Accueil du site EFITA Congresses>EFITA 2005>AOS Workshop

Available folders
Development of Integrated Technological Information Systems to Support Land Management Projects in Portugal - R.P. Coito and P.E. Duarte - (18-10-2005)

A policy for land allocation and land consolidation, as well as technical tools to support it, are crucial for sustainable land resource management. In Portugal, one of the instruments used in the land management, to solve the most important structural problems that affect the rural areas, is the implementation of land consolidation projects. The land consolidation projects involve a new reallocation of the plots. This is a very complex procedure in technical terms and also rather time consuming. So we try to improve in this area and develop software that speeds up all technical operations, maintaining high precision and flexibility. So was created EUROPOF. More...

 
Development and Application of an Irrigation Ontology -- C. Cornejo, H.W. Beck, D.Z. Haman and F.S. Zazueta - (18-10-2005)

An ontology consisting of approximately 250 concepts and 300 relationships was constructed in the domain of irrigation. More specifically, the domain covers extension information and educational materials aimed at teaching small scale farmers basic principles of irrigation. The methodology used for constructing the ontology is presented. The top-level concepts in the domain ontology along with details and examples of concepts and relationships in the irrigation domain are also described. The ontology was created using on-line tools. These tools provide complete database management facilities for the ontology and educational content associated with concepts in the ontology including text, images, and other graphic elements. The database content is automatically converted into conventional Web pages and other formats to create educational materials on demand. More...

 
The Mapping Schema from Chinese Agricultural Thesaurus to AGROVOC - A. Liang, M. Sini, Chang Chun, Li Sijing, lu Wenlin, He Chunpei and J. Keizer - (18-10-2005)

This paper introduces the criteria and the procedures for mapping the Chinese Agricultural Thesaurus (CAT) to FAO's multilingual agricultural thesaurus AGROVOC. It proposes modifications to the inter-thesaurus mapping rules provided in the Simple Knowledge Organization System (SKOS) specification. It outlines in detail the criteria for the application of each of the mapping rules. We will describe the procedure for the application for these rules and give concrete examples taken from both thesauri. More...

 
Thesaurus-Based Index Term Extraction for Agricultural Documents -- Olena Medelyan and Ian H. Witten - (12-9-2005)

This paper describes a new algorithm for automatically extracting index terms from documents relating to the domain of agriculture. The domain-specific Agrovoc thesaurus developed by the FAO is used both as a controlled vocabulary and as a knowledge base for semantic matching. The automatically assigned terms are evaluated against a manually indexed 200-item sample of the FAO's document repository, and the performance of the new algorithm is compared with a state-of-the-art system for keyphrase extraction More...

 
Ontology building process: The wine domain -- João Graça, Márcio Mourão, Orlando Anunciação, Pedro Monteiro, H. Sofia Pinto and Virgílio Loureiro - (12-9-2005)

Several attempts have been made to structure and systematize the enology field. This work proposes a new ontology for the wine domain according to several features: (i) maceration; (ii) fermentation process; (iii) grape maturity state; (iv) wine characteristics; (v) classification system according to country; and (vi) region where the wine was produced. This work describes how this ontology was built by non-ontology engineering experts from scratch. The development process followed four phases: (i) knowledge acquisition; (ii) conceptualization; (iii) formalization; and (iv) evaluation. Some of these phases occurred simultaneously (for example, evaluation was done in all phases). The final outcome was an useful and comprehensive ontology in the enology field, which we plan to use in a system that allows searching for wines using any combination of features More...

 
Automatic Term Relationship Cleaning and Refinement for AGROVOC -- Asanee Kawtrakul, A. Imsombut, A. Thunyakijjanukit, D. Soergel, Anita Liang, M. Sini, G. Johannsen, J. Keizer - (12-9-2005)

AGROVOC is a multilingual thesaurus developed and maintained by the Food and Agricultural Organization of the United Nations. Like all thesauri, it contains some explicit semantics, which allow it to be transformed into an ontology or used as a resource for ontology construction. However, most thesauri, AGROVOC included, give very broad relationships that lack the semantic precision needed in an ontology. Many relationships in a thesaurus are incorrectly applied or defined too broadly. Accordingly, extracting ontological relationships from a thesaurus requires data cleaning and refinement of semantic relationships. This paper presents a hybrid approach for (semi-)automatically detecting these problematic relationships and for suggesting more precisely defined ones. The system consists of three main modules: Rule Acquisition, Detection and Suggestion, and Verification. The Refinement Rule Acquisition module is used to acquire rules specified by experts and through machine learning. The Detection and Suggestion module uses noun phrase analysis and WordNet alignment to detect incorrect relationships and to suggest more appropriate ones based on the application of the acquired rules. The Verification module is a tool for confirming the proposed relationships. We are currently trying to apply the learning system with some semantic relationships to test our method More...

 
Food Informatics: Sharing Food Knowledge for Research & Development -- Nicole J.J.P. Koenderink, J. Lars Hulzebos, Hajo Rijgersberg and Jan L. Top - (12-9-2005)

For industrial and academic food researchers it is at present difficult to benefit from each other's data, models and experimental knowledge. Within the Food Informatics project, we recognise the need for the possibility to exchange both general and more specific food knowledge. We work on using both generic and specific knowledge as a basis for ontologies. These ontologies can be used as a means to easily access and exchange existing food knowledge. In this paper, we describe a framework for creating ontologies on the basis of existing knowledge in the form of thesauri, food models and ontologies. The knowledge contained in these structures is obtained by expert interaction, by interpreting highly structured text documents and by (semi-)automatically extracting domain knowledge from literature and Internet. In this paper, we focus on methods and tools used for extracting knowledge in the domain of food industry. More...

 
A Crop-Pest Ontology for Extension Publications -- Howard W. Beck, Soonho Kim and Diana Hagan - (12-9-2005)

An ontology in the crop-pest domain has been developed which includes concepts and relationships on crops, associated pests (insects, diseases, weeds, nematodes, and mammals), and pest management issues (integrated pest management, chemical control methods, biological control). The ontology was developed to act as a classification system for publications within EDIS (Extension Digital Information Source). EDIS is a collection of over 7000 publications developed and maintained by the Florida Cooperative Extension Service at the University of Florida. EDIS includes publications covering all aspects of Florida agricultural, natural resources, family/youth, and consumer-related information. The crop-pest ontology contains over 700 concepts, and covers approximately 1/3 of the concepts in EDIS. EDIS originally contained a loosely structure topic index with over 2000 topics, and also includes a traditional full-text search engine. The crop-pest ontology was developed in part to demonstrate the effectiveness of an ontology on searching a relatively small and manageable collection compared to these existing methods. The ontology was constructed by examining the original topic index and manually extracting concepts related to the crop-pest domain. Relationships among concepts were identified and entered into an ontology database (Lyra). The resulting ontology was compared to the original topic index in order to show advantages of using a more formally structured ontology. The crop-pest ontology is being expanded for use in classifying educational resources on biosecurity for the National Plant Diagnostics network. Results of these studies are presented. More...

 
Establishing basic infrastructural and methodological background of Semantic Web in the domain of food and agriculture in Hungary -- Laszlo Gabor Papocsi and Ferenc Kulcsar - (12-9-2005)

Agro-food ontology in the national language has been recently developed in Hungary by the translation of AGROVOC, using target oriented, online workflow management interface. The integration of semantic web standards and use of ontology is carried out in the course of implementing ongoing projects and developing new programmes. Besides basic semantic functions such as automated indexing, concept search, multilinguality and ranking; development of fingerprint technology and building of specialised ontologies are also envisioned according to the subject area of each project. More...

 
Overview of an efficient knowledge management model for improving the role of agriculture educational system in the process of developing a knowledge-based agriculture: the case of Iran -- Hamidreza Mokhtari, Behrooz Arastoo and Omid Jahanshahi - (12-9-2005)

Agriculture is an important aspect of Iranians economy and life. While there are great opportunities for excellent agricultural activities, the rate of development in agriculture has not been satisfactory yet. A reason for this dissatisfaction is that the moving toward a knowledge-based agriculture, which is the origin of the accelerated economic development in modern world, has been retarded in Iran. Based on a model proposed by USAID and in accordance with the conditions of Agriculture Education in Iran, a model has been suggested. The Knowledge Management Model for Agriculture Educational system consists of organizations and relationships between them that aim toward empowering the focal point of any agriculture production system which is agriculture household. A key entity in the model is knowledge centre that is very much similar to a library but with more varied resources, more sophisticated technologies, wider scope of activities and a more competent manager who is called a CKO. Analysing the model according to a standard measure like SWOT shows that there are many points that must be considered before the implementation of the model. Among the strengths, the systems approach is very important while in its weaknesses the opinions of the managers and the unstablished structure of the organizations seems to be critical. On the other hand there are opportunities like TAKFA-the Farsi word for the plan of development and usage of IT- that has a large amount of money available for suchlike plans. At last the most important threat is the changes in the managerial teams. More...

 
Design Approach for a Crop Information System in Mexico -- Yolanda Fernandez-Ordonez and Jesus Soria-Ruiz - (12-9-2005)

Up-to-date information on agricultural land use at the crop level is needed by several instances of the Mexican government on a yearly basis. In order to elaborate and implement policies this information must be as accurate as possible. Traditional methods of field surveying and sampling fall short of the required timeliness and accuracy. The State of Mexico is the first one amongst the 32 states of the country to have an information system on crop occupation and soil use at the 1:50,000 scale since 2003. The base information, which was gathered by a team of agronomical researchers and computer experts from satellite remote sensing, GPS/PDA (global positioning system/ personal digital assistant) instruments and extensive field work, is available to final users through statistics and maps displayed on screen or on printed format. This paper describes the general approach to the design and implementation of the SIUSEMex (Sistema de Información del Uso actual del Suelo del Estado de Mexico) information system. The design approach relies on current software engineering practices; in particular, the use case element of UML (Unified Modeling Language) is utilized to elicit and collect user requirements, and in other parts of the software development process. The paper discusses the perspectives for the evolution of the system, namely its planned connection to other land use databases currently being developed in Mexico and its applicability to other states in the country More...

 


Accueil du site EFITA Congresses>EFITA 2005>AOS Workshop
Document printing...Send a link to this document by e-mail

ACTA Informatique - 149 rue de Bercy 75595 PARIS cedex 12 Tél : 01 40 04 50 35 Mél : webmaster@acta-informatique.fr