In this study, we present a comprehensible classifier AFSNN that embeds a new type of coherence membership function, which builds upon the theoretical findings of the axiomatic fuzzy set (AFS) theory into the hidden layer of neural network with random weights (NNRWs). Borrowing from the idea of NNRWs that employs the random initialization technique, the relation among attributes, simple concepts, and complex concepts are randomly determined. Complex concepts are generated through the combination of randomly selected simple concepts by AFS logic operation. The output weights of NNRWs are utilized to evaluate the confidence of each complex concept for every target class, which means that the feasibility of complex concepts for every class is determined analytically rather than through the tuning parameters of constraint conditions such as in conventional AFS-based classifiers. For the proposed method, compared to other neural-network-based classification methods, the fuzzy descriptions generated from complex concepts in hidden layer make classification result human understandable. We have experimented with several benchmark datasets and compared the results with other neural network-based classifiers. We show that our method outperforms Ensemble, EvRBFN, NNEP, LVQ, and iRProp+ in the seven out of ten datasets. The results show that the performance of AFSNN is competitive in terms of classification accuracy and the network shows a distinctive capability of providing explicit knowledge in the form of linguistic description.
A key issue in social network group decision making (SNGDM) is to determine the weights (i.e., social influences) of individuals. Notably, in some SNGDM scenarios, the social influences of individuals may evolve over time. Meanwhile, consensus reaching is another important issue in SNGDM. In this article, we are dedicated to disclosing the natural evolution process of social influence, and further to discussing the consensus reaching issue in SNGDM. First, we establish the social influence evolution model, where the individual's social influence is obtained by combining his/her intrinsic influence and network influence. Afterward, we design the consensus reaching process based on social influence evolution (CRP-SIE) to assist the individuals to reach a consensus. Furthermore, we use a hypothetical application to show the applicability of the proposed CRP-SIE. Finally, simulation analysis is adopted to investigate the effects of social influence evolution on consensus reaching in SNGDM, and comparative analysis is conducted to demonstrate the advantages of our proposal.
In literature granular computing and formal concept analysis algorithm use only single-value attributes to knowledge discovery for the data of spatio-temporal aspects. However, most of the datasets like forest fires and tornado storms involve multiscale values for attributes. The limitation of single-value attributes of the existing approaches indicates only the data related to event occurrence which may be missing the elicitation of important knowledge related to severity of event occurrence. Motivated by these limitations, this research article proposes a novel and generalized method which uses ordinal semantic weighted multiscale values for attributes in formal concept analysis with granular computing measures especially when spatio-temporal attributes are not given. The originality of proposed methodology is using ordinal semantic weighted multiscale values for attributes that give complete information of event occurrences. Moreover, the use of ordinal semantic weighted multiscale values improves the results of granular computing measures. The significance of proposed approach is well explained by experimental evaluation performed on publicly available datasets on storm occurring in different States of America.
This study elaborates on a design of a face recognition algorithm realized with feature extraction from 2D-LDA and the use of polynomial-based radial basis function neural networks (P-RBF NNS). The overall face recognition system consists of two modules such as the preprocessing part and recognition part. The proposed polynomial-based radial basis function neural networks is used as an the recognition part of the overall face recognition system, while a data preprocessing algorithm presented of 2 dimensional linear discriminant analysis (2D-LDA) is exploited to data preprocessing. The essential design parameters are optimized by means of differential evolution (DE). The experimental results for benchmark face datasets - the Yale and ORL database - demonstrate the effectiveness and efficiency of 2D-LDA algorithm compared with other approaches such as principal component analysis (PCA), and fusion of PCA-LDA.
