Relative Density-Based Intuitionistic Fuzzy SVM for Class Imbalance Learning

Fu, Cui; Zhou, Shuisheng; Zhang, Dan; Chen, Li

doi:10.3390/e25010034

Cited by 6 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is widely used in data classification, regression fitting, and outlier detection. SVM has been successful in many practical diagnostic applications due to its ability to generalize and produce accurate predictions [31][32][33][34]. It is memory-efficient and can handle large datasets with ease.…”

Section: Multi-classification Fault Diagnosis Methods Based On Svmmentioning

confidence: 99%

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

Nie

Ren

et al. 2023

Actuators

View full text Add to dashboard Cite

A fault diagnosis method of heating, ventilation, and air conditioning (HVAC) systems based on the ReliefF-recursive feature elimination based on cross validation-support vector machine (ReliefF-RFECV-SVM) combined model is proposed to enhance the diagnosis accuracy and efficiency. The method initially uses ReliefF to screen the original features, selecting those that account for 95% of the total weight. The recursive feature elimination based on cross validation (RFECV), based on a random forest classifier, is then applied to select the optimal feature subset according to diagnostic accuracy. Finally, a support vector machine (SVM) model is constructed for fault classification. The method is tested on seven typical faults of the ASHRAE 1043-RP water chiller dataset and three typical faults of an air-cooled self-built air conditioner simulation dataset. The results show that the ReliefF-RFECV-SVM method significantly reduces diagnosis time compared to SVM, shortening it by about 50% based on the ASHRAE 1043-RP dataset, while achieving an overall accuracy of 99.98%. Moreover, the proposed method achieves a comprehensive diagnosis accuracy of 99.97% on the self-built simulation dataset, with diagnosis time the reduced by about 65% compared to single SVM.

show abstract

Section: Multi-classification Fault Diagnosis Methods Based On Svmmentioning

confidence: 99%

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

Nie

Ren

et al. 2023

Actuators

View full text Add to dashboard Cite

show abstract

“…The index called classification accuracy was employed to measure the classification performance of the seven algorithms. Two classic classifiers named KNN (K-nearest neighbor, K = 3) [68], CART (classification and regression tree) [69], and SVM (support vector machine) [70] were employed to reflect the classification performance. Generally, given a decision system DS, assuming that the set U is divided into z (Note that as 10folds cross-validation was employed in this experiment, z = 10 holds) groups which are disjointed and with the same size, i.e., U 1 , .…”

Section: Comparison Of Classification Accuracymentioning

confidence: 99%

Parallel Selector for Feature Reduction

et al. 2023

View full text Add to dashboard Cite

In the field of rough set, feature reduction is a hot topic. Up to now, to better guide the explorations of this topic, various devices regarding feature reduction have been developed. Nevertheless, some challenges regarding these devices should not be ignored: (1) the viewpoint provided by a fixed measure is underabundant; (2) the final reduct based on single constraint is sometimes powerless to data perturbation; (3) the efficiency in deriving the final reduct is inferior. In this study, to improve the effectiveness and efficiency of feature reduction algorithms, a novel framework named parallel selector for feature reduction is reported. Firstly, the granularity of raw features is quantitatively characterized. Secondly, based on these granularity values, the raw features are sorted. Thirdly, the reordered features are evaluated again. Finally, following these two evaluations, the reordered features are divided into groups, and the features satisfying given constraints are parallel selected. Our framework can not only guide a relatively stable feature sequencing if data perturbation occurs but can also reduce time consumption for feature reduction. The experimental results over 25 UCI data sets with four different ratios of noisy labels demonstrated the superiority of our framework through a comparison with eight state-of-the-art algorithms.

show abstract

“…In addition, the model generalization of IFS is also studied, such as interval type IFS [28], Atanassov-type intuitionistic fuzzy [29], intuitionistic fuzzy soft sets [30,31], intuitionistic fuzzy rough sets [32,33], intuitionistic fuzzy set and three-way decision [34][35][36][37], intuitionistic fuzzy set and dominance relationship [38,39], and other series of achievements. At present, IFS have achieved good application results in fault diagnosis [40], multi-attribute decision-making [41], incomplete data decision-making [42], deep learning [43], imbalance learning [44], and other fields.…”

Section: Introductionmentioning

confidence: 99%

Ranking Method of Intuitionistic Fuzzy Numbers and Multiple Attribute Decision Making Based on the Probabilistic Dominance Relationship

et al. 2023

View full text Add to dashboard Cite

The uncertainty of intuitionistic fuzzy numbers (IFNs) is further enhanced by the existence of the degree of hesitation (DH). The shortcomings of existing researches are mainly reflected in the following situations: when comparing IFNs, the comparison rules of IFNs are difficult to apply to the comparison of any two IFNs, or the relevant methods do not fully consider the uncertainty expressed by DH. Thus, the rationality of the decision results needs to be improved. On the other hand, multi-attribute decision making (DADM) based on IFNs is often not objective due to the need to determine the attribute weight. Moreover, the strict condition of attribute aggregation of classical dominance relation makes it a method that fails considering the practical application. Aiming at the comparison problem of IFNs, this paper takes probability conversion as the starting point and proposes an IFN comparison method based on the area method, which can better deal with the comparison problem of “either superior or inferior” IFNs. In addition, aiming at the MADM problem of an intuitionistic fuzzy information system, we propose an intuitionistic fuzzy probabilistic dominance relation model and construct the MADM method under the probabilistic dominance relation. The series properties of IFNs and probabilistic dominance relation were summarized and proved, which theoretically ensured the scientificity and rigor of the method. The results show that the comparison and ranking method of IFNs proposed in this paper can be applied to the comparison of any two IFNs, and the dominance degree of IFNs is presented in the form of probability, which is more flexible and practical than the classical method. The probabilistic dominance relation method based on IFNs avoids the problem of determining attribute weights subjectively or objectively, and the decision maker can reflect decision preference by adjusting decision parameters to better match the actual problem. The application of this model to a campus express site evaluation further verifies the feasibility of the proposed method and the rationality of the results. In addition, various extension problems of the model and method proposed in this paper are discussed, which pave the way for future related research. This paper constructs a complete decision-making framework through theoretical analysis and application from practical problems, which provides a reference for enriching and improving uncertain decision-making theory and the MADM method.

show abstract

Relative Density-Based Intuitionistic Fuzzy SVM for Class Imbalance Learning

Cited by 6 publications

References 35 publications

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

Parallel Selector for Feature Reduction

Ranking Method of Intuitionistic Fuzzy Numbers and Multiple Attribute Decision Making Based on the Probabilistic Dominance Relationship

Contact Info

Product

Resources

About