Dempster-Shafer Evidence Theory Research Articles

A Three-Zone Identification Method for Coal Mine Area Based on DS Evidence Theory

As coal ore and other resources are continuously mined, a three-zone structure is formed underground consisting of a sagging zone, fault zone, and caving zone. The use of well-logging data to identify the three zones is important for production safety and environmental management. Owing to the scarcity of data that can reflect three zones in normal coal mining, conventional identification and prediction methods face challenges when extracting data features, incurring a degree of uncertainty within prediction results. Accordingly, the accurate identification of the three zones has become a critical objective in daily production. To address this issue, we developed a method called a method called backpropagation neural networks with Dempster–Shafer (DS) evidence theory. Initially, we preprocessed the training data and deployed two backpropagation neural networks (BPNNs) to predict the three zones according to two parameters. According to these prediction results, the local and global credibility of each prediction is calculated and used to obtain the basic probability assignment function required for the DS evidence theory. Finally, the DS evidence theory is used to fuse the two BPNNs prediction results, thereby producing the final prediction results. The proposed method was demonstrated to improve prediction accuracy by 6.4% compared to a conventional neural network.

Evidence‐based fault tree analysis of the hydraulic system in CNC machine tools

AbstractThe hydraulic system is an integral part of CNC machine tools. In analyzing the reliability of machine tool hydraulic systems, their failures are influenced by both aleatory and epistemic uncertainties. This paper utilizes the fault tree analysis method to address failure modes subject to epistemic uncertainty, using the interval rough number scoring method to evaluate the probability of such failures occurring. The resulting reliability calculation is termed as “subjective reliability”. For failure modes influenced by aleatory uncertainty, objective data combined with the Dempster–Shafer evidence theory is used to determine their failure probability, with the corresponding reliability calculation referred to as “objective reliability”. Finally, a comprehensive calculation of both subjective and objective reliability is conducted to determine the overall reliability of the hydraulic system, along with the ranking of the importance of basic events of fault tree. This methodology covers scenarios with small samples, sufficient data, and their combinations, offering extensive application prospects.

A quantum group decision model for meteorological disaster emergency response based on D-S evidence theory and Choquet integral

In addressing complex and dynamic meteorological disaster decision-making environment, the traditional multi-attribute group decision-making domain model is often unable to effectively deal with the correlation between attributes and the mutual influence of group opinions. To overcome this challenge, this paper proposes a novel quantum framework for group decision-making, which is used to deal with the emergency situation of meteorological disaster. The model initially characterizes attribute correlations using 2-additive Choquet integrals and employs Dempster-Shafer evidence theory to both integrate information and ascertain attribute weights, and decision makers' weights are calculated based on grey relative correlation. On this basis, a quantum-like Bayesian network is developed to capture the interference among decision-makers' opinions. The alternatives are ranked by quantum probabilities computed based on Bayesian principle. Finally, a case study on meteorological disaster emergency scenario assessment is conducted to validate the proposed model's effectiveness and superiority. Additionally, its stability and practicality are confirmed through sensitivity analysis and comparative analysis.

SAR Image Fusion Classification Based on Improved D-S Evidence Theory

Applications for classifying Synthetic Aperture Radar (SAR) images are critical to environmental monitoring, urban planning, and land resource surveying. Fusion approaches work well for increasing SAR image categorization accuracy. However, effective processing of uncertainty information is frequently overlooked by conventional fusion classification systems. This paper presented a fusion classification approach for SAR images based on improved Dempster-Shafer (D-S) evidence theory, taking into account the uncertainty and possible conflicts in the classifiers’ output. First, after adaptively identifying the optimal hyperparameters of models, the SAR data is identified using Gradient Boosting Machine (GBM), Multilayer Perceptron (MLP), and Random Forest (RF). Different weights are then allocated in accordance with the variations in classifier performance. Ultimately, enhanced D-S evidence theory is used to integrate the output of these classifiers. In addition, uncertainty in classification results is also modeled and visualized. Experiments with Flevoland and Oberpfaffenhofen datasets show that the accuracy of this method is 85.21% and 91.88% respectively, outperforming both the soft voting ensemble classifier (SVE) and D-S evidence theory fusion method. This approach enhances the comprehension and capacity to manage uncertainty in the model output in addition to increasing the accuracy and reliability of the classification of SAR data.

Dynamic Occupancy Grid Map with Semantic Information Using Deep Learning-Based BEVFusion Method with Camera and LiDAR Fusion.

In the field of robotics and autonomous driving, dynamic occupancy grid maps (DOGMs) are typically used to represent the position and velocity information of objects. Although three-dimensional light detection and ranging (LiDAR) sensor-based DOGMs have been actively researched, they have limitations, as they cannot classify types of objects. Therefore, in this study, a deep learning-based camera-LiDAR sensor fusion technique is employed as input to DOGMs. Consequently, not only the position and velocity information of objects but also their class information can be updated, expanding the application areas of DOGMs. Moreover, unclassified LiDAR point measurements contribute to the formation of a map of the surrounding environment, improving the reliability of perception by registering objects that were not classified by deep learning. To achieve this, we developed update rules on the basis of the Dempster-Shafer evidence theory, incorporating class information and the uncertainty of objects occupying grid cells. Furthermore, we analyzed the accuracy of the velocity estimation using two update models. One assigns the occupancy probability only to the edges of the oriented bounding box, whereas the other assigns the occupancy probability to the entire area of the box. The performance of the developed perception technique is evaluated using the public nuScenes dataset. The developed DOGM with object class information will help autonomous vehicles to navigate in complex urban driving environments by providing them with rich information, such as the class and velocity of nearby obstacles.

A classification framework with multi-level fusion of object-based analysis and convolutional neural network: a case study for land use classification in mining areas

ABSTRACT To enhance the accuracy of land use classification in mining areas, the Object-based Convolutional Neural Network (OCNN) method has been widely used. However, existing researches tend to neglect the importance of decision-level fusion, focusing only on feature-level fusion. This study proposes a new classification framework with Multi-level Fusion of Object-based analysis and CNN (MFOCNN) to achieves high-accuracy land use classification in mining areas. First, Simple Linear Iterative Cluster (SLIC) is employed to generate image objects, which serve as the basic unit for classification. Second, an improved DenseNet is proposed to extract deep features from image patches, which represent image objects, and provide the classification result. Third, handcrafted features including spectral, textural and geometric of the image objects are extracted and fused with the deep features to obtain the classification result with random forest classifier. Finally, the Dempster-Shafer (DS) evidence theory is applied to fuse the two previously described classification results at the decision-level to obtain the final result. Experiments conducted in the mining areas of Erdos using Gaofen-6 images demonstrate that the proposed MFOCNN achieves the best visual performance and accuracy among all tested methods. The MFOCNN, with its feature-level fusion and decision-level fusion, significantly improves the accuracy of land use classification in mining areas. The results suggest that the proposed MFOCNN is a promising method for achieving high-accuracy land use classification in mining areas.

Air pollution concentration fuzzy evaluation based on evidence theory and the K-nearest neighbor algorithm

Background: Air pollution, characterized by complex spatiotemporal dynamics and inherent uncertainty, poses significant challenges in accurate air quality prediction, and current methodologies often fail to adequately address these complexities.Objective: This study presents a novel fuzzy modeling approach for estimating air pollution concentrations.Methods: This fuzzy evaluation method integrates an improved evidence theory with comprehensive weighting and the K-nearest neighbor (KNN) interval distance within the framework of the matter-element extension model. This involves generating the basic probability assignment (BPA) based on interval similarity, performing sequential fusion using the Dempster–Shafer evidence theory, enhancing the fusion results via comprehensive weighting, and conducting fuzzy evaluation of air pollution concentrations using the matter-element extension KNN interval distance.Results: Our method achieved significant improvements in monitoring air pollution concentrations, incorporating spatiotemporal factors and pollutant concentrations more effectively than existing methods. Implementing sequential fusion and subjective–objective weighting reduced the error rate by 38% relative to alternative methods.Discussion: Fusion of multi-source air pollution data via this method effectively mitigates inherent uncertainty and enhances the accuracy of the KNN method. It produces more comprehensive air pollution concentration fusion results, improving accuracy by considering spatiotemporal correlation, toxicity, and pollution levels. Compared to traditional air-quality indices, our approach achieves greater accuracy and better interpretability, making it possible to develop more effective air quality management strategies. Future research should focus on expanding the dataset to include more diverse geographical and meteorological conditions, further refining the model to integrate external factors like meteorological data and regional industrial activity, and improving computational efficiency for real-time applications.

Inconsistency elimination of multi-source information fusion in smart home using the Dempster-Shafer evidence theory

In the smart home, inconsistencies in multi-source information often occur due to the vast quantities and diverse varieties of context information, and the Dempster-Shafer (D-S) evidence theory exhibits remarkable efficacy in addressing this issue. However, the use of basic possibility assignment (BPA) to quantify the credibility of information may introduce the uncertainty contained in the original data. In order to obtain a more reliable BPA and improve the accuracy of multi-source information fusion, an index that combines the relationships of sources and the information volume of context (RSIVC) is defined to comprehensively calculate the uncertainty of context information. In addition, interval distance is introduced to calculate the credibility of the proposition (CoP), which quantifies the correspondence among uncertain context information and all propositions in the frame of discernment (FoD). Finally, based on the d-S evidence theory, a multi-discount context information inconsistency elimination (MDCIE) algorithm using RSIVC and CoP is proposed, which is specifically applied to address the problem of inconsistency in multi-source light intensity information in smart homes. In the experimental part, we compare the traditional and state-of-the-art inconsistency elimination algorithms to verify the effectiveness of the proposed algorithm. Besides, we also test the efficiency of various components of the MDCIE algorithm as well as several RSIVC indicator-building strategies to ensure that the proposed algorithm is optimal. Under the conditions of high precision, medium precision, and low precision of sensors, the context-judge rate reaches 99.24 %, 98.58 %, and 98.09 %, respectively, which corroborates that the MDCIE algorithm is highly effective.

Multi-association evidential feature selection and its application to identifying schizophrenia

Granular Computing (GrC)-based feature selection can remove redundant features from a massive amount of data and improve the efficiency of information processing. However, the existing method of neighborhood-based information granule only considers the distance between samples, ignoring other significant relationships existing between them. To fill this gap, this paper proposes a novel feature selection approach based on two-step multi-association neighborhood evidence entropy. This approach is constructed in three phases. Firstly, adaptive k value corresponding to each sample in sparse representation method is determined. Sparse correlation and distance measure are fused to form a multi-association information granule. Then, the samples in the multi-association information granule are estimated and weak-related information is removed to constitute a two-step multi-association information granule. Secondly, sparse correlation information is processed using Dempster-Shafer evidence theory, and a new credibility-based function is developed. In addition, the credibility is used to construct a novel neighborhood evidence entropy, which can effectively reflect the uncertainty of data. Thirdly, the proposed neighborhood evidence entropy is applied to assess the importance of features. As a result, several vital features are selected. The experimental results on twelve datasets demonstrate that the effectiveness of the proposed method is superior to other algorithms in construction of information granules and classification accuracy, respectively. Finally, the proposed method is applied to the selection of brain regions in schizophrenia. It can effectively analyze the lesions of schizophrenia and improve the prediction of the disorder. The code is available at https://github.com/fxx-Aurora/TMAE-FS/tree/main.

Phase prediction of high-entropy alloys based on machine learning and an improved information fusion approach

The phase design of high entropy alloys (HEAs) is an important issue since the phase structure affects the comprehensive properties of HEAs. Accurate prediction of phase classification can accelerate material design. In this paper, a new phase prediction framework is proposed using machine learning (ML) and an improved information fusion approach based on the Dempster-Shafer (DS) evidence theory. Considering that the classification results of different ML algorithms may conflict, and the traditional DS evidence theory cannot solve the problem of high conflict, we propose an improved information fusion approach based on the DS evidence theory. The basic probability assignment function is constructed using the ML algorithms. 761 HEAs samples are collected consisting of amorphous phase (AM), solid solution (SS), intermetallic compound (IM), and a mixture of SS and IM (SS + IM). For the small dataset of HEAs, we use a conditional generative adversarial network (CGAN) for data augmentation. Based on the enhanced dataset, the ML model is optimized by sparrow search algorithm (SSA), which can accelerate searching speed of model hyperparameters and improve the performance of the model. The results show that the proposed information fusion method performs better than several other existing techniques on the test set, and the prediction accuracy reaches 94.78 %. Meanwhile, the prediction accuracy of the proposed method is higher than that of the existing technology (93.17 %). It is proved that the proposed method can solve the high conflict problem effectively. Moreover, we present the interpretability analysis of the features by the Shapley additive explanations (SHAP) and the sensitivity matrix. A smaller atomic size difference δ (<6.6 %) is conducive to the formation of SS phase, while a larger δ (>6.6 %) is conducive to the formation of AM phase. A smaller enthalpy of mixing ΔHmix tends to form AM phase. In binary and ternary alloy systems, IM phase can be extracted by the mixing enthalpy ΔSmix < 10. In addition, we find that mean bulk modulus (K) and standard deviation of melting temperature (σT) are critical features to distinguish between SS and SS + IM.

Trustworthy multi-phase liver tumor segmentation via evidence-based uncertainty

Multi-phase liver contrast-enhanced computed tomography (CECT) images convey the complementary multi-phase information for liver tumor segmentation (LiTS), which are crucial to assist the diagnosis of liver cancer clinically. However, the performances of existing multi-phase liver tumor segmentation (MPLiTS)-based methods suffer from redundancy and weak interpretability, resulting in the implicit unreliability of clinical applications. In this paper, we propose a novel trustworthy multi-phase liver tumor segmentation (TMPLiTS), which is a unified framework jointly conducting segmentation and uncertainty estimation. The trustworthy results could assist the clinicians to make a reliable diagnosis. Specifically, Dempster–Shafer Evidence Theory (DST) is introduced to parameterize the segmentation and uncertainty with evidence following Dirichlet distribution. The reliability of segmentation results among multi-phase CECT images is quantified explicitly. Meanwhile, a multi-expert mixture scheme (MEMS) is proposed to fuse the multi-phase evidences, which can guarantee the effect of fusion procedure based on theoretical analysis. Experimental results demonstrate the superiority of TMPLiTS compared with the state-of-the-art methods. Meanwhile, the robustness of TMPLiTS is verified, where the reliable performance can be guaranteed against the perturbations.

A belief rule-based classification system using fuzzy unordered rule induction algorithm

A rule-based system is a widely used artificial intelligence system that employs a set of rules to make decisions. The belief rule-based (BRB) classification system is an extension of fuzzy rule-based (FRB) system that handles uncertainty and imprecision in classification tasks by incorporating Dempster-Shafer evidence theory and fuzzy set theory. However, the BRB classification system suffers from the combinatorial explosion and high time complexity problems. To solve these issues, the fuzzy unordered rule induction algorithm (FURIA) is introduced into the BRB classification systems to design a novel BRB classification system in this paper. FURIA is computationally less complex and has superior classification performance. The proposed system outperforms BRB classification systems in terms of classification performance and significantly reduces the number of rules and conditions. Furthermore, the proposed system offers a more effective solution than FURIA. To evaluate the validity and superiority of the proposed system, we conduct two classification experiments, comparing it with five traditional classifiers and seven rule-based systems, respectively, in terms of classification performance and interpretability.

A patent text-based product conceptual design decision-making approach considering the fusion of incomplete evaluation semantic and scheme beliefs

Conceptual design evaluation is a significant challenge in product development to select suitable conceptual schemes (CS). Relying on decision makers' (DMs) personal experience for design information may result in incomplete and ambiguous evaluation semantics, creating an incomplete decision matrix. Previous approaches use attributes based on candidate schemes to complete the missing information, but neglect the mining of associated design information from external resources such as patents, reducing the beliefs objectivity after missing semantic completion. Besides, non-compensatory nature between DMs’ interactivity and criteria have not been well considered. To fill these issues, a patent text-based CS decision approach considering the fusion of incomplete semantics and scheme beliefs is proposed. First, using the beneficial effects text from patents as historical design data, constructing general evaluation criteria using the Latent Dirichlet Allocation topic model, and introducing the Apriori model to extract strong association rules between criteria to complete the incomplete semantics. Second, a fuzzy measure model for DMs is constructed based on intuitionistic fuzzy cross-entropy and Shapley value method, supporting the allocation of DMs' interactive weights. Then, the fuzzy Dempster-Shafer evidence theory is used to transform the multi-criteria decision model into a belief fusion problem of CS that avoids aggregating the evaluation semantics of non-compensatory criteria and outputting the optimal CS with interval credibility. A practical case study of an in-pipe inspection robot will be employed to validate the proposed approach, sensitivity analysis and comparison results confirmed that the complement data have the reliability to avoid continuous investment in the evaluation process.

Machine learning-based multimodal fusion recognition of passenger ship seafarers’ workload: A case study of a real navigation experiment

Passenger ships have complex transportation systems and seafarers face high workloads, making them susceptible to serious injuries and fatalities in the event of accidents. Existing unimodal workload recognition for seafarers mainly focuses on fixed load induction in bridge simulators, whereas a multimodal approach using multi-sensor data fusion can overcome the reliability and sensitivity limitations of a single sensor. To accurately identify the workload of seafarers, we propose a machine learning-based multimodal fusion method at the feature layer and utilise the Gini index to determine the feature weight of the multimodal data. Through a real ship navigation experiment, the subjective workload assessment technique (SWAT) was employed to collect the continuous workload scores of 24 seafarers in daily tasks. Further, the Dempster–Shafer evidence theory was used to integrate these scores with the unsafe behavior probability of seafarers to obtain a calibrated workload. Electroencephalogram (EEG), electrocardiogram (ECG), and electrodermal activity (EDA) signals were collected in real time, and a high-dimensional feature matrix was extracted to construct the workload recognition model. Random forest, XGBoost, and back-propagation neural networks were used to establish multimodal fusion workload recognition models at the feature-fusion stage, and the model performances were compared. The results showed that the multimodal fusion based on EEG, ECG, and EDA had an excellent recognition accuracy. The XGBoost algorithm has better performance with an accuracy of 85.72%, which is an increment of 9.49% compared to that of the unimodal algorithm, and this improvement passed the statistical significance test. Important features suitable for multimodal fusion recognition were also analysed. The findings of this study have profound significance for enhancing risk control measures pertaining to human factors and ensuring navigation safety.

Geothermal target detection integrating multi-source and multi-temporal thermal infrared data

Thermal infrared remote sensing (TIRS) technology is intriguing for geothermal anomaly detection due to its time efficiency and cost-effectiveness. Land surface temperature (LST) derived from TIRS indicates potential geothermal anomalies. However, LST on different natural features, exhibiting relatively cold/hot anomalies in daytime and nighttime, affected the identification of abnormal areas. The aim of this study was to highlight geothermal anomalous areas by integrating multi-view daytime and nighttime LST data. Specifically, the winter LST time series of drillings on 2013–2023 was processed based on Landsat-8 TIRS in diurnal scenarios. An information aggregation classification method about Dempster-Shafer evidence theory was presented to target recognition at nighttime by the ASTER LST product. This day-night information fusion analysis effectively highlighted potential areas with geothermal anomalies. The results demonstrated that the geothermal anomalies were mainly distributed along the Ruili-Longling Fault and Wanding Fault in a Northeast (NE) – Southwest (SW) direction, and the NE side was more significant than the SW side. These findings suggested that the east side was closer to the magma heat source, and the presumed magma heat source location aligned closely with the detected geothermal anomalies. Geological data were employed for geological interpretation of the LST anomaly area, eliminating non-geothermal influences. Along with drilling data verification, this method was successfully used to identify geothermal anomaly areas in Ruili City, Yunnan Province. Overall, this study provided valuable insights into the detection of geothermal anomalies through TIRS, contributing to the successful development of geothermal resources.

An Improved Dempster–Shafer Evidence Theory Based on the Chebyshev Distance and Its Application in Rock Burst Prewarnings

An Improved Dempster–Shafer Evidence Theory Based on the Chebyshev Distance and Its Application in Rock Burst Prewarnings

A two-level fusion model of vibro-acoustic signals for centrifugal fan blade crack detection

Blade crack detection is the key to ensuring the smooth and safe operation of centrifugal fans. However, a single vibration signal is difficult to fully reflect the health state of the blade and is susceptible to noise interference in the industrial field, which makes it difficult to detect blade cracks. Therefore, a two-level fusion model of vibro-acoustic signals is proposed for blade crack detection of centrifugal fans. Firstly, based on the designed correlated degree of cyclostationarity fusion rule, the data-level fusion of multi-source homogeneous vibro-acoustic signals is completed, and the fused signals with more obvious fault features are obtained. Then, a one-dimensional feature pyramid network is proposed to extract the vibro-acoustic features and generate initial decisions. Finally, a basic probability assignment acquisition method based on the precision of the initial classifiers and a weighted average method based on the Pignistic probability distance are proposed to minimize the conflict between multi-source evidence, and the Dempster-Shafer evidence theory method is used to obtain the blade crack detection results. The effectiveness of the proposed method is verified by the centrifugal fan blade crack detection experiments. Compared with other related methods, the proposed method has better detection performance and stronger robustness.

Hidden Markov Models based intelligent health assessment and fault diagnosis of rolling element bearings.

Hidden Markov Models (HMMs) have become an immensely popular tool for health assessment and fault diagnosis of rolling element bearings. The advantages of an HMM include its simplicity, robustness, and interpretability, while the generalization capability of the model still needs to be enhanced. The Dempster-Shafer theory of evidence can be used to conduct a comprehensive evaluation, and Stacking provides a novel training strategy. Therefore, the HMM-based fusion method and ensemble learning method are proposed to increase the credibility of quantitative analysis and optimize classifiers respectively. Firstly, vibration signals captured from bearings are decomposed into intrinsic mode functions (IMFs) using ensemble empirical mode decomposition (EEMD), and then the Hilbert envelope spectra of main components are obtained; Secondly, multi-domain features are extracted as model input from preprocessed signals; Finally, HMM-based intelligent health assessment framework and fault diagnosis framework are established. In this work, the life cycle health assessment modeling is performed using a few training samples, the bearing degradation state is quantitatively evaluated, normal and abnormal samples are effectively distinguished, and the accuracy of fault diagnosis is significantly improved.

An Improved CBBA Generation Method Based on Triangular Fuzzy Numbers

AbstractAcknowledged as a robust tool for managing uncertain information, Dempster–Shafer evidence theory has seen significant progress in recent years, especially in the refinement of mass functions, also known as basic belief assignments (BBAs). This progress is particularly noticeable in complex domains where the effective handling of uncertainty is considered of paramount importance. Despite these advancements, the generation of complex mass functions, referred to as complex basic belief assignments (CBBAs), continues to be viewed as an open and challenging aspect within the framework of complex evidence theory. A method for CBBA generation based on triangular fuzzy numbers was introduced by Xiao, specifically applied to target recognition. However, despite its application, there is notable room for improvement in the recognition rate achieved by this method. In response to this gap, an improved CBBA generation method based on triangular fuzzy numbers is proposed in this paper. Notably, the consideration of attribute weights is incorporated into the CBBA generation process by this approach. This refinement is rooted in the recognition that, in practical scenarios, different attributes carry distinct levels of importance. Hence, adopting a more rational approach by assigning higher weights to crucial attributes becomes imperative. The proposed method is subjected to rigorous testing in the paper of target recognition, with its performance systematically compared against Xiao’s method and the conventional Dempster–Shafer evidence theory. The ensuing simulation results unequivocally demonstrate the superior efficacy of the proposed method in achieving enhanced target recognition rates.

A collapse risk assessment method for subway foundation pit based on cloud model and improved Dempster–Shafer evidence theory

Collapse is a major engineering hazard in open-cut foundation pit construction, and risk assessment is crucial for considerably reducing engineering hazards. This study aims to address the ambiguity problem of qualitative index quantification and the failure of high-conflict evidence fusion in risk assessment. Thus, a fast-converging and high-reliability multi-source data fusion method based on the cloud model (CM) and improved Dempster–Shafer evidence theory is proposed. The method can achieve an accurate assessment of subway pit collapse risks. First, the CM is introduced to quantify the qualitative metrics. Then, a new correction parameter is defined for improving the conflicts among evidence bodies based on conflict degree, discrepancy degree and uncertainty, while a fine-tuning term is added to reduce the subjective effect of global focal element assignment. Finally, the risk assessment result is obtained according to the maximum affiliation principle. The method is successfully applied to Luochongwei Station, where the difference between the maximum value and the second largest value of the basic probability assignment is 0.624, and the global uncertainty degree is 0.087. Both values satisfy the decision evaluation condition; however, values of other methods only satisfy one or neither condition. In addition, the proposed method requires only four cycles to reach the steady state by fusing data of the same index, which has faster convergence compared with that of other methods. The proposed method has good universality and effectiveness in subway pit collapse risk assessment.