Penerapan Model Hybrid Sistem Pendukung Keputusan Berbasis Pengetahuan Untuk Pencegahan Penyebaran Demam Berdarah Dengue

Abstract

There are many types of model development for decision support systems (DSS Decision Support Systems), but the uncertainty of their results needs to be estimated when they are used to support decisions involving heterogeneous data. We review various methods that have been or can be applied to evaluate the uncertainties associated with the deterministic model output and propose our new model which is a hybrid model to improve the accuracy of the results of two different models proposed by previous researchers. Hybrids from knowledge based models and the old models used conventionally begin with seven phases of analysis. These phases are problem identification, problem analysis and synthesis, available alternative generation and solver, model development, alternative analysis, choice and execution. Support System Model Knowledge-based decisions involving a lot of heterogeneous data can be applied to prevent the spread of Dengue Hemorrhagic Fever (DHF). In this Hybrid Decision Support Model-HDSS System research we use data warehouse technology, OLAP (online analytical Processing), data mining techniques and AI (artificial intelligence). With the HDSS model the location of the spread of dengue cases from a number of case scenarios can be anticipated quickly and accurately. The purpose of this DSS model is to support more accurate and integral decision makers in preventing the spread of DHF. Although it involves a lot of heterogeneous data and information, it can build a simple, easy to implement model, but with a complete phase can help in explaining the development process for decision support systems. Hybrid knowledge-based decision support architectural models aim to adapt to the needs of contemporary and future business management, so that decisions can be made quickly and precisely and integrally.