Multi-agents based data mining for intelligent decision support systems

Abstract

Recent rapid development of computer technology has introduced a data explosion challenge. In addition, data mining and multi agent techniques are known as a very popular approach for dealing with complex datasets. Such a hybrid approach can be considered as an effective approach for the development of intelligent decision support systems in health domain. In this paper we propose an improved data mining and multi agent technique called DMMA, which uses a real time agent mining approach to mine large datasets in a distributed environment. This study found that the processing speed is improved as the result of the multi-agent mining approach, although there can be a corresponding marginal loss of accuracy. This loss of accuracy gap tends to close over time as more data becomes available.

Untitled

“…According to D. Sharma and F. Shadabi (2014), the possible configuration of the DSS architecture, which represents the structure of a single decision-maker -i.e., several agents of data developers -has serious limitations when it comes to extensibility and the ability to integrate into the overall structure of support for organizational decisions. However, in many real-life situations, the system of sole decision-making still matters (UK Essays 2015; Konyavsky and Ross 2019b).…”

“…Viešoji politika ir administravimas. 2020, T. 19, Nr. 2, tology of DSS provides an easy construction of DSS-type systems by incorporating not only domain models, but also knowledge of the system itself.…”

Application of actor model for distributed execution of data mining algorithms

“…Another existing approach to solve Data Mining problems is the multi-agent based system solutions which described in the researches [8] and [9]. Though, the lack of widely used industrial systems is a big disadvantage of this solution.…”

Multi Agent Based Diabetes Diagnosing and Classification with the Aid of Hybrid Firefly-Neural Network

“…(6) Here, O corresponds to the neural network output and h signifies the total number of neurons in the hidden layer.…”

“…Multi agent approaches have been utilized in building numerous efficacious schemes where a set of agents cooperatively work together to accomplish multifaceted tasks [6]. Multi-Agent system (MAS) has inordinate potential aptitudes in DDM due to its distribution, adaptability, openness, and the collaboration, communication, reactivity, selflearning amongst agents.…”