摘要
由一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-关于人工智能的最新研究结果已经发表。根据NewsRx编辑来自Italy Firenze的消息，这项研究指出：“利用智能手机在农民中的广泛应用和人工智能在计算机视觉中的应用，最近在农业领域出现了各种各样的移动应用。本文介绍了GranoScan，这是一款可以在主要在线平台上免费访问的移动电子应用程序。”专为实时检测和识别80多种影响地中海地区小麦的威胁而设计。新闻记者从National Research Council(CNR)的研究中获得了一句话："通过与意大利农民直接合作的共同设计方法开发，这种参与性方法产生了一个应用程序feature：(i)为不同的野外照明条件优化的图形界面，(ii)用户友好的界面，允许从预先定义的菜单中快速选择，(iii)即使在低连接或没有连接的情况下也可操作。(iv)一个简单的操作指南，以及(v)在PHOT O中指定目标威胁识别感兴趣的领域的能力。GranoScan的基础是一个名为高效最小自适应集成的深度学习架构，用于获得准确和可靠的人工智能模型。该方法基于一种使用EfficientNet-b0架构的两个实例作为核心模型的扩展策略，在此阶段，对害虫、叶害、根病、穗茎病等各类任务的精度达到了100%，对发芽后阶段杂草的精度在80%和100%之间，对开花前杂草的精度在100%之间，对所有各类杂草的精度都达到了100%，对发芽后杂草的精度在80%和100%之间，对开花前杂草的精度在100%之间。在对最终用户野外照片的识别精度方面，GranoScan取得了良好的性能，对叶斑病和穗病、茎病和根病的平均识别率分别为77%和95%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news originating from Firenze, Ital y, by NewsRx editors, the research stated, "Capitalizing on the widespread adopt ion of smartphones among farmers and the application of artificial intelligence in computer vision, a variety of mobile applications have recently emerged in th e agricultural domain. This paper introduces GranoScan, a freely available mobil e app accessible on major online platforms, specifically designed for the real-t ime detection and identification of over 80 threats affecting wheat in the Medit erranean region." The news journalists obtained a quote from the research from National Research C ouncil (CNR): "Developed through a co-design methodology involving direct collab oration with Italian farmers, this participatory approach resulted in an app fea turing: (i) a graphical interface optimized for diverse in-field lighting condit ions, (ii) a user-friendly interface allowing swift selection from a predefined menu, (iii) operability even in low or no connectivity, (iv) a straightforward o perational guide, and (v) the ability to specify an area of interest in the phot o for targeted threat identification. Underpinning GranoScan is a deep learning architecture named efficient minimal adaptive ensembling that was used to obtain accurate and robust artificial intelligence models. The method is based on an e nsembling strategy that uses as core models two instances of the EfficientNet-b0 architecture, selected through the weighted F1-score. In this phase a very good precision is reached with peaks of 100% for pests, as well as in leaf damage and root disease tasks, and in some classes of spike and stem diseas e tasks. For weeds in the post-germination phase, the precision values range bet ween 80% and 100%, while 100% is reache d in all the classes for preflowering weeds, except one. Regarding recognition accuracy towards end-users in-field photos, GranoScan achieved good performances , with a mean accuracy of 77% and 95% for leaf disea ses and for spike, stem and root diseases, respectively."
NETL
NSTL