A fuzzy preference-based Dempster-Shafer evidence theory for decision fusion

Multimodal multi-instance evidence fusion neural networks for cancer survival prediction

Accurate cancer survival prediction plays a crucial role in assisting clinicians in formulating treatment plans. Multimodal data, such as histopathological images, genomic data, and clinical information, provide complementary and comprehensive information, significantly enhancing the accuracy of this task. However, existing methods, despite achieving some promising results, still exhibit two significant limitations: they fail to effectively utilize global context and overlook the uncertainty of different modalities, which may lead to unreliable predictions. In this study, we propose a multimodal multi-instance evidence fusion neural network for cancer survival prediction, called M2EF-NNs. Specifically, to better capture global information from images, we employ a pre-trained vision transformer model to extract patch feature embeddings from histopathological images. Additionally, we are the first to apply the Dempster-Shafer evidence theory to the cancer survival prediction task and introduce subjective logic to estimate the uncertainty of different modalities. We then dynamically adjust the weights of the class probability distribution after multimodal fusion based on the estimated evidence from the fused multimodal data to achieve trusted survival prediction. Finally, the experimental results on three cancer datasets demonstrate that our method significantly improves cancer survival prediction regarding overall C-index and AUC, thereby validating the model's reliability.

Multimodal fall detection for solitary individuals based on audio-video decision fusion processing

Falls often pose significant safety risks to solitary individuals, especially the elderly. Implementing a fast and efficient fall detection system is an effective strategy to address this hidden danger. We propose a multimodal method based on audio and video. On the basis of using non-intrusive equipment, it reduces to a certain extent the false negative situation that the most commonly used video-based methods may face due to insufficient lighting conditions, exceeding the monitoring range, etc. Therefore, in the foreseeable future, methods based on audio and video fusion are expected to become the best solution for fall detection. Specifically, this article outlines the following methodology: the video-based model utilizes YOLOv7-Pose to extract key skeleton joints, which are then fed into a two stream Spatial Temporal Graph Convolutional Network (ST-GCN) for classification. Meanwhile, the audio-based model employs log-scaled mel spectrograms to capture different features, which are processed through the MobileNetV2 architecture for detection. The final decision fusion of the two results is achieved through linear weighting and Dempster-Shafer (D-S) theory. After evaluation, our multimodal fall detection method significantly outperforms the single modality method, especially the evaluation metric sensitivity increased from 81.67% in single video modality to 96.67% (linear weighting) and 97.50% (D-S theory), which emphasizing the effectiveness of integrating video and audio data to achieve more powerful and reliable fall detection in complex and diverse daily life environments.

Multi-Source Information Fusion Based on Negation of Reconstructed Basic Probability Assignment with Padded Gaussian Distribution and Belief Entropy

Multi-source information fusion is widely used because of its similarity to practical engineering situations. With the development of science and technology, the sources of information collected under engineering projects and scientific research are more diverse. To extract helpful information from multi-source information, in this paper, we propose a multi-source information fusion method based on the Dempster-Shafer (DS) evidence theory with the negation of reconstructed basic probability assignments (nrBPA). To determine the initial basic probability assignment (BPA), the Gaussian distribution BPA functions with padding terms are used. After that, nrBPAs are determined by two processes, reassigning the high blur degree BPA and transforming them into the form of negation. In addition, evidence of preliminary fusion is obtained using the entropy weight method based on the improved belief entropy of nrBPAs. The final fusion results are calculated from the preliminary fused evidence through the Dempster's combination rule. In the experimental section, the UCI iris data set and the wine data set are used for validating the arithmetic processes of the proposed method. In the comparative analysis, the effectiveness of the BPA determination using a padded Gaussian function is verified by discussing the classification task with the iris data set. Subsequently, the comparison with other methods using the cross-validation method proves that the proposed method is robust. Notably, the classification accuracy of the iris data set using the proposed method can reach an accuracy of 97.04%, which is higher than many other methods.

BDD-Net: An End-to-End Multiscale Residual CNN for Earthquake-Induced Building Damage Detection

Building damage maps can be generated from either optical or Light Detection and Ranging (Lidar) datasets. In the wake of a disaster such as an earthquake, a timely and detailed map is a critical reference for disaster teams in order to plan and perform rescue and evacuation missions. Recent studies have shown that, instead of being used individually, optical and Lidar data can potentially be fused to obtain greater detail. In this study, we explore this fusion potential, which incorporates deep learning. The overall framework involves a novel End-to-End convolutional neural network (CNN) that performs building damage detection. Specifically, our building damage detection network (BDD-Net) utilizes three deep feature streams (through a multi-scale residual depth-wise convolution block) that are fused at different levels of the network. This is unlike other fusion networks that only perform fusion at the first and the last levels. The performance of BDD-Net is evaluated under three different phases, using optical and Lidar datasets for the 2010 Haiti Earthquake. The three main phases are: (1) data preprocessing and building footprint extraction based on building vector maps, (2) sample data preparation and data augmentation, and (3) model optimization and building damage map generation. The results of building damage detection in two scenarios show that fusing the optical and Lidar datasets significantly improves building damage map generation, with an overall accuracy (OA) greater than 88%.

An ambient air quality evaluation model based on improved evidence theory

It is significant to evaluate the air quality scientifically for the management of air pollution. As an air quality comprehensive evaluation problem, its uncertainty can be effectively addressed by the Dempster–Shafer (D–S) evidence theory. However, there is not enough research on air quality comprehensive assessment using D–S theory. Aiming at the counterintuitive fusion results of the D–S combination rule in the field of comprehensive decision, an improved evidence theory with evidence weight and evidence decision credibility (here namely DCre-Weight method) is proposed, and it is used to comprehensively evaluate air quality. First, this method determines the weights of evidence by the entropy weight method and introduces the decision credibility by calculating the dispersion of different evidence decisions. An algorithm case shows that the credibility of fusion results is improved and the uncertainty is well expressed. It can make reasonable fusion results and solve the problems of D–S. Then, the air quality evaluation model based on improved evidence theory (here namely the DCreWeight model) is proposed. Finally, according to the hourly air pollution data in Xi’an from June 1, 2014, to May 1, 2016, comparisons are made with the D–S, other improved methods of evidence theory, and a recent fuzzy synthetic evaluation method to validate the effectiveness of the model. Under the national AQCI standard, the MAE and RMSE of the DCreWeight model are 1.02 and 1.17. Under the national AQI standard, the DCreWeight model has the minimal MAE, RMSE, and maximal index of agreement, which validated the superiority of the DCreWeight model. Therefore, the DCreWeight model can comprehensively evaluate air quality. It can provide a scientific basis for relevant departments to prevent and control air pollution.

Weighted assignment fusion algorithm of evidence conflict based on Euclidean distance and weighting strategy, and application in the wind turbine system

In the process of intelligent system operation fault diagnosis and decision making, the multi-source, heterogeneous, complex, and fuzzy characteristics of information make the conflict, uncertainty, and validity problems appear in the process of information fusion, which has not been solved. In this study, we analyze the credibility and variation of conflict among evidence from the perspective of conflict credibility weight and propose an improved model of multi-source information fusion based on Dempster-Shafer theory (DST). From the perspectives of the weighting strategy and Euclidean distance strategy, we process the basic probability assignment (BPA) of evidence and assign the credible weight of conflict between evidence to achieve the extraction of credible conflicts and the adoption of credible conflicts in the process of evidence fusion. The improved algorithm weakens the problem of uncertainty and ambiguity caused by conflicts in the information fusion process, and reduces the impact of information complexity on analysis results. And it carries a practical application out with the fault diagnosis of wind turbine system to analyze the operation status of wind turbines in a wind farm to verify the effectiveness of the proposed algorithm. The result shows that under the conditions of improved distance metric evidence discrepancy and credible conflict quantification, the algorithm better shows the conflict and correlation among the evidence. It improves the accuracy of system operation reliability analysis, improves the utilization rate of wind energy resources, and has practical implication value.