Flight training is an important means for the cadets to master the theoretical knowledge, improve the practical operation ability and train the mental quality of the flight. This paper established a FOQ (Flight Operat...
详细信息
ISBN:
(纸本)9789813146969
Flight training is an important means for the cadets to master the theoretical knowledge, improve the practical operation ability and train the mental quality of the flight. This paper established a FOQ (Flight Operational Quality) evaluation model based on the fuzzy logic to score the cadets' FOQ level, then defined the physiological signal state variables which used to evaluate the physiological signal. Finally, the FOQ score and the physiological state were made curve fitting. The fitting results show that the physiological signals of the cadets are directly related to the flight control level of the cadets.
Multi-view clustering suffers from the curse of dimensionality. We propose a locally adaptive feature weighting method based on subspace learning for multi-view data, which is an effective way to overcome the curse. I...
详细信息
ISBN:
(纸本)9789813146969
Multi-view clustering suffers from the curse of dimensionality. We propose a locally adaptive feature weighting method based on subspace learning for multi-view data, which is an effective way to overcome the curse. It modifies the traditional subspace learning methods, to explore the subspaces of the multiple views. It locally adapts the feature weighting of each cluster automatically according to the tightness of views to improve the performance of multi-view learning. The experiment results demonstrate that the proposed method is good at dealing with the multi-view data of high-dimension.
In this paper, we develop a new method denoted by PKM-SIM for the selection of the k initial modes for the k-modes clustering method in an uncertain context. The PKM-SIM combines the possibility theory with the standa...
详细信息
ISBN:
(纸本)9789813146969
In this paper, we develop a new method denoted by PKM-SIM for the selection of the k initial modes for the k-modes clustering method in an uncertain context. The PKM-SIM combines the possibility theory with the standard version of the k-modes (SKM). Besides, it is considered as an improvement of the possibilistic k-modes (PKM). It uses the same parameters of PKM when handling uncertain attributes using possibility theory. However, our proposal overcomes the main limitation of both SKM and PKM by avoiding the random selection of initial modes, especially that this random choice can influence the final clustering result. Hence, we make the PKM-SIM able to select the k initial modes from the most dissimilar objects of the training set. To show the effectiveness of our proposal, we compare it to the SKM and PKM based on different evaluation criteria. Results show the improvement made on the final partitions when selecting the initial modes by PKM-SIM.
This study proposes a novel approach called Intuitionistic Cognitive Map, for evaluating and assessing the criteria which influence the pricing strategy of a company in the new product development process. Intuitionis...
详细信息
ISBN:
(纸本)9789813146969
This study proposes a novel approach called Intuitionistic Cognitive Map, for evaluating and assessing the criteria which influence the pricing strategy of a company in the new product development process. Intuitionistic fuzzy sets and cognitive mapping are used together to capture fuzziness in information and to define cause and effect relations between the criteria in order to represent the complexity of strategic marketing decisions.
We introduce in this paper a tool for the diagnosis of autism called DAS-Autism. For this, we use our knowledge-based system shell RAMOLI. This system handles knowledge in the multi-valued context. Moreover, its infer...
详细信息
ISBN:
(纸本)9789813146969
We introduce in this paper a tool for the diagnosis of autism called DAS-Autism. For this, we use our knowledge-based system shell RAMOLI. This system handles knowledge in the multi-valued context. Moreover, its inference engine executes an approximate reasoning based on linguistic modifiers that we have introduced in a previous work. We have built a knowledge base that represents the domain expertise, in collaboration with the child psychiatry department of Razi hospital.
Covariance tracking has achieved impressive successes in recent years due to its competent region covariance-based feature descriptor. However, it is easy to be affected by partly occlusion and background distraction,...
详细信息
ISBN:
(纸本)9789813146969
Covariance tracking has achieved impressive successes in recent years due to its competent region covariance-based feature descriptor. However, it is easy to be affected by partly occlusion and background distraction, which leads to inconsecutive tracking trajectory and object drifting. In this work, a multi-block based covariance tracking algorithm using integral region is proposed, which extends the classic covariance tracking based on single block to multi-block and generalizes the traditional integral image computation into adaptive integral region computation. The former makes the proposed algorithm more robust for partly occlusion and distraction, and alleviates the object drifting problem;the latter speeds up the computation of block covariance. Our approach shows excellent target representation ability, faster speed, and more robustness, which has been verified on many video sequences.
The robustness analysis of intuitionistic fuzzy difference (IFD) is based on an evaluation of the delta sensitivity in representable fuzzy negations, triangular norms and conorms. The results in the class of IFD opera...
详细信息
ISBN:
(纸本)9789813146969
The robustness analysis of intuitionistic fuzzy difference (IFD) is based on an evaluation of the delta sensitivity in representable fuzzy negations, triangular norms and conorms. The results in the class of IFD operators preserve projections and dual constructions related to their intuitionistic approach.
Qualitative Cross Impact Analysis is a futures research tool used to explore both direct and indirect relationships of variables in a system to structure and formalize judgmental forecasting. The analysis, dealing wit...
详细信息
ISBN:
(纸本)9789813146969
Qualitative Cross Impact Analysis is a futures research tool used to explore both direct and indirect relationships of variables in a system to structure and formalize judgmental forecasting. The analysis, dealing with future events, often involves uncertain information and highly subjective judgments which can be better handled using fuzzy sets rather than subjective crisp numbers. However, fuzzy sets present limitations to model the uncertainty originating from hesitation that might arise in the assignment of membership degrees of the elements to a fuzzy set. Since the assessment process in Qualitative Cross Impact Analysis requires the participation of a variety of experts, dealing with this type of uncertainty becomes even more crucial. To address this issue this paper proposes a hesitant fuzzy approach to qualitative cross impact analysis and provides an illustrative example.
As the textile materials and processes have inherent variability, estimation of their properties by mathematical models often yields a very high prediction error. Artificial Neural Network (ANN) systems present the po...
详细信息
ISBN:
(纸本)9789813146969
As the textile materials and processes have inherent variability, estimation of their properties by mathematical models often yields a very high prediction error. Artificial Neural Network (ANN) systems present the potential solutions for the modeling and optimization of predicting. This paper presents a new multilayer perceptron (MLP) pruning algorithm for predicting denim fabric hand from stonewash treatment parameters. To optimize the MLP structure two techniques are used: (i) variance sensitivity analysis to prune hidden neurons (pruning does not concern inputs that corresponds to stonewash parameters) and (ii) k-fold Cross-Validation. The stop criteria are based on a performance evaluation of the network results from both learning and validation datasets. The obtained results show that neural network models could predict the desired fabric hand with reasonable accuracy.
作者:
Holcapek, M.Univ Ostrava
NSC IT4Innovt Inst Res & Applicat Fuzzy Modeling 30 Dubna 22 Ostrava 70103 1 Czech Republic
In this article, we propose the non-parametric estimation of functions and their partial derivatives from samples using the discrete version of the multivariate fuzzy transform of higher degree.
ISBN:
(纸本)9789813146969
In this article, we propose the non-parametric estimation of functions and their partial derivatives from samples using the discrete version of the multivariate fuzzy transform of higher degree.
暂无评论