Enhancing information fusion and feature selection efficiency via the PROMETHEE method for multi-source dynamic decision data sets

Abstract

With the surge in big data, the complexity of synthesizing information from multiple sources has become a critical challenge for feature selection methodologies. Feature selection is the process of reducing the number of attributes in data. Traditional single-source centric approaches are inefficient, requiring extensive preprocessing for multi-source data consolidation prior to feature selection. At the same time, an information fusion method is needed to transform the multi-source information system with selected features into a single-source information system. This paper introduces a novel multi-source information fusion and feature selection approach that seamlessly integrates the Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) with a dynamic adaptation mechanism. This method is adept at addressing the complexities introduced by the evolving nature of feature and information source dimensions. The Attribute Evaluation Matrix (AEM) and the Attribute Preference Degree Matrix (APDM) are proposed to systematically assess and rank the significance of attributes within a static decision-making framework. Following this, an information fusion method using the source center is proposed. The dynamic feature selection and information fusion methods are proposed to deal with the condition when number of attributes and samples change. Extensive experimental validation confirms that this method not only reduces the computational overhead associated with multi-source feature selection but also significantly enhances the efficiency as the volume and variety of data sources increase.