By Topic

Granular Computing (GrC), 2012 IEEE International Conference on

Date 11-13 Aug. 2012

Filter Results

Displaying Results 1 - 25 of 162
  • Projective lag synchronization of neural networks with time delay

    Publication Year: 2012, Page(s):201 - 204
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (504 KB) | HTML iconHTML

    In this paper, projective lag synchronization of coupled neural networks with time delay is studied. An error dynamic system resulting from the drive and response systems is formulated to analyze projective lag synchronization behavior. A general criterion is established to ensure the asymptotic stability of the error system, by which we design an appropriate adaptive controller. Numerical simulat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of neural network to brain-computer interface

    Publication Year: 2012, Page(s):163 - 168
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (670 KB) | HTML iconHTML

    In this study, an neural-network-based system is proposed for the applications of brain-computer interface (BCI). Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system consists of three procedures, including enhanced active segment selection, feature extraction, and classification. Firstly, combined with the use of continuous wavelet transform (CWT) ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parameter estimation of Conditional Random Fields model based on cloud computing

    Publication Year: 2012, Page(s):59 - 62
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (238 KB) | HTML iconHTML

    Conditional Random Field (CRF), a type of conditional probability model, has been widely used in Nature Language Processing (NLP), such as sequential data segmentation and labeling. The advantage of CRF model is the ability to express long-distance-dependent and overlapping features. However, the model parameter estimation of CRF is very time-consuming because of the large amount of calculation. T... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frequent pattern mining for price fluctuation based on cloud computing

    Publication Year: 2012, Page(s):50 - 54
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (451 KB) | HTML iconHTML

    Frequent pattern mining is a hot topic in data mining field, and is now widely used in various areas. Cloud computing, a newly developed framework for parallel computing, offers great advantages over traditional parallel computing in big data processing. In this paper, we present a parallel frequent pattern mining for price fluctuation based on cloud computing. Firstly, original dataset is pre-pro... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A novel Tolerant Skyline Operator for decision support

    Publication Year: 2012, Page(s):26 - 31
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1016 KB) | HTML iconHTML

    Skyline operator is significantly important for Decision oriented Data Analysis (DDA) due to its capability of finding a number of user-interested objects. However, an inherent weakness of conventional skyline queries is that the output size is hard to be controlled by users. It actually includes two aspects. On one hand, the number of returned skyline set might be too large to make the output mea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vertical mining for high utility itemsets

    Publication Year: 2012, Page(s):429 - 434
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (878 KB) | HTML iconHTML

    Recently, high utility itemsets mining becomes one of the most important research issues in data mining due to its ability to consider different profit values for every item. In the past studies, most algorithms generate high utility itemsets from a set of transactions in horizontal data format. Inspired by the problem of frequent itemset mining, vertical mining may be a promising approach superio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dual Locality Preserving Nonnegative Matrix Factorization for image analysis

    Publication Year: 2012, Page(s):300 - 303
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (735 KB) | HTML iconHTML

    Recently, Nonnegative Matrix Factorization(NMF) has been viewed as an effective method for data engineering for its part-based interpretability and superior performance. However, ordinary NMF merely views a r1 × r2 image as a vector in r1 × r2 dimensional space and the pixels of the image are considered independent. It fails to consider tha... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling repetitive patterns: A bridge between pattern theory and data mining

    Publication Year: 2012, Page(s):493 - 498
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (764 KB) | HTML iconHTML

    Traditional learning algorithms generate a predictive model by effectively partitioning the input or feature space in search for regions having a dominant single class. In this paper we point to the existence of problems where the relation among these regions corresponds to repetitive patterns that can be mapped to high-level models. We show how a formalism for the representation of patterns, also... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tackle three practical classification problems via Ensemble Learning

    Publication Year: 2012, Page(s):248 - 252
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (836 KB) | HTML iconHTML

    News Categorization, Intrusion Detection and Spam Detection are three practical problems1 in Data Mining and Cybersecurity. Their focus is on string sequences analysis towards application of knowledge discovery techniques for protecting personal computer information by means of detection, prevention, and response to various attacks. These three string sequences analysis problems could b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An empirical study of applying data mining techniques to the prediction of TAIEX Futures

    Publication Year: 2012, Page(s):277 - 282
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (877 KB) | HTML iconHTML

    It is an inevitable trend to learn and extract useful knowledge from massive data, so that data miming has been one of popular fields for researches and practitioners. Recently, data stream mining has emerged as an important subfield of data mining, because data samples usually are generated in a sequence over time and collected in a form of a stream in many cases in the real world. In this paper,... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Attribute Oriented Induction of High-level Emerging Patterns

    Publication Year: 2012, Page(s):525 - 530
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1333 KB) | HTML iconHTML

    Attribute Oriented Induction (AOI) produces high-level characteristic summary data but does not discover new emerging patterns. Emerging Pattern (EP) algorithms discover emerging patterns between datasets but mostly consider low-level data. This paper introduces an algorithm, AOI-HEP, derived from both AOI and High-level Emerging Patterns (HEP), where HEP discriminates the high level data from AOI... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mining important association rules on different customer potential value segments for life insurance database

    Publication Year: 2012, Page(s):283 - 288
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1348 KB) | HTML iconHTML

    To maximize customer profitability, companies should exert effort to acquire new customers, as well as to retain existing customers and add value. An efficient way of achieving such goals is to explore and profile customers' past purchase behavior and mine out their possible further needs and wants. When faced with increasingly diversified consumption demands, customers should be segmented based o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Formalizing data mining with association rules

    Publication Year: 2012, Page(s):406 - 411
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (618 KB) | HTML iconHTML

    A formal framework for data mining with association rules is introduced. The goal is to help to better understand to data mining process and to introduce a platform for automation of this process. Association rules are understood as general relations of two general Boolean attributes and logical calculus of association rules is used. Important items of domain knowledge are formalized and used in t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A random walk model based approach for quantifying technology emergence and impact for research articles

    Publication Year: 2012, Page(s):553 - 555
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (400 KB) | HTML iconHTML

    This article presents our proposal of using a random walk model based approach for quantifying technology emergence and impact for research articles based on a concept map extracted from related literature databases. The same approach should be easily adapted to citation networks and author networks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time adaptive classification system for intelligent sensing in manufacturing environment A feasibility study

    Publication Year: 2012, Page(s):761 - 766
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (770 KB) | HTML iconHTML

    The deployment of a sensor node to manage a group of sensors and collate their readings for system health monitoring is gaining popularity within the manufacturing industry. Such a sensor node is able to perform real-time configurations of the individual sensors that are assigned to it. Sensors are capable of acquiring data at different sampling frequencies based on the sensing requirements. The d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rough set over dual-universes in general incomplete information system

    Publication Year: 2012, Page(s):779 - 782
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (343 KB) | HTML iconHTML

    For the universality of incomplete information and superiority of rough set over dual-universes, we research rough set over dual-universes in incomplete information system. In this paper, we provide a general character function in incomplete information system. Then lower and upper approximation operators of rough set over dual-universes in incomplete information system are constructed utilizing g... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face image recognition based on time series motif discovery

    Publication Year: 2012, Page(s):72 - 77
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (707 KB) | HTML iconHTML

    This paper proposes a new face image recognition method based on time series motifs. Time series motifs are previously unknown, frequently occurring patterns in time series. In this paper, we make full use of time series motifs to discovery and recognize the face images. First, we convert face images into time series by extracting the time series features from three (primary color) vectors of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Attribute reduction algorithms based on the matroidal structure of rough set

    Publication Year: 2012, Page(s):447 - 452
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (318 KB) | HTML iconHTML

    Rough set is a tool for dealing with uncertainty in information systems. Matroid is a structure that generalizes the notion of linear independence in vector spaces. In this paper, we study attribute reduction algorithms based on the matroidal structure of rough set. Firstly, an approach is proposed to convert a partition into a matrix, then turn this matrix into a matroid. Secondly, several basic ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matroidal structure of covering rough sets based on multigranulation

    Publication Year: 2012, Page(s):195 - 200
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (418 KB) | HTML iconHTML

    Multigranulation rough sets provide an effective way to extend the classical rough sets based on single granulation to multigranulation. Covering rough set is a generalisation of classical rough set. This paper extends single granulation matroid to multigranulation matroid based on covering rough set. On one hand, we construct a multigranulation matroid through union of several independent sets. T... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modified attribute reduction algorithm of consistent covering decision information systems

    Publication Year: 2012, Page(s):89 - 92
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (267 KB) | HTML iconHTML

    Decision information system based on rough set is an important processing form in data mining. Attribute reduction is one of the most critical issues in rough set theory. Chen et.al. proposed an attribute reduction algorithm for decision information system based on the covering generalized rough sets. In this paper, we first point out that Chen's algorithm applies to the fifth, the sixth and the s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new K-means algorithm for community structures detection based on fuzzy clustering

    Publication Year: 2012, Page(s):1 - 5
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1157 KB) | HTML iconHTML

    Finding community structures from networks is one of the most popular research areas in recent years. Because of the shortcoming of FCM, for example, its results depend on the initial center node and need to specify the community number, based on the fuzzy theory, an improved FCM algorithm(NKFCM) is proposed, which can get the number of communities and the community centers automatically. NKFCM is... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A re-ranking method based on concept hierarchy using cloud model

    Publication Year: 2012, Page(s):639 - 644
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (685 KB) | HTML iconHTML

    This paper implemented the query terms level's concept extending to acquire the numerical characteristics of the query terms based on cloud model, elevated the concept of the lower query terms level to the higher query level, used the numerical characteristics of the query we gained from the concept level arisen to re-rank documents. This paper researched document re-ranking from the perspective t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A data-driven model for software reliability prediction

    Publication Year: 2012, Page(s):326 - 331
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (757 KB) | HTML iconHTML

    In the actual software development, failure data is rarely pure linear or nonlinear. It is usually formed by the linear and nonlinear patterns at the same time. These models can be divided into two main categories: analytical model and data-driven model. Analytical SRMs are proposed based on underlying assumptions about the nature of software faults, the stochastic behavior of the software process... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • QoM: An effective querying method for time series database

    Publication Year: 2012, Page(s):129 - 134
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (962 KB) | HTML iconHTML

    A very promising idea for fast searching in time series databases is to map the time series into a representative space. In this paper, we propose an effective querying algorithm QoM (Querying on Motif) based on time series motifs. First, we map the time series into representative motifs by motif discovery algorithm. Second, we look for a time series data based on these motifs by QoM. The QoM can ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A decision generation algorithm based on granular computing

    Publication Year: 2012, Page(s):475 - 480
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1392 KB) | HTML iconHTML

    Granular computing aims to provide different views at different granules of data, and to derive knowledge from the process of data abstraction. In this paper, a decision-rule generation algorithm based on granular computing (DGAGC) is proposed. The DGAGC consists of two stages, the rule generation stage and the decision making stage. In the rule generation stage, the DGAGC employs a rule combinati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.