Yiyu Yao

University of Regina, Regina, Saskatchewan, Canada

Are you Yiyu Yao?

Claim your profile

Publications (99)51.72 Total impact

  • Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: There exist two formulations of the theory of rough sets. A conceptual formulation emphasizes on the meaning and interpretation of the concepts and notions of the theory, whereas a computational formulation focuses on procedures and algorithms for constructing these notions. Except for a few earlier studies, computational formulations dominate research in rough sets. In this paper, we argue that an oversight of conceptual formulations makes an in-depth understanding of rough set theory very difficult. The conceptual and computational formulations are the two sides of the same coin; it is essential to pay equal, if not more, attention to conceptual formulations. As a demonstration, we examine and compare conceptual and computational formulations of two fundamental concepts of rough sets, namely, approximations and reducts.
    Knowledge-Based Systems 01/2015; 80. DOI:10.1016/j.knosys.2015.01.004 · 3.06 Impact Factor
  • Yiyu Yao, Xiaofei Deng
    [Show abstract] [Hide abstract]
    ABSTRACT: Subsethood measures, also known as set-inclusion measures, inclusion degrees, rough inclusions, and rough-inclusion functions, are generalizations of the set-inclusion relation for representing graded inclusion. This paper proposes a framework of quantitative rough sets based on subsethood measures. A specific quantitative rough set model is defined by a particular class of subsethood measures satisfying a set of axioms. Consequently, the framework enables us to classify and unify existing generalized rough set models (e.g., decision-theoretic rough sets, probabilistic rough sets, and variable precision rough sets), to investigate limitations of existing models, and to develop new models. Various models of quantitative rough sets are constructed from different classes of subsethood measures. Since subsethood measures play a fundamental role in the proposed framework, we review existing methods and introduce new methods for constructing and interpreting subsethood measures.
    Information Sciences 05/2014; 267:306-322. DOI:10.1016/j.ins.2014.01.039 · 3.89 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper summarizes the discussions at a panel on Multidisciplinary Approaches to Computing at CCECE 2013, showcasing multidisciplinary research at the University of Regina. The panellist were invited from Fine Arts, Arts, Science, and Engineering. They elaborated on interdisciplinary and multidisciplinary views of computing, covering various topics such as agents, arts, knowledge engineering, granular computing, environment, mobile computing, multi-media, new media, scientistic computing, teaching, and Web-based support systems. The emerged theme of multidisciplinary computing brings new insights and in-depth understanding of computing.
    Electrical and Computer Engineering (CCECE), 2013 26th Annual IEEE Canadian Conference on; 01/2013
  • Xiaofei Deng, Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: The model of decision-theoretic shadowed sets provides a cost-sensitive approach to three-valued approximation of a fuzzy set on a finite universe. We introduce a semantic meaningful objective function for modeling shadowed sets using the decision theory. This paper is an extension and generalization of the decision-theoretic shadowed sets. We improve the cost-sensitive approach by generalizing the three-valued shadowed sets approximation using mean values. In particular, a mean value of the membership grades that are neither 1 nor 0 is used to represent the shadow. As a result, we have a more general and practical decision-theoretic shadowed set model, in which the optimal pair of thresholds is related to the membership structures of objects.
    IFSA World Congress and NAFIPS Annual Meeting (IFSA/NAFIPS), 2013 Joint; 01/2013
  • Yiyu Yao, Rong Fu
    [Show abstract] [Hide abstract]
    ABSTRACT: Rough set approaches to data analysis involve removing redundant attributes, redundant attribute-value pairs, and redundant rules in order to obtain a minimal set of simple and general rules. Pawlak arranges these tasks into a three-step sequential process based on a central notion of reducts. However, reducts used in different steps are defined and formulated differently. Such an inconsistency in formulation may unnecessarily affect the elegancy of the approach. Therefore, this paper introduces a generic definition of reducts of a set, uniformly defines various reducts used in rough set analysis, and examines several mathematically equivalent, but differently formulated, definitions of reducts. Each definition captures a different aspect of a reduct and their integration provides new insights.
    Transactions on Rough Sets XVI; 01/2013
  • Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: In rough set theory, one typically considers pairs of dual entities such as a pair of lower and upper approximations, a pair of indiscernibility and discernibility relations, a pair of sets of core and non-useful attributes, and several more. By adopting a framework known as hypercubes of duality, of which the square of opposition is a special case, this paper investigates the role of duality for interpreting fundamental concepts in rough set analysis. The objective is not to introduce new concepts, but to revisit the existing concepts by casting them in a common framework so that we can obtain more insights into an understanding of these concepts and their relationships. We demonstrate that these concepts can, in fact, be defined and explained in a common framework, although they first appear to be very different and have been studied in somewhat isolated ways.
    Fundamenta Informaticae 01/2013; 127(1-4):49-64. DOI:10.3233/FI-2013-895 · 0.48 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Peculiarity oriented mining (POM), aimed at discovering peculiarity rules hidden in a dataset, is a data mining method. Peculiarity factor (PF) is one of the most important concepts in POM. In this paper, it is proved that PF can accurately characterize the peculiarity of data sampled from a normal distribution. However, for a general one-dimensional distribution, it does not have the property. A local version of PF, called LPF, is proposed to solve the difficulty. LPF can effectively describe the peculiarity of data sampled from a continuous one-dimensional distribution. Based on LPF, a framework of local peculiarity oriented mining is presented, which consists of two steps, namely, peculiar data identification and peculiar data analysis. Two algorithms for peculiar data identification and a case study of peculiar data analysis are given to make the framework practical. Experiments on several benchmark datasets show their good performance.
    International Journal of Information Technology and Decision Making 12/2012; 11(06). DOI:10.1142/S0219622012500319 · 1.89 Impact Factor
  • Yiyu Yao, Sheila Petty
    [Show abstract] [Hide abstract]
    ABSTRACT: The web, as a new medium for information and knowledge creation, storage, communication, and sharing, offers both opportunities and challenges. By applying the principles of granular computing, we argue that multiple representations and presentations of web content are essential to effective knowledge utilization through the web. The same web content should be represented in many versions and in multiple levels in each version to facilitate informative communication, personalized searches, web exploration, and tailored presentation of retrieval results.
    Proceedings of the 2012 international conference on Brain Informatics; 12/2012
  • Yiyu Yao, Liquan Zhao
    [Show abstract] [Hide abstract]
    ABSTRACT: Measurement of granularity is one of the foundational issues in granular computing. This paper investigates a class of measures of granularity of partitions. The granularity of a set is defined by a strictly monotonic increasing transformation of the cardinality of the set. The granularity of a partition is defined as the expected granularity of all blocks of the partition with respect to the probability distribution defined by the partition. Many existing measures of granularity are instances of the proposed class. New measures of granularity of partitions are also introduced.
    Information Sciences 12/2012; 213:1–13. DOI:10.1016/j.ins.2012.05.021 · 3.89 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cognitive informatics is a transdisciplinary enquiry of computer science, information sciences, cognitive science, and intelligence science that investigates the internal information processing mechanisms and processes of the brain and natural intelligence, as well as their engineering applications in cognitive computing. Cognitive computing is an emerging paradigm of intelligent computing methodologies and systems based on cognitive informatics that implements computational intelligence by autonomous inferences and perceptions mimicking the mechanisms of the brain. This article presents a set of collective perspectives on cognitive informatics and cognitive computing, as well as their applications in abstract intelligence, computational intelligence, computational linguistics, knowledge representation, symbiotic computing, granular computing, semantic computing, machine learning, and social computing.
    12/2012; 4:1-24. DOI:10.4018/978-1-4666-1743-8.ch001
  • [Show abstract] [Hide abstract]
    ABSTRACT: One of the fundamental tasks of targeted marketing is to elicit associations between customers and products. Based on the results from information retrieval and utility theory, this article proposes a unified framework of targeted marketing. The customer judgments of products are formally described by preference relations and the connections of customers and products are quantitatively measured by market value functions. Two marketing strategies, known as the customer-oriented and product-oriented marketing strategies, are investigated. Four marketing models are introduced and examined. They represent, respectively, the relationships between a group of customers and a group of products, between a group of customers and a single product, between a single customer and a group of products, and between a single customer and a single product. Linear and bilinear market value functions are suggested and studied. The required parameters of a market value function can be estimated by exploring three types of information, namely, customer profiles, product profiles, and transaction data. Experiments on a real-world data set are performed to demonstrate the effectiveness of the proposed framework.
    Computational Intelligence 11/2012; 30(3). DOI:10.1111/coin.12003 · 0.87 Impact Factor
  • Yiyu Yao, Bingxue Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a framework for the study of covering based rough set approximations. Three equivalent formulations of the classical rough sets are examined by using equivalence relations, partitions, and σ-algebras, respectively. They suggest the element based, the granule based and the subsystem based definitions of approximation operators. Covering based rough sets are systematically investigated by generalizing these formulations and definitions. A covering of universe of objects is used to generate different neighborhood operators, neighborhood systems, coverings, and subsystems of the power set of the universe. They are in turn used to define different types of generalized approximation operators. Within the proposed framework, we review and discuss covering based approximation operators according to the element, granule, and subsystem based definitions.
    Information Sciences 10/2012; 200:91–107. DOI:10.1016/j.ins.2012.02.065 · 3.89 Impact Factor
  • Xiaofei Deng, Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: In a probabilistic rough set model, the positive, negative and boundary regions are associated with classification errors or uncertainty. The uncertainty is controlled by a pair of thresholds defining the three regions. The problem of searching for optimal thresholds can be formulated as the minimization of uncertainty induced by the three regions. By using Shannon entropy as a measure of uncertainty, we present an information-theoretic approach to the interpretation and determination of thresholds.
    Proceedings of the 7th international conference on Rough Sets and Knowledge Technology; 08/2012
  • Fundamenta Informaticae 01/2012; 115(2). · 0.48 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Based on classical rough set approximations, the LERS (Learning from Examples based on Rough Sets) data mining system induces two types of rules, namely, certain rules from lower approximations and possible rules from upper approximations. By relaxing the stringent requirement of the classical rough sets, one can obtain probabilistic approximations. The LERS can be easily applied to induce probabilistic positive and boundary rules from probabilistic positive and boundary regions. This paper discusses several fundamental issues related to probabilistic rule induction with LERS, including rule induction algorithm, quantitative measures associated with rules, and the rule conflict resolution method. © 2011 Wiley Periodicals, Inc. © 2011 Wiley Periodicals, Inc.
    International Journal of Intelligent Systems 06/2011; 26(6):518-539. DOI:10.1002/int.20482 · 1.41 Impact Factor
  • Source
    Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: Granular computing concerns a particular human-centric paradigm of problem solving by means of multiple levels of granularity and its applications in machines. It is closely related to Artificial Intelligence (AI) that aims at understanding human intelligence and its implementations in machines. Basic ideas of granular computing have appeared in AI under various names, including abstraction and reformulation, granularity, rough set theory, quotient space theory of problem solving, hierarchical problem solving, hierarchical planning, learning, etc. However, artificial intelligence perspectives on granular computing have not been fully explored. This chapter will serve the purpose of filling in such a gap. The results will have bidirectional benefits. A synthesis of results from artificial intelligence will enrich granular computing; granular computing philosophy, methodology, and tools may help in facing the grand challenge of reverse-engineering the brain, which has significant implications to artificial machine intelligence.
    04/2011: pages 17-34;
  • Yiyu Yao
    [Show abstract] [Hide abstract]
    ABSTRACT: Three-way decisions provide a means for trading off different types of classification error in order to obtain a minimum cost ternary classifier. This paper compares probabilistic three-way decisions, probabilistic two-way decisions, and qualitative three-way decisions of the standard rough set model. It is shown that, under certain conditions when considering the costs of different types of miss-classifications, probabilistic three-way decisions are superior to the other two.
    Information Sciences 03/2011; 181:1080-1096. DOI:10.1016/j.ins.2010.11.019 · 3.89 Impact Factor
  • Source
    Dun Liu, Yiyu Yao, Tianrui Li
    [Show abstract] [Hide abstract]
    ABSTRACT: The decision-theoretic rough set model is adopted to derive a profit-based three-way approach to investment decision-making. A three-way decision is made based on a pair of thresholds on conditional probabilities. A positive rule makes a decision of investment, a negative rule makes a decision of noninvestment, and a boundary rule makes a decision of deferment. Both cost functions and revenue functions are used to calculate the required two thresholds by maximizing conditional profit with the Bayesian decision procedure. A case study of oil investment demonstrates the proposed method.
    International Journal of Computational Intelligence Systems 02/2011; 4(1):66-74. DOI:10.1080/18756891.2011.9727764 · 1.47 Impact Factor
  • Source
    Yiyu Yao, Xiaofei Deng
    [Show abstract] [Hide abstract]
    ABSTRACT: When approximating a concept, probabilistic rough set models use probabilistic positive, boundary and negative regions. Rules obtained from the three regions are recently interpreted as making three-way decisions, consisting of acceptance, deferment, and rejection. A particular decision is made by minimizing the cost of correct and incorrect classifications. This framework is further extended into sequential three-way decision-making, in which the cost of obtaining required evidence or information is also considered.
    Proceedings of the 10th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2011, 18-20 August 2011, Banff, Alberta, Canada; 01/2011
  • Article: Preface.
    Davide Ciucci, Yiyu Yao