Anusha Indika Walisadeera

An ontological approach to meet information needs of farmers in sri lanka

Farmers in Sri Lanka are badly affected by not being able to get vital information required to support their farming activities in a timely manner. Some of the required information can be found in government websites, agriculture department leaflets, and through radio and television programs on agriculture. Due to its unstructured and varied format, and lack of targeted delivery methods, this knowledge is not reaching the farmers. Therefore, this knowledge needs to be provided not only in a structured way, but also in a context-specific manner. To address this shortcoming an international collaborative research project was launched to develop a Social Life Network to provide necessary information to farmers using mobile devices. Agricultural information has strong local characteristics in relation to climate, culture, history, languages, and local plant varieties. These local characteristics as well as the need to provide information in a context-specific manner made us to develop an ontology for agriculture. In this paper we present the approach we used to derive contextual information related to the farmers and the ontological approach that we developed to meet information needs of the farmers at various stages of the farming life cycle.

User centered ontology for Sri Lankan farmers

Abstract Farmers in Sri Lanka are badly affected by not being able to get vital information required to support their farming activities in a timely manner. Some of the required information can be found in government websites, agriculture department leaflets, and through radio and television programs on agriculture. This knowledge is not reaching the farmers due to its unstructured, incomplete, varied formats, and lack of targeted delivery methods. Thus finding the right information within the context in which information is required in a timely manner is a challenge. The information and knowledge needs to be provided not only in a structured and complete way, but also in a context-specific manner. For instance, farmers need agricultural information within the context of location of their farm land, their economic condition, their interest and beliefs, and available agricultural equipment. To investigate some of the underlying farmer centric research challenges an International Collaborative Research Project to develop mobile based information systems for people in developing countries has been launched. Farmer centered ontology was developed as part of this project. Agricultural information has strong local characteristics in relation to climate, culture, history, languages, and local plant varieties. These local characteristics as well as the need to provide information in a context-specific manner made us develop this user centered ontology for Sri Lankan farmers. Because of the complex nature of the relationships among various concepts we selected an ontological approach that supports description logic to create the knowledge repository. For this we developed a new approach to model the domain knowledge to meet particular access requirements of the farmers in Sri Lanka. Through this approach, we have investigated how to create a knowledge repository of agricultural information to respond to user queries taking into account the context in which information is needed by farmers at various stages of the farming life cycle. The Delphi Method and the OOPS! (web-based tool) were used to validate the ontology. Initial system was trialed with a group of farmers in Sri Lanka. The online knowledge base with a SPARQL endpoint was created to share and reuse the domain knowledge that can be queried based on farmer context.

Conceptualizing crop life cycle events to create a user centered ontology for farmers

People need contextualized information and knowledge to make better decisions. In case of farmers, the information that they require is available through agricultural websites, agriculture department leaflets and mass media. However, available information and knowledge are general, incomplete, heterogeneous, and unstructured. Since the farmers need the information and knowledge within their own context and need to represent information in complete and structured manner we developed a farmer centered ontology in the domain of agriculture. Because of the data complexity of the relationships among various concepts, to attenuate the incompleteness of the data, and also to add semantics and background knowledge about the domain we have selected a logic based ontological approach to create our knowledge repository. In this study, we have investigated how to model the actual representation of the domain and its challenges. The internal evaluation has been done to test the usefulness of the ontology during the design process. We have developed the online knowledge base that can be queried based on the farmer context.

Digital Knowledge Ecosystem for Achieving Sustainable Agriculture Production: A Case Study from Sri Lanka

Crop production problems are common in Sri Lanka which severely effect rural farmers, agriculture sector and the countrys economy as a whole. A deeper analysis revealed that the root cause was farmers and other stakeholders in the domain not receiving right information at the right time in the right format. Inspired by the rapid growth of mobile phone usage among farmers a mobile-based solution is sought to overcome this information gap. Farmers needed published information (quasi static) about crops, pests, diseases, land preparation, growing and harvesting methods and real-time situational information (dynamic) such as current crop production and market prices. This situational information is also needed by agriculture department, agro-chemical companies, buyers and various government agencies to ensure food security through effective supply chain planning whilst minimising waste. We developed a notion of context specific actionable information which enables user to act with least amount of further processing. User centered agriculture ontology was developed to convert published quasi static information to actionable information. We adopted empowerment theory to create empowerment-oriented farming processes to motivate farmers to act on this information and aggregated the transaction data to generate situational information. This created a holistic information flow model for agriculture domain similar to energy flow in biological ecosystems. Consequently, the initial Mobile-based Information System evolved into a Digital Knowledge Ecosystem that can predict current production situation in near real enabling government agencies to dynamically adjust the incentives offered to farmers for growing different types of crops to achieve sustainable agriculture production through crop diversification.

A Framework for End-to-End Ontology Management System

An Ontology once developed needs to be kept up-to-date preferably as a collaborative process which will require web based tools. We have developed a large user centered ontology for Sri Lankan agriculture domain to represent agricultural information and relevant knowledge that can be queried in user context. We have generalized our design approach. In doing so we have identified various processes that are required to manage an ontology as a collaborative process. Based on these processes we developed an ontology management system to manage the ontology life cycle. The main processes such as modify, extend and prune the ontology components as required are included. It also has facilities to capture users’ information needs in context for modifications, search domain information, reuse and share the ontological knowledge. This is a semi-automatic ontology management system that helps to develop and manage complex real-world applications based ontologies collaboratively.

Ontology Evaluation Approaches: A Case Study from Agriculture Domain

The quality of an ontology very much depends on its validity. Therefore, ontology validation and evaluation is very important task. However, according to the current literature, there is no agreed method or approach to evaluate an ontology. The choice of a suitable approach very much depends on the purpose of validation or evaluation, the application in which the ontology is to be used, and on what aspect of the ontology we are trying to validate or evaluate. We have developed large user centered ontology to represent agricultural information and relevant knowledge in user context for Sri Lankan farmers. In this paper, we described the validation and evaluation procedures we applied to verify the content and examine the applicability of the developed ontology. We obtained expert suggestions and assessments for the criteria used to develop the ontology as well as to obtain user feedback especially from the farmers to measure the ontological commitment. Delphi Method, Modified Delphi Method and OOPS! Web-based tool were used to validate the ontology in terms of accuracy and quality. The implemented ontology is evaluated internally and externally to identify the deficiencies of the artifact in use. An online knowledge base with a SPARQL endpoint was created to share and reuse the domain knowledge. It was also made use of for the evaluation process. A mobile-based application is developed to check user satisfaction on the knowledge provided by the ontology. Since there is no single best or preferred method for ontology evaluation we reviewed various approaches used to evaluate the ontology and finally identified classification for ontology evaluation approaches based on our work.

User-Friendly Ontology Structure Maintenance Mechanism Targeting Sri Lankan Agriculture Domain

As a result of recent enhancements in global knowledge sharing capabilities, knowledge representation and reasoning with ontologies for acquisition of implicit learning is gaining more attention among general communities. Agriculture being a dynamic economic sector in the Sri Lankan context, can massively benefit from such a knowledge repository that can be accessed and maintained by the community. However, existing approaches for ontology maintenance are complex and are designed for users with ontology-engineering expertise. Thus, despite numerous benefits, adoption and diffusion of ontology based knowledge systems within ontology-illiterate agriculture community is significantly hindered. This study investigates means of addressing the said limitation by proposing a user-friendly mechanism to incorporate evolving knowledge into ontologies. Updating the ontology structure while assuring real-time consistency maintenance is considered the prime objective of the approach. Task based evaluation results prove the effectiveness of our approach against the existing work.

User centered ontology for Sri Lankan agriculture domain

People working in the agriculture domain in Sri Lanka are affected by not being able to get vital information required to support their domain related activities in a timely manner. Some of the required information can be found in government websites, agriculture department leaflets, newspapers, etc. The required information is hard to find from these knowledge sources due to its unstructured, incomplete, varied formats, and lack of targeted delivery methods. Thus finding the right information within the context in which information is required in a timely manner is a challenge. The required information and relevant knowledge needs to be provided not only in a structured and complete way, but also in a context-specific manner. To investigate some of the underlying research challenges an International Collaborative Research Project to develop mobile based information systems for people in developing countries was launched. User centered Ontology was developed as a part of this project. We developed a new approach to model the domain knowledge to meet particular access requirements of the users in agriculture domain in Sri Lanka. Through this approach, we have investigated how to create a knowledge repository of agricultural information to respond to user queries taking into account the context in which information is needed by them at various stages of the farming life cycle. The Delphi Method, Modified Delphi Method and the OOPS! (web-based tool) were used to validate the quality of the ontology. Initial system was trialed with a group of farmers in Sri Lanka. The online knowledge base with a SPARQL endpoint was created to share and reuse the domain knowledge that can be queried based on user context. A semi-automatic end-to-end ontology management system was developed to manage the developed ontology as well as the knowledge base. It provides the facilities to reuse, share, modify, extend, and prune the ontology components as required.

Towards a User-Friendly Solution for Collaboratively Managing a Developed Ontology

Ontologies are getting popular for knowledge representation because it is capable of representing the semantics of the knowledge. However, with the evolution of the knowledge, maintaining and support evolution of a developed ontology becomes a complex task. We can get help of domain experts to maintain the ontology as a solution. But, that approach has another problem which is often domain experts do not know about ontology concepts, languages and tools. Also, if we try to accomplish ontology maintenance by the help of domain experts, there should be a technique to maintain ontology collaboratively. In a collaborative ontology development environment, when one user modifying the ontology, other users should also aware of that modification. In order to achieve this awareness, keeping a history of modifications is required. Furthermore, one user’s modifications may conflict with others modifications; therefore, the ontology development system should support that kind of situations too. This study mainly concerns how to maintain the structure of a developed ontology collaboratively. This study follows synchronous collaborative technique by keeping ontology in a central server. Collaborative partners are able to modify and maintain the ontology through user-friendly web-based interfaces. Since the ontology keeps in central place every user knows what modifications happen to the ontology in real time. Also modifications are recorded in a relational database and users are allowed to access those change history when it needed. Versions of the ontology are generated based on modification types. If the modification affects backward compatibility then a new version is created and if not current version is updated. To distinguish different versions, semantic versioning standard is used. The implemented system is validated individually and evaluated by the help of a user group. Validation and evaluation results prove that system is performing as expected.

A Semi-automatic Approach to Collaboratively Populate an Ontology for Ontology-Illiterate Users.

If we can represent the knowledge as a fully machine interpreted way, it offers many advantages to solving various kinds of problems in knowledge engineering. Most of the knowledge can be found scattered with in a domain of interest as websites, televisions, radios, publications, etc. This knowledge needs to be extracted and to be represented, so that can be used in many applications. Ontology is one of the knowledge representation techniques that is suitable for modeling domain knowledge. Knowledge evolves over time. With respect to that, we should maintain the ontology for better usage of knowledge. Ontology population is a key aspect of the ontology maintenance. However, the existing approaches for ontology populating are complex and designed for knowledge-engineering experts. Ontology Population looks for instantiating the constituent elements of an ontology. Manual population by domain experts and knowledge engineers is an expensive and time-consuming task. Thus, automatic or semi-automatic approaches are needed. The purpose of this study is to investigate in addressing the said limitation by proposing a user-friendly mechanism to incorporate evolving knowledge into ontologies, targeting ontology-illiterate end users. Maintaining ontology population and accurate inference of new knowledge are considered prime objectives of the research. A framework with flexible means of populating the ontology was developed while hiding the underlying ontology base from users. A web-based approach was adopted to support easy access and collaboratively populate. We implemented a tool based on the proposed method and checked the correctness of the method with respect to the mapping rules and all the SQL database components manually. Results proved that the proposed approach provides correct OWL-based ontology sources for the population performed through the interface. The proposed framework is designed to use any domain irrespective of the content.