Open Spatiotemporal Data Warehouse For Agriculture Production Analytics

Wisnubhadra, Irya and Kamal Baharin, Safiza Suhana and Herman, Nanna Suryana (2020) Open Spatiotemporal Data Warehouse For Agriculture Production Analytics. International Journal of Intelligent Engineering and Systems, 13 (6). pp. 419-431. ISSN 2185-3118

Text 2020123137.PDF Download (901kB)

Abstract

Business Intelligence (BI) technology with Extract, Transform, and Loading process, Data Warehouse, and OLAP have demonstrated the ability of information and knowledge generation for supporting decision making. In the last decade, the advancement of the Web 2.0 technology is improving the accessibility of web of data across the cloud. Linked Open Data, Linked Open Statistical Data, and Open Government Data is increasing massively, creating a more significant computer-recognizable data available for sharing. In agricultural production analytics, data resources with high availability and accessibility is a primary requirement. However, today’s data accessibility for production analytics is limited in the 2 or 3-stars open data format and rarely has attributes for spatiotemporal analytics. The new data warehouse concept has a new approach to combine the openness of data resources with mobility or spatiotemporal data in nature. This new approach could help the decision-makers to use external data to make a crucial decision more intuitive and flexible. This paper proposed the development of a spatiotemporal data warehouse with an integration process using service-oriented architecture and open data sources. The data sources are originating from the Village and Rural Area Information System (SIDeKa) that capture the agricultural production transaction in a daily manner. This paper also describes the way to spatiotemporal analytics for agricultural production using a new spatiotemporal data warehouse approach. The experiment results, by executing six relevant spatiotemporal query samples on DW with fact table contains 324096 tuples with temporal integer/float for each tuple, 4495 tuples of field dimension with geographic data as polygons, 80 tuples of village dimension, dozens of tuples of the district, subdistrict, province dimensions. The DW time dimension contains 3653 tuples representing a date for ten years, proved that this new approach has a convenient, simple model, and expressive performance for supporting executive to make decisions on agriculture production analytics based on spatiotemporal data. This research also underlines the prospects for scaling and nurturing the spatiotemporal data warehouse initiative.

Item Type:	Article
Uncontrolled Keywords:	Agriculture production analytics, Data warehouse, Open data, Spatiotemporal
Divisions:	Faculty of Information and Communication Technology
Depositing User:	Sabariah Ismail
Date Deposited:	10 Dec 2020 16:44
Last Modified:	10 Dec 2020 16:44
URI:	http://eprints.utem.edu.my/id/eprint/24835
Statistic Details:	View Download Statistic

Actions (login required)

View Item