Use of precision technologies and advanced analytical techniques for early detection and measurement of lameness in dairy herds

使用精密技术和先进的分析技术来早期检测和测量奶牛群的跛行

• 批准号: 2593739
• 金额: --
• 依托单位: University of Nottingham
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2593739
• 关键词: Use; precision; technologies; advanced; analytical

Early intervention is critical to improving treatment outcomes and reducing recurrence of lameness in dairy cows; however, this is dependent on the reliable detection of lame cows. Advances in sensor and smart computing technologies and their use on-farm provide possibilities to achieve this and therefore potential to produce huge gains for the industry through lameness reduction. This research aims to explore and develop novel data driven solutions for accurate automated identification of lameness in dairy cattle, using cutting-edge sensor technologies. The approaches to develop technology-based objective methods to measure lameness will include; 1) Using existing commercially available senor technologies to classify lameness 2) Investigate the feasibility of novel sensors to classify lameness 3) Optimise the use of multiple sensors and performance of learning algorithms from sensor data The research will combine advanced data analytics, including machine learning, with the practical aspects of developing a novel methodology of measurement. In addition, the industrial partner (Agriculture and Horticulture Development Board; AHDB) will provide the student with the opportunity to participate in work related to translation of research outputs to the industry. The successful applicant will gain knowledge in the feature engineering and use various machine learning algorithms, such as Neural Networks, K-nearest Neighbor, Support Vector Machines and Decision Trees. The research will be conducted at the 'Centre for Dairy Science Innovation' (CDSI) at Nottingham, utilising recent investments in this high-level research infrastructure. The successful student will also spend a period of time with the industrial partner, AHDB.

早期干预对于改善治疗结果和减少奶牛跛行复发至关重要;然而，这取决于对跛行奶牛的可靠检测。传感器和智能计算技术的进步及其在农场的使用为实现这一目标提供了可能性，因此有可能通过减少跛行为该行业带来巨大收益。本研究旨在探索和开发新的数据驱动的解决方案，用于使用尖端的传感器技术准确自动识别奶牛跛行。开发基于技术的客观方法来测量跛行的方法包括：1）使用现有的市售传感器技术对跛行进行分类2）调查新型传感器对跛行进行分类的可行性3）优化多个传感器的使用和从传感器数据中学习算法的性能该研究将结合联合收割机先进的数据分析，包括机器学习，与开发一种新的测量方法的实际方面。此外，工业合作伙伴（农业和园艺发展委员会; AHDB）将为学生提供参与将研究成果转化为工业的机会。成功的申请人将获得特征工程方面的知识，并使用各种机器学习算法，如神经网络，K最近邻，支持向量机和决策树。这项研究将在诺丁汉的“乳品科学创新中心”（CDSI）进行，利用最近对这一高水平研究基础设施的投资。成功的学生还将与工业合作伙伴AHDB一起度过一段时间。