International Journal of Approximate Reasoning最新文献

英文中文

Attribute reduction based on weighted neighborhood constrained fuzzy rough sets induced by grouping functions

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-25 DOI: 10.1016/j.ijar.2024.109354

Shan He , Junsheng Qiao , Chengxi Jian

Attribute reduction can extract the most critical attributes from multi-dimensional datasets, this reduces data dimensionality, simplifies data processing and analysis, and the fuzzy rough set (FRS) model-based attribute reduction method is one of the most commonly used attribute reduction methods. In this paper, we construct a new FRS model named G-WNC-FRS for attribute reduction by introducing a new inter-sample distance and two aggregation functions. Specifically, we first introduce the weighted neighborhood constrained distance between samples to make the difference in attributes between different class samples obvious. Then we introduce two not necessarily associative aggregation functions, overlap and grouping functions, to replace the commonly used triangular norms and triangular conorms in FRS model. Finally, we design G-WNC-FRS-based attribute reduction algorithm to select important attributes for classification tasks. Numerical experiments on 11 datasets demonstrate that the attribute reduction algorithm based on G-WNC-FRS has a strong ability to eliminate redundant attributes. Additionally, noise experiments and sensitivity experiments on 4 datasets show that the algorithm has high noise immunity and is able to adapt to different types of datasets.

{"title":"Attribute reduction based on weighted neighborhood constrained fuzzy rough sets induced by grouping functions","authors":"Shan He , Junsheng Qiao , Chengxi Jian","doi":"10.1016/j.ijar.2024.109354","DOIUrl":"10.1016/j.ijar.2024.109354","url":null,"abstract":"<div><div>Attribute reduction can extract the most critical attributes from multi-dimensional datasets, this reduces data dimensionality, simplifies data processing and analysis, and the fuzzy rough set (FRS) model-based attribute reduction method is one of the most commonly used attribute reduction methods. In this paper, we construct a new FRS model named G-WNC-FRS for attribute reduction by introducing a new inter-sample distance and two aggregation functions. Specifically, we first introduce the weighted neighborhood constrained distance between samples to make the difference in attributes between different class samples obvious. Then we introduce two not necessarily associative aggregation functions, overlap and grouping functions, to replace the commonly used triangular norms and triangular conorms in FRS model. Finally, we design G-WNC-FRS-based attribute reduction algorithm to select important attributes for classification tasks. Numerical experiments on 11 datasets demonstrate that the attribute reduction algorithm based on G-WNC-FRS has a strong ability to eliminate redundant attributes. Additionally, noise experiments and sensitivity experiments on 4 datasets show that the algorithm has high noise immunity and is able to adapt to different types of datasets.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"178 ","pages":"Article 109354"},"PeriodicalIF":3.2,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143141991","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Measures of association and dependence properties of nested random sets

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-19 DOI: 10.1016/j.ijar.2024.109352

Bernhard Schmelzer

The aim of this paper is to demonstrate how measures of association and dependence properties that are well-known for random variables can be defined for nested random sets. More precisely, definitions of Kendall's tau, Spearman's rho, quadrant dependence, tail monotonicity, stochastic monotonicity and tail dependence are provided. In a previous paper, the author presented a version of Sklar's theorem for nested random sets, i.e., it was shown that the joint distribution of nested random sets is linked to its marginals via a copula. Using this result it is shown that the aforementioned measures of association and dependence properties are properties of the copula if the nested random sets are nonatomic – similarly, as it is the case for continuous random variables. A characterization of nonatomicity based on the (one-point) covering function is provided and a probability integral transform for nonatomic nested random closed sets is proven.

引用次数: 0

Integration of evolutionary prejudices in Dempster-Shafer theory

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-12 DOI: 10.1016/j.ijar.2024.109351

Florence Dupin de Saint-Cyr, Francis Faux

This paper deals with belief change in the framework of Dempster-Shafer theory in the context where an agent has a prejudice, i.e., a priori knowledge about a situation. Our study is based on a review of the literature in the social sciences and humanities. Our framework relies on the claim that prejudices and evidences should be dealt with separately because of their very different natures (prejudices being at the meta level, governing the evolution of beliefs). Hence, the cognitive state of an agent is modeled as a pair whose components reflect its prejudices and uncertain beliefs. We propose a general formalism for encoding the evolution of this pair when new information arrives, this is why the study is related to Dempster's revision. Several cases of prejudice are described: the strong persistent prejudice (which never evolves and forbids beliefs to change), the prejudice that is slightly decreasing each time a belief contradicts it, etc. A general example with several prejudices and complex masses illustrates our approach.

引用次数: 0

Generalized multiview sequential three-way decisions based on local partition order product space

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-09 DOI: 10.1016/j.ijar.2024.109350

Jin Qian , Chuanpeng Zhou , Ying Yu , Mingchen Zheng , Chengxin Hong , Hui Wang

The hierarchical sequential three-way decision model is a method for addressing complex problem-solving. The existing hierarchical sequential three-way decision models mostly employ multi-view and/or multi-level approaches. However, as the number of views increases and the levels deepen, the model becomes too large to solve problems efficiently. In order to solve this problem, this paper proposes a generalized multiview hierarchical sequential three-way decisions based on local partition order product space model. Specifically, we first use a nested partition sequence to represent a view. Next, the linear order relations between levels within the views are split according to the number of levels to obtain local linear order relations. Then, in the multiple views, the local linear order relations between levels close to each other from different views are combined using Cartesian product operations to construct a generalized local partition order product space. Finally, by integrating the hierarchical sequential three-way decisions, the generalized local partition order product space is transformed into a multiview hierarchical sequential three-way decisions model. Experimental results on multiple datasets demonstrate that the proposed multiview hierarchical sequential three-way decision model achieves better performance compared to the existing models.

{"title":"Generalized multiview sequential three-way decisions based on local partition order product space","authors":"Jin Qian , Chuanpeng Zhou , Ying Yu , Mingchen Zheng , Chengxin Hong , Hui Wang","doi":"10.1016/j.ijar.2024.109350","DOIUrl":"10.1016/j.ijar.2024.109350","url":null,"abstract":"<div><div>The hierarchical sequential three-way decision model is a method for addressing complex problem-solving. The existing hierarchical sequential three-way decision models mostly employ multi-view and/or multi-level approaches. However, as the number of views increases and the levels deepen, the model becomes too large to solve problems efficiently. In order to solve this problem, this paper proposes a generalized multiview hierarchical sequential three-way decisions based on local partition order product space model. Specifically, we first use a nested partition sequence to represent a view. Next, the linear order relations between levels within the views are split according to the number of levels to obtain local linear order relations. Then, in the multiple views, the local linear order relations between levels close to each other from different views are combined using Cartesian product operations to construct a generalized local partition order product space. Finally, by integrating the hierarchical sequential three-way decisions, the generalized local partition order product space is transformed into a multiview hierarchical sequential three-way decisions model. Experimental results on multiple datasets demonstrate that the proposed multiview hierarchical sequential three-way decision model achieves better performance compared to the existing models.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"178 ","pages":"Article 109350"},"PeriodicalIF":3.2,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143141989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-label learning based on neighborhood rough set label-specific features

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-06 DOI: 10.1016/j.ijar.2024.109349

Jiadong Zhang, Jingjing Song, Huige Li, Xun Wang, Xibei Yang

Multi-label learning emerges as a novel paradigm harnessing diverse semantic datasets. Its objective involves eliciting a prognostic framework capable of allocating correlated labels to an unseen instance. Within the multifaceted domain of multi-label learning, the adoption of a label-specific feature methodology is prevalent. This approach entails the induction of a classification model that forecasts the relevance of each class label, utilizing tailored features specific to each label rather than relying on the original features. However, some irrelevant or redundant features will inevitably be generated when constructing features. To address this issue, we extend the current approach and introduce a straightforward yet potent multi-label learning method named NRS-LIFT, i.e., Neighborhood Rough Set Label-specIfic FeaTures. Specifically, a sample selection method is used to reduce the computational complexity, and then a set of tailored features is customized for each label through the neighborhood rough set. Finally, a learning model is induced to predict unseen instances. To fully evaluate the effectiveness of NRS-LIFT, we conduct extensive experiments on 12 multi-label datasets. Compared with mature multi-label learning methods, it is verified that NRS-LIFT has strong performance for multi-label datasets.

{"title":"Multi-label learning based on neighborhood rough set label-specific features","authors":"Jiadong Zhang, Jingjing Song, Huige Li, Xun Wang, Xibei Yang","doi":"10.1016/j.ijar.2024.109349","DOIUrl":"10.1016/j.ijar.2024.109349","url":null,"abstract":"<div><div>Multi-label learning emerges as a novel paradigm harnessing diverse semantic datasets. Its objective involves eliciting a prognostic framework capable of allocating correlated labels to an unseen instance. Within the multifaceted domain of multi-label learning, the adoption of a label-specific feature methodology is prevalent. This approach entails the induction of a classification model that forecasts the relevance of each class label, utilizing tailored features specific to each label rather than relying on the original features. However, some irrelevant or redundant features will inevitably be generated when constructing features. To address this issue, we extend the current approach and introduce a straightforward yet potent multi-label learning method named NRS-LIFT, i.e., Neighborhood Rough Set Label-specIfic FeaTures. Specifically, a sample selection method is used to reduce the computational complexity, and then a set of tailored features is customized for each label through the neighborhood rough set. Finally, a learning model is induced to predict unseen instances. To fully evaluate the effectiveness of NRS-LIFT, we conduct extensive experiments on 12 multi-label datasets. Compared with mature multi-label learning methods, it is verified that NRS-LIFT has strong performance for multi-label datasets.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"178 ","pages":"Article 109349"},"PeriodicalIF":3.2,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143141990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Simple contrapositive assumption-based argumentation frameworks with preferences: Partial orders and collective attacks

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-03 DOI: 10.1016/j.ijar.2024.109340

Ofer Arieli , Jesse Heyninck

In this paper, we consider assumption-based argumentation frameworks that are based on contrapositive logics and partially-ordered preference functions. It is shown that these structures provide a general and solid platform for representing and reasoning with conflicting and prioritized arguments. Two useful properties of the preference functions are identified (selectivity and max-lower-boundedness), and extended forms of attack relations are supported (∃–attacks and ∀-attacks), which assure several desirable properties and a variety of formal settings for argumentation-based conclusion drawing. These two variations of attacks may be further extended to collective attacks. Such (existential or universal) collective attacks allow to challenge a collective of assertions rather than single assertions. We show that these extensions not only enhance the expressive power of the framework, but in certain cases also enable more rational patterns of reasoning with conflicting assertions.

引用次数: 0

Interactive preference elicitation under noisy preference models: An efficient non-Bayesian approach

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-12-02 DOI: 10.1016/j.ijar.2024.109333

Guillaume Escamocher , Samira Pourkhajouei , Federico Toffano , Paolo Viappiani , Nic Wilson

The development of models that can cope with noisy input preferences is a critical topic in artificial intelligence methods for interactive preference elicitation. A Bayesian representation of the uncertainty in the user preference model can be used to successfully handle this, but there are large costs in terms of the processing time which limit the adoption of these techniques in real-time contexts. A Bayesian approach also requires one to assume a prior distribution over the set of user preference models. In this work, dealing with multi-criteria decision problems, we consider instead a more qualitative approach to preference uncertainty, focusing on the most plausible user preference models, and aim to generate a query strategy that enables us to find an alternative that is optimal in all of the most plausible preference models. We develop a non-Bayesian algorithmic method for recommendation and interactive elicitation that considers a large number of possible user models that are evaluated with respect to their degree of consistency of the input preferences. This suggests methods for generating queries that are reasonably fast to compute. We show formal asymptotic results for our algorithm, including the probability that it returns the actual best option. Our test results demonstrate the viability of our approach, including in real-time contexts, with high accuracy in recommending the most preferred alternative for the user.

{"title":"Interactive preference elicitation under noisy preference models: An efficient non-Bayesian approach","authors":"Guillaume Escamocher , Samira Pourkhajouei , Federico Toffano , Paolo Viappiani , Nic Wilson","doi":"10.1016/j.ijar.2024.109333","DOIUrl":"10.1016/j.ijar.2024.109333","url":null,"abstract":"<div><div>The development of models that can cope with noisy input preferences is a critical topic in artificial intelligence methods for interactive preference elicitation. A Bayesian representation of the uncertainty in the user preference model can be used to successfully handle this, but there are large costs in terms of the processing time which limit the adoption of these techniques in real-time contexts. A Bayesian approach also requires one to assume a prior distribution over the set of user preference models. In this work, dealing with multi-criteria decision problems, we consider instead a more qualitative approach to preference uncertainty, focusing on the most plausible user preference models, and aim to generate a query strategy that enables us to find an alternative that is optimal in all of the most plausible preference models. We develop a non-Bayesian algorithmic method for recommendation and interactive elicitation that considers a large number of possible user models that are evaluated with respect to their degree of consistency of the input preferences. This suggests methods for generating queries that are reasonably fast to compute. We show formal asymptotic results for our algorithm, including the probability that it returns the actual best option. Our test results demonstrate the viability of our approach, including in real-time contexts, with high accuracy in recommending the most preferred alternative for the user.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"178 ","pages":"Article 109333"},"PeriodicalIF":3.2,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143141987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Extending choice assessments to choice functions: An algorithm for computing the natural extension

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-11-28 DOI: 10.1016/j.ijar.2024.109331

Arne Decadt, Alexander Erreygers, Jasper De Bock

We study how to infer new choices from prior choices using the framework of choice functions, a unifying mathematical framework for decision-making based on sets of preference orders. In particular, we define the natural (most conservative) extension of a given choice assessment to a coherent choice function—whenever possible—and use this natural extension to make new choices. We provide a practical algorithm for computing this natural extension and various ways to improve scalability. Finally, we test these algorithms for different types of choice assessments.

引用次数: 0

Adding imprecision to hypotheses: A Bayesian framework for testing practical significance in nonparametric settings 增加假设的不精确性：在非参数设置中检验实际意义的贝叶斯框架

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-11-28 DOI: 10.1016/j.ijar.2024.109332

Rodrigo F.L. Lassance , Rafael Izbicki , Rafael B. Stern

Instead of testing solely a precise hypothesis, it is often useful to enlarge it with alternatives deemed to differ negligibly from it. For instance, in a bioequivalence study one might test if the concentration of an ingredient is exactly the same in two drugs. In such a context, it might be more relevant to test the enlarged hypothesis that the difference in concentration between them is of no practical significance. While this concept is not alien to Bayesian statistics, applications remain mostly confined to parametric settings and strategies that effectively harness experts' intuitions are often scarce or nonexistent. To resolve both issues, we introduce the Pragmatic Region Oriented Test (PROTEST), an accessible nonparametric testing framework based on distortion models that can seamlessly integrate with Markov Chain Monte Carlo (MCMC) methods and is available as an R package. We develop expanded versions of model adherence, goodness-of-fit, quantile and two-sample tests. To demonstrate how PROTEST operates, we use examples, simulated studies that critically evaluate features of the test and an application on neuron spikes. Furthermore, we address the crucial issue of selecting the threshold—which controls how much a hypothesis is to be expanded—even when intuitions are limited or challenging to quantify.

与其仅仅检验一个精确的假设，还不如用被认为与之相差微不足道的替代方案来扩大它，这往往是有用的。例如，在生物等效性研究中，人们可能会测试两种药物中某种成分的浓度是否完全相同。在这种情况下，检验它们之间的浓度差异没有实际意义的扩大假设可能更有意义。虽然这个概念与贝叶斯统计并不陌生，但应用仍然主要局限于参数设置，而有效利用专家直觉的策略往往很少或根本不存在。为了解决这两个问题，我们引入了实用区域导向测试（PROTEST），这是一个基于失真模型的可访问的非参数测试框架，可以与马尔可夫链蒙特卡罗（MCMC）方法无缝集成，并作为R包提供。我们开发了模型依从性、拟合优度、分位数和双样本检验的扩展版本。为了证明PROTEST是如何运作的，我们使用了一些例子，模拟研究，批判性地评估测试的特征和神经元峰值的应用。此外，我们解决了选择阈值的关键问题-控制假设扩展的程度-即使在直觉有限或难以量化的情况下。

{"title":"Adding imprecision to hypotheses: A Bayesian framework for testing practical significance in nonparametric settings","authors":"Rodrigo F.L. Lassance , Rafael Izbicki , Rafael B. Stern","doi":"10.1016/j.ijar.2024.109332","DOIUrl":"10.1016/j.ijar.2024.109332","url":null,"abstract":"<div><div>Instead of testing solely a precise hypothesis, it is often useful to enlarge it with alternatives deemed to differ negligibly from it. For instance, in a bioequivalence study one might test if the concentration of an ingredient is exactly the same in two drugs. In such a context, it might be more relevant to test the enlarged hypothesis that the difference in concentration between them is of no practical significance. While this concept is not alien to Bayesian statistics, applications remain mostly confined to parametric settings and strategies that effectively harness experts' intuitions are often scarce or nonexistent. To resolve both issues, we introduce the Pragmatic Region Oriented Test (<span>PROTEST</span>), an accessible nonparametric testing framework based on distortion models that can seamlessly integrate with Markov Chain Monte Carlo (MCMC) methods and is available as an <span>R</span> package. We develop expanded versions of model adherence, goodness-of-fit, quantile and two-sample tests. To demonstrate how <span>PROTEST</span> operates, we use examples, simulated studies that critically evaluate features of the test and an application on neuron spikes. Furthermore, we address the crucial issue of selecting the threshold—which controls how much a hypothesis is to be expanded—even when intuitions are limited or challenging to quantify.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"178 ","pages":"Article 109332"},"PeriodicalIF":3.2,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142757051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cautious classifier ensembles for set-valued decision-making 用于集值决策的谨慎分类器组合

IF 3.2 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

International Journal of Approximate Reasoning

Pub Date : 2024-11-26 DOI: 10.1016/j.ijar.2024.109328

Haifei Zhang , Benjamin Quost , Marie-Hélène Masson

Classifiers now demonstrate impressive performances in many domains. However, in some applications where the cost of an erroneous decision is high, set-valued predictions may be preferable to classical crisp decisions, being less informative but more reliable. Cautious classifiers aim at producing such imprecise predictions so as to reduce the risk of making wrong decisions. In this paper, we describe two cautious classification approaches rooted in the ensemble learning paradigm, which consist in combining probability intervals. These intervals are aggregated within the framework of belief functions, using two proposed strategies that can be regarded as generalizations of classical averaging and voting. Our strategies aim at maximizing the lower expected discounted utility to achieve a good compromise between model accuracy and determinacy. The efficiency and performance of the proposed procedure are illustrated using imprecise decision trees, thus giving birth to cautious variants of the random forest classifier. The performance and properties of these variants are illustrated using 15 datasets.

目前，分类器在许多领域都表现出令人印象深刻的性能。然而，在某些应用中，错误判定的代价很高，集值预测可能比经典的简明判定更可取，因为集值预测的信息量更少，但可靠性更高。谨慎分类器的目标就是生成这种不精确的预测，从而降低做出错误决策的风险。在本文中，我们介绍了两种植根于集合学习范式的谨慎分类方法，它们都是由概率区间组合而成。这些区间在信念函数的框架内聚集，使用两种建议的策略，可视为经典平均法和投票法的一般化。我们的策略旨在最大化较低的预期贴现效用，从而在模型准确性和确定性之间取得良好的折衷。我们使用不精确的决策树来说明所建议程序的效率和性能，从而产生了随机森林分类器的谨慎变体。利用 15 个数据集说明了这些变体的性能和特性。

{"title":"Cautious classifier ensembles for set-valued decision-making","authors":"Haifei Zhang , Benjamin Quost , Marie-Hélène Masson","doi":"10.1016/j.ijar.2024.109328","DOIUrl":"10.1016/j.ijar.2024.109328","url":null,"abstract":"<div><div>Classifiers now demonstrate impressive performances in many domains. However, in some applications where the cost of an erroneous decision is high, set-valued predictions may be preferable to classical crisp decisions, being less informative but more reliable. Cautious classifiers aim at producing such imprecise predictions so as to reduce the risk of making wrong decisions. In this paper, we describe two cautious classification approaches rooted in the ensemble learning paradigm, which consist in combining probability intervals. These intervals are aggregated within the framework of belief functions, using two proposed strategies that can be regarded as generalizations of classical averaging and voting. Our strategies aim at maximizing the lower expected discounted utility to achieve a good compromise between model accuracy and determinacy. The efficiency and performance of the proposed procedure are illustrated using imprecise decision trees, thus giving birth to cautious variants of the random forest classifier. The performance and properties of these variants are illustrated using 15 datasets.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"177 ","pages":"Article 109328"},"PeriodicalIF":3.2,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142723044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

首页上一页

下一页尾页

类型

全部化学•材料生命科学医学物理工程技术环境•农林材料科学地球科学法学管理学化学环境科学与生态学计算机科学教育学经济学农林科学人文科学生物学数学物理与天体物理心理学综合性期刊其他工业工程理学历史学农学文学信息工程

数据库

全部 ACS Publications Elsevier ieeexplore Springer The Royal Society of Chemistry Wiley

期刊

International Journal of Approximate Reasoning

全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.

﹀