An ensemble extended belief rule base decision model for imbalanced classification problems

Yang, Long-Hao; Ren, Tianyu; Ye, Fei-Fei; Nicholl, Patricia; Wang, Ying‐Ming; Lu, Haitian

doi:10.1016/j.knosys.2022.108410

Cited by 12 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the missing or incomplete data mentioned above, a disjunctive extended rule base is proposed with an attenuation factor to update the weight of incomplete rules (Liu et al, 2021). Yang et al (2022) improved the EBRB inference model by the clustering ensemble and activation factor (CEAF-EBRB model), which handles the uncertain or unlimited antecedents, and parameter optimization subjective problem of the model. However, the application of EBRB to the bilateral problem of matching volunteer needs with rescue and recovery tasks has not been reported.…”

Section: Extended Belief Rule-based (Ebrb) Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Extended belief rule-based method for the assessment of matching between rescue tasks and volunteers

Chen

Chen²,

Yang³

2022

View full text Add to dashboard Cite

PurposeThis paper aims to solve the major assessment problem in matching the satisfaction of psychological gratification and mission accomplishment pertaining to volunteers with the disaster rescue and recovery tasks.Design/methodology/approachAn extended belief rule-based (EBRB) method is applied with the method's input and output parameters classified based on expert knowledge and data from literature. These parameters include volunteer self-satisfaction, experience, peer-recognition, and cooperation. First, the model parameters are set; then, the parameters are optimized through data envelopment analysis (DEA) and differential evolution (DE) algorithm. Finally, a numerical mountain rescue example and comparative analysis between with-DEA and without-DEA are presented to demonstrate the efficiency of the proposed method. The proposed model is suitable for a two-way matching evaluation between rescue tasks and volunteers.FindingsDisasters are unexpected events in which emergency rescue is crucial to human survival. When a disaster occurs, volunteers provide crucial assistance to official rescue teams. This paper finds that decision-makers have a better understanding of two-sided match objects through bilateral feedback over time. With the changing of the matching preference information between rescue tasks and volunteers, the satisfaction of volunteer's psychological gratification and mission accomplishment are also constantly changing. Therefore, considering matching preference information and satisfaction at two-sided match objects simultaneously is necessary to get reasonable target values of matching results for rescue tasks and volunteers.Originality/valueBased on the authors' novel EBRB method, a matching assessment model is constructed, with two-sided matching of volunteers to rescue tasks. This method will provide matching suggestions in the field of emergency dispatch and contribute to the assessment of emergency plans around the world.

show abstract

Section: Extended Belief Rule-based (Ebrb) Methodsmentioning

confidence: 99%

“…, 2021). Yang et al. (2022) improved the EBRB inference model by the clustering ensemble and activation factor (CEAF-EBRB model), which handles the uncertain or unlimited antecedents, and parameter optimization subjective problem of the model.…”

Section: Literature Reviewmentioning

confidence: 99%

Extended belief rule-based method for the assessment of matching between rescue tasks and volunteers

Chen

Chen²,

Yang³

2022

View full text Add to dashboard Cite

show abstract

“…The most common of these methods is random selection with replacement of samples from among all training samples, which is called the bagging method [18]. Other implicit methods include fuzzy integral [19], Dempster-Shafer [20], knowledge-behaviour space [21] and decision model [22].…”

Section: Introductionmentioning

confidence: 99%

Investigating an Ensemble Classifier Based on Multi-Objective Genetic Algorithm for Machine Learning Applications

LIU

2024

ijacsa

View full text Add to dashboard Cite

Ensemble learning in machine learning applications is crucial because it leverages the collective wisdom of multiple models to enhance predictive performance and generalization. Ensemble learning is a method to provide a better approximation of an optimal classifier. A number of basic classifiers are used in ensemble learning. In order to improve performance, it is important for the basic classifiers to possess adequate efficacy and exhibit distinct classification errors. Additionally, an appropriate technique should be employed to amalgamate the outcomes of these classifiers. Numerous methods for ensemble classification have been introduced, including voting, bagging and reinforcement methods. In this particular study, an ensemble classifier that relies on the weighted mean of the basic classifiers' outputs was proposed. To estimate the combination weights, a multi-objective genetic algorithm, considering factors such as classification error, diversity, sparsity, and density criteria, was utilized. Through implementations on UCI datasets, the proposed approach demonstrates a significant enhancement in classification accuracy compared to other conventional ensemble classifiers. In summary, the obtained results showed that genetic-based ensemble classifiers provide advantages such as enhanced capability to handle complex datasets, improved robustness and generalization, and flexible adaptability. These advantages make them a valuable tool in various domains, contributing to more accurate and reliable predictions. Future studies should test and validate this method on more and larger datasets to determine its actual performance.

show abstract

“…This section introduces three improved BRBs based on decoupling matrix, BRB-c [9] , independent factor-based ABRB [6] , and extended Belief Rule Base based on cluster integration and activation factor (CEAF-EBRB) [11] . The proposed FC-BRB was tested for comparison.…”

mentioning

confidence: 99%

Belief rule base model considering dependencies between attributes

Yang

Cui

et al. 2022

Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022)

View full text Add to dashboard Cite

Although the Belief Rule Base (BRB) established based on single attribute rules solves the problem of rule explosion, the dependency between attributes makes it impossible to accurately describe the relationship between attributes and results, resulting in low accuracy. For this problem, existing solutions are mostly limited by expert knowledge or only applicable to weakly correlated attributes. Therefore, a method of attribute clustering and intersection guided by particle swarm optimization is proposed, which integrates attributes linearly or non-linearly to obtain new attributes, which are used in the BRB model. This method can effectively solve the influence of attribute interdependence on BRB prediction results. Experiments show that the method has good accuracy in solving typical fault diagnosis, pattern recognition and other classification problems, and the number of rules has a linear relationship with the number of attributes and reference values, avoiding rule explosion.

show abstract

An ensemble extended belief rule base decision model for imbalanced classification problems

Cited by 12 publications

References 45 publications

Extended belief rule-based method for the assessment of matching between rescue tasks and volunteers

Extended belief rule-based method for the assessment of matching between rescue tasks and volunteers

Investigating an Ensemble Classifier Based on Multi-Objective Genetic Algorithm for Machine Learning Applications

Belief rule base model considering dependencies between attributes

Contact Info

Product

Resources

About