In practical decision-making, the behavior factors of decision makers often affect the final decision-making results. Regret theory is an important behavioral decision theory. Based on the regret theory, a novel decision-making method is proposed for the multiattribute decision-making problem with incomplete attribute weight information, and the attribute values are expressed by Atanassov intuitionistic fuzzy numbers. At first, a new distance of intuitionistic fuzzy sets is put forward based on the traditional Canberra distance. Then, we utilize it for the definition of the regret value (rejoice) for the attribute value of each alternative with the corresponding values of the positive point (negative point). The objective of this method is to maximize the comprehensive perceived utility of the alternative set by the decision maker. The optimal attribute weight vector is solved, and the optimal comprehensive perceived utility value of each alternative is obtained. Finally, according to the optimal comprehensive perceived utility value, the rank order of all alternatives is concluded.
The social network is a social structure made up of individuals who are tied by social links. With the rapid development of information technology, online social networking services and microblogging service received a lot of attention. Social networks provide a comprehensive communication platform of interaction, knowledge sharing, information dissemination to people, etc. They also bring a significant impact on people's working style and interpersonal communication. Drawing from trait theory, regulatory focus theory, followership theory, political skills, self-construal theory, and performance theory, this study systematically investigates the antecedents that induce the difference in followership behavior and the different consequences of behavior on job performance. We introduce a novel hybrid similarity measure, and the best matching based supervised learning process is conducted for training the time series. The events before the current timestamp can be adopted as a training set, and an early predictor will be generated by learning the rules from the training set. The newly coming events will be used for verifying the predictor, or assessing and tuning it. This paper clarifies the antecedents' mechanism for differences in followership behavior and the consequence mechanism that followership behavior differently impacts job performance.
The intuitionistic fuzzy entropy has been widely used in measuring the uncertainty of intuitionistic fuzzy sets. In view of some counterintuitive phenomena of the existing intuitionistic fuzzy entropies, this article proposes an improved intuitionistic fuzzy entropy based on the cotangent function, which not only considers the deviation between membership and non-membership, but also expresses the hesitancy degree of decision makers. The analyses and comparison of the data show that the improved entropy is reasonable. Then, a new IF similarity measure whose value is an IF number is proposed. The intuitionistic fuzzy entropy and similarity measure are applied to the study of the expert weight in group decision making. Based on the research of the existing expert clustering and weighting methods, we summarize an intelligent expert combination weighting scheme. Through the new intuitionistic fuzzy similarity, the decision matrix is transformed into a similarity matrix, and through the analysis of threshold change rate and the design of risk parameters, reasonable expert clustering results are obtained. On this basis, each category is weighted; the experts in the category are weighted by entropy weight theory, and the total weight of experts is determined by synthesizing the two weights. This scheme provides a new method in determining the weight of experts objectively and reasonably. Finally, the method is applied to the evaluation of railway reconstruction scheme, and an example shows the feasibility of the method.
In the realm of intelligent education, knowledge tracking is a critical study topic. Deep learning-based knowledge tracking models have better predictive performance compared to traditional knowledge tracking models, but the models are less interpretable and also often ignore the intrinsic differences among students (e.g., learning capability, guessing capability, etc.), resulting in a lack of personalization of predictive results. To further reflect the personalized differences among students and enhance the interpretability of the model at the same time, a Deep Knowledge Tracking model integrating Learning Capability and Item Response Theory (DKT-LCIRT) is proposed. The model dynamically calculates students’ learning capability by each time interval and allocates each student to groups with similar learning capabilities to increase the predictive performance of the model. Furthermore, the model introduces item response theory to enhance the interpretability of the model. Substantial experiments on four real datasets were carried out, and the experimental results showed that the DKT-LCIRT model improved the AUC by 3% and the ACC by 2% compared to other models. The results confirmed that the DKT-LCIRT model outperformed other classical models in terms of predictive performance, fully reflecting students’ individualization and adding a more meaningful interpretation to the model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.