Advisory system architecture in agricultural environment to support decision making process

Abstract

The aim of this paper is to proposed software architecture for ontology-driven advisory systems. The architecture reflects the situation in our current agricultural advisory systems where farmers as a client request an advice from the experts to help them in decision making process in their cultivating. The architecture consists of three components, users, module and knowledge/database. Each component complies with the basic process in advisory systems, knowledge acquisition, cognition, and interface. The architecture embeds three approaches in this systems, personalization, knowledge management and ontology. In semantic web architecture all information is spread over the Internet. By using these technologies, we can easily share and reused the information via Internet.Keywords-Advisory system, decision making process in agricultural, ontology-driven system, semantic web, knowledge modeling, processes in advisory system

A Formal Approach to Designing Reliable Advisory Systems

“…These are: (1) the knowledge base that lists domain specific knowledge; (2) a data monitoring agent that collects (stream) data; (3) the inference engine that interprets problems from the data and uses expert knowledge to deduce suitable solutions and (4) the user interface for supporting human-computer interactions. In the literature, there are many examples of advisory systems that are deployed in various industrial settings using this architecture, such as finance, medicine and process control [3][4][5][6][7][8][9][10]. However, since system failures in these settings can result in potentially serious consequences, such as loss of revenue, loss of productivity and damage to property, it is important to ensure that advisory systems are both reliable and dependable [13].…”

“…The basic purpose of an advisory system is to assist the end-user in identifying suitable solutions to complex, unstructured problems [1][2][3][4][5][6][7][8][9][10]. In decision-making, an un-structured problem is one that is characterised with contextual uncertainty, where there are no definite processes in place for predictably responding to a problem that is, well-defined actions that do not necessarily lead to predictable outcomes [2].…”

“…From these applications, it is clear that designs of advisory systems are based on the illustrated architecture and perform according to one of two main styles. These are: (1) monitoring and evaluation and (2) diagnosis and recovery [2][3][4][5][6][7][8][9]. In the monitoring and evaluation style, advisory systems simply monitor data streams to identify statistical anomalies that may represent a potential problem or to identify predictive behaviour patterns.…”

“…Farmers provide the system with values for various input parameters to frame the problem, where expert knowledge is applied to infer possible solutions on which area a farmer is most likely to be successful and the types of crops that should be grown. In a final example, presented by Engrand and Mitchell [6], a set of advisory systems embedded in shuttle flight computer systems are described, where separate advisory systems are used for diagnosing malfunctions and handling faults. The user interacts with these systems to determine the cause of malfunctions and identify how these may be repaired.…”