International Journal of Computer Applications (0975 – 8887) Volume 70– No.11, May 2013 43 Developing an Expert System for Water Types Identification in the Context of Physicochemical Indicators in Aridity-based Regions Shah Murtaza Rashid Al Masud Faculty of Computer Science and Information Systems Najran University Najran, Saudi Arabia ABSTRACT Expert System (ES) is an Artificial Intelligent (AI) technique and program that uses knowledge and inference procedures to solve problems that are difficult enough to require significant human expertise for their solutions. The proposed ES presented in this paper is able to easily identify the major water quality types and make appropriate recommendations according to the users’ needs. Although water is important for all living substances human-animals-fish-plants-agriculture, but water is continuously contaminated naturally and artificially which ultimately affects on its quality. Due to the lack of knowledge about the quality of water, the harmful effects of water to the animals’ body including human, and also necessity of ideal water for agriculture remain unknown. To identify the types of water the researchers had to analyze the physicochemical (physical + chemical) indicators of water such as, positive hydrogen-pH, total dissolved solids-TDS, electrical conductivity-EC, and temperature-T 0 c. The motivation behind this work was due to the insufficient knowledge about the quality of water and the need to provide novel approaches towards water quality identification and management. A rule-based, web enabled expert system shell: expertise2go was used to design about 56 rules which involved a knowledge component, decision component, design component, graphical user interface component, and the user component. General Terms Artificial Intelligence, Expert System Keywords Expert System, Artificial Intelligence, Water Types, Rule- based, Knowledge 1. INTRODUCTION Expert systems (ES) are a branch of artificial intelligence (AI), and were developed by the AI community in the mid- 1960s [1]. One can infer from this definition that expertise can be transferred from a human to a computer and then stored in the computer in a suitable form that users can call upon the computer for specific advice as needed. Then the system can make inferences and arrive at a specific conclusion to give advices and explains, if necessary, the logic behind the advice. ES provide powerful and flexible means for obtaining solutions to a variety of problems that often cannot be dealt with by other, more traditional and orthodox methods [2]. The four main components of knowledge-based systems KBS are: a knowledge base, an inference engine, a knowledge engineering tool, and a specific user interface. Some of KBS important applications include the following: medical treatment, engineering failure analysis, decision support, knowledge representation, climate forecasting, decision making and learning, and chemical process controlling [2]. Previous work has shown that a system with water quality type identification was very limited. A well-designed expert system is able to explicitly explain in detail the reasoning that led to a conclusion. Depending on the software and hardware, expert systems may respond faster than a human expert. A multi-user expert system can serve more users at a time. By taking the above considerations into the account, our contributions are as follows:  Analysis the factors of physical and chemical indicators of water that are directly related to its quality.  Identify the major water quality types, namely: neutrality of water, fresh water types, drinking water quality, salinity, acidity, and alkalinity of water according to the factors as mentioned before for designing the proposed expert system.  Design a rule-based expert system which is able to analysis rules and facts automatically according to the users’ demands and also able to make necessary recommendations when needed following the rules of certainty factors (CF). After analyzing the physicochemical indicators of water our expert system classified and obtained the result of water quality types into: neutral, acidic, severe acidic, alkaline, brine, saline, slightly saline, moderate saline, highly saline, sea and rain water, fresh water, drinking and excellent drinking water including bottled drinking water, brackish to highly brackish water. Depending on the water quality types the proposed expert system also made necessary recommendations and actions for the human life and life stock; aquatic life and fresh water fish; plants; cattle and baby calves; sea fish-animal-plants. The proposed expert system will be very helpful for the researchers to indentifying water types, and recommendations necessary for life stock, aquatic life, cattle, and plants. As the proposed system is web-based, so at anytime from any place any user can access to it and get recommendations he needed. This paper is organized in this way, Section 2 Problem definition. Section 3 Analysis the major types of water quality. Section 4 Expert system’s main components and an analytical model for the proposed system. Section 5 Design of the proposed expert system. Section 6 Implementation of the