I-Corps: Data Analytics for Hand-Picked Agriculture

I-Corps项目的更广泛的影响/商业潜力是通过个性化的地理空间数据收集来改善手工收获的粮食作物的食品安全和保障。就像高速公路摄像头有能力告知给定高速公路的交通状况一样，通过每个司机和他们的手机的个性化数据，极大地改善了高速公路上的交通状况，手工收获的食物可以受益于从街区级别的数据到单一收割点的可跟踪性和透明度的提高，回忆起交叉地图数据。与文本块数据相比，特定于地理位置的数据还可以更好地测量土地生产力。个性化的、个人拥有的数据使员工能够拥有信息的可携带性，从而构建一份可靠性和绩效的简历。此外，它还成为可行的透明计划的一个组成部分。该项目将潜在地提高收割机的经济地位，提高农民更好地了解他们的劳动力和土地的能力，帮助营销人员改善数据，以确保食品安全不会出现故障，并使消费者在不增加系统步骤的情况下提高透明度。这个i-Corps项目进一步开发了高价值手工采摘的特殊作物的改进数据收集方法。问题中的数据是关于谁收获了什么、何时何地收获的准确记录。背景数据(质量、灌溉/施肥数据、文化实践地图等)为农民添加并可视化。该项目将测试数据集之间的关系，以提高决策技能；更好的管理取决于更好的衡量标准。它提供了对空间和时间不均匀的更好的理解。解决这些不均衡性导致调查和减少差异。该系统将能够理解劳动力过程中的瓶颈和工作流问题，并允许动态和实时的决策。该系统还将允许采用量化方法，在系统的几个部分寻找最佳决策，并为根据共同数据进行分散决策提供一个平台。

The broader impact/commercial potential of this I-Corps project is to improve food safety and security of hand harvested food crops through individualized geo-spatial data collection. Much like highway cameras have an ability to tell the status of traffic on a given freeway are vastly improved through the individualized data of each driver and their phones, hand harvested food can benefit from improving traceability and transparency from block level data to single points of harvest, recalling intersecting mapping data. Geo-specific data can also enable better land productivity measurement over textual block data. Individualized, personally owned, data enables workers to have portability of information, building a resume of dependability and performance. In addition, it becomes an integral component of a viable transparency scheme. The project will potentially improve the economic standing of harvesters, improve the capability of farmers to better understand their workforce and land, assist marketers with improved data to insure against breakdowns in food safety, and enable consumers transparency without added steps to the system.This I-Corps project further develops improved data collection methods in high-value hand-picked specialty crops. The data in question is a precise record of who harvests what, where and when. Contextual data (quality, irrigation/fertilization data, cultural practice maps, etc.) are added and visualized for farmers. The project will test the relationship of data sets toward improved decision skills; better management depends on better measurement. It provides a better understanding of inhomogeneities in space and time. Addressing these inhomogeneities leading to investigation and reductions of variance. The system will enables comprehension of bottlenecks and workflow problems in labor process and allow dynamic and real-time decisions. The system will also allow quantitative approaches toward finding optimal decisions in several parts of the system and provide a platform for decentralized decision-making based on common data.