Application of VPRS model with enhanced threshold parameter selection mechanism to automatic stock market forecasting and portfolio selection

This study proposes a technique based upon Fuzzy C-Means (FCM) classification theory and related fuzzy theories for choosing an appropriate value of the Variable Precision Rough Set (VPRS) threshold parameter (β) when applied to the classification of continuous information systems. The VPRS model is then combined with a moving Average Autoregressive Exogenous (ARX) prediction model and Grey Systems theory to create an automatic stock market forecasting and portfolio selection mechanism. In the proposed mechanism, financial data are collected automatically every quarter and are input to an ARX prediction model to forecast the future trends of the collected data over the next quarter or half-year period. The forecast data are then reduced using a GM(1, N) model, classified using a FCM clustering algorithm, and then supplied to a VPRS classification module which selects appropriate investment stocks in accordance with a pre-determined set of decision-making rules. Finally, a grey relational analysis technique is employed to weight the selected stocks in such a way as to maximize the rate of return of the stock portfolio. The validity of the proposed approach is demonstrated using electronic stock data extracted from the financial database maintained by the Taiwan Economic Journal (TEJ). The portfolio results obtained using the proposed hybrid model are compared with those obtained using a Rough Set (RS) selection model. The effects of the number of attributes of the RS lower approximation set and VPRS β-lower approximation set on the classification are systematically examined and compared. Overall, the results show that the proposed stock forecasting and stock selection mechanism not only yields a greater number of selected stocks in the β-lower approximation set than in the RS approximation set, but also yields a greater rate of return.     

Non-Deterministic Outlier Detection Method Based on the Variable Precision Rough Set Model

This study presents a method for the detection of outliers based on the Variable Precision Rough Set Model (VPRSM). The basis of this model is the generalisation of the standard concept of a set inclusion relation on which the Rough Set Basic Model (RSBM) is based. The primary contribution of this study is the improvement in detection quality, which is achieved due to the generalisation allowed by the classification system that allows a certain degree of uncertainty. From this method, a computationally efficient algorithm is proposed. The experiments performed with a real scenario and a comparison of the results with the RSBM-based method demonstrate the effectiveness of the method as well as the algorithm’s efficiency in diverse contexts, which also involve large amounts of data.     

Clustering rows and/or columns of a two-way contingency table and a related distribution theory

The row-wise multiple comparison procedure proposed in Hirotsu [Hirotsu, C., 1977. Multiple comparisons and clustering rows in a contingency table. Quality 7, 27–33 (in Japanese); Hirotsu, C., 1983. Defining the pattern of association in two-way contingency tables. Biometrika 70, 579–589] has been verified to be useful for clustering rows and/or columns of a contingency table in several applications. Although the method improved the preceding work there was still a gap between the squared distance between the two clusters of rows and the largest root of a Wishart matrix as a reference statistic for evaluating the significance of the clustering. In this paper we extend the squared distance to a generalized squared distance among any number of rows or clusters of rows and dissolves the loss of power in the process of the clustering procedure. If there is a natural ordering in columns we define an order sensitive squared distance and then the reference distribution becomes that of the largest root of a non-orthogonal Wishart matrix, which is very difficult to handle. We therefore propose a very nice χ²-approximation which improves the usual normal approximation in Anderson [Anderson, T.W., 2003. An Introduction to Multivariate Statistical Analysis. 3rd ed. Wiley Intersciences, New York] and also the first χ²-approximation introduced in Hirotsu [Hirotsu, C., 1991. An approach to comparing treatments based on repeated measures. Biometrika 75, 583–594]. A two-way table reported by Guttman [Guttman, L., 1971. Measurement as structural theory. Psychometrika 36, 329–347] and analyzed by Greenacre [Greenacre, M.J., 1988. Clustering the rows and columns of a contingency table. Journal of Classification 5, 39–51] is reanalyzed and a very nice interpretation of the data has been obtained.     

Perturbing Bézier coefficients for best constrained degree reduction in the L2-norm

This paper first shows how the Bézier coefficients of a given degree n polynomial are perturbed so that it can be reduced to a degree m (<n) polynomial with the constraint that continuity of a prescribed order is preserved at the two endpoints. The perturbation vector, which consists of the perturbation coefficients, is determined by minimizing a weighted Euclidean norm. The optimal degree n−1 approximation polynomial is explicitly given in Bézier form. Next the paper proves that the problem of finding a best L₂-approximation over the interval [0,1] for constrained degree reduction is equivalent to that of finding a minimum perturbation vector in a certain weighted Euclidean norm. The relevant weights are derived. This result is applied to computing the optimal constrained degree reduction of parametric Bézier curves in the L₂-norm.     

The unification problem for confluent right-ground term rewriting systems

The unification problem for term rewriting systems (TRSs) is the problem of deciding, for a given TRS R and two terms M and N, whether there exists a substitution θ such that Mθ and Nθ are congruent modulo R (i.e., Mθ↔_R^*Nθ). In this paper, the unification problem for confluent right-ground TRSs is shown to be decidable. To show this, the notion of minimal terms is introduced and a new unification algorithm for obtaining a substitution whose range consists of minimal terms is proposed. Our result extends the decidability of unification for canonical (i.e., terminating and confluent) right-ground TRSs given by Hullot [Proceedings of the 5th Conference on Automated Deduction, LNCS, vol. 87, 1980, p. 318] in the sense that the termination condition can be omitted.     

Linear programming based approximation algorithms for feedback set problems in bipartite tournaments

We consider the feedback vertex set and feedback arc set problems on bipartite tournaments. We improve on recent results by giving a 2-approximation algorithm for the feedback vertex set problem. We show that this result is the best that we can attain when using optimal solutions to a certain linear program as a lower bound on the optimal value. For the feedback arc set problem on bipartite tournaments, we show that a recent 4-approximation algorithm proposed by Gupta (2008) [8] is incorrect. We give an alternative 4-approximation algorithm based on an algorithm for the feedback arc set on (non-bipartite) tournaments given by van Zuylen and Williamson (2009) [14].     

Testing for independence in heavy-tailed time series using the codifference function

In this paper, we consider a Portmanteau-type test of randomness for symmetric α stable random variables with exponent 0<α≤2, using a test statistic that differs from, but has the same general form as Box–Pierce Q-statistic, which is defined using the codifference function. We obtain that unlike a similar test proposed in [Runde, R., 1997. The asymptotic null distribution of the Box–Pierce Q-statistic for random variables with infinite variance—with an application to German stock returns. Journal of Econometrics 78, 205–216], the asymptotic distribution of the proposed statistic is similar to the classical case, that is asymptotically χ² distributed, both in finite and infinite variance cases. Simulation studies are performed to obtain the small sample performance of the proposed statistic. We found that the proposed statistic works fairly well, in the sense that in the infinite variance case, under suitable choice of the design parameter, its empirical levels are closer to the theoretical ones than Runde’s statistic. In the finite variance case, its empirical level is approximately the same as that of Ljung–Box’s statistic [Ljung, G.M. and Box, G.E.P., 1978. On a measure of lack of fit in time series models. Biometrika 65, 297–303]. Furthermore, the statistic also has good power against the AR(1) alternative. We provide an empirical example using some stocks chosen from the LQ45 index listed in the Indonesia Stock Exchange (IDX).     

Generalizations of -fuzzy subalgebras in BCK/BCI-algebras

More general form of the notion of quasi-coincidence of a fuzzy point with a fuzzy set is considered, and generalizations of results in the papers [Y. B. Jun, On (α,β)-fuzzy subalgebras of BCK/BCI-algebras, Bull. Korean Math. Soc. 42 (4) (2005) 703–711; Y. B. Jun, Fuzzy subalgebras of type (α,β) in BCK/BCI-algebras, Kyungpook Math. J. 47 (2007) 403–410] are discussed. The notions of -fuzzy subalgebras and -fuzzy subalgebras in a BCK/BCI-algebra X are introduced, and several properties are investigated. Characterizations of -fuzzy subalgebra in a BCK/BCI-algebra X are discussed.     

A variable precision rough set approach to the remote sensing land use/cover classification

Nowadays the rough set method is receiving increasing attention in remote sensing classification although one of the major drawbacks of the method is that it is too sensitive to the spectral confusion between-class and spectral variation within-class. In this paper, a novel remote sensing classification approach based on variable precision rough sets (VPRS) is proposed by relaxing subset operators through the inclusion error β. The remote sensing classification algorithm based on VPRS includes three steps: (1) spectral and textural information (or other input data) discretization, (2) feature selection, and (3) classification rule extraction. The new method proposed here is tested with Landsat-5 TM data. The experiment shows that admitting various inclusion errors β, can improve classification performance including feature selection and generalization ability. The inclusion of β also prevents the overfitting to the training data. With the inclusion of β, higher classification accuracy is obtained. When β=0 (i.e., the original rough set based classifier), overfitting to the training data occurs, with the overall accuracy=0.6778 and unrecognizable percentage=12%. When β=0.07, the highest classification performance is reached with overall accuracy and unrecognizable percentage up to 0.8873% and 2.6%, respectively.     

An efficient architecture for designing reverse converters based on a general three-moduli set

In this paper, a high-speed, low-cost and efficient design of reverse converter for the general three-moduli set {2^α, 2^β − 1, 2^β + 1} where α < β is presented. The simple proposed architecture consists of a carry save adder (CSA) and a modulo adder. As a result it can be efficiently implemented in VLSI circuits. The values of α and β are set in order to provide the desired dynamic range and also to obtain a balanced moduli set. Based on the above, two new moduli sets {2^n+k, 2²ⁿ − 1, 2²ⁿ + 1} and {2²ⁿ⁻¹, 2²ⁿ⁺¹ − 1, 2²ⁿ⁺¹ + 1}, which are the special cases of the moduli set {2^α, 2^β − 1, 2^β + 1} are proposed. The reverse converters for these new moduli sets are derived from the proposed general architecture with better performance compared to the other reverse converters for moduli sets with similar dynamic range.     

Robust stabilization of infinite dimensional systems by finite dimensional controllers

The problem of robustly stabilizing an infinite dimensional system with transfer function G, subject to an additive perturbation Δ is considered. It is assumed that: G ε ₀(σ) of systems introduced by Callier and Desoer [3]; the perturbation satisfies |W₁ΔW₂| < ε, where W₁ and W₂ are stable and minimum phase; and G and G + Δ have the same number of poles in ⁺. Now write W₁GW₂=G₁ + G₁, where G₁ is rational and totally unstable and G₂ is stable. Generalizing the finite dimensional results of Glover [12] this family of perturbed systems is shown to be stabilizable if and only if ε σ_min (G^*₁)( = the smallest Hankel singular value of G^*₁). A finite dimensional stabilizing controller is then given by where 2 is a rational approximation of G₂ such that

Full-size image

) and K₁ robustly stabilizes G₁ to margin ε. The feedback system (G, K) will then be stable if |W₁ΔW₂| _∞< ε − Δ.     

Algebraic Riccati equation and J-spectral factorization for estimation

In this paper we investigate on the existence of the stabilizing solution of the algebraic Riccati equation (ARE) related to the filtering problem with a prescribed attenuation level γ. It is well known that such a solution exists and is positive definite for γ larger than a certain γ_F and it does not exist for γ smaller than a certain γ₀. We consider the intermediate case γ(γ₀,γ_F] and show that in this interval the stabilizing solution does exist, except for a finite number of values of γ. We show how the solution of the ARE may be employed to obtain a minimum-phase J-spectral factor of the J-spectrum associated with the filtering problem.     

One for the Price of Two: a Unified Approach for Approximating Covering Problems

We present a simple and unified approach for developing and analyzing approximation algorithms for covering problems. We illustrate this on approximation algorithms for the following problems: Vertex Cover, Set Cover, Feedback Vertex Set, Generalized Steiner Forest, and related problems. The main idea can be phrased as follows: iteratively, pay two dollars (at most) to reduce the total optimum by one dollar (at least), so the rate of payment is no more than twice the rate of the optimum reduction. This implies a total payment (i.e., approximation cost) ≤ twice the optimum cost. Our main contribution is based on a formal definition for covering problems, which includes all the above fundamental problems and others. We further extend the Bafna et al. extension of the Local-Ratio theorem. Our extension eventually yields a short generic r -approximation algorithm which can generate most known approximation algorithms for most covering problems. Another extension of the Local-Ratio theorem to randomized algorithms gives a simple proof of Pitt's randomized approximation for Vertex Cover. Using this approach, we develop a modified greedy algorithm, which for Vertex Cover gives an expected performance ratio ≤ 2 . Received September 17, 1997; revised March 5, 1998.     

Fully polynomial time approximation scheme for the weighted flow-time minimization on a single machine with a fixed non-availability interval

In a recent paper [Theoretical Computer Science 363, 257–265], He, Zhong and Gu considered the non-resumable case of the scheduling problem with a fixed non-availability interval under the non-resumable scenario. They proposed a polynomial time approximation scheme (PTAS) to minimize the total completion time.In this paper, we propose a fully polynomial-time approximation scheme to minimize the total weighted completion time. The FPTAS has O(n²/ε²) time complexity, where n is the number of jobs and ε is the required error bound. The proposed FPTAS outperforms all the previous approximation algorithms designed for this problem and its running time is strongly polynomial.     

Discrete-time linear periodic systems: A note on the reachability and controllability interval length

Discrete-time linear systems with periodic coefficients of period T are considered in this paper. The reachability and controllability indices at time t for periodic systems, μ_rt and μ_ct, are defined. It is shown that the reachability [controllability] subspace at time t does coincide with the reachability [controllability] subspace over the interval (t − μ_rt,T, t) [(t, t + μ_ct.,T)] and properly includes the reachability [controllability] subspace over the interval (t −(μ_rt−1) T, t) [(t, t +(μ_cr−1)T)].     

Fair Π

In this paper, we define fair computations in the π-calculus [Milner, R., Parrow, J. & Walker, D., A Calculus of Mobile Processes, Part I and II, Information and Computation 100 (1992) 1–78]. We follow Costa and Stirling's approach for CCS-like languages [Costa, G. & Stirling, C., A Fair Calculus of Communicating Systems, Acta Informatica 21 (1984) 417–441, Costa, G. & Stirling, C., Weak and Strong Fairness in CCS, Information and Computation 73 (1987) 207–244] but exploit a more natural labeling method of process actions to filter out unfair process executions. The new labeling allows us to prove all the significant properties of the original one, such as unicity, persistence and disappearance of labels. It also turns out that the labeled π-calculus is a conservative extension of the standard one. We contrast the existing fair testing [Brinksma, E., Rensink, A. & Vogler, W., Fair Testing, Proc. of CONCUR'95, LNCS, 962 (1995) 313–327, Natarajan, V. & Cleaveland, R., Divergence and Fair Testing, Proc. of ICALP '95, LNCS, 944 (1995) 648–659] with those that naturally arise by imposing weak and strong fairness as defined by Costa and Stirling. This comparison provides the expressiveness of the various fair testing-based semantics and emphasizes the discriminating power of the one already proposed in the literature.     

An optimal strategy for a conflict resolution problem

Relevant to the design of multiple access protocols is the problem of finding the largest of N i.i.d. numbers X₁,…,X_N uniformly distributed over [0,1] using the minimum number of questions of the following type. We pick a set A(1) [0, 1] and ask which X_i ε A(1). Depending on the response, we pick another subset A(2) and ask which X_i ε A(2), and so on, until we identify the largest X_i. It is shown that the optimum sequence of questions must be of the type A(k) = (a(k), 1]; the best sequence {a(k)} can then be determined by dynamic programming following the work of Arrow, Pesotchinsky and Sobel.     

Generating fuzzy rules from training instances for fuzzy classification systems

In recent years, many methods have been proposed to generate fuzzy rules from training instances for handling the Iris data classification problem. In this paper, we present a new method to generate fuzzy rules from training instances for dealing with the Iris data classification problem based on the attribute threshold value α, the classification threshold value β and the level threshold value γ, where α  [0, 1], β  [0, 1] and γ  [0, 1]. The proposed method gets a higher average classification accuracy rate than the existing methods.     

Multicast Pull Scheduling: When Fairness Is Fine

Abstract. We investigate server scheduling policies to minimize average user perceived latency in pull-based client-server systems (systems where multiple clients request data from a server) where the server answers requests on a multicast/ broadcast channel. We first show that there is no O(1) -competitive algorithm for this problem. We then give a method to convert any nonclairvoyant unicast scheduling algorithm A to nonclairvoyant multicast scheduling algorithm B . We show that if A works well, when jobs can have parallel and sequential phases, then B works well if it is given twice the resources. More formally, if A is an s -speed c -approximation unicast algorithm, then its counterpart algorithm B is a 2s -speed c -approximation multicast algorithm. It is already known [5] that Equi-partition, which devotes an equal amount of processing power to each job, is a (2 + ε) -speed O(1 + 1/ε) -approximation algorithm for unicast scheduling of such jobs. Hence, it follows that the algorithm {BEQUI}, which broadcasts all requested files at a rate proportional to the number of outstanding requests for that file, is a (4 + ε) -speed O(1 + 1/ε) -approximation algorithm. We give another algorithm BEQUI-EDF and show that BEQUI-EDF is also a (4 + ε) -speed O(1 + 1/ε) -approximation algorithm. However, BEQUI-EDF has the advantage that the maximum number of preemptions is linear in the number of requests, and the advantage that no preemptions occur if the data items have unit size.     

An alternative specification of generalized linear mixed models

Consider stratified data in which Y_i1,…,Y_ini denote real-valued response variables corresponding to the observations from stratum i, i=1,…,m and suppose that Y_ij follows an exponential family distribution with canonical parameter of the form θ_ij=x_ijβ+γ_i. In analyzing data of this type, the stratum-specific parameters are often modeled as random effects; a commonly-used approach is to assume that γ₁,…,γ_m are independent, identically distributed random variables.The purpose of this paper is to consider an alternative approach to defining the random effects, in which the stratum means of the response variable are assumed to be independent and identically distributed, with a distribution not depending on β. It will be shown that inferences about β based on this formulation of the generalized linear mixed model have many desirable properties. For instance, inferences regarding β are less sensitive to the choice of random effects distribution, are less subject to bias from omitted stratum-level covariates and are less affected by separate between- and within-cluster covariate effects.