Search

• We propose a joint framework that integrates estimation, consistency improvement and consensus reaching into one phase. • We propose a minimum adjustment model with completeness, consistency, and consensus control (MAM-CCCC). • We present a completeness, consistency, and consensus reaching process (CCCRP) to support the GDM problems with incomplete fuzzy preference relations (FPRs). • We verify the effectiveness of MAM-CCCC through simulation and comparison analyses. In group decision making (GDM), there exists a situation in which experts may not able to provide comparative judgements regarding all pairs of alternatives, and therefore leading to the expression of incomplete preference. The existing frameworks to manage the GDM problem with incomplete preference relations have been investigated intensively and followed a common resolution scheme composed of three processes: estimation, consistency improvement, and consensus reaching. However, the consensus reaching process is applied after the estimation process and consistency improvement processes, leading to the destruction of the consistency of estimated preference relations, which will duplicate the process of improving consistency and consensus, resulting in significant adjustments of experts' preferences. To avoid this issue, we first propose a joint framework to integrate the consensus reaching process with estimation and consistency improvement. This framework is designed based on a minimum adjustment optimization model with completeness, consistency, and consensus control. It can produce complete preference relations with acceptable consistency and consensus, and simultaneously guarantee the minimum adjustment of experts' preferences. Finally, simulation and comparative analyses are used to justify the validity of the proposal. [ABSTRACT FROM AUTHOR]

In uncertainty reasoning, conjunctive and disjunctive combination rules are the core tools for information updates. As an extension of evidential reasoning, random permutation set reasoning models uncertain information based on ordered focal sets. Existing combination rules in random permutation set theory, orthogonal sums, do not satisfy the commutativity of one of the original distributions and overly obey its order information. In this paper, the random permutation set theory is interpreted as an refined extension of Dempster–Shafer theory, and a layer-2 belief structure is proposed to describe the permutation event space. Compared with the traditional belief structure, the proposed structure can model both symbolic and numerical uncertainty. Based on the above, the conjunctive and disjunctive combination rules in Dempster–Shafer theory are extended to random permutation set theory. Through properties analysis and simulation demonstration, we demonstrate that the proposed methods can not only resolve the counter-intuitive results of orthogonal sums, but make full use of order information in distributions as well. In addition, we also extend the product space operations and discounting methods based on the proposed methods, and give a general framework of multi-source information fusion under the random permutation set theory. • First interpret the random permutation set from the layer-2 belief structure perspective. • First discuss the requirements of combination rules in random permutation set theory. • First propose the conjunctive and disjunctive rules in random permutation set theory. • First propose the multi-source information fusion approach in random permutation set theory. [ABSTRACT FROM AUTHOR]

· Proposing a novel 3WD-GMCR framework under hesitant fuzzy environment. · Improving the option prioritization to explain the ranking strength of states. · Redefining the concepts of conflict stability. · Embedding the DMs' preference differences into the stability analysis. Multi-criteria decision aiding/making (MCDA/M) approach and three-way decisions (3WD) are embedded into the framework of graph model for conflict resolution (GMCR). The objective of this study is to develop more reasonable preference ranking for decision makers (DMs) produced from the perspective of options. This implies further simplification of the underlying computing behind conflict resolution. More specifically, DMs' original option statements are evaluated by hesitant fuzzy sets (HFSs), then a three-way decisions approach is used to screen out the infeasible and rank the feasible option statements, and the feasible option statements' loss values of three-way decisions approach are determined based on the hesitant fuzzy (HF) evaluation values. In addition, based on the value of conditional probability of the feasible option statements, an improved option prioritization technique with objective weights is developed to efficiently rank the conflict states, so that it can efficiently reflect the intensity of the ranking. Then, considering the preference thresholds of DMs, new definitions of threshold stabilities are proposed. As demonstrated by the case study in the problem of a carbon emission conflict in supply chain under "3060 carbon peak and neutrality" goal in China, the proposed novel three-way decisions graph model for conflict resolution (3WD-GMCR) framework can be widely applied to the realistic scenarios of decision-making. Compared with previous studies, the proposed approach can not only obtain the intensity ranking of conflict states, but also resolve complex large-scale conflicts effectively. [ABSTRACT FROM AUTHOR]

The management of uncertainty in decision-making problems remains a very challenging and timely research issue despite many proposals. An interesting topic in this area in recent years has been Granular Computing. In this paper, we present a coherent framework for various models of information granules, using hierarchies of information for dealing with knowledge acquired and processed at different levels of abstraction. Granular Computing, a paradigm for handling higher types of uncertainty in decision analysis, is considered a new conceptual and algorithmic asset of decision-making studies and, in particular, data-driven decision-making. Most relevant studies have focused on categories of information granules, namely intervals, fuzzy sets, rough sets, and shadowed sets. To better understand this promising area, this study provides a comprehensive overview of Granular Computing for decision-making through literature analysis, enhancing a variety of extensions, applications, and challenges. • We propose a comprehensive review for granular computing in decision making. • We provide a bibliometric review for granular computing in decision making. • We review main applications in granular computing in decision making. • We provide some future directions for granular computing in decision making. [ABSTRACT FROM AUTHOR]

Host cardinality estimation is one crucial task in network traffic measurement. Super host is the host that exhibits anomalies in host cardinality and it is usually related to network abnormal events. Therefore, accurate host cardinality estimation is the premise of super host identification and it can be used to measure the trust degree of a network. Sketches have been widely used in super host identification. However, expanding network scale and increasing link rate bring challenges to the efficiency and accuracy of sketch-based super host identification. The size of the counters in most sketches requires a trade-off between memory resources and accuracy. To meet the need of measuring high cardinalities, large size counters are applied, which leads to memory waste in monitoring low cardinality hosts. On the other hand, most sketches have high computational overhead when tracking superhosts, resulting in inefficiency. In order to address these issues, we propose a novel memory efficient and reversible sketch, named ExtendedSketch+, to provide accurate host cardinality estimation with the purpose of super host identification and network host trust evaluation. ExtendedSketch+ achieves both high memory utilization efficiency and high accuracy, in addition to high super host identification efficiency. It applies extensible counters to record unbalanced host cardinality distribution, by adaptively expanding the counters with the increase of cardinality. It adopts a lossless traffic information transfer strategy during counter extension to ensure the accuracy of cardinality estimation. It can directly tracks the host with the highest cardinality in each bucket, which greatly improves the identification efficiency of super hosts. Based on accurate cardinality estimation of ExtendedSketch+, we can further accurately evaluate host trust degree. We theoretically analyze ExtendedSketch+ with regard to its space and time complexities and estimation accuracy. We conduct performance evaluation based on real network traffic traces. Experimental results show that ExtendedSketch+ performs better than state-of-the-art sketches regarding super host identification and provides accurate host trust evaluation. • A memory efficient and reversible sketch named ExtendedSketch+. • A quick and accurate super host identification method based on ExtendedSketch+. • An accurate network host trust evaluation method based on ExtendedSketch+. • A detailed theoretical analysis on ExtendedSketch+ on complexities and accuracy. • A performance comparison to show the superiority of ExtendedSketch+. [ABSTRACT FROM AUTHOR]

In the elicitation of decision makers' fuzzy and uncertain assessments, linguistic terms are natural and efficient as the preference modeling tools. Although the linguistic variables are available, they would not be operational without any detailed quantification. Motivated by the flexibility of information granularity, this paper develops information granules to represent linguistic terms in the form of intervals and interval type-2 fuzzy sets (IT2FSs) in best worst method (BWM). The development is aimed at minimizing inconsistency in the decision making (DM) process to ensure the rationality of the assessments provided by decision makers. Furthermore, the input and output based consistencies of BWM are considered. The granulation of entries of pairwise comparison vectors are the foundation of BWM to formulate an optimization problem where particle swarm optimization (PSO) algorithm serves as the optimization framework. Both individual and group decision making (GDM) scenarios are taken into consideration. For the GDM process, a performance index for measuring the group consensus is also proposed. Several examples and validity analysis are covered to illustrate the major ideas of this study. Finally, as a case study, a recommendation of the sequence of visiting tourist attractions in Wuhan and the corresponding comparative analysis are represented. • A granular computing-based method in BWM framework is proposed. • Construction of granular linguistic information to represent preference information of DMs is given. • A novel Euclidean distance function to measure the agreement among the group is proposed. • A case study of scenic spots recommendation in Wuhan with online reviews is exhibited. [ABSTRACT FROM AUTHOR]

• We focus on the unification and fusion of heterogeneous distributed linguistic information. • We present several minimum information-loss transformation models with desirable properties. • We present a multi-attribute group decision making framework in a heterogeneous distributed linguistic context. • We demonstrate the necessity of flexibility in distributed linguistic decision making. In the problems that linguistic assessments are conducted by adopting multiple sources of information representations, the management of unification of heterogeneous information and information loss are necessary. To support a useful fusion of heterogeneous distributed information in linguistic group decision making, a minimum information-loss transformation framework is proposed in this paper. First, distributed linguistic distance measurements are defined to measure information loss among heterogeneous distributed linguistic preference information, and then several minimum information-loss transformation models (MILTMs) with desirable properties are proposed. Furthermore, the application of the MILTMs in addressing the fusion of heterogeneous distributed linguistic information in a multi-attribute group decision context is discussed, and the flexibility of distributed linguistic information is studied to justify the MILTMs through numerical examples and comparative analyses. [ABSTRACT FROM AUTHOR]

A group of experts are commonly invited to find an optimal solution to a complex decision making problem. When the bipolarity of decision information should be considered in group decision making (GDM), intuitionistic fuzzy values (IFVs) have the capability to model such opinions of decision makers (DMs). This paper develops a consensus model in GDM under intuitionistic fuzzy environments with flexibility. First, it is assumed that the initial opinions of DMs are expressed as intuitionistic fuzzy preference relations (IFPRs). A novel additive consistency index is constructed to measure the deviation degree of IFPRs from fuzzy preference relations (FPRs) with additive consistency, where the non-determinacy degree of IFPRs is incorporated. The thresholds of the proposed index corresponding to IFPRs with acceptable additive consistency are discussed and computed. Second, the consensus level of DMs is defined using the similarity degree between two IFVs. An optimization problem is established by maximizing the fitness function, which is constructed by linearly combining the proposed additive consistency index and consensus level. Two flexibility degrees are offered to each DM such that the initial opinions with the bipolarity can be adjusted correspondingly. Third, individual IFPRs in GDM are optimized using the particle swarm optimization (PSO) algorithm. Numerical examples are carried out to illustrate the proposed consensus model by comparing with the existing ones. The obtained results reveal that the proposed additive consistency index can reflect the inherent property of IFPRs. Different with the previous studies, two original flexibility degrees are proposed to characterize the multi-granularity of decision information in GDM. • A novel consistency index is constructed to measure the inconsistency degree of IFPRs. • An optimization model is proposed by considering the consistency degree and consensus level. • A novel algorithm of group decision making is established where the PSO algorithm is used. [ABSTRACT FROM AUTHOR]

• Evaluating different models' perspectives for real-time adversarial attack detection in VANETs. • Identifying and preprocessing DSRC adversarial data using standard and fusion preprocessing approaches. • Selection for the golden ML model using a fuzzy decision-making framework for VANETs. • Evaluating the efficiency of the developed framework in four assessment processes. This paper addresses various issues in the literature concerning adversarial attack detection in Vehicular Ad-hoc Networks (VANETs). These issues include the failure to consider both normal and adversarial attack perspectives simultaneously in Machine Learning (ML) model development, the lack of diversity preprocessing techniques for VANETs communication datasets, the inadequate selection guidelines for real-time adversarial attack detection models, and the limited emphasis on explainability in adversarial attack detection. In this study, we propose an original fuzzy decision-making framework that incorporates multiple fusion standpoints. Our framework aims to evaluate multi-ML models for real-time adversarial attack detection in VANETs, focusing on three stages. The first stage involves identifying and preprocessing Dedicated Short-Range Communication (DSRC) data using standard and fusion preprocessing approaches. Two communication scenarios, normal and jammed, are considered, resulting in two DSRC datasets. In the second stage, we develop multi-ML models based on the DSRC datasets using standard preprocessing and feature fusion preprocessing for dataset-1 and dataset-2, respectively. The third stage evaluates the multi-ML models using a fuzzy decision-making approach based on the Fuzzy Decision by Opinion Score Method (FDOSM) and an adversarial attack decision fusion matrix. The External Fusion Decision (EFD) settings of the FDOSM address individual ranking variance, provide a unique rank and select the best model. Experimental results demonstrate that the K-Nearest Neighbors Algorithm (kNN) model achieves the highest explain score of 0.2048 in dataset-1 using standard preprocessing, while the Random Forest (RF) model applied to dataset-2 using fusion preprocessing emerges as the most robust and golden model against adversarial attacks, with a score of 0.1819. This finding suggests that the fusion preprocessing approach using Principal Component Analysis (PCA) is more suitable for addressing normal and adversarial attack perspectives. Furthermore, our fuzzy framework undergoes evaluation in terms of systematic rank, sensitivity analysis, explainability analysis, and comparison analysis. Overall, this framework provides valuable insights for researchers and practitioners in VANETs, informing the execution, selection, and interpretation of multi-ML models to tackle adversarial attack detection problems effectively. The new fuzzy framework demonstrates that multi-ML models based on feature fusion preprocessing are more effective. [ABSTRACT FROM AUTHOR]

Accurate and timely network traffic measurement is essential for network status monitoring, network fault analysis, network intrusion detection, and network security management. With the rapid development of the network, massive network traffic brings severe challenges to network traffic measurement. However, existing measurement methods suffer from many limitations for effectively recording and accurately analyzing big-volume traffic. Recently, sketches, a family of probabilistic data structures that employ hashing technology for summarizing traffic data, have been widely used to solve these problems. However, current literature still lacks a thorough review on sketch-based traffic measurement methods to offer a comprehensive insight on how to apply sketches for fulfilling various traffic measurement tasks. In this paper, we provide a detailed and comprehensive review on the applications of sketches in network traffic measurement. To this end, we classify the network traffic measurement tasks into four categories based on the target of traffic measurement, namely cardinality estimation, flow size estimation, change anomaly detection, and persistent spreader identification. First, we briefly introduce these four types of traffic measurement tasks and discuss the advantages of applying sketches. Then, we propose a series of requirements with regard to the applications of sketches in network traffic measurement. After that, we perform a fine-grained classification for each sketch-based measurement category according to the technologies applied on sketches. During the review, we evaluate the performance, advantages and disadvantages of current sketch-based traffic measurement methods based on the proposed requirements. Through the thorough review, we gain a number of valuable implications that can guide us to choose and design proper traffic measurement methods based on sketches. We also review a number of general sketches that are highly expected in modern network systems to simultaneously perform multiple traffic measurement tasks and discuss their performance based on the proposed requirements. Finally, through our serious review, we summarize a number of open issues and identify several promising research directions. • Main traffic measurement tasks and advantages of applying sketches. • Criteria to evaluate sketch-based network traffic measurement methods. • Serious review on the state-of-art sketch-based traffic measurement. • Significant open issues and promising future research directions. [ABSTRACT FROM AUTHOR]

• Propose a linguistic information granulation model. • Develop a penalty function-based co-evolutionary PSO (PFCPSO) solution approach. • Present the whole algorithm framework for the PFCPSO solution approach. • Discuss how the granulation model and the PFCPSO solution approach work in practice. • Compare PFCPSO and co-evolutionary PSO in terms of the performance of the solution. This study focuses on linguistic information operational realization through information granulation in group decision-making (GDM) scenarios where the preference information offered by decision-makers over alternatives is described using distributed linguistic preference relations (DLPRs). First, an information granulation model is proposed to arrive at the operational realization of linguistic information in the GDM with DLPRs. The information granulation is formulated as a certain optimization problem where a combination of consistency degree of individual DLPRs and consensus degree among individuals is regarded as the underlying performance index. Then, considering that the proposed model is a constrained optimization problem (COP) with an adjustable parameter, which is difficult to be effectively solved using general optimization methods, we develop a novel approach towards achieving the optimal solution, referred to as penalty function-based co-evolutionary particle swarm optimization (PFCPSO). Within the PFCPSO setting, the designed penalty function is used to transform the COPs into unconstrained ones. Besides, the penalty factors and the adjustable parameter, as well as the decision variables of the optimization problems, are simultaneously optimized through the co-evolutionary mechanism of two populations in co-evolutionary particle swarm optimization (CPSO). Finally, a comprehensive evaluation problem about car brands is studied using the proposed model and the newly developed PFCPSO approach, which demonstrates their applicability. Two comparative studies are also conducted to show the effectiveness of the proposals. Overall, this study exhibits two facets of originality: the presentation of the linguistic information granulation model, and the development of the PFCPSO approach for solving the proposed model. [ABSTRACT FROM AUTHOR]

• Identifying digital transformation barriers in construction industry. • Introducing the loss function adopted in PEA in COG. • Obtaining the ranking of barriers using dynamic COG and PEA. • Applying the SNA to derive the weight vector of barriers. • Establishing the COG-PEA-SNA framework using the Nash equilibrium. The absence of a reliable, dynamic evaluation system has impeded early-stage industrial research progress, particularly in the digital transformation of the construction industry. Moreover, existing research studies rarely explore the impact of digitalt transformation barriers considering the interplays among them. This paper aims to introduce an innovative framework to generate dynamic collective opinions for barrier analysis in such context. The proposed dynamic collective opinion generation framework comprises three key components: Collective Opinion Generation, Prediction with Expert Advice (PEA), and Social Network Analysis. Its goal is to provide dependable decision support when subjective evaluation data from experts is available. Initially, a bi-objective optimization model generates the initial barrier weight vector. The PEA incorporates a loss function to measure the deviation between aggregated probablity density function and actual observed data, updating the weight vector over time. Next, an influence network covering all barriers is established. Node significance is evaluated through metrics like degree centrality, closeness centrality, and eigenvector centrality. The gravity model based on three metrics is used to determine interrelationships among barriers, resulting in a weight vector capturing these interplays. The two weight vectors are combined with Nash equilibrium, yielding the ultimate weight vector for barriers. The effectiveness of the proposed dynamic collective opinion generation framework is showcased through a case study on China Construction Third Bureau. Results indicate that talent structure notably influences construction companies' digital transformation. Additionally, market structure and strategic position significantly impact digital transformation in this industry. [ABSTRACT FROM AUTHOR]

In today's world of connectivity, various domains use different multi-sensor Internet of Things (IoT) and Intelligent Systems (IS) applications. These applications involve extensive interactions between thousands or millions of components in open environments, which challenges verifying their reliability and efficiency. This paper introduces the first investigation in verifying IoT applications and intelligent systems in multi-source data settings with multi-agent commitment protocols in uncertain or inconsistent environments. Specifically, we present original and efficient solutions for modeling and verifying these systems with conditional and unconditional commitment protocols under uncertain or inconsistent settings. We introduce 4v-CTL c and 4v-CTL c c , multi-valued logics of commitment for reasoning about inconsistency over these systems that expand 3v-CTL c and 3v-CTL c c for reasoning about uncertainty. Moreover, we introduce new reduction algorithms for reducing our multi-valued model checking problems to the two-valued ones. To implement these algorithms, we develop two new automatic verification tools. The first tool translates the multi-valued logics to CTL and automatically interacts with the NuSMV model checker. The second tool translates these logics to the two-valued versions, CTL c and CTL c c , and automatically interacts with the MCMAS+ model checker. We apply our verification approaches to a Smart Home, a Smart Hospital and a Smart Mortgage system with multi-source data as case studies using sets of properties, including safety, liveness and reachability. The experimental results obtained by the proposed multi-valued model checking techniques proved these techniques' high efficiency and applicability to modeling and verifying intelligent and autonomous multi-source data systems. • New multi-valued logics to reason about inconsistency in multi-source data settings. • Modeling IoT and IS applications using different multi-valued commitment logics. • New reduction-based model checking algorithms for multi-source data applications. • Implementing two new model checking tools: MCMAS-interactor and NuSMV-interactor. [ABSTRACT FROM AUTHOR]

The phase of operation and maintenance (O&M) is the most time-consuming and cost-intensive stage in the project life cycle. However, the potential benefits of Building Information Modeling (BIM) in this phase have not been fully explored, unlike in the design and construction phases. This is particularly evident in the absence of a comprehensive assessment of its application capabilities. In light of this setting, we develop a BIM maturity assessment model (BIM MAM) for the project's O&M phase. The proposed model comprises of an assessment indicator system that facilitates experts in providing individual assessment results, and a collective opinion aggregation method in a probabilistic context based on a multi-objective optimization model that is employed to generate the ultimate collective assessment results. The established multi-objective optimization model for BIM MAM incorporates the influence of human behavior factors on the final results by introducing the fairness concern utility level as an objective. Finally, we take Wuhan Jiangxia Sewage Treatment Plant as a practical case to illustrate the effectiveness and feasibility of the proposed BIM MAM. • We establish a BIM maturity assessment model for the project's O&M phase. • We build multi-objective optimization-based collective opinion aggregation. • We apply the proposed model for a real-life case study. [ABSTRACT FROM AUTHOR]

Traffic classification groups similar or related traffic data, which is one main stream technique of data fusion in the field of network management and security. With the rapid growth of network users and the emergence of new networking services, network traffic classification has attracted increasing attention. Many new traffic classification techniques have been developed and widely applied. However, the existing literature lacks a thorough survey to summarize, compare and analyze the recent advances of network traffic classification in order to deliver a holistic perspective. This paper carefully reviews existing network traffic classification methods from a new and comprehensive perspective by classifying them into five categories based on representative classification features, i.e., statistics-based classification, correlation-based classification, behavior-based classification, payload-based classification, and port-based classification. A series of criteria are proposed for the purpose of evaluating the performance of existing traffic classification methods. For each specified category, we analyze and discuss the details, advantages and disadvantages of its existing methods, and also present the traffic features commonly used. Summaries of investigation are offered for providing a holistic and specialized view on the state-of-art. For convenience, we also cover a discussion on the mostly used datasets and the traffic features adopted for traffic classification in the review. At the end, we identify a list of open issues and future directions in this research field. • Comprehensive evaluation criteria to assess classification methods. • A thorough review on traffic classification methods. • A discussion on advantages and disadvantages of classification methods. • An analysis on classification granularity by dividing it into four levels. • Exploration of open issues and future research directions. [ABSTRACT FROM AUTHOR]

• A dynamic hybrid trust network is formed to represent social relationships among DMs. • Spectral clustering is used to efficiently cluster DMs into more trusted sub-groups. • Willingness of DMs to cooperate is considered in the two-stage consensus model. • Preference modification suggestions are generated for both sub-groups and individuals. Clustering and the feedback mechanism in a consensus reaching process (CRP) have been regarded as two critical components when solving the large-scale group decision-making (LSGDM) problem. However, the necessity of treating decision makers (DMs) as a dynamic social network (in terms of their trust relationships) in the DM clustering has not been fully investigated. Also, with people's increased democratic awareness, it appears essential to consider the individual's willingness to cooperate when designing the feedback mechanism in the CRP. This study will focus on solving the LSGDM problem considering dynamic social networks and propose a novel two-stage consensus model. First, a hybrid trust network is built to dynamically represent social relationships among DMs (i.e., the hybrid trust network evolves with the CRP). Spectral clustering algorithm is then used to cluster DMs into more trusted sub-groups, thus improving the efficiency of coordinating DMs. Second, a two-stage feedback mechanism is designed to help DMs reach a consensus in a more human-centric manner. To reach a consensus without seriously violating the willingness of DMs, we strike a balance between maximizing the consensus degree and minimizing the adjustment cost and further develop two nonlinear programming models to provide modification suggestions for sub-groups and individuals, respectively. The originality of the proposed consensus model can be summarized as clustering the dynamic hybrid trust network integrated with balancing the decision-making efficiency against the willingness of DMs to cooperate. The feasibility and effectiveness of the developed model are demonstrated through the detailed application study. [ABSTRACT FROM AUTHOR]

The available method based on statistical principles for aggregating hesitant fuzzy linguistic term set (HFLTS) possibility distribution is the N -two-stage algorithmic aggregation paradigm driven by the K -means clustering (N2S-KMC). Nonetheless, the N2S-KMC method is subject to two significant limitations. (i) The grouping technique is capable of effectively partitioning decision-making information into N groups. However, it does not determine the appropriate placement of members within each group, as the number of computations is dependent on the number of elements present in each group, rather than the elements themselves. (ii) The initial clustering centers of K -means clustering are chosen without adhering to the distribution law within the aggregated hesitant 2-tuple linguistic terms set (H2TLTS) possibility distribution. This may result in a reduction in the clustering performance. In order to address the aforementioned limitations, we suggest two enhancement techniques for the former. Firstly, we propose the utilization of the minimum average difference (MAD) method to ascertain the number of groups. This approach aims to reduce the time required for the initial stage of aggregation following grouping. Secondly, we recommend the implementation of the maximize compactness degree of inter-group grouping (MCDIGG) method. This method enables the identification of group members, resulting in a more concentrated distribution of data subsequent to grouping. The present study suggests the utilization of MAD and MCDIGG techniques as a substitute for the grouping approach in the N2S-KMC model. This leads to the development of a new algorithm, IN2S-DO-KMC, wherein the data is partitioned into K subsets in a descending order to determine the initial center for KMC. Furthermore, with respect to the issue present in the subsequent phase, we propose the utilization of the density canopy (DC) algorithm to perform pre-clustering of the data and produce the initial clustering center and the quantity of clusters for the K -means algorithm. Subsequently, a refined version of the N2S-KMC model, denoted as IN2S-DC-KMC, has been suggested. Ultimately, an empirical study is conducted to assess the validity and practicability of the proposed framework for evaluating failure modes in medical devices. The outcomes are evaluated with regards to the efficacy of the algorithm, the numerical dispersion, and the pragmatic ramifications. • We propose the MAD method that determines the number of groups for the aggregated HFLTS possibility distributions. • We propose the MCDIGG method that determines member of each group with HFLTS possibility distributions. • We apply an improved density canopy clustering algorithm to the K-means clustering algorithm for pre-clustering process. • We propose a measure to predict the degree of compactness after data aggregated in different grouping cases. • We propose two aggregation algorithms, IN2S-DO-KMC and IN2S-DC-KMC, for HFLTS possibility distributions. [ABSTRACT FROM AUTHOR]

The accurate segmentation of medical images plays a crucial role in diagnosing and treating diseases. Although many methods now use multimodal joint segmentation, the joint use of segmentation features extracted by multiple models can lead to heterogeneity and uncertainty. Unreasonable fusion methods cannot exploit the advantages of multiple models and still lack good performance in segmentation. Therefore, this study proposes the FTransCNN model, which is composed of a convolutional neural network (CNN) and Transformer and is based on a fuzzy fusion strategy that jointly utilizes the features extracted by a CNN and Transformer through a new fuzzy fusion module. First, the CNN and Transformer act as the backbone network for parallel feature extraction. Second, channel attention is used to promote the global key information of Transformer to improve the feature representation ability, and spatial attention is used to enhance the local details of CNN features and suppress irrelevant regions. Third, the proposed model applies the Hadamard product to model fine-grained interactions between the two branches and uses the Choquet fuzzy integral to suppress heterogeneity and uncertainty in fused features. Fourth, FTransCNN employs fuzzy attention fusion module (FAFM) hierarchical upsampling to effectively capture both low-level spatial features and high-level semantic context. Finally, the new model obtains the final segmentation result by using the deconvolution and results in an improvement in segmentation. The experimental results on Chest X-ray and Kvasir-SEG dataset show that FTransCNN has better performance on segmentation tasks than the-state-of-the-art deep segmentation models. [ABSTRACT FROM AUTHOR]

Estimating interest rates is a typical multivariate prediction problem that has garnered considerable attention in the finance industry. However, the rising complexity of the prediction environment has presented significant obstacles to the methodology and application of traditional single-scale rational prediction models. Considering this challenge, the paper presents a new multivariate fusion prediction system that aims to tackle the following issues: (1) How to mine prediction information from multi-scale information systems (MSISs)? (2) How to describe the irrational behavior of decision-makers (DMs) in prediction processes? (3) How to improve the prediction performance and generalization capability of the models? Specifically, the score function of each feature under MSISs is primarily established by applying scale rules, regret theory (RT), and dominance relations to thoroughly explore prediction information across varying scales. Second, an adaptive S3WD model is developed for feature selection, which leverages the feature score distribution and the sequential three-way decision (S3WD) concept to avoid the problem of dimensional disasters, thereby improving the accuracy of selected features and reducing the learning cost. Furthermore, to enhance the effectiveness and rationality of the kernel extreme learning machine (KELM), an improved version known as IKELM is developed, which combines the regret-based comprehensive score of each sample. Finally, a multivariate fusion prediction system is constructed and abbreviated as an S3WD-IKELM-PSO system, where the particle swarm optimization (PSO) algorithm is employed to determine optimal parameters. It is worth noting that actual interest rate estimation datasets are utilized to verify the feasibility and validity of the proposed prediction system. According to the experimental results, the S3WD-IKELM-PSO system exhibits superior prediction performance and generalization ability compared to existing machine learning models. • A regret theory-based multivariate prediction system in MSISs is explored. • A regret-based feature evaluation system in an MSIS is designed. • An adaptive S3WD model for feature selection is proposed. • An improved KELM model is proposed. [ABSTRACT FROM AUTHOR]

• A novel large-group failure mode and effects analysis framework is provided. • RBULI is proposed to flexibly assess the risk level of failure modes. • The SFAKM clustering and CRP are utilized to manage consensus in FMEA. • The behavioral TOPSIS is introduced to rank failure modes. • Potential failure modes of angle grinder are identified and analyzed. Accidents associated with the use of construction equipment are among the leading causes of fatal injuries in the construction industry. In particular, angle grinders are associated with a significant number of occupational injuries every year. However, practitioners and researchers have paid limited attention to this issue. To facilitate the development of more sophisticated plans and guidelines to prevent angle grinder-related accidents, failure mode and effects analysis (FMEA) is employed for risk management in such a context. The conventional FMEA method is extensively used for examining potential failure in many industries, but has been criticized much in the literature for its various limitations. This study presents a novel large-group FMEA (LGFMEA) model, which integrates a clustering analysis for handling experts at large scale, a consensus reaching process with relative basic uncertain linguistic information (RBULI) to manage opinion diversity among experts, and the behavioral TOPSIS method to rank failure modes. The assessment information is characterized by the RBULI, a novel information representation construction method applied to handle complex evaluations under uncertainty. Finally, the proposed LGFMEA approach is performed for risk analysis related to angle grinder use to obtain insights into risk mitigation, and the sensitive and comparative analyses are performed to verify the rationality and feasibility of the model. [ABSTRACT FROM AUTHOR]