I-Corps: Herd Management through Internet of Things Systems
I-Corps: Herd Management through Internet of Things Systems
批准号:
1943346
负责人:
Joseph Skovira
金额:
$5.0万
依托单位:
依托单位国家:
美国
项目类别:
Standard Grant
财政年份:
2019
资助国家:
美国
项目状态:
已结题
起止时间:
2019-09-15 至 2021-02-28
中文摘要
该I-Corps项目的更广泛影响/商业潜力是通过测量个体奶牛采食量来提高奶牛的产奶效率,这是一个重要的数据点,通常在行业中无法获得。该数据点使奶农能够优化饮食配方,从而提高每头奶牛的产奶量,并通过提供足够的营养来支持奶牛的产奶水平,从而减少疾病。 使用来自该平台的数据也将有可能改善牛群的基因库。 该项目的商业影响有可能通过提供早期检测五种最常见疾病和节省饲料成本的重要好处,为奶农节省大量成本。这个I-Corps项目使用定制设计的射频识别传感器平台,安装在饲养通道和奶牛场的垫料上。这些传感器的设计目的是区分奶牛是否食用或筛选饲料,以提供一种新的有效方式来监测每头奶牛的干物质摄入量。传感器还可以捕捉每头奶牛躺下的时间(反刍时间)和进入饲喂场的次数。传感器收集的所有数据都将持续发送到云端,并通过独特的机器学习算法进行分析,以确定每头奶牛的一系列行为事件,包括饲料摄入量监测,以确定饲料效率最高/最低的奶牛。一段时间内采食量的减少也意味着疾病的发生,可以在成为临床病例之前被发现,以减少抗生素的使用。该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查标准进行评估,被认为值得支持。
英文摘要
The broader impact/commercial potential of this I-Corps project is to improve milk production efficiency of dairy cows by measuring individual cow feed intake, a vital datapoint not typically commercially available in the industry. This datapoint allows dairy farmers to optimize diet formulation which would result in higher milk production per cow and reduce illnesses by being able to provide sufficient nutrients to support the cow's level of milk production. Using the data derived from this platform will also potentially improve the genetic pool of the herd. The commercial impact of the project has the potential to result in significant cost savings for dairy farmers by providing the vital benefits of early detection of the five most common diseases and feed costs savings.This I-Corps project uses custom-designed radio frequency identification sensor platform that is installed on feeding alleys and bedding of dairy barns. The sensors are designed to distinguish a cow from consuming or sifting through the feeds to provide a new and efficient way of monitoring dry matter intake on a per cow basis. The sensors also capture individual cow's time spent lying down (rumination time) and the number of visits to the feeding alley. All data gathered by the sensors are sent to the cloud continuously and analyzed by unique machine-learning algorithms to determine a range of behavioral events per individual cow, including feed intake monitoring to identify the most/least feed efficient cows. Decrease in feed intake over a period of time also signifies the onset of illnesses which can be detected prior to becoming clinical cases to reduce the use of antibiotics.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
海外基金