Fu Zetian

Pig-vet: a web-based expert system for pig disease diagnosis

When a pig shows disease symptoms, it is important to make an accurate diagnosis to support control strategies. Diagnosing diseases in pigs requires considerable expertise. Only a few experts have the ability to do this, and each expert has his own specific domain. To make it more generally accessible and reduce the waiting time, an expert system named Pig-Vet has been developed by China Agricultural University. Based on investigations, this paper analyzes users’ needs and describes the architecture, main components, and their functions. The system has over 300 rules and 202 images and graphics for different types of diseases and symptoms. It can diagnose 54 types of common diseases of pigs. At present the system is in pilot in north of China. The stage achievements in developing the intellectual expert system of pig disease diagnosis are summarized. q 2005 Elsevier Ltd. All rights reserved.

Applying evolutionary prototyping model in developing FIDSS: An intelligent decision support system for fish disease/health management

Fish disease and health management is becoming a key barrier and major problem that currently limits expanded production and sustainable development of aquaculture and bring out food-safety issues. There has been a marked growth of interest in developing expert system to aid fish disease/health management. The literature shows that a few have been used to any extent due to the lack of deep user requirement analysis and long-term support and maintenance. This paper presents the effort to apply evolutionary prototyping model in developing an intelligent decision support system for fish disease/ health management. The paper describes in detail about the four evolution stages as the system development experienced, every stage including the system design and implementation, feedback and requirement from system evaluation, and system redevelopment until a blown system. At last the evolution process is concluded from three directions. The evolutionary prototyping benefits and challenges experienced during the development and promotion are also discussed from the project management

Developing a Web-based Early Warning System for Fish Disease based on Water Quality Management

The suboptimal water quality, including the eutrophication and the pollutants of NH3, H2S as well as organic compounds, is the main reason of damaging fish resources, which are suffered by the aquaculture ponds in the north of China and result in great losses to Chinese aquatic products every year. Therefore, it is important and the best way to develop decision aids that can help to assess the risks of fish disease through water quality management. EWS-FDWQ: a Web-based early-warning system for fish disease based on water quality management has been developed by us. real-time water quality monitoring and a series of water quality management mathematic models, including water eutrophic assessment, pollutant risk assessment and water quality forecast as well as potential risk early warning of fish disease, are the key advantages of our system

Development of the ES-FDD: an expert system for fish disease diagnosis

ES-FDD is a web-based expert system for fish disease diagnosis developed by China Agricultural University. The system contains a large amount of fish disease data and images and can mimic experiences from many experts had accumulated through many years fish disease expertise and diagnose 126 kinds of fish diseases with a user-friendly interface. A 5-step development process for the ES-FDD included identify and understand the problem domain, make sense of the diagnosis process and acquire knowledge, design, build and evaluate 0 order prototype, test and expand prototype into full system and maintain the system and promotion. To increase adoption of the software, a representative sample of end-users was extensively involved during the development process. End-user contributions resulted in additional modules for water quality calculator programs, user-friendly interface and addition of a database module for data recording and analyses

Evaluation of the aquaculture pond water quality

According to the questionnaire and the fish’s endurance to the factors of water quality, this paper brings forward five grades water quality standard, establishes the index system of the evaluation, and calculates and selects the thickness of index system of the evaluation. The evaluation model and method were established. By the data one year monitored in North China, it proved that this model and the method could match the real situation well. This model and method can provide decision support for water management to the fishery farmers. The evaluation determines appropriate level of the factors of pond water.

Agrilnfo : an agricultural information system based on a call centre in China

Abstract This paper presents research to develop an agricultural information system based on a call centre (Agrilnfo) by Key Laboratory for Modern Precision Agriculture System Integration, China Agricultural University. Based on investigations, we analyse user needs and the difficulties involved in developing the system. User needs, architecture, main components, functions and working processes of the system are described. Last, we discuss the piloted effects of Agrilnfo and draw conclusions. Valuable insights into the use of the call centre as a tele‐consultation tool in agriculture are highlighted. Agrilnfo was piloted in the north of China. It shows that Agrilnfo can remove barriers by transmitting agricultural information to rural areas and provide a multilayer information service to match different farmer demands.

Development of an early-warning system for risk management in aquatic products market, China

Aquaculture is being promoted as a means of generating an alternative source of income for farmers and in enhancing food security over the past two decades in China. But the technological advancement in the production and storage of fishery products has exceeded the development of efficient market demand over the past one-decade. As a result, participants within the fishery industry have frequently found themselves facing more market risk brought by increased variable and declining prices or other factors, negatively affected the fishery industry. So it is necessary to provide early warning to aquaculture market risk. An early-warning system for aquaculture market risk was developed by China Agricultural University, which is granted by both the National Nature Science Foundation and China Academy of Fishery Science. Based on questionnaire and interviews, we analyze the decision problems, user needs and the difficulties involved in developing the system. The system architecture and its components, such as database, rule base, method base and model base and their functions are described. At last we discussed on end-user contributions and the problems we had encountered during development and promotion.

On knowledge representation in fish disease diagnosis expert system

Knowledge representation is the generator in Fish Disease Diagnosis Expert System (Fish-expert), so it is necessary that develop an explicit formalization capable of compiling the knowledge of experts to uniformity of expression and describing all kinds of fish diseases. In this paper we focus on the knowledge representation formalism in Fish-expert. With integrated fish disease diagnostics with experiences from many experts had accumulated through many years, we brought forward the conceptualization architecture for fish disease diagnosis, which describes the causality relations inherent in fish disease diagnosis knowledge. Then we represented them via a hybrid formalism that combines conventional and logic production rules and Neural Network. The conventional rule is employed to represent the knowledge from experience of experts cutting down the problem space. The logic rule represents the causality relations among symptoms, diseases and pathogenies and The Neural Network is used for training and forming the relations among them. Compared with the knowledge representation formalism only employed the conventional rule, the fundamental characteristic of the formalism is that it can represent both the frequency of occurrence of symptoms with diseases and the strength of confirmation of symptoms for diseases. With application of the hybrid formalism the amount of rules of Fish-expert had been decreased from 1890 to 312 and the reasoning speed and veracity had been promoted from 1 second to 0.5 second and 85% to 95% or more separately.