Decision making trial and evaluation laboratory (DEMATEL) is a commonly used method for Multiple Criteria Decision Making (MCDM). The method was primarily developed to analyze real world problems using real valued cri...
详细信息
ISBN:
(纸本)9789813146969
Decision making trial and evaluation laboratory (DEMATEL) is a commonly used method for Multiple Criteria Decision Making (MCDM). The method was primarily developed to analyze real world problems using real valued crisp data. However, in practice, it is often hard to acquire precise information and that is why the values are increasingly expressed as fuzzy sets or fuzzy numbers. A considerable number of studies have been devoted to the fuzzy extension of the DEMATEL method, but none provided the hesitant fuzzy extensions, which proves to be useful for the solution of various real world problems especially in a group decision making environment. This paper addresses this issue and proposes an interval-valued hesitant fuzzy approach to DEMATEL and provides an illustrative example.
With the rapid development of E-commerce, a growing number of people tend to purchase garment products online. Therefore, the fitting evaluation of virtual try-on plays an important role in the clothing industry. In t...
详细信息
ISBN:
(纸本)9789813146969
With the rapid development of E-commerce, a growing number of people tend to purchase garment products online. Therefore, the fitting evaluation of virtual try-on plays an important role in the clothing industry. In this paper, we proposed a method to evaluate the fitting based on Bayesian Discriminant. The inputs of the proposed model are clothing pressures and the outputs are two garment fitting condition: fit or unfit. For constructing the proposed model, two clothing pressure databases were collected, one is fit databases and the other is unfit database. And then the two databases were used for model training and testing. Finally, a fitting prediction model was developed. We only input a new sample's clothing pressures;the fit condition will be evaluated by the proposed model. The results of test show that the prediction accuracy of back substitution of the proposed model reaches to 100% and the prediction accuracy of new samples reaches to 87.5%.
This paper is a continuation to the study of a special kind of generalized syllogisms with intermediate quantifiers. In this paper, we will address some special kinds of syllogisms that are called Consequent Conjuncti...
详细信息
ISBN:
(纸本)9789813146969
This paper is a continuation to the study of a special kind of generalized syllogisms with intermediate quantifiers. In this paper, we will address some special kinds of syllogisms that are called Consequent Conjunctive generalized syllogisms in the sense that all premises contain general intermediate quantifiers. We will show relationships between the validity of intermediate syllogisms and a graded 5-square of opposition.
To process fuzziness and incomparability associated with human's intelligent activities in the real world, an assessment approach with linguistic truth-valued intuitionistic fuzzy reasoning is proposed. Based on l...
详细信息
ISBN:
(纸本)9789813146969
To process fuzziness and incomparability associated with human's intelligent activities in the real world, an assessment approach with linguistic truth-valued intuitionistic fuzzy reasoning is proposed. Based on linguistic truth-valued intuitionistic fuzzy algebra (LTV-IFA), the hesitancy degree is discussed. And the concepts and properties of the linguistic-valued truth credibility degree (LVTCD) and its inverse operator are studied. The model and algorithm of the assessment approach with linguistic truth-valued intuitionistic fuzzy reasoning are given. The approach is useful to process multiple attribute assessment problems by linguistic terms under uncertain environment.
We propose a new theoretical background of autoregressive fuzzy associative memories (AFAM). It stems from the theory of fuzzy relation equations and eigen sets of their solutions. We introduce a couple of related AFA...
详细信息
ISBN:
(纸本)9789813146969
We propose a new theoretical background of autoregressive fuzzy associative memories (AFAM). It stems from the theory of fuzzy relation equations and eigen sets of their solutions. We introduce a couple of related AFAM models that share the same fuzzy relation. For one particular couple, we propose a fast algorithm of data retrieval. We characterize the types of noise that can be removed/reduced by the related models of a couple.
The modern Conflict-Driven Clause Learning (CDCL) SAT solver usually choose a single decision variable in each step, which requires multiple decisions, and sometimes causes too many conflicts and poor efficiency. In t...
详细信息
ISBN:
(纸本)9789813146969
The modern Conflict-Driven Clause Learning (CDCL) SAT solver usually choose a single decision variable in each step, which requires multiple decisions, and sometimes causes too many conflicts and poor efficiency. In this paper, we propose a heuristic complete algorithm by using logic deduction. First, a decision variable is given by the Variable State Independent Decaying Sum (VSIDS) algorithm, then start logic deduction procedure in the unresolved clauses from this variable, and a group of decision variables was generated, which is called the bootstrap set and is used to guide algorithm for first searching the subspace that feasible solution lie in. Experimental results shows that the strategy based logical deduction can significantly improve the performance of CDCL solver compared with other branching heuristics.
Community detection is a widely used method to extract useful information from social networks. Since many types of data are time-dependent, dynamic network clustering has drawn great attention in recent years. A good...
详细信息
ISBN:
(纸本)9789813146969
Community detection is a widely used method to extract useful information from social networks. Since many types of data are time-dependent, dynamic network clustering has drawn great attention in recent years. A good dynamic clustering approach should result in a smooth cluster evolution and determine the number of communities automatically. In this paper, we propose a Dirichlet Process based Dynamic Network Clustering Method using Temporal Dirichlet Process with stochastic block model, which is able to detect communities and meet requirements mentioned above. We did experiments on synthetic data and result shows our method is outperformed several state-of- the-art methods in both the accuracy of determining the number of clusters and the capability of resisting noisy data.
In this paper, cluster ensemble is reformulated by dark knowledge which reveals much information of base learning models. Then, a Gaussian mixture model for cluster ensemble is designed and the inference of the propos...
详细信息
ISBN:
(纸本)9789813146969
In this paper, cluster ensemble is reformulated by dark knowledge which reveals much information of base learning models. Then, a Gaussian mixture model for cluster ensemble is designed and the inference of the proposed model is also illustrated. Finally, some real datasets are selected for comparing experiments. And the results show that the proposed model can outperform the traditional cluster ensemble algorithms in most of times.
The emergence of big data greatly promotes the development of data-driven machine learning technologies. The common assumption in machine learning that the training data and the test data have identical feature spaces...
详细信息
ISBN:
(纸本)9789813146969
The emergence of big data greatly promotes the development of data-driven machine learning technologies. The common assumption in machine learning that the training data and the test data have identical feature spaces with underlying distributions impedes the development of machine learning. To deal with this issue, transfer learning is studied to exploit the knowledge accumulated from data in auxiliary domains to facilitate predictive modelling consisting of different data patterns in the current domain. There have been a significant number of methods proposed to address the classification, as the task, through transfer learning, but the studies targeted at regression problems are still scarce. In this paper, we propose a new transfer learning method to deal with the regression task in the target domain where few data are available. Takagi-Sugeno fuzzy model is used to construct the model for regression task in the source domain, and the prototypes and linear functions of the existing model are modified to make the model more compatible for the target domain. The experimental results demonstrate that our method can improve the performance of the existing model of the source domain on addressing current task in the target domain.
We constructed the equivalent conditions of normal filter of pseudo BL-algebras, then we reveal the relation between Boolean filter and normal filter of pseudo BL-algebras, based on which, we solve an open problem tha...
详细信息
ISBN:
(纸本)9789813146969
We constructed the equivalent conditions of normal filter of pseudo BL-algebras, then we reveal the relation between Boolean filter and normal filter of pseudo BL-algebras, based on which, we solve an open problem that whether or not every Boolean filter is normal in pseudo BL-algebras.
暂无评论