The classical k nearest neighbor (k-nn) classification assumes that a fixed global metric is defined and searching for nearest neighbors is always based on this global metric. In the paper we present a model with local induction of a metric. Any test object induces a local metric from the neighborhood of this object and selects k nearest neighbors according to this locally induced metric. To in...

In this paper, a new approach is prposed for ordering fuzzy numbers based on bi-symmetrical weighted distance. The proposed method considers the bi-symmetrical weighted function and the bisymmetrical weighted distance of fuzzy numbers to rank fuzzy numbers. Some examples to compare the advantage of this approch with the existing metric index ranking methods is illustrated. The process to rank t...

In [15], Higham considered two types of nearest correlation matrix problem, namely the W -weighted case and the H-weighted case. While the W -weighted case has since then been well studied to make several Lagrangian dual based efficient numerical methods available, the H-weighted case remains numerically challenging. The difficulty of extending those methods from the W -weighted case to the H-w...

Let H be the Cartesian product of a family finite abelian groups. Via polynomial approach, we give sufficient conditions for partition induced by weighted poset metric to reflexive, which also become necessary some special scenarios. Moreover, examining roots Krawtchouk polynomials, combinatorial non-reflexive, and then several examples non-reflexive partitions. When is vector space over field ...

a weighted linear regression model with impercise response and p-real explanatory variables is analyzed. the lr fuzzy random variable is introduced and a metric is suggested for coping with this kind of variables. a least square solution for estimating the parameters of the model is derived. the result are illustrated by the means of some case studies.

The k-nearest neighbour (KNN) technique is a simple yet effective method for classification. In this paper, we propose an efficient weighted nearest neighbour classification algorithm, called PINE, using vertical data representation. A metric called HOBBit is used as the distance metric. The PINE algorithm applies a Gaussian podium function to set weights to different neighbours. We compare PIN...

In this paper, we focus on the aggregation problem for (trust, distrust) couples in trust networks. In particular, we study approaches based on classical and induced ordered weighted averaging (OWA) operators.