Concept lattice based composite classifiers for high predictability

Xie, Zhipeng; Hsu, Wynne; Liu, Zongtian; Lee, Mong Li

doi:10.1080/09528130210164206

Cited by 19 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…which is not a formal concept of box (m ′ , g ′ ). Then by the antimonotonicity of Galois connections and relations (13 )- (14), the condition (15) contradicts the definition of boxing. After all, based on the definition of box (m ′ K , g ′ K ) the m ′ is the largest extent among the formal concepts of context K = (G, M, I), having the attribute m in the intent.…”

Section: The Decomposition Of Contextmentioning

confidence: 99%

“…There are various algorithms of the binary classification on based FCA. They are including: algorithms RULEARNER, GALOIS, GRAND, CITRIC, based on the use of all concepts lattice [12,13], algorithms CLAN and CLUB, LEGAL, using some subset of the concepts lattice [14], and algorithms which are based on hypotheses [6,15]. A visual representation of the results in the form of lattices is the advantage of these algorithms.…”

Section: Statement Of the Problemmentioning

confidence: 99%

“…The algebraic approach of R. Wille and B. Ganter has found wide application in various areas of machine learning [11][12][13][14][15][16]. Traditionally the classification of natural language texts is carried out based on quantitative proximity measures of the considered texts [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On Algebraic Approach of R. Wille and B. Ganter in the Investigation of Texts

Быкова¹,

Mongush²

2017

J. Sib. Fed. Univ., Math. phys.

View full text Add to dashboard Cite

The statement of the problem of a binary classification by precedents using formal concept lattices is given, in which the initial data are two binary contexts. It is specified that this problem is intractable due to the high computational complexity of discovery process of the formal concept and constructing for them of the lattices. The decomposition reception, which allows reducing the computational complexity of this process is proposed and theoretically justified. The reduction of computational complexity is achieved by separation of every initial context on polynomial number of boxes (subcontexts), followed by a search of the formal concepts in each selected box. The results of computational experiments are presented and they confirm the effectiveness of the proposed of reception of the reducing computational complexity.

show abstract

Section: The Decomposition Of Contextmentioning

confidence: 99%

Section: Statement Of the Problemmentioning

confidence: 99%

See 1 more Smart Citation

On Algebraic Approach of R. Wille and B. Ganter in the Investigation of Texts

Быкова¹,

Mongush²

2017

J. Sib. Fed. Univ., Math. phys.

View full text Add to dashboard Cite

show abstract

“…Nguifo and Njiwoua71 proposed IGLUE, an algorithm combining lattice‐based and instance‐based learning techniques. Fu et al72 give an experimental comparison of FCA‐based classification algorithms, such as GRAND,73 LEGAL,74 GALOIS,75 RULEARNER,76 CIBLe, and CLNN and CLNB 77. JSM hypotheses in FCA terms22,41,78 are positive intents (i.e., concept intents of the context given by positive examples) not contained in negative example intents, symmetrically for negative hypotheses.…”

Section: Relationships Of Fca To Models Of Knowledge Representation Amentioning

confidence: 99%

Knowledge representation and processing with formal concept analysis

Kuznetsov

Poelmans

2013

WIREs Data Min & Knowl

View full text Add to dashboard Cite

During the last three decades, formal concept analysis (FCA) became a well‐known formalism in data analysis and knowledge discovery because of its usefulness in important domains of knowledge discovery in databases (KDD) such as ontology engineering, association rule mining, machine learning, as well as relation to other established theories for representing knowledge processing, like description logics, conceptual graphs, and rough sets. In early days, FCA was sometimes misconceived as a static crisp hardly scalable formalism for binary data tables. In this paper, we will try to show that FCA actually provides support for processing large dynamical complex (may be uncertain) data augmented with additional knowledge. © 2013 Wiley Periodicals, Inc. This article is categorized under: Fundamental Concepts of Data and Knowledge > Key Design Issues in Data Mining Fundamental Concepts of Data and Knowledge > Knowledge Representation Technologies > Computational Intelligence

show abstract

“…Multiple approaches have been proposed so far, con¯rming the relevance of using a Galois lattice for a classi¯cation task. Among these approaches, we can mention LEGAL and LEGAL-E, 19 Galois, 7 Zenou and Samuelides', 28 GRAND 25 and RULEARNER 27 which are based on a selection of the concepts directly, the CIBLe approach 21 which is based on object¯ltering and the CLNN and CLNB methods 34 where contextual rules are used.…”

Section: Introductionmentioning

confidence: 99%

Navigala: An Original Symbol Classifier Based on Navigation Through a Galois Lattice

Visani

Bertet

Ogier

2011

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

This paper deals with a supervised classification method, using Galois Lattices based on a navigation-based strategy. Coming from the field of data mining techniques, most literature on the subject using Galois lattices relies on selection-based strategies, which consists of selecting/choosing the concepts which encode the most relevant information from the huge amount of available data. Generally, the classification step is then processed by a classical classifier such as the k-nearest neighbors rule or the Bayesian classifier. Opposed to these selection-based strategies are navigation-based approaches which perform the classification stage by navigating through the complete lattice (similar to the navigation in a classification tree), without applying any selection operation. Our approach, named Navigala, proposes an original navigation-based approach for supervised classification, applied in the context of noisy symbol recognition. Based on a state of the art dealing with Galois Lattices classification based methods, including a comparison between possible selection and navigation strategies, this paper proposes a description of NAVIGALA and its implementation in the context of symbol recognition. Some objective quantitative and qualitative evaluations of the approach are proposed, in order to highlight the relevance of the method.

show abstract

Concept lattice based composite classifiers for high predictability

Cited by 19 publications

References 14 publications

On Algebraic Approach of R. Wille and B. Ganter in the Investigation of Texts

On Algebraic Approach of R. Wille and B. Ganter in the Investigation of Texts

Knowledge representation and processing with formal concept analysis

Navigala: An Original Symbol Classifier Based on Navigation Through a Galois Lattice

Contact Info

Product

Resources

About