This study proposes an architecture based on a weighted fuzzy Dempster-Shafer framework (WFDSF), which can adjust weights associated with inconsistent evidence obtained by different classification approaches, to realize a fusion system for integrating multimodal information. The Dempster-Shafer theory (D-S theory) of evidence enables us to integrate heterogeneous information from multiple sources to obtain collaborative inferences for a given problem. To conquer various uncertainties associated with the collected information, our system assigns beliefs and plausibilities to possible hypotheses of each decision maker and uses a combination rule to fuse multimodal information. For information fusion, an important step in D-S aggregation is to find an appropriate basic probability assignment scheme for allocating support to each possible hypothesis/class, which remains an arduous and unsolved problem. Here, we propose a mathematical structure to aggregate weighted evidence extracted from two different types of approaches: fuzzy Na_ve Bayes and nearest mean classification rule. Further, an intuitionistic belief assignment is employed to address uncertainties between hypotheses/classes. Finally, 12 benchmark problems from the UCI machine learning repository for classification are employed to validate the proposed WFDSF-based scheme. In addition, an application of WFDSF to a practical brain-computer interface problem involving multimodal data fusion is demonstrated in this study. The experimental results show that the WFDSF is superior to several existing methods.

中文翻译：

---

用于多模式信息集成的加权模糊 Dempster__hafer 框架


本研究提出了一种基于加权模糊Dempster-Shafer框架（WFDSF）的体系结构，该体系结构可以调整与不同分类方法获得的不一致证据相关的权重，以实现集成多模态信息的融合系统。 Dempster-Shafer 证据理论（DS 理论）使我们能够整合来自多个来源的异构信息，以获得给定问题的协作推论。为了克服与收集的信息相关的各种不确定性，我们的系统将信念和合理性分配给每个决策者可能的假设，并使用组合规则来融合多模态信息。对于信息融合，DS聚合的一个重要步骤是找到合适的基本概率分配方案来为每个可能的假设/类别分配支持，这仍然是一个艰巨且未解决的问题。在这里，我们提出了一种数学结构来聚合从两种不同类型的方法中提取的加权证据：模糊朴素贝叶斯和最近平均分类规则。此外，采用直觉信念分配来解决假设/类别之间的不确定性。最后，使用 UCI 机器学习存储库中的 12 个分类基准问题来验证所提出的基于 WFDSF 的方案。此外，本研究还演示了 WFDSF 在涉及多模态数据融合的实际脑机接口问题中的应用。实验结果表明WFDSF优于现有的几种方法。