An optimization-based formulation for three-way decisions

Liu, Jiubing; Li, Huaxiong; Zhou, Xianzhong; Huang, Bing; Wang, Tianxing

doi:10.1016/j.ins.2019.05.010

Cited by 52 publications

(9 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a more general discussion about TWD in ML, we refer the reader to the recent surveys by Campagner et al [6] and Liu et al [25]. Furthermore, approaches for cautious classification based on TWD have recently been investigated also from a theoretical and conceptual perspective: Liu et al [26] studied an an alternative model for TWD based on optimization; Yao [46] studied the connections between TWD and set-based approaches; Yao [45] explored the foundations of TWD based on geometrical and numerical concepts; while Xu [38] studied the connections between TWD-based classification and the theory of confusion matrices. We refer the reader to the reviews by Yang et al [40] and Yao [44] for further details.…”

Section: Three-way Decisionmentioning

confidence: 99%

Three-way decision and conformal prediction: Isomorphisms, differences and theoretical properties of cautious learning approaches

Campagner

Cabitza

Berjano

et al. 2021

Information Sciences

View full text Add to dashboard Cite

The aim of this article is to study the relationship between two popular Cautious Learning approaches, namely: Three-way decision (TWD) and conformal prediction (CP). Based on the novel proposal of a technique to transform threeway decision classifiers into conformal predictors, and vice-versa, we provide conditions for the equivalence between TWD and CP. These theoretical results provide error-bound guarantees for TWD, together with a formal construction to define cost-sensitive cautious classifiers based on CP. The proposed techniques are then applied and evaluated on a collection of benchmark and real-world datasets. The results of the experiments show that the proposed techniques can be used to obtain cautious learning classifiers that are competitive with, and often out-perform, state-of-the-art approaches. Further, through a qualitative medical case study we discuss the usefulness of cautious learning in the development of robust Machine Learning.

show abstract

Section: Three-way Decisionmentioning

confidence: 99%

Three-way decision and conformal prediction: Isomorphisms, differences and theoretical properties of cautious learning approaches

Campagner

Cabitza

Berjano

et al. 2021

Information Sciences

View full text Add to dashboard Cite

show abstract

“…The linguistic terms are employed to cope with the situations that are too ill‐defined or too complex to be reasonably described by quantitative expressions 41 …”

Section: Preliminariesmentioning

confidence: 99%

“…The linguistic terms are employed to cope with the situations that are too ill-defined or too complex to be reasonably described by quantitative expressions. 41 Let S = {s i , i = 0, 1, 2, …, g} be a finite and completely ordered discrete linguistic variable set, where g denotes a possible value of a linguistic term. The characteristics of the linguistic variable set are as follows:…”

Section: Linguistic Variablesmentioning

confidence: 99%

An improving approach for failure mode and effect analysis under uncertainty environment: A case study of critical function component

Huang

Xiao

Zhang

et al. 2020

Quality & Reliability Eng

View full text Add to dashboard Cite

Failure mode and effect analysis (FMEA) is a powerful risk discerning technique for identifying, evaluating, and reducing possible failures of products or processes. However, the classical FMEA has been criticized for inherent limitations, such as equal weights of risk elements and lack of capability in handling inaccurate information. Although fuzzy-based modified FMEA methods are frequently utilized to handle vagueness of experts' judgments, they still have some drawbacks, for example, requiring extra assumptions, neglecting experts' bounded rationality and psychological effects, lacking consideration of randomness, and only considering three classical risk elements among most of them. Therefore, this study develops an extended risk assessment method to enhance the performance of FMEA, which integrates the superiority of rough number theory in handling subjective and inaccurate information and the advantage of cloud model theory in reflecting the randomness of qualitative evaluations. Moreover, two synthetic weighting methods are developed to determine the weights of risk elements and handle the experts' individual effects, respectively, which consider both subjective and objective aspects. In addition, maintenance is added into the classical risk elements, and then a hierarchical structure containing four risk dimensions is built to evaluate failures' risk levels comprehensively. Finally, an application case to demonstrate the effectiveness of the developed FMEA model is presented. K E Y W O R D S cloud model, failure mode and effect analysis, hierarchical TOPSIS, rough number theory, synthetic weight 1 | INTRODUCTION Failure mode and effect analysis (FMEA) is a reliable risk assessment technique to determine the known and/or potential failure modes, causes, and effects on the stability and performance of a system, design, service, and process to identify the most crucial ones and conduct actions to eliminate them. 1 In the 1960s, it was firstly used by NASA in the aerospace industry to ensure the safety and quality of products. 2 FMEA is commonly performed by a cross-functional team contained experts with different knowledge and experience to analyze and quantify the relationships between

show abstract

“…Three-Way Decision (3WD) model is first proposed by Yao [1][2][3]. Derived from decision-theoretic rough sets, 3WD models uncertainty and reduces decision cost by adding a boundary decision to the decision-making options [4][5][6][7]. The traditional 3WD is a static and one-step strategy.…”

Section: Introductionmentioning

confidence: 99%

Incremental sequential three-way decision based on continual learning network

Min

et al. 2021

Int. J. Mach. Learn. & Cyber.

Self Cite

View full text Add to dashboard Cite

Continual learning has attracted much attention in recent years, and many continual learning methods based on deep neural networks have been proposed. However, several important problems about these methods may lead to high decision cost and affect the practical application of continual learning networks. First, continual learning networks treat all categories equally, although the unbalance of misclassification cost happens in real-world cases. Second, there is a trade-off between learning new knowledge and keep old knowledge, which leads to the forgetting of old knowledge (i.e., the catastrophic forgetting). Third, even if low confidence of a sample, the continual learning methods based on the neural network will still give a clear classification result. We propose a sequential three-way decision model for continual learning to address these problems, named Incremental Sequential Three-Way Decision model (ISTWD). Introducing cost-sensitive sequential threeway decision to continual learning network, ISTWD reduces the decision cost of continual learning, which may alleviate the potentially high cost caused by the accuracy loss in continual learning. Besides, ISTWD includes a checkpoint procedure to judge whether the process of continual learning should stop. Experimental results on CIFAR-100 and Tiny-ImageNet verify the effectiveness of our method.

show abstract

An optimization-based formulation for three-way decisions

Cited by 52 publications

References 47 publications

Three-way decision and conformal prediction: Isomorphisms, differences and theoretical properties of cautious learning approaches

Three-way decision and conformal prediction: Isomorphisms, differences and theoretical properties of cautious learning approaches

An improving approach for failure mode and effect analysis under uncertainty environment: A case study of critical function component

Incremental sequential three-way decision based on continual learning network

Contact Info

Product

Resources

About