Application of Common Information platform to foster Data-driven Agriculture in Taiwan In 2017, the Council of Agriculture in Taiwan initiated
“Smart Agriculture (SA)”, a 6-year research program.
Base on sensor/sensing technologies, intelligent robots, Internet of Things (IoTs) and big data analytics, it is expected to build smart production, marketing and digital service systems locally to efficiently enhance the whole agricultural productivity and capacity.
In addition, it is anticipated to build an active, all-purpose agricultural consumption/service platform to integrate important information and technical resources in agriculture, fishery and livestock to facilitate the convenient usage of data and digital service, thus increasing customer’s trust for food safety and fostering data-driven agriculture. In the SA program, especially, a common information platform (CIP) which uses the Open Application Programming Interface (Open API) to connect with a range of existing application databases has been established.
Some applications of the CIP to foster data-driven agriculture in future are being developed and presented in this paper. Firstly, by integrating Information and Communication Technologies with the CIP, some digital agricultural convenience services are provided.
In order to provide the optimal growing environment for crops under facility cultivation, utilization of IoTs in facilities is definitely necessary. Some information systems in the agricultural facilities are therefore built
for accumulating information in terms of agricultural m at e r ials, m a np owe r, t r a ce able ag r icu lt u r al products and production scheduling. Integrated with environmental control and crop production management systems, all information come from these systems will be shown on a dashboard to form ‘SITUATION ROOM’ module, allowing different managers to grasp the status of facilities and crops through mobile devices and facilitate the management by walking around to effectively take advantage of the optimal use of assets and production resources. Additionally, the collection of the production and management data will be used to analyze and predict the production capacity of every farm in each region. These results of analysis and prediction will then become the basis for production decision-making. Besides, utilization of big data analytic technology embedded in the CIP has generated some expert group decision models. These models will not only provide decision-making advices for agricultural production management, but also establish integrated application models of agricultural value chain. Last but not the least, by providing a consumer-oriented production model and constructing a cross-channel between production and marketing, a digital service system has been established. With information services taking machine-readable, format-open, interface-indexing and machine-writable into consideration, a mechanism based on open application interface program is established to provide services for farmers, agricultural enterprises and system developers. For example, a common agricultural consumption/service platform is implemented to connect the supply chain of agricultural produce (food) between farmers and consumers. At present, traceable food safety information services given by ‘LUNCH MONITOR’ module has been applied for campus lunches in more than 3,000 primary and secondary schools through big data exchange mechanism. The mechanism can establish a traceability food chain management between the origins and schools, and provide more immediate and convenient information
農 藝 作 物
for food safety. As a result, the risks and reaction time of food safety incident will be reduced, thus increasing the trust of all stakeholders on food safety.
Application of Common Information Platform and Agricultural Management System “i-PLANT”
for Consumer-Friendly Food Production in Taiwan The agro-product traceability system is considered an approach that may lead to create product differentiation in the market, elevate product competitiveness, and bring about better production and consumption environment for agro-products in Taiwan. Through the integration of self-monitoring by agro-product operators, verification of product sources by distributors, feedback from consumers and government oversight with regulation, the local agricultural sector is able to promote the effectiveness of Taiwan’s agro-product traceability system and help to differentiate these products in the market.
“Smart Agriculture (SA)”, a 6-year research program initiated by the Council of Agriculture in 2017 and based on sensor/sensing technology, intelligent robot, internet of things (IoTs) and big data analysis, is expected to build locally smar t production, marketing and digital service systems to efficiently enhance the whole agricultural productivity and capacity. Furthermore, it is anticipated to build an active, all-purpose agricultural consumption/service platform to increase customer’s trust for food safety by completing the program. In the SA program, a common information platform which uses the Open Application Programming Interface (Open API) to connect with a range of existing application databases has been established. According to the policy of the food safety, all primary and secondary schools need to use traceable agricultural and aquaculture products tagged with the information of the “3 Labels and One QR Code (3L1Q)” The Campus Food Ingredients Registration Platform of the Ministry of Education can get food safety information daily from the common information platform by Open API mechanism to ensure safety of campus lunch. The agriculture
management system “i-PLANT” applies technologies in terms of geographic information system (GIS), IoTs and aerial photography, as well as cumulative agricultural experience and the information recorded via the mobile application (APP) of crop production.
That is, ‘i-PLANT’ combines environmental layer nesting with data services for field production risk management and decision analysis. It promises a new type of “agriculture service industry”, which allows farmers to cultivate and record field data more easily and also enables consumers to eat with confidence for food safety. Moreover, the relationship between agricultural operations and food can be further strengthened by the system, connecting the upstream agricultural production and middle or lower reached logistics sales to smart agri-food supply chains.
全基因體QTL 熱點檢測之研究 全基因體 QTL 望QTL 頻 度（expected QTL frequency, EQF）， 將 QTL 區間資料應用均勻分布轉換為期望 QTL 頻度矩 陣（EQF matrix），接著考量性狀間的相關性做分 群，再合併各群內性狀之EQF 獲得降維的 EQF 矩 陣，性狀分群後的置換演算能得到較嚴格的門檻值，
避免檢測到假熱點。本方法所開發的QHOT 套件已 可在R CRAN 供下載使用。
Introduction to the Plant Protection Network Platform Plant protection experts from Taiwan’s governmental agricultural research units (including Taiwan Agricultural Research Institute, Council of Agriculture, Executive Yuan (TARI), the Agricultural Research and Extension Stations and the Tea Research and Extension Stations) have engaged in long-term
農 藝 作 物
pest diagnosis and consultation undertakings. In general, farmers would provide crop pest samples, such as strains, leaves, flowers, branches, or fruits, farmland locations, crop names and field management (including pesticide and fer tilizer application situations) and other related data, which enable plant protection experts to execute pest diagnostic appraisal and related consultation work. In addition, they visited the sites whenever necessary to perform more comprehensive diagnostic consultation. Although the agencies accumulated considerable pest diagnostic information for executing the undertakings over the years, the research units lacked effective informative management and value-added applications. Even though the current plant protection experts are well experienced in pest appraisal, the most plant protection experts kept the records on paper or scattered in the computer files with different ways. Take wood pests for example, by examining the holes on the surface of wood, the category of pest possibly hiding inside the wood can be determined. However, the critical pest appraisal knowledge are usually unavailable with words and may be lost with the relocation of personnel involved. In addition, some research units have already established appraisal information systems for specific pest categories. Nevertheless, these systems may differ in datasheet format and program language and are
facing issues such as sustainability, management, and maintenance. In view of the aforementioned issues, the TARI set up the “Plant Protection Network Platform” in 2018, which was intended for plant protection experts in Taiwan to jointly conduct pest diagnostic appraisal research on the platform, facilitate information integration, sharing and value-added applications among the research units through platform use, thereby providing more multi-faceted services and reducing information exchange and integration problems. The main features of the platform are briefed below.
利 用RStudio 及 roxygen2 套 件 建 立 屬 於自己 的R 套件 R 是一個結合統計分析與繪圖功能的免 費自由軟體，主要用於統計分析及圖表繪製，最早 由Ross Ihaka 與 Robert Gentleman（1966）所開發，
因此稱為R。目前開發的核心團隊是由一群熱心專 業的統計資訊學者所組成，其網址為：https://www.
r-project.org，該網站中可見到 R 有多種不同作業系 統版本，例如Unix、Windows 及 MacOS，及有關 R 的操作手冊與常見問題等學習資源。R 本身也是一 種程式語言，如發展新的分析方法，可自行撰寫程 式來做資料分析，亦有研究員將最新發表的統計方 法寫成R 套件（Packages，R 使用者撰寫的功能）
搭配發表期刊方式公開分享，R 的功能可以透過安 裝套件增強，本文將以Windows 為例，說明如何利 用RStudio 及 roxygen2 套件，建立自己的 R 套件並 上傳到R CRAN 分享。