检测精度上有所提升，同时也保障了动物福利。但该方法通常需要采集奶牛新鲜的乳汁，然后进行乳汁相关图像的分析与处理，因此对环境要求较为严格，不利于推广应用，自动化程度也较低；

    3）基于AMS的奶牛乳房炎检测技术，能够取得更高的检测精度与速度，可以在奶牛挤奶同时，实时检测乳汁中相关成分含量与理化特征，自动化程度较高。但由于AMS造价较高，鲜有国内养殖场引入。而且AMS在挤奶时，也会对奶牛乳房造成一定损伤，不利于动物福利；

    4）基于其他传感器的奶牛乳房炎检测技术，基本能够满足乳房炎快速、实时的检测需求，而且成本较低，操作简便。但使用单个传感器进行奶牛乳房炎检测，通常获取的乳房炎特征维度较小，检测精度难以提升。

    4.2   未来发展趋势

    基于以上奶牛乳房炎自动检测技术存在的问题与挑战，未来该研究领域的发展趋势与研究重点是：

    1）基于乳房热红外图像的奶牛乳房炎检测方面，精准计算奶牛乳房温度、提高乳房炎检测模型的精度、乳房热图像中获取多维特征数据，是目前基于热图像的奶牛乳房炎研究中的重点；

    2）基于乳汁图像的奶牛乳房炎检测方面，研究重点在于提高检测的自动化程度，实现乳房炎的实时快速检测，并且在检测SCC后，构建奶牛乳房炎预测模型，更有利于该方法的推广与应用；

    3）基于AMS的奶牛乳房炎检测技术，研究重点在于降低AMS成本，并且减小挤奶仪器对奶牛乳房乳头的伤害。中国研究学者应设计符合国情的AMS，并研发用于奶牛常见疾病检测的嵌入式设备，是未来该领域的发展趋势；

    4）基于其他传感器的奶牛乳房炎检测方面，需要结合多种传感器类型，共同诊断奶牛乳房炎患病情况。多传感器集成与多模态数据的获取，能够增加特征数据维度，提高乳房炎检测精度，更有利于该方法的推广应用；

    5）上述4类奶牛乳房炎检测方法各有优劣，未来研究中，综合多种乳房炎检测方法，采集多种传感器数据，扩大奶牛乳房炎数据样本量，并丰富样本种类，利用数字图像处理、深度学习与数据分析等先进的计算机技术，构建实时、精准、自动、轻量级的检测模型，是目前奶牛乳房炎自动检测领域的研究重点与趋势。

    5.   结　语

    本文主要介绍了奶牛乳房炎自动检测技术的3种主要方法。首先是基于视觉传感器的奶牛乳房炎检测技术，该技术又分为基于乳房热红外图像的与基于乳汁图像的奶牛乳房炎检测。综述了近年来基于视觉传感器的奶牛乳房炎自动检测研究进展，并分析了该方法的优势与短板。其次介绍了基于自动挤奶系统的奶牛乳房炎检测技术，分析了该检测方法的研究特点，并整理了近年来使用AMS检测奶牛乳房炎的研究进展。然后阐述了基于其他传感器的奶牛乳房炎检测方法的研究流程与研究重点。最后提出了当前奶牛乳房炎自动检测研究所面临的精度低、实时性差、自动化程度不足等问题，以及未来该领域的发展趋势。与欧美等发达国家相比，虽然中国在奶牛乳房炎自动检测领域已取得了较大突破，但与研究成果的推广应用还有较大距离。因此，亟需结合中国奶牛养殖业现状，研发精准、实时、经济的奶牛乳房炎自动检测技术。

  • 图  1   基于视觉传感器的奶牛乳房炎检测技术示意图

    Figure  1.   Sketch map of mastitis detection technology in dairy cow based on visual sensors

    下载: 全尺寸图片 幻灯片

    图  2   基于IRT与深度学习的奶牛关键部位检测[46]

    Figure  2.   Key parts detection of dairy cows based on IRT (infrared thermo graphy) and deep learning[46]

    下载: 全尺寸图片 幻灯片

    图  3   基于其他传感器的奶牛乳房炎检测技术示意图

    Figure  3.   Sketch map of mastitis detection technology in dairy cow based on other sensors

    下载: 全尺寸图片 幻灯片

    图  4   基于物联网的奶牛社会行为感知框架[100]

    注：A～F为奶牛ID，t为时刻，p为患病概率

    Figure  4.   Dairy cow social behavior perception framework based on Internet of things[100]

    Note: A～F are dairy cow’s ID, t is the moment, p is the probability of illness.

    下载: 全尺寸图片 幻灯片

    表  1   基于视觉传感器的奶牛乳房炎检测技术

    Table  1   Researches on mastitis detection technology in dairy cow based on visual sensors

    年份
    Year    		采集设备
    Collecting equipment    		技术方法
    Technical methods    		特征
    Features    		研究结果
    Research results    		文献
    Literature
    2019FLIR A615热像仪数字图像处理眼乳温差临床型乳房炎检测准确率87.5%，隐性乳房炎准确率33.3%[44]
    2019ThermaCAM B20 HSV热像仪数字图像处理乳房温度乳房炎检测敏感性93.75%，特异性94.96%[45]
    2020FLIR A615热像仪数字图像处理
    深度学习    		眼乳温差乳房炎检测准确率83.33%[46]
    2021FLIR A615热像仪深度学习眼乳温差乳房炎检测精度77.3%[47]
    2021MAG62热像仪数字图像处理
    深度学习    		眼乳温差临床型乳房炎检测准确率91.4%， 隐性乳房炎检测准确率85.3%[48]
    2022Fotric-625c热像仪数字图像处理
    数据分析    		乳区温度分布
    拟合线斜率    		健康乳区识别精度76%，患病乳区识别精度75%[49]
    2022Guide C400M热像仪数字图像处理
    数据分析    		乳房温度−[50]
    2022FLIR A310热像仪深度学习眼乳温差
    双乳温差    		乳房炎检测准确率87.62%[51]
    2023FLIR A310热像仪深度学习热图像纹理、
    色彩、结构    		乳房炎检测准确率88.4%[52]
    2015显微镜数字图像处理体细胞数与人工SCC相比，乳房炎检测准确率99.7%[53]
    2017Logitech5000 USB相机、pH试纸数字图像处理体细胞数与高精度SCC相比，乳房炎检测平均相对误差为3.67%[54]
    2020数码显微镜数字图像处理体细胞数与高精度SCC相比，乳房炎检测最大偏差低于8%[55]
    下载: 导出CSV

    表  2   基于自动挤奶系统的奶牛乳房炎检测技术

    Table  2   Researches on mastitis detection technology in dairy cow based on AMS (automatic milking systems)

    年份
    Year    		特征
    Features    		技术方法
    Technical methods    		研究结果
    Research results    		文献
    Literature
    2001电导率（electric conductivity, EC）、产奶量线性回归乳房炎检测特异性98%，敏感性100%[66]
    2008EC、RGB、产奶量线性回归−[67]
    2009前奶EC线性回归乳房炎检测敏感性68%～88%[68]
    2010产次、产奶天数、季节、体细胞数等贝叶斯网络−[69]
    2010EC、RGB、警报原因、警报次数等朴素贝叶斯网络临床型乳房炎假阳警报减少35%[70]
    2013泌乳等级、产奶量、EC、季节等支持向量机乳房炎检测敏感性89%，特异性92%[71]
    2014产奶量变化协同控制临床型乳房炎检测敏感性63%[72]
    2019氧浓度混合线性模型隐性乳房炎检测敏感性84%，特异性46%[73]
    2020EC、奶牛活动量、反刍、产次逻辑混合模型隐性乳房炎检测ROC曲线下方面积（area under curve, AUC）0.92[74]
    2022体细胞数、EC、产次、产奶量等梯度增强慢性乳房炎检测准确率88.8%[75]
    2022EC、产奶量等广义线性混合模型临床型乳房炎检测敏感性最高78%，特异性最高97%[76]
    下载: 导出CSV

    表  3   基于其他传感器的奶牛乳房炎检测技术

    Table  3   Researches on mastitis detection technology in dairy cow based on other sensors

    年份
    Year    		传感器类型
    Sensor type    		特征
    Features    		技术方法
    Technical methods    		研究结果
    Research results    		文献
    Literature
    2007单片机EC、pH值阈值CM检测准确率94%，SCM检测准确率67%[94]
    2007化学传感器乳汁分泌物主成分分析与交叉验证CM检测敏感性93%，特异性96%[95]
    2008体细胞计数仪EC、SCC模糊逻辑CM检测错误率最高2.1%[96]
    2013手持式乳汁电导率仪EC贝叶斯网络乳房炎检测敏感性89.9%，特异性86.8%[97]
    2017测力传感器双侧乳区硬度差异阈值CM检测敏感性62.5%，特异性96.7%[98]
    2022超声波乳汁分析仪脂肪、蛋白质、乳糖、pH值、EC等多元回归自适应样条
    （Multivariate Adaptive
    Regression Splines, MARS）    		乳房炎检测准确率83%[99]
    2022GPS奶牛运动轨迹与社会行为物联网乳房炎预测结果与SCC一致[100]
    2023榨奶系统、项圈、声波传感器产奶量、EC、活动量、反刍时间随机森林乳房炎检测准确率88%[101]
    下载: 导出CSV
    • 参考文献(102)
  • [1] 王蕾,李文科. 高质量发展背景下我国畜牧业提质增效制约因素分析及对策探讨[J]. 黑龙江畜牧兽医,2021(22):1-5. WANG Lei, LI Wenke. Analysis of restrictive factors and countermeasures for improving quality and efficiency of animal husbandry under the background of high quality development in China[J]. Heilongjiang Animal Science and Veterinary Medicine, 2021(22): 1-5. (in Chinese with English abstract

    WANG Lei, LI Wenke. Analysis of restrictive factors and countermeasures for improving quality and efficiency of animal husbandry under the background of high quality development in China[J]. Heilongjiang Animal Science and Veterinary Medicine, 2021(22): 1-5. (in Chinese with English abstract)
    [2] 熊学振,杨春,马晓萍. 我国畜牧业发展现状与高质量发展策略选择[J]. 中国农业科技导报,2022,24(3):1-10. XIONG Xuezhen, YANG Chun, MA Xiaoping. Situation of China's animal husbandry development and high-quality development strategy selection[J]. Journal of Agricultural Science and Technology, 2022, 24(3): 1-10. (in Chinese with English abstract

    XIONG Xuezhen, YANG Chun, MA Xiaoping. Situation of China's animal husbandry development and high-quality development strategy selection[J]. Journal of Agricultural Science and Technology, 2022, 24(3): 1-10. (in Chinese with English abstract)
    [3] SMULSKI S, GEHRKE M, LIBERA K, et al. Effects of various mastitis treatments on the reproductive performance of cows[J]. BMC Veterinary Research, 2020, 16(1):1-10. doi: 10.1186/s12917-019-2207-z

    SMULSKI S, GEHRKE M, LIBERA K, et al. Effects of various mastitis treatments on the reproductive performance of cows[J]. BMC Veterinary Research, 2020, 16(1): 1-10. doi: 10.1186/s12917-019-2207-z
    [4] LUO T T, STEENEVELD W, NIELEN M, et al. Linear mixed-effects model to quantify the association between somatic cell count and milk production in italian dairy herds[J]. Animals, 2023, 13(1):80-92.

    LUO T T, STEENEVELD W, NIELEN M, et al. Linear mixed-effects model to quantify the association between somatic cell count and milk production in italian dairy herds[J]. Animals, 2023, 13(1): 80-92.
    [5] DALANEZI F M, JOAQUIM S F, GUIMARÃES F F, et al. Influence of pathogens causing clinical mastitis on reproductive variables of dairy cows[J]. Journal of Dairy Science, 2020, 103(4):3648-3655. doi: 10.3168/jds.2019-16841

    DALANEZI F M, JOAQUIM S F, GUIMARÃES F F, et al. Influence of pathogens causing clinical mastitis on reproductive variables of dairy cows[J]. Journal of Dairy Science, 2020, 103(4): 3648-3655. doi: 10.3168/jds.2019-16841
    [6] 闫涛涛,姚婷婷,王正兴,等. 基于Web of Science和CNKI数据库的奶牛乳房炎研究文献计量分析[J]. 黑龙江畜牧兽医,2022(24):14-23. YAN Taotao, YAO Tingting, WANG Zhengxing, et al. Bibliometric analysis of dairy cow mastitis research based on Web of Science and CNKI database[J]. Heilongjiang Animal Science and Veterinary Medicine, 2022(24): 14-23. (in Chinese with English abstract

    YAN Taotao, YAO Tingting, WANG Zhengxing, et al. Bibliometric analysis of dairy cow mastitis research based on Web of Science and CNKI database[J]. Heilongjiang Animal Science and Veterinary Medicine, 2022(24): 14-23. (in Chinese with English abstract)
    [7] WOLLOWSKI L, HEUWIESER W, KOSSATZ A, et al. The value of the biomarkers cathelicidin, milk amyloid A, and haptoglobin to diagnose and classify clinical and subclinical mastitis[J]. Journal of Dairy Science, 2021, 104(2):2106-2122. doi: 10.3168/jds.2020-18539

    WOLLOWSKI L, HEUWIESER W, KOSSATZ A, et al. The value of the biomarkers cathelicidin, milk amyloid A, and haptoglobin to diagnose and classify clinical and subclinical mastitis[J]. Journal of Dairy Science, 2021, 104(2): 2106-2122. doi: 10.3168/jds.2020-18539
    [8] BONESTROO J, FALL N, HOGEVEEN H, et al. The costs of chronic mastitis:A simulation study of an automatic milking system farm[J]. Preventive Veterinary Medicine, 2023, 210:105799-105811. doi: 10.1016/j.prevetmed.2022.105799

    BONESTROO J, FALL N, HOGEVEEN H, et al. The costs of chronic mastitis: A simulation study of an automatic milking system farm[J]. Preventive Veterinary Medicine, 2023, 210: 105799-105811. doi: 10.1016/j.prevetmed.2022.105799
    [9] MUKHAMADIEVA N, JULANOV M, ZAINETTINOVA D, et al. Prevalence, Diagnosis and improving the effectiveness of therapy of mastitis in cows of dairy farms in east Kazakhstan[J]. Veterinary Sciences, 2022, 9(8):398-412. doi: 10.3390/vetsci9080398

    MUKHAMADIEVA N, JULANOV M, ZAINETTINOVA D, et al. Prevalence, diagnosis and improving the effectiveness of therapy of mastitis in cows of dairy farms in east Kazakhstan[J]. Veterinary Sciences, 2022, 9(8): 398-412. doi: 10.3390/vetsci9080398
    [10] FERROUDJ S, ELAFRI A, HALASSI I, et al. Herd practices and their association with subclinical mastitis prevalence in dairy cows in semiarid regions of northeastern Algeria[J]. Acta Veterinaria Eurasia, 2021, 47(3):1-7.

    FERROUDJ S, ELAFRI A, HALASSI I, et al. Herd practices and their association with subclinical mastitis prevalence in dairy cows in semiarid regions of northeastern Algeria[J]. Acta Veterinaria Eurasia, 2021, 47(3): 1-7.
    [11] MBINDYO C M, GITAO G C, MULEI C M. Prevalence, etiology, and risk factors of mastitis in dairy cattle in Embu and Kajiado Counties, Kenya[J]. Veterinary Medicine International, 2020, 2020:1-12.

    MBINDYO C M, GITAO G C, MULEI C M. Prevalence, etiology, and risk factors of mastitis in dairy cattle in Embu and Kajiado Counties, Kenya[J]. Veterinary Medicine International, 2020, 2020: 1-12.
    [12] DABELE D T, BORENA B M, SNR P A, et al. Prevalence and risk factors of mastitis and isolation, identification and antibiogram of staphylococcus species from mastitis positive zebu cows in toke kutaye, cheliya, and dendi districts, west shewa zone, Oromia, Ethiopia[J]. Infection and Drug Resistance, 2021, 14:987-998. doi: 10.2147/IDR.S295257

    DABELE D T, BORENA B M, SNR P A, et al. Prevalence and risk factors of mastitis and isolation, identification and antibiogram of staphylococcus species from mastitis positive zebu cows in toke kutaye, cheliya, and dendi districts, west shewa zone, Oromia, Ethiopia[J]. Infection and Drug Resistance, 2021, 14: 987-998. doi: 10.2147/IDR.S295257
    [13] 韩晓霞,田磊,郭抗抗,等. 陕西省某牛场奶牛隐性乳房炎的发病规律调查分析[J]. 中国兽医学报,2020,40(4):806-810. HAN Xiaoxia, TIAN Lei, GUO Kangkang, et al. Investigation and analysis on incidence of subclinical mastitis of dairy cows in a dairy farm in Shaanxi Province[J]. Chinese Journal of Veterinary Science, 2020, 40(4): 806-810. (in Chinese with English abstract

    HAN Xiaoxia, TIAN Lei, GUO Kangkang, et al. Investigation and analysis on incidence of subclinical mastitis of dairy cows in a dairy farm in Shaanxi Province[J]. Chinese Journal of Veterinary Science, 2020, 40(4): 806-810. (in Chinese with English abstract)
    [14] 刘凯,孙卫星,张立梅,等. 中国奶牛乳房炎致病菌地域分布及时间变化[J]. 中国兽医杂志,2020,56(2):22-26. LIU Kai, SUN Weixing, ZHANG Limei, et al. Regional distribution and temporal changes of pathogenic bacteria in Chinese dairy cow mastitis[J]. Chinese Journal of Veterinary Medicine, 2020, 56(2): 22-26. (in Chinese with English abstract

    LIU Kai, SUN Weixing, ZHANG Limei, et al. Regional distribution and temporal changes of pathogenic bacteria in Chinese dairy cow mastitis[J]. Chinese Journal of Veterinary Medicine, 2020, 56(2): 22-26. (in Chinese with English abstract)
    [15] 刘景喜,张进,芦娜,等. 2018年天津市原料奶细菌总数、体细胞数及奶牛乳房炎病原菌、耐药基因调研报告[J]. 畜牧与兽医,2020,52(3):130-134. LIU Jingxi, ZHANG Jin, LU Na, et al. Report on investigation of total bacteria number, somatic cell count in raw milk and pathogens, resistance gene of mastitis in cows in Tianjin in 2018[J]. Animal Husbandry & Veterinary Medicine, 2020, 52(3): 130-134. (in Chinese with English abstract

    LIU Jingxi, ZHANG Jin, LU Na, et al. Report on investigation of total bacteria number, somatic cell count in raw milk and pathogens, resistance gene of mastitis in cows in Tianjin in 2018[J]. Animal Husbandry & Veterinary Medicine, 2020, 52(3): 130-134. (in Chinese with English abstract)
    [16] 王富伟,武乃雯,陈鹏,等. 河北省奶牛临床型乳房炎发病特征调查[J]. 中国兽医杂志,2022,58(7):14-16. WANG Fuwei, WU Naiwen, CHEN Peng, et al. Investigation on the incidence characteristics of clinical mastitis in Hebei Province[J]. Chinese Journal of Veterinary Medicine, 2022, 58(7): 14-16. (in Chinese with English abstract

    WANG Fuwei, WU Naiwen, CHEN Peng, et al. Investigation on the incidence characteristics of clinical mastitis in Hebei Province[J]. Chinese Journal of Veterinary Medicine, 2022, 58(7): 14-16. (in Chinese with English abstract)
    [17] 陶晓丽. 河南省临颍县奶牛乳房炎病原菌感染情况调查与药敏分析[J]. 中国兽医杂志,2020,56(3):107-108. TAO Xiaoli. Survey and drug sensitivity analysis of mastitis pathogen infection in dairy cows in Linying County, Henan Province[J]. Chinese Journal of Veterinary Medicine, 2020, 56(3): 107-108. (in Chinese with English abstract

    TAO Xiaoli. Survey and drug sensitivity analysis of mastitis pathogen infection in dairy cows in Linying County, Henan Province[J]. 2020, 56(3): 107-108. (in Chinese with English abstract)
    [18] 张宇航,陈琳方,刘国文. 吉林地区奶牛隐性乳腺炎流行病学与相关因素的调查分析[J]. 中国兽医杂志,2021,57(1):32-36. ZHANG Yuhang, CHEN Linfang, LIU Guowen. Investigation and analysis on epidemiology and related factors of subclinical mastitis in dairy cows in Jilin Province[J]. Chinese Journal of Veterinary Medicine, 2021, 57(1): 32-36. (in Chinese with English abstract

    ZHANG Yuhang, CHEN Linfang, LIU Guowen. Investigation and analysis on epidemiology and related factors of subclinical mastitis in dairy cows in Jilin Province[J]. Chinese Journal of Veterinary Medicine, 2021, 57(1): 32-36. (in Chinese with English abstract)
    [19] FUKUSHIMA Y, KINO E, FURUTANI A, et al. Epidemiological study to investigate the incidence and prevalence of clinical mastitis, peracute mastitis, metabolic disorders and peripartum disorders, on a dairy farm in a temperate zone in Japan[J]. BMC Veterinary Research, 2020, 16(1):1-10. doi: 10.1186/s12917-019-2207-z

    FUKUSHIMA Y, KINO E, FURUTANI A, et al. Epidemiological study to investigate the incidence and prevalence of clinical mastitis, peracute mastitis, metabolic disorders and peripartum disorders, on a dairy farm in a temperate zone in Japan[J]. BMC Veterinary Research, 2020, 16(1): 1-10. doi: 10.1186/s12917-019-2207-z
    [20] BISCOTTO J V G, AMARAL M M, DA CUNHA A F. Prevalence and influence of clinical and subclinical mastitis in the service period of dairy cows in Tarumirim (MG)[J]. Acta Veterinaria Brasilica, 2022, 16(3):205-210. doi: 10.21708/avb.2022.16.3.10609

    BISCOTTO J V G, AMARAL M M, DA CUNHA A F. Prevalence and influence of clinical and subclinical mastitis in the service period of dairy cows in Tarumirim (MG)[J]. Acta Veterinaria Brasilica, 2022, 16(3): 205-210. doi: 10.21708/avb.2022.16.3.10609
    [21] GONÇALVES J L, DE CAMPOS J L, STEINBERGER A J, et al. Incidence and treatments of bovine mastitis and other diseases on 37 dairy farms in Wisconsin[J]. Pathogens, 2022, 11(11):1282-1294. doi: 10.3390/pathogens11111282

    GONÇALVES J L, DE CAMPOS J L, STEINBERGER A J, et al. Incidence and treatments of bovine mastitis and other diseases on 37 dairy farms in Wisconsin[J]. Pathogens, 2022, 11(11): 1282-1294. doi: 10.3390/pathogens11111282
    [22] SEMINA L K, AVDUEVSKYA N N, SKULYABINA Z A, et al. Improved measures for the prevention of mass mastitis in cows in the Vologda region farms[C]//IOP Conference Series:Earth and Environmental Science, 2020, 548(4):42006-42012.

    SEMINA L K, AVDUEVSKYA N N, SKULYABINA Z A, et al. Improved measures for the prevention of mass mastitis in cows in the Vologda region farms[J]//IOP Conference Series: Earth and Environmental Science, 2020, 548: 042006.
    [23] GIRMA A, TAMIR D. Prevalence of bovine mastitis and its associated risk factors among dairy cows in Ethiopia during 2005-2022:a systematic review and meta-analysis[J]. Veterinary Medicine International, 2022:1-19.

    GIRMA A, TAMIR D. Prevalence of bovine mastitis and its associated risk factors among dairy cows in Ethiopia during 2005–2022: A systematic review and meta-analysis[J]. Veterinary Medicine International, 2022, 2022: 7775197.
    [24] SAMARAWEERA A M, BOERNER V, DISNAKA S, et al. Genetic associations between mastitis, milk electrical conductivity, and milk flow rate in temperate dairy cows in tropics[J]. Livestock Science, 2022, 264:105064-105070. doi: 10.1016/j.livsci.2022.105064

    SAMARAWEERA A M, BOERNER V, DISNAKA S, et al. Genetic associations between mastitis, milk electrical conductivity, and milk flow rate in temperate dairy cows in tropics[J]. Livestock Science, 2022, 264: 105064-105070. doi: 10.1016/j.livsci.2022.105064
    [25] 童津津,张华,熊本海,等. 奶牛乳腺内微生物区系与乳房健康的关系研究进展[J]. 动物营养学报,2021,33(2):651-657. Tong Jinjin, Zhang Hua, Xiong Benhai, et al. Research advance of relationship of udder microbiota and udder healthy of dairy cows[J]. Chinese Journal of Animal Nutrition, 2021, 33(2): 651-657. (in Chinese with English abstract

    Tong Jinjin, Zhang Hua, Xiong Benhai, et al. Research advance of relationship of udder microbiota and udder healthy of dairy cows[J]. Chinese Journal of Animal Nutrition, 2021, 33(2): 651-657. (in Chinese with English abstract)
    [26] DŽERMEIKAITĖ K, BAČĖNINAITĖ D, ANTANAITIS R. Innovations in cattle farming:Application of innovative technologies and sensors in the diagnosis of diseases[J]. Animals, 2023, 13(5):780-802. doi: 10.3390/ani13050780

    DŽERMEIKAITĖ K, BAČĖNINAITĖ D, ANTANAITIS R. Innovations in cattle farming: Application of innovative technologies and sensors in the diagnosis of diseases[J]. Animals, 2023, 13(5): 780-802. doi: 10.3390/ani13050780
    [27] BARBAGIANNI M S, GOULETSOU P G. Modern imaging techniques in the study and disease diagnosis of the mammary glands of animals[J]. Veterinary Sciences, 2023, 10(2):83-98. doi: 10.3390/vetsci10020083

    BARBAGIANNI M S, GOULETSOU P G. Modern imaging techniques in the study and disease diagnosis of the mammary glands of animals[J]. Veterinary Sciences, 2023, 10(2): 83-98. doi: 10.3390/vetsci10020083
    [28] 王豪杰,李旭妮,彭小兵,等. 奶牛乳房炎诊断方法研究进展[J]. 动物医学进展,2022,43(10):90-93. WANG Haojie, LI Xuni, PENG Xiaobing, et al. Progress on methods for diagnosis of dairy cow mastitis[J]. Progress In Veterinary Medicine, 2022, 43(10): 90-93. (in Chinese with English abstract

    WANG Haojie, LI Xuni, PENG Xiaobing, et al. Progress on methods for diagnosis of dairy cow mastitis[J]. Progress In Veterinary Medicine, 2022, 43(10): 90-93. (in Chinese with English abstract)
    [29] NAKADA S, FUJIMOTO Y, KOHARA J, et al. Economic losses associated with mastitis due to bovine leukemia virus infection[J]. Journal of Dairy Science, 2023, 106(1):576-588. doi: 10.3168/jds.2021-21722

    NAKADA S, FUJIMOTO Y, KOHARA J, et al. Economic losses associated with mastitis due to bovine leukemia virus infection[J]. Journal of Dairy Science, 2023, 106(1): 576-588. doi: 10.3168/jds.2021-21722
    [30] DENG Z, LAM T, HOGEVEEN H, et al. Regularly fluctuating somatic cell count pattern in dairy herds[J]. Journal of Dairy Science, 2021, 104(10):11126-11134. doi: 10.3168/jds.2020-20063

    DENG Z, LAM T, HOGEVEEN H, et al. Regularly fluctuating somatic cell count pattern in dairy herds[J]. Journal of Dairy Science, 2021, 104(10): 11126-11134. doi: 10.3168/jds.2020-20063
    [31] 詹经纬,童津津,熊本海,等. 奶牛乳腺健康与乳中体细胞数之间关系的研究进展[J]. 动物营养学报,2021,33(3):1299-1305. ZHAN Jingwei, TONG Jinjin, XIONG Benhai, et al. Research progress on relationship of mammary gland health and milk somatic cell count of dairy cows[J]. Chinese Journal of Animal Nutrition, 2021, 33(3): 1299-1305. (in Chinese with English abstract

    ZHAN Jingwei, TONG Jinjin, XIONG Benhai, et al. Research progress on relationship of mammary gland health and milk somatic cell count of dairy cows[J]. 2021, 33(3): 1299-1305. (in Chinese with English abstract)
    [32] 李海强,杨大盛,卢琦,等. 2种奶牛隐性乳房炎检测方法比较[J]. 中国畜牧兽医,2020,47(8):2677-2683.
    [33] ALI A, MIR M U R, GANIE S A, et al. Milk-compositional study of metabolites and pathogens in the milk of bovine animals affected with subclinical mastitis[J]. Molecules, 2022, 27(23):8631-8652. doi: 10.3390/molecules27238631

    ALI A, MIR M U R, GANIE S A, et al. Milk-compositional study of metabolites and pathogens in the milk of bovine animals affected with subclinical mastitis[J]. Molecules, 2022, 27(23): 8631-8652. doi: 10.3390/molecules27238631
    [34] INZAGHI V, ZUCALI M, THOMPSON P D, et al. Changes in electrical conductivity, milk production rate and milk flow rate prior to clinical mastitis confirmation[J]. Italian Journal of Animal Science, 2021, 20(1):1554-1561. doi: 10.1080/1828051X.2021.1984852

    INZAGHI V, ZUCALI M, THOMPSON P D, et al. Changes in electrical conductivity, milk production rate and milk flow rate prior to clinical mastitis confirmation[J]. Italian Journal of Animal Science, 2021, 20(1): 1554-1561. doi: 10.1080/1828051X.2021.1984852
    [35] 张玉龙,左之才,王宇,等. 使用多重PCR检测奶牛乳房炎乳汁中的病原菌[J]. 中国兽医杂志,2021,57(11):38-43. ZHANG Yulong, ZUO Zhicai, WANG Yu, et al. Use of multiplex PCR to detect pathogens in milk of dairy cows with mastitis[J]. Chinese Journal of Veterinary Medicine, 2021, 57(11): 38-43. (in Chinese with English abstract

    ZHANG Yulong, ZUO Zhicai, WANG Yu, et al. Use of multiplex PCR to detect pathogens in milk of dairy cows with mastitis[J]. Chinese Journal of Veterinary Medicine, 2021, 57(11): 38-43. (in Chinese with English abstract)
    [36] 初梦苑,司永胜,李前,等. 家畜体尺自动测量技术研究进展[J]. 农业工程学报,2022,38(13):228-240. CHU Mengyuan, SI Yongsheng, LI Qian, et al. Research advances in the automatic measurement technology for livestock body size[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(13): 228-240. (in Chinese with English abstract

    CHU Mengyuan, SI Yongsheng, LI Qian, et al. Research advances in the automatic measurement technology for livestock body size[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(13): 228-240. (in Chinese with English abstract)
    [37] 陈长喜,张宏福,王兆毅,等. 畜禽健康养殖预警体系研究与应用[J]. 农业工程学报,2010,26(11):215-220. CHEN Changxi, ZHANG Hongfu, WANG Zhaoyi, et al. Study and application of early warning architecture of animal health culture[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(11): 215-220. (in Chinese with English abstract

    CHEN Zhangxi, ZHANG Hongfu, WANG Zhaoyi, et al. Study and application of early warning architecture of animal health culture[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2010, 26(11): 215-220. (in Chinese with English abstract)
    [38] 康熙,刘刚,初梦苑,等. 基于计算机视觉的奶牛生理参数监测与疾病诊断研究进展及挑战[J]. 智慧农业(中英文),2022,4(2):1-18. KANG Xi, LIU Gang, CHU Mengyuan, et al. Advances and challenges in physiological parameters monitoring and diseases diagnosing of dairy cows based on computer vision[J]. Smart Agriculture, 2022, 4(2): 1-18. (in Chinese with English abstract

    KANG Xi, LIU Gang, CHU Mengyuan, et al. Advances and challenges in physiological parameters monitoring and diseases diagnosing of dairy cows based on computer vision[J]. Smart Agriculture, 2022, 4(2): 1-18. (in Chinese with English abstract)
    [39] LELIVELD L M C, PROVOLO G. A review of welfare indicators of indoor-housed dairy cow as a basis for integrated automatic welfare assessment systems[J]. Animals, 2020, 10(8):1430-1447. doi: 10.3390/ani10081430

    LELIVELD L M C, PROVOLO G. A review of welfare indicators of indoor-housed dairy cow as a basis for integrated automatic welfare assessment systems[J]. Animals, 2020, 10(8): 1430-1447. doi: 10.3390/ani10081430
    [40] ALZUBAIDI L, ZHANG J, HUMAIDI A J, et al. Review of deep learning:Concepts, CNN architectures, challenges, applications, future directions[J]. Journal of Big Data, 2021, 8(1):1-74. doi: 10.1186/s40537-020-00387-6

    ALZUBAIDI L, ZHANG J, HUMAIDI A J, et al. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions[J]. Journal of Big Data, 2021, 8(1): 1-74. doi: 10.1186/s40537-020-00387-6
    [41] KANG J, ULLAH Z, GWAK J. Mri-based brain tumor classification using ensemble of deep features and machine learning classifiers[J]. Sensors, 2021, 21(6):2222-2242. doi: 10.3390/s21062222

    KANG J, ULLAH Z, GWAK J. Mri-based brain tumor classification using ensemble of deep features and machine learning classifiers[J]. Sensors, 2021, 21(6): 2222-2242. doi: 10.3390/s21062222
    [42] 尹仕斌,任永杰,刘涛,等. 机器视觉技术在现代汽车制造中的应用综述[J]. 光学学报,2018,38(8):11-22. YIN Shibin, REN Yongjie, LIU Tao, et al. Review on application of machine vision in modern automobile manufacturing[J]. Acta Optica Sinica, 2018, 38(8): 11-22. (in Chinese with English abstract

    YIN Shibin, REN Yongjie, LIU Tao, et al. Review on application of machine vision in modern automobile manufacturing[J]. Acta Optica Sinica, 2018, 38(8): 11-22. (in Chinese with English abstract)
    [43] 魏秀琨,所达,魏德华,等. 机器视觉在轨道交通系统状态检测中的应用综述[J]. 控制与决策,2021,36(2):257-282. WEI Xiukun, SUO Da, WEI Dehua, et al. A survey of the application of machine vision in rail transit system inspection[J]. Control and Decision, 2021, 36(2): 257-282. (in Chinese with English abstract

    WEI Xiukun, SUO Da, WEI Dehua, et al. A survey of the application of machine vision in rail transit system inspection[J]. Control and Decision, 2021, 36(2): 257-282. (in Chinese with English abstract)
    [44] 张旭东,康熙,马丽,等. 基于热红外图像的奶牛乳房炎自动检测方法[J]. 农业机械学报,2019,50(S1):248-255. ZHANG Xudong, KANG Xi, MA Li, et al. Automatic detection method of dairy cow mastitis based on thermal infrared image[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1): 248-255. (in Chinese with English abstract

    ZHANG Xudong, KANG Xi, MA Li, et al. Automatic detection method of dairy cow mastitis based on thermal infrared image[J]. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50(S1): 248-255. (in Chinese with English abstract)
    [45] WATZ S, PETZL W, ZERBE H, et al. Automatic evaluation of infrared thermal images by computerized active shape modeling of bovine udders challenged with Escherichia coli[J]. Journal of Dairy Science, 2019, 102(5):4541-4545. doi: 10.3168/jds.2018-15761

    WATZ S, PETZL W, ZERBE H, et al. Automatic evaluation of infrared thermal images by computerized active shape modeling of bovine udders challenged with Escherichia coli[J]. Journal of Dairy Science, 2019, 102(5): 4541-4545. doi: 10.3168/jds.2018-15761
    [46] ZHANG X D, KANG X, FENG N N, et al. Automatic recognition of dairy cow mastitis from thermal images by a deep learning detector[J]. Computers and Electronics in Agriculture, 2020, 178:105754-105764. doi: 10.1016/j.compag.2020.105754

    ZHANG X D, KANG X, FENG N N, et al. Automatic recognition of dairy cow mastitis from thermal images by a deep learning detector[J]. Computers and Electronics in Agriculture, 2020, 178: 105754-105764. doi: 10.1016/j.compag.2020.105754
    [47] 王彦超,康熙,李孟飞,等. 基于改进YOLO v3-tiny的奶牛乳房炎自动检测方法[J]. 农业机械学报,2021,52(S1):276-283. WANG Yanchao, KANG Xi, LI Mengfei, et al. Automatic detection method for dairy cow mastitis based on improved YOLO v3-tiny[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 276-283. (in Chinese with English abstract

    WANG Yanchao, KANG Xi, LI Mengfei, et al. Automatic detection method for dairy cow mastitis based on improved YOLO v3-tiny[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(S1): 276-283. (in Chinese with English abstract)
    [48] 宋子琪. 基于热红外图像的奶牛乳房炎检测方法研究[D]. 杨凌: 西北农林科技大学, 2021.

    Song Ziqi. Detection of Dairy Cow Mastitis Based on Thermal Infrared Image[D]. Yangling: Northwest A&F University, 2021. (in Chinese with English abstract)
    [49] 郭艳娇,杨圣慧,迟宇,等. 基于热红外图像的奶牛乳区温度分布与乳房炎识别方法[J]. 农业工程学报,2022,38(2):250-259. GUO Yanjiao, YANG Shenghui, CHI Yu, et al. Recognizing mastitis using temperature distribution from thermal infrared images in cow udder regions[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(2): 250-259. (in Chinese with English abstract doi: 10.11975/j.issn.1002-6819.2022.02.028

    GUO Yanjiao, YANG Shenghui, CHI Yu, et al. Recognizing mastitis using temperature distribution from thermal infrared images in cow udder regions[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2022, 38(2): 250-259. (in Chinese with English abstract) doi: 10.11975/j.issn.1002-6819.2022.02.028
    [50] KHAKIMOV A R, PAVKIN D Y, YUROCHKA S S, et al. Development of an algorithm for rapid herd evaluation and predicting milk yield of mastitis cows based on infrared thermography[J]. Applied Sciences, 2022, 12(13):6621. doi: 10.3390/app12136621

    KHAKIMOV A R, PAVKIN D Y, YUROCHKA S S, et al. Development of an algorithm for rapid herd evaluation and predicting milk yield of mastitis cows based on infrared thermography[J]. Applied Sciences, 2022, 12(13): 6621. doi: 10.3390/app12136621
    [51] WANG Y, KANG X, HE Z, et al. Accurate detection of dairy cow mastitis with deep learning technology:A new and comprehensive detection method based on infrared thermal images[J]. Animal, 2022, 16(10):100646. doi: 10.1016/j.animal.2022.100646

    WANG Y, KANG X, HE Z, et al. Accurate detection of dairy cow mastitis with deep learning technology: A new and comprehensive detection method based on infrared thermal images[J]. Animal, 2022, 16(10): 100646. doi: 10.1016/j.animal.2022.100646
    [52] 张倩,杨颖,刘刚,等. 融合数据增强与改进ResNet34的奶牛热红外图像乳腺炎检测[J]. 光谱学与光谱分析,2023,43(1):280-288. ZHANG Qian, YANG Ying, LIU Gang, et al. Detection of dairy cow mastitis from thermal images by data enhancement and improved ResNet34[J]. Spectroscopy and Spectral Analysis, 2023, 43(1): 280-288. (in Chinese with English abstract

    ZHANG Qian, YANG Ying, LIU Gang, et al. Detection of dairy cow mastitis from thermal images by data enhancement and improved ResNet34[J]. Spectroscopy and Spectral Analysis, 2023, 43(1): 280-288. (in Chinese with English abstract)
    [53] DE MELO G J A, GOMES V, BACCILI C C, et al. A robust segmentation method for counting bovine milk somatic cells in microscope slide images[J]. Computers and Electronics in Agriculture, 2015, 115:142-149. doi: 10.1016/j.compag.2015.05.018

    DE MELO G J A, GOMES V, BACCILI C C, et al. A robust segmentation method for counting bovine milk somatic cells in microscope slide images[J]. Computers and Electronics in Agriculture, 2015, 115: 142-149. doi: 10.1016/j.compag.2015.05.018
    [54] 蔡一欣, 马丽, 刘刚. 奶牛隐性乳房炎便携式计算机视觉快速检测系统设计与试验[J]. 农业工程学报, 2017, 33（增刊1）: 63-69.

    CAI Yixin, MA Li, LIU Gang. Design and experiment of rapid detection system of cow subclinical mastitis based on portable computer vision technology[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(Supp. 1): 63-69. (in Chinese with English abstract)
    [55] GAO F, WANG J, GE Y, et al. A vision-based instrument for measuring milk somatic cell count[J]. Measurement Science and Technology, 2020, 31(12):125904-125922. doi: 10.1088/1361-6501/ab9f44

    GAO F, WANG J, GE Y, et al. A vision-based instrument for measuring milk somatic cell count[J]. Measurement Science and Technology, 2020, 31(12): 125904-125922. doi: 10.1088/1361-6501/ab9f44
    [56] MOTA-ROJAS D, PEREIRA A M F, WANG D, et al. Clinical applications and factors involved in validating thermal windows used in infrared thermography in cattle and river buffalo to assess health and productivity[J]. Animals, 2021, 11(8):2247-2269. doi: 10.3390/ani11082247

    MOTA-ROJAS D, PEREIRA A M F, WANG D, et al. Clinical applications and factors involved in validating thermal windows used in infrared thermography in cattle and river buffalo to assess health and productivity[J]. Animals, 2021, 11(8): 2247-2269. doi: 10.3390/ani11082247
    [57] MOTA-ROJAS D, WANG D, TITTO C G, et al. Pathophysiology of fever and application of infrared thermography (IRT) in the detection of sick domestic animals:Recent advances[J]. Animals, 2021, 11(8):2316-2348. doi: 10.3390/ani11082316

    MOTA-ROJAS D, WANG D, TITTO C G, et al. Pathophysiology of fever and application of infrared thermography (IRT) in the detection of sick domestic animals: Recent advances[J]. Animals, 2021, 11(8): 2316-2348. doi: 10.3390/ani11082316
    [58] CAI Z J, CUI J L, YUAN H B, et al. Application and research progress of infrared thermography in temperature measurement of livestock and poultry animals:a review[J]. Computers and Electronics in Agriculture, 2023, 205:107586-107600. doi: 10.1016/j.compag.2022.107586

    CAI Z J, CUI J L, YUAN H B, et al. Application and research progress of infrared thermography in temperature measurement of livestock and poultry animals: A review[J]. Computers and Electronics in Agriculture, 2023, 205: 107586-107600. doi: 10.1016/j.compag.2022.107586
    [59] ASHRAF A, IMRAN M. Causes, types, etiological agents, prevalence, diagnosis, treatment, prevention, effects on human health and future aspects of bovine mastitis[J]. Animal Health Research Reviews, 2020, 21(1):36-49. doi: 10.1017/S1466252319000094

    ASHRAF A, IMRAN M. Causes, types, etiological agents, prevalence, diagnosis, treatment, prevention, effects on human health and future aspects of bovine mastitis[J]. Animal Health Research Reviews, 2020, 21(1): 36-49. doi: 10.1017/S1466252319000094
    [60] REDMON J, FARHADI A. YOLOv3:An incremental improvement[EB/OL]. 2018, ArXiv:abs/1084.02767.

    REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. 2018, ArXiv: abs/1084.02767.
    [61] METZNER M, SAUTER-LOUIS C, SEEMUELLER A, et al. Infrared thermography of the udder after experimentally induced Escherichia coli mastitis in cows[J]. The Veterinary Journal, 2015, 204(3):360-362. doi: 10.1016/j.tvjl.2015.04.013

    METZNER M, SAUTER-LOUIS C, SEEMUELLER A, et al. Infrared thermography of the udder after experimentally induced Escherichia coli mastitis in cows[J]. The Veterinary Journal, 2015, 204(3): 360-362. doi: 10.1016/j.tvjl.2015.04.013
    [62] ZHU X, LYU S, WANG X, et al. TPH-YOLOv5:Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021:2778-2788.

    ZHU X, LYU S, WANG X, et al. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 2778-2788.
    [63] ZANINELLI M, REDAELLI V, LUZI F, et al. First evaluation of infrared thermography as a tool for the monitoring of udder health status in farms of dairy cows[J]. Sensors, 2018, 18(3):862-873. doi: 10.3390/s18030862

    MONTERAL, CANADA, ZANINELLI M, et al. First evaluation of infrared thermography as a tool for the monitoring of udder health status in farms of dairy cows[J]. Sensors, 2018, 18(3): 862-873. doi: 10.3390/s18030862
    [64] HOGEVEEN H, KLAAS I C, DALEN G, et al. Novel ways to use sensor data to improve mastitis management[J]. Journal of Dairy Science, 2021, 104(10):11317-11332. doi: 10.3168/jds.2020-19097

    HOGEVEEN H, KLAAS I C, DALEN G, et al. Novel ways to use sensor data to improve mastitis management[J]. Journal of Dairy Science, 2021, 104(10): 11317-11332. doi: 10.3168/jds.2020-19097
    [65] KATO N, MAO B, TANG F, et al. Ten challenges in advancing machine learning technologies toward 6G[J]. IEEE Wireless Communications, 2020, 27(3):96-103. doi: 10.1109/MWC.001.1900476

    KATO N, MAO B, TANG F, et al. Ten challenges in advancing machine learning technologies toward 6G[J]. IEEE Wireless Communications, 2020, 27(3): 96-103. doi: 10.1109/MWC.001.1900476
    [66] DE MOL R M, OUWELTJES W. Detection model for mastitis in cows milked in an automatic milking system[J]. Preventive Veterinary Medicine, 2001, 49(1-2):71-82. doi: 10.1016/S0167-5877(01)00176-3

    DE MOL R M, OUWELTJES W. Detection model for mastitis in cows milked in an automatic milking system[J]. Preventive Veterinary Medicine, 2001, 49(1-2): 71-82. doi: 10.1016/S0167-5877(01)00176-3
    [67] KAMPHUIS C, PIETERSMA D, VAN DER TOL R, et al. Using sensor data patterns from an automatic milking system to develop predictive variables for classifying clinical mastitis and abnormal milk[J]. Computers and Electronics in Agriculture, 2008, 62(2):169-181. doi: 10.1016/j.compag.2007.12.009

    KAMPHUIS C, PIETERSMA D, VAN DER TOL R, et al. Using sensor data patterns from an automatic milking system to develop predictive variables for classifying clinical mastitis and abnormal milk[J]. Computers and Electronics in Agriculture, 2008, 62(2): 169-181. doi: 10.1016/j.compag.2007.12.009
    [68] CLAYCOMB R W, JOHNSTONE P T, MEIN G A, et al. An automated in-line clinical mastitis detection system using measurement of conductivity from foremilk of individual udder quarters[J]. New Zealand Veterinary Journal, 2009, 57(4):208-214. doi: 10.1080/00480169.2009.36903

    CLAYCOMB R W, JOHNSTONE P T, MEIN G A, et al. An automated in-line clinical mastitis detection system using measurement of conductivity from foremilk of individual udder quarters[J]. New Zealand Veterinary Journal, 2009, 57(4): 208-214. doi: 10.1080/00480169.2009.36903
    [69] STEENEVELD W, VAN DER GAAG L C, BARKEMA H W, et al. Simplify the interpretation of alert lists for clinical mastitis in automatic milking systems[J]. Computers and Electronics in Agriculture, 2010, 71(1):50-56. doi: 10.1016/j.compag.2009.12.011

    STEENEVELD W, VAN DER GAAG L C, BARKEMA H W, et al. Simplify the interpretation of alert lists for clinical mastitis in automatic milking systems[J]. Computers and Electronics in Agriculture, 2010, 71(1): 50-56. doi: 10.1016/j.compag.2009.12.011
    [70] STEENEVELD W, VAN DER GAAG L C, OUWELTJES W, et al. Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems[J]. Journal of Dairy Science, 2010, 93(6):2559-2568. doi: 10.3168/jds.2009-3020

    STEENEVELD W, VAN DER GAAG L C, OUWELTJES W, et al. Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems[J]. Journal of Dairy Science, 2010, 93(6): 2559-2568. doi: 10.3168/jds.2009-3020
    [71] MAMMADOVA N, KESKIN I. Application of the support vector machine to predict subclinical mastitis in dairy cattle[J]. The Scientific World Journal, 2013, 2013:603897-603906.

    MAMMADOVA N, KESKIN I. Application of the support vector machine to predict subclinical mastitis in dairy cattle[J]. The Scientific World Journal, 2013, 2013: 603897-603906.
    [72] HUYBRECHTS T, MERTENS K, DE BAERDEMAEKER J, et al. Early warnings from automatic milk yield monitoring with online synergistic control[J]. Journal of Dairy Science, 2014, 97(6):3371-3381. doi: 10.3168/jds.2013-6913

    HUYBRECHTS T, MERTENS K, DE BAERDEMAEKER J, et al. Early warnings from automatic milk yield monitoring with online synergistic control[J]. Journal of Dairy Science, 2014, 97(6): 3371-3381. doi: 10.3168/jds.2013-6913
    [73] WITTEK T, MADER C, RIBITSCH V, et al. Measurement of oxygen concentration for detection of subclinical mastitis[J]. Schweizer Archiv Fur Tierheilkunde, 2019, 161(10):659-665. doi: 10.17236/sat00228

    WITTEK T, MADER C, RIBITSCH V, et al. Measurement of oxygen concentration for detection of subclinical mastitis[J]. Schweizer Archiv Fur Tierheilkunde, 2019, 161(10): 659-665. doi: 10.17236/sat00228
    [74] KHATUN M, THOMSON P C, CLARK C E F, et al. Prediction of quarter level subclinical mastitis by combining in-line and on-animal sensor data[J]. Animal Production Science, 2019, 60(1):180-186.

    KHATUN M, THOMSON P C, CLARK C E F, et al. Prediction of quarter level subclinical mastitis by combining in-line and on-animal sensor data[J]. Animal Production Science, 2019, 60(1): 180-186.
    [75] BONESTROO J, VAN DER VOORT M, HOGEVEEN H, et al. Forecasting chronic mastitis using automatic milking system sensor data and gradient-boosting classifiers[J]. Computers and Electronics in Agriculture, 2022, 198:107002-107010. doi: 10.1016/j.compag.2022.107002

    BONESTROO J, VAN DER VOORT M, HOGEVEEN H, et al. Forecasting chronic mastitis using automatic milking system sensor data and gradient-boosting classifiers[J]. Computers and Electronics in Agriculture, 2022, 198: 107002-107010. doi: 10.1016/j.compag.2022.107002
    [76] BAUSEWEIN M, MANSFELD R, DOHERR M G, et al. Sensitivity and specificity for the detection of clinical mastitis by automatic milking systems in Bavarian dairy herds[J]. Animals, 2022, 12(16):2131-2148. doi: 10.3390/ani12162131

    BAUSEWEIN M, MANSFELD R, DOHERR M G, et al. Sensitivity and specificity for the detection of clinical mastitis by automatic milking systems in Bavarian dairy herds[J]. Animals, 2022, 12(16): 2131-2148. doi: 10.3390/ani12162131
    [77] LESSIRE F, MOULA N, HORNICK J L, et al. Systematic review and meta-analysis:Identification of factors influencing milking frequency of cows in automatic milking systems combined with grazing[J]. Animals, 2020, 10(5):913. doi: 10.3390/ani10050913

    LESSIRE F, MOULA N, HORNICK J L, et al. Systematic review and meta-analysis: Identification of factors influencing milking frequency of cows in automatic milking systems combined with grazing[J]. Animals, 2020, 10(5): 913. doi: 10.3390/ani10050913
    [78] COGATO A, BRŠČIĆ M, GUO H, et al. Challenges and tendencies of automatic milking systems (AMS):A 20-years systematic review of literature and patents[J]. Animals, 2021, 11(2):356-376. doi: 10.3390/ani11020356

    COGATO A, BRŠČIĆ M, GUO H, et al. Challenges and tendencies of automatic milking systems (AMS): A 20-years systematic review of literature and patents[J]. Animals, 2021, 11(2): 356-376. doi: 10.3390/ani11020356
    [79] Penry J F. Mastitis control in automatic milking systems[J]. Veterinary Clinics:Food Animal Practice, 2018, 34(3):439-456. doi: 10.1016/j.cvfa.2018.06.004

    Penry J F. Mastitis control in automatic milking systems[J]. Veterinary Clinics:Food Animal Practice, 2018, 34(3): 439-456. doi: 10.1016/j.cvfa.2018.06.004
    [80] HANSEN B G, HERJE H O, HÖVA J. Profitability on dairy farms with automatic milking systems compared to farms with conventional milking systems[J]. International Food and Agribusiness Management Review, 2019, 22(2):215-228. doi: 10.22434/IFAMR2018.0028

    HANSEN B G, HERJE H O, HÖVA J. Profitability on dairy farms with automatic milking systems compared to farms with conventional milking systems[J]. International Food and Agribusiness Management Review, 2019, 22(2): 215-228. doi: 10.22434/IFAMR2018.0028
    [81] ZUCALI M, BAVA L, TAMBURINI A, et al. Association between udder and quarter level indicators and milk somatic cell count in automatic milking systems[J]. Animals, 2021, 11(12):3485-3498. doi: 10.3390/ani11123485

    ZUCALI M, BAVA L, TAMBURINI A, et al. Association between udder and quarter level indicators and milk somatic cell count in automatic milking systems[J]. Animals, 2021, 11(12): 3485-3498. doi: 10.3390/ani11123485
    [82] 李小明,高振江,金红伟,等. 挤奶机真空度对牛奶体细胞数和牛乳头末端壁厚的影响[J]. 农业工程学报,2017,33(9):308-314. LI Xiaoming, GAO Zhenjiang, JIN Hongwei, et al. Effect of vacuum degree of milking machine on milk somatic cell counts (SCC) and teat end wall thickness[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(9): 308-314. (in Chinese with English abstract

    LI Xiaoming, GAO Zhenjiang, JIN Hongwei, et al. Effect of vacuum degree of milking machine on milk somatic cell counts (SCC) and teat end wall thickness[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2017, 33(9): 308-314. (in Chinese with English abstract)
    [83] GHAFFARIAN S, VAN DER VOORT M, VALENTE J, et al. Machine learning-based farm risk management:A systematic mapping review[J]. Computers and Electronics in Agriculture, 2022, 192:106631-106647. doi: 10.1016/j.compag.2021.106631

    GHAFFARIAN S, VAN DER VOORT M, VALENTE J, et al. Machine learning-based farm risk management: A systematic mapping review[J]. Computers and Electronics in Agriculture, 2022, 192: 106631-106647. doi: 10.1016/j.compag.2021.106631
    [84] ZHOU X, XU C, WANG H, et al. The early prediction of common disorders in dairy cows monitored by automatic systems with machine learning algorithms[J]. Animals, 2022, 12(10):1251-1264. doi: 10.3390/ani12101251

    ZHOU X, XU C, WANG H, et al. The early prediction of common disorders in dairy cows monitored by automatic systems with machine learning algorithms[J]. Animals, 2022, 12(10): 1251-1264. doi: 10.3390/ani12101251
    [85] WANG J, LOVARELLI D, ROTA N, et al. The potentialities of machine learning for cow-specific milking:Automatically setting variables in milking machines[J]. Animals, 2022, 12(13):1614-1627. doi: 10.3390/ani12131614

    WANG J, LOVARELLI D, ROTA N, et al. The potentialities of machine learning for cow-specific milking: Automatically setting variables in milking machines[J]. Animals, 2022, 12(13): 1614-1627. doi: 10.3390/ani12131614
    [86] ANGLART D, HALLÉN-SANDGREN C, WALDMANN P, et al. Modeling cow somatic cell count using sensor data as input to generalized additive models[J]. Journal of Dairy Research, 2020, 87(3):282-289. doi: 10.1017/S0022029920000692

    ANGLART D, HALLÉN-SANDGREN C, WALDMANN P, et al. Modeling cow somatic cell count using sensor data as input to generalized additive models[J]. Journal of Dairy Research, 2020, 87(3): 282-289. doi: 10.1017/S0022029920000692
    [87] KHATUN M, BRUCKMAIER R M, THOMSON P C, et al. Suitability of somatic cell count, electrical conductivity, and lactate dehydrogenase activity in foremilk before versus after alveolar milk ejection for mastitis detection[J]. Journal of Dairy Science, 2019, 102(10):9200-9212. doi: 10.3168/jds.2018-15752

    KHATUN M, BRUCKMAIER R M, THOMSON P C, et al. Suitability of somatic cell count, electrical conductivity, and lactate dehydrogenase activity in foremilk before versus after alveolar milk ejection for mastitis detection[J]. Journal of Dairy Science, 2019, 102(10): 9200-9212. doi: 10.3168/jds.2018-15752
    [88] ANGLART D, EMANUELSON U, RÖNNEGÅRD L, et al. Detecting and predicting changes in milk homogeneity using data from automatic milking systems[J]. Journal of Dairy Science, 2021, 104(10):11009-11017. doi: 10.3168/jds.2021-20517

    ANGLART D, EMANUELSON U, RÖNNEGÅRD L, et al. Detecting and predicting changes in milk homogeneity using data from automatic milking systems[J]. Journal of Dairy Science, 2021, 104(10): 11009-11017. doi: 10.3168/jds.2021-20517
    [89] DOMINIAK K N, KRISTENSEN A R. Prioritizing alarms from sensor-based detection models in livestock production-a review on model performance and alarm reducing methods[J]. Computers and Electronics in Agriculture, 2017, 133:46-67. doi: 10.1016/j.compag.2016.12.008

    DOMINIAK K N, KRISTENSEN A R. Prioritizing alarms from sensor-based detection models in livestock production-a review on model performance and alarm reducing methods[J]. Computers and Electronics in Agriculture, 2017, 133: 46-67. doi: 10.1016/j.compag.2016.12.008
    [90] DE MOL R M, WOLDT W E. Application of fuzzy logic in automated cow status monitoring[J]. Journal of Dairy Science, 2001, 84(2):400-410. doi: 10.3168/jds.S0022-0302(01)74490-6

    DE MOL R M, WOLDT W E. Application of fuzzy logic in automated cow status monitoring[J]. Journal of Dairy Science, 2001, 84(2): 400-410. doi: 10.3168/jds.S0022-0302(01)74490-6
    [91] SKARBYE A P, KROGH M A, DENWOOD M, et al. Effect of enhanced hygiene on transmission of Staphylococcus aureus, Streptococcus agalactiae, and Streptococcus dysgalactiae in dairy herds with automatic milking systems[J]. Journal of Dairy Science, 2021, 104(6):7195-7209. doi: 10.3168/jds.2020-19635

    SKARBYE A P, KROGH M A, DENWOOD M, et al. Effect of enhanced hygiene on transmission of Staphylococcus aureus, Streptococcus agalactiae, and Streptococcus dysgalactiae in dairy herds with automatic milking systems[J]. Journal of Dairy Science, 2021, 104(6): 7195-7209. doi: 10.3168/jds.2020-19635
    [92] VAN DEN BORNE B H P, VAN GRINSVEN N J M, HOGEVEEN H. Trends in somatic cell count deteriorations in Dutch dairy herds transitioning to an automatic milking system[J]. Journal of Dairy Science, 2021, 104(5):6039-6050. doi: 10.3168/jds.2020-19589

    VAN DEN BORNE B H P, VAN GRINSVEN N J M, HOGEVEEN H. Trends in somatic cell count deteriorations in Dutch dairy herds transitioning to an automatic milking system[J]. Journal of Dairy Science, 2021, 104(5): 6039-6050. doi: 10.3168/jds.2020-19589
    [93] ADRIAENS I, VAN DEN BRULLE I, GEERINCKX K, et al. Milk losses linked to mastitis treatments at dairy farms with automatic milking systems[J]. Preventive Veterinary Medicine, 2021, 194:105420-105430. doi: 10.1016/j.prevetmed.2021.105420

    ADRIAENS I, VAN DEN BRULLE I, GEERINCKX K, et al. Milk losses linked to mastitis treatments at dairy farms with automatic milking systems[J]. Preventive Veterinary Medicine, 2021, 194: 105420-105430. doi: 10.1016/j.prevetmed.2021.105420
    [94] 李晋阳,田富洋,李法德,等. 奶牛乳腺炎智能检测仪的设计与研究[J]. 仪器仪表学报,2007,28(2):264-267. LI Jinyang, TIAN Fuyang, LI Fade, et al. Design and study of intelligent detection gauge for cow mastitis[J]. Chinese Journal of Scientific Instrument, 2007, 28(2): 264-267. (in Chinese with English abstract doi: 10.19650/j.cnki.cjsi.2007.02.013

    LI Jinyang, TIAN Fuyang, LI Fade, et al. Design and study of intelligent detection gauge for cow mastitis[J]. Chinese Journal of Scientific Instrument, 2007, 28(2): 264-267. (in Chinese with English abstract) doi: 10.19650/j.cnki.cjsi.2007.02.013
    [95] MOTTRAM T, RUDNITSKAYA A, LEGIN A, et al. Evaluation of a novel chemical sensor system to detect clinical mastitis in bovine milk[J]. Biosensors and Bioelectronics, 2007, 22(11):2689-2693. doi: 10.1016/j.bios.2006.11.006

    MOTTRAM T, RUDNITSKAYA A, LEGIN A, et al. Evaluation of a novel chemical sensor system to detect clinical mastitis in bovine milk[J]. Biosensors and Bioelectronics, 2007, 22(11): 2689-2693. doi: 10.1016/j.bios.2006.11.006
    [96] KAMPHUIS C, SHERLOCK R, JAGO J, et al. Automatic detection of clinical mastitis is improved by in-line monitoring of somatic cell count[J]. Journal of Dairy Science, 2008, 91(12):4560-4570. doi: 10.3168/jds.2008-1160

    KAMPHUIS C, SHERLOCK R, JAGO J, et al. Automatic detection of clinical mastitis is improved by in-line monitoring of somatic cell count[J]. Journal of Dairy Science, 2008, 91(12): 4560-4570. doi: 10.3168/jds.2008-1160
    [97] FOSGATE G T, PETZER I M, KARZIS J. Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle[J]. The Veterinary Journal, 2013, 196(1):98-102. doi: 10.1016/j.tvjl.2012.07.026

    FOSGATE G T, PETZER I M, KARZIS J. Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle[J]. The Veterinary Journal, 2013, 196(1): 98-102. doi: 10.1016/j.tvjl.2012.07.026
    [98] REES A, FISCHER-TENHAGEN C, HEUWIESER W. Udder firmness as a possible indicator for clinical mastitis[J]. Journal of Dairy Science, 2017, 100(3):2170-2183. doi: 10.3168/jds.2016-11940

    REES A, FISCHER-TENHAGEN C, HEUWIESER W. Udder firmness as a possible indicator for clinical mastitis[J]. Journal of Dairy Science, 2017, 100(3): 2170-2183. doi: 10.3168/jds.2016-11940
    [99] ALTAY Y, AYTEKIN İ, EYDURAN E. Use of multivariate adaptive regression splines, classification trees and ROC curve in diagnosis of subclinical mastitis in dairy cattle[J]. Journal of the Hellenic Veterinary Medical Society, 2022, 73(1):3817-3826. doi: 10.12681/jhvms.25864

    ALTAY Y, AYTEKIN İ, EYDURAN E. Use of multivariate adaptive regression splines, classification trees and ROC curve in diagnosis of subclinical mastitis in dairy cattle[J]. Journal of the Hellenic Veterinary Medical Society, 2022, 73(1): 3817-3826. doi: 10.12681/jhvms.25864
    [100] FENG Y, NIU H, WANG F, et al. SocialCattle:IoT-based mastitis detection and control through social cattle behavior sensing in smart farms[J]. IEEE Internet of Things Journal, 2021, 9(12):10130-10138.

    FENG Y, NIU H, WANG F, et al. SocialCattle: IoT-based mastitis detection and control through social cattle behavior sensing in smart farms[J]. IEEE Internet of Things Journal, 2021, 9(12): 10130-10138.
    [101] 赵紫瑄,陈梦醒,周晓晶. 基于传感器监测数据的预测泌乳牛乳房炎机器学习算法研究[J]. 黑龙江畜牧兽医,2023(2):43-50. ZHAO Zixuan, CHEN Mengxing, ZHOU Xiaojing. Study on machine learning algorithm for predicting lactating cow mastitis based on sensor monitoring data[J]. Heilongjiang Animal Science and Veterinary Medicine, 2023(2): 43-50. (in Chinese with English abstract

    ZHAO Zixuan, CHEN Mengxing, ZHOU Xiaojing. Study on machine learning algorithm for predicting lactating cow mastitis based on sensor monitoring data[J]. Heilongjiang Animal Science and Veterinary Medicine, 2023(2): 43-50. (in Chinese with English abstract)
    [102] DENG Z, HOGEVEEN H, LAM T J G M, et al. Performance of online somatic cell count estimation in automatic milking systems[J]. Frontiers in Veterinary Science, 2020, 7:221-229. doi: 10.3389/fvets.2020.00221

    DENG Z, HOGEVEEN H, LAM T J G M, et al. Performance of online somatic cell count estimation in automatic milking systems[J]. Frontiers in Veterinary Science, 2020, 7: 221-229. doi: 10.3389/fvets.2020.00221
    • 相关文章
    • 施引文献(4)

  • 期刊类型引用(3)

    1. 班泽宇，王春光，宗哲英，苏力德，王帅，苑文博，袁泽，任晓丹. 奶牛乳房炎检测方法的研究进展:传统方法、传感器与计算机视觉. 内蒙古农业大学学报(自然科学版). 2025(01): 89-100 . 百度学术
    2. 刘敏清，王得宁，张文慧，刘怡萱，董晴，姜雪峰，冯海鹏，张康. 甘肃、宁夏部分地区奶牛乳房炎病原分离鉴定. 中国乳业. 2024(04): 36-41 . 百度学术
    3. 王丽娜，张小宁，张学虎. 奶牛乳房炎病原菌的分离鉴定与耐药性分析. 中国动物保健. 2024(08): 120-121 . 百度学术

    其他类型引用(1)

    • 资源附件(0)
图(4)  /  表(3)
计量
  • 文章访问数:  104
  • HTML全文浏览量:  0
  • PDF下载量:  113
  • 被引次数: 4
出版历程
  • 收稿日期:  2023-03-20
  • 修回日期:  2023-05-05
  • 网络出版日期:  2023-08-01
  • 刊出日期:  2023-06-14

目录

摘要
HTML全文

  • 0.   引　言

  • 1.   基于视觉传感器的奶牛乳房炎检测技术

  • 1.1   基于乳房热红外图像的奶牛乳房炎检测

  • 1.2   基于乳汁图像的奶牛乳房炎检测

  • 2.   基于自动挤奶系统的奶牛乳房炎检测技术

  • 3.   基于其他传感器的奶牛乳房炎检测技术

  • 4.   讨　论

  • 4.1   当前主要挑战

  • 4.2   未来发展趋势

  • 5.   结　语

参考文献(102)
相关文章
施引文献(4)
资源附件(0)

/

返回文章
返回
友情链接>

版权所有 © 农业工程学报 京ICP备06025802号-3

地址：北京朝阳区麦子店街41号（100125）

电话：010-59197078/7077/7076

邮箱：tcsae@tcsae.org

邮件订阅 RSS

  • 今日头条
    今日头条
  • 抖音号
    抖音号
  • 视频号
    视频号
  • 淘宝
    淘宝
  • 微店
    微店

本系统由 北京仁和汇智信息技术有限公司 开发  百度统计