An expert system for recommending suitable ornamental fish addition to an aquarium based on aquarium condition

Expert systems prove to be suitable replacement for human experts when human experts are unavailable for different reasons. Various expert system has been developed for wide range of application. Although some expert systems in the field of fishery and aquaculture has been developed but a system that aids user in process of selecting a new addition to their aquarium tank never been designed. This paper proposed an expert system that suggests new addition to an aquarium tank based on current environmental condition of aquarium and currently existing fishes in aquarium. The system suggest the best fit for aquarium condition and most compatible to other fishes in aquarium.

A Fuzzy expert system for goalkeeper quality recognition

Goalkeeper (GK) is an expert in soccer and goalkeeping is a complete professional job. In fact, achieving success seems impossible without a reliable GK. His effect in successes and failures is more dominant than other players. The most visible mistakes in a game are those of goalkeeper's. In this paper the expert fuzzy system is used as a suitable tool to study the quality of a goalkeeper and compare it with others. Previously done researches are used to find the goalkeepers' indexes in soccer. Soccer experts have found that a successful GK should have some qualifications. A new pattern is offered here which is called "Soccer goalkeeper quality recognition using fuzzy expert systems". This pattern has some important capabilities. Firstly, among some goalkeepers the one with the best quality for the main team arrange can be chosen. Secondly, the need to expert coaches for choosing a GK using their senses and experiences decreases a lot. Thirdly, in the survey of a GK, quantitative criteria can be included, and finally this pattern is simple and easy to understand.

Design and Development of an Expert System to Help Head of University Departments

One of the basic tasks which is responded for head of each university department, is employing lecturers based on some default factors such as experience, evidences, qualifies and etc. In this respect, to help the heads, some automatic systems have been proposed until now using machine learning methods, decision support systems (DSS) and etc. According to advantages and disadvantages of the previous methods, a full automatic system is designed in this paper using expert systems. The proposed system is included two main steps. In the first one, the human expert's knowledge is designed as decision trees. The second step is included an expert system which is evaluated using extracted rules of these decision trees. Also, to improve the quality of the proposed system, a majority voting algorithm is proposed as post processing step to choose the best lecturer which satisfied more expert's decision trees for each course. The results are shown that the designed system average accuracy is 78.88. Low computational complexity, simplicity to program and are some of other advantages of the proposed system.