Search

Building information modeling (BIM) can be recognized as the most promising technology that was introduced to the construction sector in the recent past. The current BIM-based safety risk assessment methods ignore data uncertainty. Hence, this study integrates BIM with fuzzy set theory for safety risk prediction. A Fuzzy Inference System (FIS) was developed based on the causality of safety incidents. The FIS extracts construction project data from BIM models while automatically assessing each potential safety hazard and project's total risk. The proposed method was demonstrated by using a building project in which the safety risk was predicted as low. Safety records of the above project revealed that no safety incidents were recorded in this project. The proposed method can indicate the safety risks level at various stages of a construction project and help to enhance the safety of construction workers on a construction site. Key words: building information modeling, construction safety, fuzzy set theory, predictive planning, 1. Introduction Currently, 1.4 million Canadians are employed directly and indirectly in the construction sector, and 70% of the 368 000 construction industry firms employ less than five people (Buildforce [...]

We consider the problem of clustering observations using a potentially large set of features. One might expect that the true underlying clusters present in the data differ only with respect to a small fraction of the features, and will be missed if one clusters the observations using the full set of features. We propose a novel framework for sparse clustering, in which one clusters the observations using an adaptively chosen subset of the features. The method uses a lasso-type penalty to select the features. We use this framework to develop simple methods for sparse K-means and sparse hierarchical clustering. A single criterion governs both the selection of the features and the resulting clusters. These approaches are demonstrated on simulated and genomic data. KEY WORDS: Hierarchical clustering; High-dimensional; K-means clustering; Lasso; Model selection; Sparsity; Unsupervised learning.

The rapid development of global economy and the resulting increase in competition have prompted attention to be focused on supply chain management (SCM) for improved competitiveness. Supplier selection for reducing supplier base is an important goal in SCM. This paper aims at contributing an effective method that combines an FP-growth algorithm with set theory to identify the primary and secondary suppliers. An example of the proposed method to find key suppliers is presented, and the results show the proposed method to be effective. doi:10.1057/jors.2008.157 Published online 25 February 2009 Keywords: FP-growth algorithm; set theory; supplier selection; purchasing supply chain management

In this paper, we consider the nonnegatively constrained multichannel image deblurring problem and propose regularizing active set methods for numerical restoration. For image deblurring problems, it is reasonable to solve a regularizing model with nonnegativity constraints because of the physical meaning of the image. We consider a general regularizing [l.sub.p]-[l.sub.q] model with nonnegativity constraints. For p and q equaling 2, the model is in a convex quadratic form, therefore, the active set method is proposed since the nonnegativity constraints are imposed naturally. For p and q not equaling 2, we present an active set method with a feasible Newton-conjugate gradient solution technique. Numerical experiments are presented for ill-posed three-channel blurred image restoration problems. OCIS codes: 100.1830, 100.3020, 100.3190, 000.4430.

Conditioning difficulties often thwart the characterization of damage by model updating. Methods that can provide information on damage location without explicit selection of free parameters are important for improving the likelihood of success. A technique that satisfies this objective known as the dynamic damage locating vector method locates damage as regions where a stress field that is computed in a model of the reference state, using loads extracted from changes in the transfer matrix, is identically zero. Central to the present paper is the fact that existence of the noted loads requires that the change in the transfer matrix be rank deficient everywhere in C. Specifically, the paper examines the situation where the change in the transfer matrix is full normal rank and shows that although zero stress excitations are not generally feasible, useful surrogates can often be obtained from conditions defined by the invariant zero triplets (i.e., zero, zero direction, and zero input) of a mathematical structure, designated as the delta system, which maps inputs to changes in the output. The paper discusses the formulation of the delta system, the extraction of the invariant zeros, and the computation of the associated stress fields. Selection of the potentially damaged set of elements is based on a decision logic that uses the aggregate information from all (or any subset) of the identified zeros. CE Database subject headings: Damage; Parameters; Localization.

A design stage method is proposed for assessing performance reliability of systems with competing time-variant responses due to components with uncertain degradation rates. Findings reveal the effectiveness of the proposed method in providing a realistic way for predicting performance reliability.

To recruit and retain high-potential talent is critical for semiconductor companies to maintain competitive advantages in a modern knowledge-based economy. Conventional personnel selection methodologies focusing on static work and job analysis will no longer be appropriate for knowledge workers in high-tech industries. This paper aims to develop an effective data mining approach based on Rough Set Theory to explore and analyze human resource data for personnel selection and human capital enhancement. An empirical study was conducted in a leading semiconductor company in Taiwan to estimate the validity of the proposed approach for predicting work behaviors including performance and resignation. The results showed that latent knowledge can be discovered as a basis to derive specific recruitment and human resource management strategies. In particular, 29 rules have been adopted as references for recruiting the right talent. This paper concludes with discussions of empirical findings and future research directions. Index Terms--Competitive advantage, data mining, decision analysis, human capital, personnel selection, rough set theory (RST).

This paper proposes the use of cylinders as primary invariant sets to be used in certain state-constrained control designs. Following the idea originally introduced by O'Dell, the primary invariant set is intersected with the state constraints to yield sets which retain the invariance under some conditions. Although several results presented here apply to fairly general nonlinear systems and primary invariant sets of any shape, the focus is on constrained sliding-mode control (SMC) using infinite cylinders as the primary invariant set. Their use is motivated by a coordinate transformation where the sliding motion is decoupled from the overall convergence to the origin. Robust positive invariance conditions are given for cylinders having convex and compact cross sections. For the case of cylinders with ellipsoidal cross sections, the invariance condition is given in the form of a linear matrix inequality. Further, a decision procedure to qualify each state constraint is given as a tool for the selection of the switching gain. A numerical example for a third-order plant illustrates the method. Index Terms--Constrained control, positively invariant sets, sliding-mode control, variable structure control.

Rough set theory is a useful tool for data mining. It is based on equivalence relations and has been extended to covering-based generalized rough set. This paper studies three kinds of covering generalized rough sets for dealing with the vagueness and granularity in information systems. First, we examine the properties of approximation operations generated by a covering in comparison with those of the Pawlak's rough sets. Then, we propose concepts and conditions for two coverings to generate an identical lower approximation operation and an identical upper approximation operation. After the discussion on the interdependency of covering lower and upper approximation operations, we address the axiomization issue of covering lower and upper approximation operations. In addition, we study the relationships between the covering lower approximation and the interior operator and also the relationships between the covering upper approximation and the closure operator. Finally, this paper explores the relationships among these three types of covering rough sets. Index Terms--Rough sets, approximation, covering, data mining, reduct, fuzzy sets, granular computing, computing with words.

The application of fuzzy set theory to derive genetic algorithms, for the scheduling of fabric cutting tasks on parallel machines in an apparel factory, is described.

Usage of fuzzy logic for analytical hierarchical programming, to analyze group decisions and negotiations, during strategic planning of management of knowledge portals, is described.

Usage of set theory to determine bargaining capacity in group decisions and negotiations is described.

Application of set theory with multilevel programming during fuzzy goal programming to determine tolerance values for membership functions is described.

A study on identification of false matches in data surveyed and reduction of vehicle roadside survey's mistakes, using set theory, is analyzed.

A novel weighting technique named pairwise optimal weight realization (POWER) for further acceleration of the adaptive parallel subgradient projection (PSP) algorithm is described. The examples have shown that the proposed technique for r= 1 yields faster convergence than not only adaptive PSP with uniform weights, affine projection algorithm and fast Newton transversal filters but also the regularized recursive least squares algorithm.

A study on equilibrium selection using the set-valued concept, which is based on p-dominance concept of game theory, is presented. p-best response set is a generalized form of p-dominance concept.

An easily implemented curve evolution by means of coupled level set functions is presented, which allows triple junctions and has no restrictions concerning the number of regions, thus leading to extension of active contours to multiple regions. The segmentation technique, in combination with hierarchical splitting, could be employed to minimize the energy of Zhu-Yuille in the level set framework.

Interaction of criteria in multi-criteria decision making is modelled using aggregation functions.

The problem of shortest path in resource constraints in operations management is addressed by using nodal aggregation method.

The high generalization ability of support vector machines (SVMs) has been shown in many practical applications, however, they are considerably slower in test phase than other learning approaches due to the possibly big number of support vectors comprised in their solution. In this letter, we describe a method to reduce such number of support vectors. The reduction process iteratively selects two nearest support vectors belonging to the same class and replaces them by a newly constructed one. Through the analysis of relation between vectors in input and feature spaces, we present the construction of the new vectors that requires to find the unique maximum point of a one-variable function on (0,1), not to minimize a function of many variables with local minima in previous reduced set methods. Experimental results on real life dataset show that the proposed method is effective in reducing number of support vectors and preserving machine's generalization performance. Index Terms--Feature space, input space, kernel methods, reduced set method, support vector machines (SVMs).

Abstract: Rough set theory is an elegant theory for knowledge discovery and it is mainly used in the classification and knowledge reduction tasks. The theory provides the reduct and core [...]

Application of set theory, for analyzing spatial model of electoral behavior of voters and candidates, is described.

The way of voting under constraints by the committees, where the voters have to choose a subset from a set of objects is explained.

A hybrid approach that integrates rough sets and neural networks to data mining classification rules from large database is presented. The effectiveness of this approach is verified by the experiments comparing with traditional rough set and neural network approaches.

A membership function is used to identify households as poor or non-poor in the construction of social programs, drawing from fuzzy sets theory. A test of the method's targeting performance is also included.

Usage of set theory in combination with non-linear programming, to create model for business forecasting, based on least-squares estimates, is described.

Usage of set theory to formulate a genetic algorithm, for scheduling of drivers' shifts for public transport systems in the United Kingdom, is described.

Usage of set theory in combination with possibility theory to develop models, for scheduling of uncertain orders during negotiations between customers and subcontractors, is described.

Usage of set theory for graph decomposition of temporal characteristics during project management as part of operations analysis is described.

Use of fuzzy set theory for solving problems of nonlinear programming is presented.

Usage of weighting functions to formulate an aggregation scheme, based on generalized mixture operators for multiple attribute decision making, is described. Comparison of this aggregation scheme with standard aggregation methods using weighted and ordered weighted averages is presented.

Utilization of a hypersphere for solving linear programming problems pertaining to ranking of full set or subset of efficient extreme point solutions is discussed.

Utilization of aggregate dispersed consequences for construction of criteria for evaluation of flood risk reduction strategies is discussed.

This note deals with the approximation of sets of linear time-invariant systems via orthonormal basis functions. This problem is relevant to conditional set membership identification, where a set of feasible systems is available from observed data, and a reduced-complexity model must be estimated. The basis of the model class is made of impulse responses of linear filters. The objective of the note is to select the basis function poles according to a worst-case optimality criterion. Suboptimal conditional identification algorithms are introduced and tight bounds are provided on the associated identification errors. Index Terms--Basis functions, identification, reduced-complexity models, set membership.

The role of aggregate concentration measurement in economic research is examined, using data from the United States from the 1980s to the late 1990s. The relevance of examining aggregate concentrations is discussed, focusing on the prediction of the significant mergers and acquisitions events of the late 1980s and early 1990s.

The usage of rough sets model for financial and economical forecasting is presented.

This article extends ideas from the economics literature on multiple output production and efficiency to develop methods for comparing baseball players that take into account the many dimensions to batting performance. A key part of this approach is the output aggregator. The weights in this output aggregator can be selected a priori (as is done with batting or slugging averages) or can be estimated statistically based on the performance of the best players in baseball. Once the output aggregator is obtained, an individual player can then be measured relative to the best, and a number between 0 and 1 characterizes his performance as a fraction of the best. The methods are applied to hitters using data from 1995-1999 on all regular players in baseball's major leagues. KEY WORDS: Bayesian; Efficiency; Markov chain Monte Carlo; Stochastic frontier model., 1. INTRODUCTION Academics and sports fans alike are often interested in a statistical comparison of baseball players. This is hard to do, because baseball is fundamentally a multiple-output sport. For [...]

This paper presents a conceptual possibilistic approach using fuzzy set theory to manage the uncertainties in the reliability input data of real power systems. In this paper, an algorithm is introduced to calculate the possibilistic reliability indices according to the degree of uncertainty in the given data. The probability distribution function can be transformed into an appropriate possibilistic representation using the probability-possibility consistency principle (PPCP) algorithm. In this algorithm, the transformation is performed by making a compromise between the transformation consistency and the human experience. Fuzzy classification theory is applied to reduce the number of load data points. The fuzzy classification method determines the closeness 1 of load data points by assigning them to various clusters and then J determining the distance between the clusters. The IEEE-RTS with 32-generating units is used to demonstrate the capability of the proposed algorithm. Index Terms--Loss-of-load expectation, forced outage rate, probability-possibility consistency principle, fuzzy clustering.

A new study uses fuzzy numbers to investigate the multi-constraint knapsack problem experienced in the areas of capital budgeting and resource allocation.

Many universities, research institutions, and government funding agencies are continuously attempting to grade or rank journals for their academic value. Such grading is needed both for funding and resource allocation purposes and for personnel decisions. In grading journals, objective information, such as the impact factors (the most commonly used journal citation information provided by Journal Citation Reports) and/or subjective information, such as experts' judgments about the journals, are used. Grading of journals is typically done by a committee. Most of the existing approaches only consider either the subjective or the objective information. While such approaches work in many cases, they may not work in many others. Complaints about politics, inconsistencies, and unfairness are common in many situations. This paper presents a methodology that integrates both types of information, providing a comprehensive method for assessing the quality of journals. The method employs a fuzzy set approach that also deals with the imprecise and missing information frequently inherited in the evaluation process. The proposed evaluation model is implemented in a Web-based system. A pilot evaluation study indicated that participants clearly preferred the system and its major features. Index Terms--Evaluating academic journals, fuzzy set, group decision making, objective evaluation, subjective evaluation.