International Journal of Approximate Reasoning最新文献

筛选
英文 中文
An axiom system of the analytic hierarchy process based on the completeness of preferences 基于偏好完备性的层次分析法的一个公理系统
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-10 DOI: 10.1016/j.ijar.2025.109449
Fang Liu , Lin-Tao Dai , Fei-Yang Cheng , Wei-Guo Zhang
{"title":"An axiom system of the analytic hierarchy process based on the completeness of preferences","authors":"Fang Liu ,&nbsp;Lin-Tao Dai ,&nbsp;Fei-Yang Cheng ,&nbsp;Wei-Guo Zhang","doi":"10.1016/j.ijar.2025.109449","DOIUrl":"10.1016/j.ijar.2025.109449","url":null,"abstract":"<div><div>Decision outcomes rely on the preferences of the decision maker (DM) over alternatives. The completeness axiom is a fundamental assumption of preference theory. This paper reports an axiom system of the analytic hierarchy process (AHP) under the theory of preferences. First, the existing axiomatic foundations of AHP are analyzed. It is found that the Saaty's one is limited by strict mathematical intuition for the reciprocal property of comparison ratios. The uncertainty-induced one could lead to the confusion of preferences owing to the breaking of reciprocal property. Second, the constrained relation of comparison ratios is constructed according to the completeness of preferences, which is used to form a novel axiom system of AHP. Third, the concepts of ordinal consistency and acceptable ordinal consistency are developed for pairwise comparison matrices (PCMs). The index of measuring ordinal consistency is constructed using Spearman rank correlation coefficient to overcome the shortcoming in the existing one. The prioritization method is discussed to reveal that the geometric mean method is suitable for PCMs with ordinal consistency. It is revealed that the developed axiomatic foundation of AHP reasonably embeds the preference information of DMs. The results help to identify how to flexibly apply AHP in practice by considering the complete preferences of DMs under uncertainty.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109449"},"PeriodicalIF":3.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143833176","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
Box atlas: An interval version of atlas 盒式地图集:地图集的间隔版本
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-04 DOI: 10.1016/j.ijar.2025.109441
Arthur Ignazi, Remy Guyonneau, Sébastien Lagrange, Sébastien Lahaye
{"title":"Box atlas: An interval version of atlas","authors":"Arthur Ignazi,&nbsp;Remy Guyonneau,&nbsp;Sébastien Lagrange,&nbsp;Sébastien Lahaye","doi":"10.1016/j.ijar.2025.109441","DOIUrl":"10.1016/j.ijar.2025.109441","url":null,"abstract":"<div><div>This paper presents an adaptation of the notion of atlas to interval analysis named box atlas. This new concept makes it possible to directly use interval analysis methods on compact manifolds. This can be useful to solve path planning problems or to compute attainability in robotics. To demonstrate the relevance of the approach, a box atlas for two classic manifolds is proposed and an application for a path planning problem is presented. The paper also proposes a paving construction for every compact manifolds of dimension 2 that is box atlas compatible.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109441"},"PeriodicalIF":3.2,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143791162","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
DFF-Net: Dynamic feature fusion network for time series prediction DFF-Net:用于时间序列预测的动态特征融合网络
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-02 DOI: 10.1016/j.ijar.2025.109436
Bin Xiao , Zheng Chen , Yanxue Wu , Min Wang , Shengtong Hu , Xingpeng Zhang
{"title":"DFF-Net: Dynamic feature fusion network for time series prediction","authors":"Bin Xiao ,&nbsp;Zheng Chen ,&nbsp;Yanxue Wu ,&nbsp;Min Wang ,&nbsp;Shengtong Hu ,&nbsp;Xingpeng Zhang","doi":"10.1016/j.ijar.2025.109436","DOIUrl":"10.1016/j.ijar.2025.109436","url":null,"abstract":"<div><div>Time series forecasting predicts future values based on historical observations within a sequential dataset. However, popular attention mechanisms exhibit high computational complexity when it comes to capturing channel correlations. Additionally, multi-scale feature fusion methods often generate information redundancy when processing diverse features, which can result in unstable model learning. In this paper, we propose a Dynamic Feature Fusion Network (DFF-Net) to address the aforementioned challenges. The network consists of two key modules: the Stochastic Feature Aggregator (SFA) and the Dimensional Mixer (DMix). First, the SFA module extracts core feature representations by utilizing random training sampling and weighted averaging during the inference process. These core features are then integrated with individual feature representations. Second, the DMix module utilizes scalable dimensional transformations to achieve feature compression and reconstruction. The compressed features and the reconstructed features are then concatenated to enhance data representations. Experimental results demonstrate that DFF-Net outperforms seven state-of-the-art methods in both prediction accuracy and computational efficiency across multiple benchmark time series datasets.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109436"},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143759329","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
An equivalent characterization for admissible orders on n-dimensional intervals generated by matrices 由矩阵生成的n维区间上可容许阶的等价刻画
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-02 DOI: 10.1016/j.ijar.2025.109438
Wei Zhang
{"title":"An equivalent characterization for admissible orders on n-dimensional intervals generated by matrices","authors":"Wei Zhang","doi":"10.1016/j.ijar.2025.109438","DOIUrl":"10.1016/j.ijar.2025.109438","url":null,"abstract":"<div><div>The <em>n</em>-dimensional intervals are a generalization of intervals, and they are also the membership degrees of <em>n</em>-dimensional fuzzy sets. They can be used to represent high-dimensional data. This paper first defines a binary relation on <em>n</em>-dimensional intervals using a matrix. Then, we prove that this binary relation is an admissible order on <em>n</em>-dimensional intervals if and only if the determinant of the corresponding matrix is not equal to zero, and for each column of the matrix, the first non-zero element is greater than zero. Finally, we apply this type of admissible order to a specific multi-criteria group decision-making case.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109438"},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768382","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
Bipolar decomposition integrals 双极分解积分
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-02 DOI: 10.1016/j.ijar.2025.109439
Jabbar Abbas , Radko Mesiar , Radomír Halaš
{"title":"Bipolar decomposition integrals","authors":"Jabbar Abbas ,&nbsp;Radko Mesiar ,&nbsp;Radomír Halaš","doi":"10.1016/j.ijar.2025.109439","DOIUrl":"10.1016/j.ijar.2025.109439","url":null,"abstract":"<div><div>The idea of decomposition integral, inspired by the concept of Lebesgue integral, is a common framework for unifying many nonlinear integrals, such as the Choquet, the Shilkret, the PAN, and the concave integrals. This framework concerns aggregation on a unipolar scale, and depends on the distinguished decomposition system under some constraints on the sets being considered for each related integral. The aim of this paper is to provide a general framework to deal with integrals concerning aggregation on unipolar and bipolar scales. To achieve this aim, we propose in this paper an extension of the idea of decomposition integral of the integrated function to be suitable for bipolar scales depending on the distinguished bipolar decomposition system under some constraints on the bipolar collections being considered for each related bipolar fuzzy integral. Then, we introduce some properties of bipolar decomposition integrals, including those establishing that our approach covers the Cumulative Prospect Theory (CPT) model and the integrals with respect to bipolar capacities. Finally, we conclude with certain directions on some additional findings related to the research.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109439"},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768384","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
Prospect utility with hyperbolic tangent function 具有双曲正切函数的前景实用程序
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-02 DOI: 10.1016/j.ijar.2025.109440
Patrick Adjei, Santiago Gomez-Rosero, Miriam A.M. Capretz
{"title":"Prospect utility with hyperbolic tangent function","authors":"Patrick Adjei,&nbsp;Santiago Gomez-Rosero,&nbsp;Miriam A.M. Capretz","doi":"10.1016/j.ijar.2025.109440","DOIUrl":"10.1016/j.ijar.2025.109440","url":null,"abstract":"<div><div>One branch of safety in reinforcement learning is through integrating risk sensitivity within the Markov Decision Process framework. The objective is to mitigate low-probability events that could lead to severe negative outcomes. Eliminating such risky events is usually done by incorporating a utility function on the expected return; therefore, reshaping the reward structures according to the risk levels associated with different outcomes. The temporal difference learning algorithm can be modified with a utility to capture risk. Notably, such utility functions are either convex or concave depending on the desired risk behavior. Given the outcome space and depending on the risk-sensitivity mode, concave utilities may promote risk-averse behavior and convex utilities may encourage risk-seeking strategies. Such function structure is demonstrated in Prospect Theory, and this motivates a novel formulation using the hyperbolic tangent function called PTanh. Using PTanh, experiments are performed to assess the effect of the diminishing marginal property on the risk-averse policies. It is concluded that there is a correlation between the marginal and selecting the risk-averse parameters. The marginals influence the effectiveness of the averse policies. When the marginals are considered, PTanh can demonstrate better results in terms of a ratio of average reward per prohibited state rate. Furthermore, using empirical evidence, the policy experiments shown with PTanh generalize to other utilities of the Prospect Shape.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109440"},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768383","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
Towards machine learning as AGM-style belief change 将机器学习作为agm风格的信念改变
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-04-02 DOI: 10.1016/j.ijar.2025.109437
Theofanis Aravanis
{"title":"Towards machine learning as AGM-style belief change","authors":"Theofanis Aravanis","doi":"10.1016/j.ijar.2025.109437","DOIUrl":"10.1016/j.ijar.2025.109437","url":null,"abstract":"<div><div>Artificial Neural Networks (ANNs) are powerful computational models that are able to reproduce complex non-linear processes, and are being widely used in a plethora of contemporary disciplines. In this article, we study the statics and dynamics of a certain class of ANNs, called binary ANNs, from the perspective of belief-change theory. A binary ANN is a feed-forward ANN whose inputs and outputs take binary values, and as such, it is suitable for a wide range of practical applications. For this type of ANNs, we point out that their knowledge (expressed via their input-output relationship) can symbolically be represented in terms of a propositional logic language. Furthermore, in the realm of belief change, we identify the process of changing (revising/contracting) an initial belief set to a modified belief set, as a process of a gradual transition of intermediate belief sets — such a gradualist approach to belief change is more congruent with the behaviors of real-world agents. Along these lines, we provide natural metrics for measuring the distance between these intermediate belief sets, effectively quantifying the disparity in their encoded knowledge. Thereafter, we demonstrate that, similar to belief change, the training process of binary ANNs, through backpropagation, can be emulated via a sequence of successive transitions of belief sets, the distance between which is intuitively related through one of the aforementioned metrics. We also prove that the alluded successive transitions of belief sets can be modeled by means of rational revision and contraction operators, defined within the fundamental belief-change framework of Alchourrón, Gärdenfors and Makinson (AGM). Thus, the process of machine learning (specifically, training binary ANNs) is framed as an operation of AGM-style belief change, offering a modular and logically structured perspective on neural learning.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109437"},"PeriodicalIF":3.2,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768381","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
On optimal scale combinations in generalized multi-scale set-valued ordered information systems 广义多尺度集值有序信息系统的最优尺度组合
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-03-27 DOI: 10.1016/j.ijar.2025.109429
Jia-Ru Zhang , Wei-Zhi Wu , Harry F. Lee , Anhui Tan
{"title":"On optimal scale combinations in generalized multi-scale set-valued ordered information systems","authors":"Jia-Ru Zhang ,&nbsp;Wei-Zhi Wu ,&nbsp;Harry F. Lee ,&nbsp;Anhui Tan","doi":"10.1016/j.ijar.2025.109429","DOIUrl":"10.1016/j.ijar.2025.109429","url":null,"abstract":"<div><div>As a computing paradigm inspired by human cognition, granular computing has demonstrated remarkable effectiveness in processing large data sets. Multi-scale rough set analysis, a prominent framework within multi-granular computing, requires optimal scale selection as a critical prerequisite for knowledge extraction from multi-scale data. This study investigates optimal scale selection in generalized multi-scale set-valued ordered information systems (GMSOISs) using Dempster-Shafer evidence theory and information quantification. We first formalize GMSOISs by defining granular information transformations based on inclusion criteria. We then establish dominance relations over object sets induced by attribute subsets under different scale combinations, along with their associated information granules. Building on these constructs, we further derive lower/upper approximations and quantify belief/plausibility degrees of decision dominance classes in generalized multi-scale set-valued ordered decision systems (GMSODSs). Finally, six types of optimal scale combinations are rigorously defined for GMSOISs, consistent GMSODSs, and inconsistent GMSODSs, and their relationships are systematically elucidated. Case studies also validate the proposed theoretical framework with concrete examples.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109429"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740134","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
Matrix-based approach for knowledge structure construction using variable precision models 基于矩阵的变精度模型知识结构构建方法
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-03-27 DOI: 10.1016/j.ijar.2025.109427
Chuanyi Huang , Han-liang Huang , Jinjin Li
{"title":"Matrix-based approach for knowledge structure construction using variable precision models","authors":"Chuanyi Huang ,&nbsp;Han-liang Huang ,&nbsp;Jinjin Li","doi":"10.1016/j.ijar.2025.109427","DOIUrl":"10.1016/j.ijar.2025.109427","url":null,"abstract":"<div><div>Assessment of knowledge acquiring and learning is a complex and multidimensional process that involves the evaluation and measurement of an individual's performance in the process of learning and acquiring knowledge. The concept of fuzzy skill encapsulates an individual's latent cognitive abilities and overall competence. In the disjunctive model, an individual must achieve proficiency in at least one relevant skill to solve an item. In contrast, the conjunctive model requires proficiency in all relevant skills. The disjunctive model's excessive leniency and the conjunctive model's excessive rigor have prompted the development of variable precision <em>α</em>-models to mediate between these extremes. Nonetheless, the variable precision <em>α</em>-model warrants further exploration.</div><div>Consequently, this paper is conducting a comprehensive analysis of the variable precision <em>α</em>-model, presenting three variants, and examining their respective properties. Additionally, no existing algorithm addresses the construction of the knowledge structure within this model. For this purpose, a new matrix operation is defined, and its properties related to fuzzy skill inclusion degree are investigated. The variable precision model is refined for constructing the knowledge structure, and the corresponding algorithm is designed. Moreover, the applicability of the matrix approach in constructing knowledge structures for variable precision models in the context of dynamic items is examined. Finally, a dataset is used to empirically evaluate the feasibility and effectiveness of the proposed algorithm.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"183 ","pages":"Article 109427"},"PeriodicalIF":3.2,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740135","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
A novel active learning approach to label one million unknown malware variants 一种新的主动学习方法来标记一百万个未知的恶意软件变体
IF 3.2 3区 计算机科学
International Journal of Approximate Reasoning Pub Date : 2025-03-26 DOI: 10.1016/j.ijar.2025.109426
Ahmed Bensaoud, Jugal Kalita
{"title":"A novel active learning approach to label one million unknown malware variants","authors":"Ahmed Bensaoud,&nbsp;Jugal Kalita","doi":"10.1016/j.ijar.2025.109426","DOIUrl":"10.1016/j.ijar.2025.109426","url":null,"abstract":"<div><div>Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one million malware examples belonging to different unknown modern malware families. The first model is Inception-V4+PCA combined with several support vector machine (SVM) algorithms (UTSVM, PSVM, SVM-GSU, TBSVM). The second model is Vision Transformer based Bayesian Neural Networks ViT-BNN. Our proposed ViT-BNN is a state-of-the-art active learning approach that differs from current methods and can apply to any particular task. The experiments demonstrate that the ViT-BNN is more stable and robust in handling uncertainty.</div></div>","PeriodicalId":13842,"journal":{"name":"International Journal of Approximate Reasoning","volume":"182 ","pages":"Article 109426"},"PeriodicalIF":3.2,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726068","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信