Asset Data Amalgamation and Analysis for Agricultural Platform

农业平台资产数据融合与分析

• 批准号: 570644-2021
• 负责人: Blum, Susan
• 金额: $ 1.82万
• 依托单位: Saskatchewan Polytechnic
• 依托单位国家: 加拿大
• 项目类别: Applied Research and Development Grants - Level 1
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=724638
• 关键词: Asset; Data; Amalgamation; Analysis; Agricultural

In partnership with Mera Development Corp (MDC), Saskatchewan Polytechnic (SP) is developing a sub system for MDC's Asset Data Management (ADaM) platform. Specifically, the proposed applied research will develop a system capable of performing data aggregation and migration across multiple corporate databases while maintaining or introducing relationships between the data points. The system infrastructure will collect, scan and import data to a NoSQL database (Lake). That aggregated data will be used to support machine learning (ML) and AI algorithms to provide end users with analysis of their data. The Engage phase of the project will focus on data migration and preprocessing. This will involve: (a) building the database (DB) and user interface, (b) determine how to best migrate the data from different types (brands) of database (c) and selection of the appropriate preprocessing techniques for that data. This sets the foundation to allow individuals without extensive data expertise to migrate and preprocess their data. The application will benefit anyone who needs to take more control over their data aggregation strategies and aid in the application of ADaM functionality to improve and optimize their business and manufacturing processes.

萨斯喀彻温理工学院 (SP) 与 Mera Development Corp (MDC) 合作，正在为 MDC 的资产数据管理 (ADaM) 平台开发子系统。具体来说，拟议的应用研究将开发一个能够跨多个企业数据库执行数据聚合和迁移的系统，同时维护或引入数据点之间的关系。系统基础设施将收集、扫描数据并将其导入到 NoSQL 数据库（Lake）。这些聚合数据将用于支持机器学习 (ML) 和人工智能算法，为最终用户提供数据分析。该项目的参与阶段将重点关注数据迁移和预处理。这将涉及：(a) 构建数据库 (DB) 和用户界面，(b) 确定如何最好地从不同类型（品牌）的数据库迁移数据，(c) 并为该数据选择适当的预处理技术。这为没有丰富数据专业知识的个人迁移和预处理数据奠定了基础。该应用程序将使任何需要更多地控制其数据聚合策略并帮助应用 ADaM 功能来改进和优化其业务和制造流程的人受益。