A. Elmoataz et al. (Eds.): ICISP 2010, LNCS 6134, pp. 113–121, 2010. © Springer-Verlag Berlin Heidelberg 2010 Assessment of the Artificial Habitat in Shrimp Aquaculture Using Environmental Pattern Classification José Juan Carbajal Hernández, Luis Pastor Sánchez Fernández, and Marco Antonio Moreno Ibarra Centre of Computer Research – National Polytechnic Institute, Av. Juan de Dios Bátiz, Col. Nva. Industrial Vallejo, México D.F., México. 57296000, Ext. 56573 juancarvajal@sagitario.cic.ipn.mx, {lsanchez,marcomoreno}@cic.ipn.mx Abstract. This paper presents a novel model for assessing the water quality for the artificial habitat in shrimp aquaculture. The physical-chemical variables involved in the artificial habitat are measured and studied for modeling the environment of the ecosystem. A new physical-chemical index (Г) classifies the behavior of the environmental variables, calculating the frequency and the deviations of the measurements based on impact levels. A fuzzy inference system (FIS) is used for establishing a relationship between environmental variables, describing the negative ecological impact of the concentrations reported. The FIS uses a reasoning process for classifying the environmental levels providing a new index, which describes the general status of the water quality (WQI); excellent, good, regular and poor. Keywords: Artificial intelligence, fuzzy inference systems, classification, water management. 1 Introduction Water management is an important factor in shrimp aquaculture, where the ecosystem must be under control. A disestablished habitat is not conducive for a good farming, also an organism with a weakened immunological system is more likely for getting sick (for example Taura virus, Mancha Blanca, Cabeza Amarilla, Etc.) The main purpose on water management and aquaculture systems is to control and maintain the optimal conditions for the surviving and good growing of the organisms to the closest to a natural ecosystem [1]. The assessment of the water quality can be estimated using the relationships between the physical, chemical and biological parameters. The combination of the environmental variables determines the status of the water quality [2], [3]. Actually, in the world the laws do not provide enough criteria to resolve this problem and the ecological standards only describe the toxicity limits of the pollutants into the water bodies and the methodologies to measure them [4], [5], [6], [7]. Environmental variables have some concentration limits, where low or high concentrations (depending of the variable) can be harmful for the organism [1], [2], [3]. Following this behaviors, it is possible to implement a model in the attention that those limits and changes in the variables can be used for determining when a