N-ary decomposition for multi-class classification

Data-driven decomposition for multi-class classification

This paper presents a new study on a method of designing a multi-class classifier: Data-driven Error Correcting Output Coding (DECOC). DECOC is based on the principle of Error Correcting Output Coding (ECOC), which uses a code matrix to decompose a multi-class problem into multiple binary problems. ECOC for multi-class classification hinges on the design of the code matrix. We propose to explor...

On $n$-ary Hypergroups and Fuzzy $n$-ary Homomorphism

A Generic Disjunctive/Conjunctive Decomposition Model for n-ary Relations.

This paper discusses a generic decomposition model that represents an arbitrary n-ary relation as a disjunctive or conjunctive combination of a number of n-ary component relations of a prespecified type. An important subclass of order-preserving decompositions is defined and its properties are derived. The generic model is shown to subsume various known models as special cases, including the mo...

Exploiting Associations between Class Labels in Multi-label Classification

Multi-label classification has many applications in the text categorization, biology and medical diagnosis, in which multiple class labels can be assigned to each training instance simultaneously. As it is often the case that there are relationships between the labels, extracting the existing relationships between the labels and taking advantage of them during the training or prediction phases ...

Canonical (m,n)−ary hypermodules over Krasner (m,n)−ary hyperrings

The aim of this research work is to define and characterize a new class of n-ary multialgebra that may be called canonical (m, n)&minus hypermodules. These are a generalization of canonical n-ary hypergroups, that is a generalization of hypermodules in the sense of canonical and a subclasses of (m, n)&minusary hypermodules. In addition, three isomorphism theorems of module theory and canonical ...