SEMANTIC ANNOTATION OF AQUACULTURE PRODUCTION DATA

被引:0
作者
Amaral, Pedro [1 ]
Oliveira, Pedro [1 ]
Moutinho, Marcio [2 ]
Matado, Daniel [3 ]
Costa, Ruben [1 ]
Sarraipa, Joao [1 ]
机构
[1] Univ Nova Lisboa, FCT, UNINOVA, CTS,Dept Engn Electrotecn, P-2829516 Caparica, Portugal
[2] Fed Univ Western Para, UFOPA, IEG, PC, Santarem, Brazil
[3] Univ Nova Lisboa, Fac Ciencias & Tecnol, Dep Engn Electrotecn, Caparica, Portugal
来源
PROCEEDINGS OF THE ASME INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, 2016, VOL. 2 | 2016年
基金
欧盟地平线“2020”;
关键词
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Aquaculture is probably the fastest growing food-producing sector in the world producing nearly 50 percent of the fish that is Used for food, according to the Food and Agriculture Organization of the United Nations (FAO). With the growing of the Aquaculture sector, problems of global knowledge access, seamless data exchanges and lack of data reuse between aquaculture companies and its related stakeholders become more evident. From an IT perspective, aquaculture is characterized by high volumes of heterogeneous data, and lack of interoperability intra and inter-organizations. Each organization uses different data representations, using its native languages and legacy classification systems to manage and organize information, leading to a problem of integrating information from different sources due to lack of semantic interoperability that exists among knowledge organization tools used in different information systems. The lack of semantic interoperability that exists can be minimized, if innovative semantic techniques for representing, indexing and searching sources of non-structured information are applied. To address these issues, authors are developing a platform specifically designed for the aquaculture sector, which will allow even small companies to explore their data and extract knowledge, to improve in terms of use of feed, environmental impact, growth of the fish, cost, etc.
引用
收藏
页数:7
相关论文
共 7 条
[1]  
Bo L., 2013, J KNOWLEDGE INFORM S, V34, P597
[2]  
FAO, 2015, FAO GLOSS
[3]  
FAO and MCS, 2013, YUNGA INT DRAW COMP
[4]   The importance of generalizability for anomaly detection [J].
Peterson, Gilbert L. ;
McBride, Brent T. .
KNOWLEDGE AND INFORMATION SYSTEMS, 2008, 14 (03) :377-392
[5]  
Sarraipa J., 2016, P 6 INT C INF SOC TE
[6]  
Varun C, 2008, EXPERT SYST APPL, V35, P1721
[7]   A process-mining framework for the detection of healthcare fraud and abuse [J].
Yang, WS ;
Hwang, SY .
EXPERT SYSTEMS WITH APPLICATIONS, 2006, 31 (01) :56-68