Scalable Estimates of Concept Stability

The Quality issues, measures of interestingness and evaluation of data mining models Workshop (QIMIE'09) focuses on the theory, the techniques and the practices that can ensure that the discovered knowledge of a datamining process is of quality. This first edition of QIMIE'09 is organized in association with PAKDD'09 conference (, the QIMIE'09 Web master (Philippe Tanguy from Telecom Bretagne).

2014

Abstract. It is a common issue thatKdd processes may generate a large number of patterns depending on the algorithm used, and its parameters. It is hence impossible for an expert to sustain these patterns. This is the case with the well-known Apriori algorithm. One of the methods used to cope with such an amount of output depends on the use of associa-tion rule interestingness measures. Stating that selecting interesting rules also means using an adapted measure, we present a formal and an exper-imental study of 20 measures. The experimental studies carried out on 10 datasets lead to an experimental classification of the measures. This study is compared to an analysis of the formal and meaningful properties of the measures. Last, the properties are used in a multi-criteria deci-sion analysis in order to select amongst the available measures the one or those that best take into account the user’s needs. These approaches seem to be complementary and could be profitable for the problem...

First International Conference on Networks & Soft Computing (ICNSC), 2014, 2014

The difficult job in association rules is to identify the frequent item sets immersed into the huge collection of data. The association rules can be discovered using Formal Concept Analysis (FCA). Several contexts often contain large number of rules and hence interesting rules are required to be determined. With this objective, this paper proposes a method for determining interesting rules in FCA involving many-valued contexts based on Shannon's information entropy (IE) theory. For this purpose we define a gain_lift measure on association rules. The proposed method is illustrated by means of an example available from the field of medical diagnosis.

2009

This thesis would not be possible without the support of many individuals, to whom I would like to express my gratitude. I will always be indebted to my supervisors, Prof. Fakhri Karray and Prof. Mohamed Kamel, for their support, encouragement, guidance, and most importantly trust. Prof. Karray's trust and support was instrumental in giving me confidence to achieve many accomplishments. I would like to thank Prof. Karray for his encouragement and guidance throughout my research. Prof. Kamel's input and guidance was invaluable to the quality and contribution of the work presented in this thesis, as well as in other publications. I would like to thank Prof. Kamel for his advice, valuable insights and feedback throughout my research. Without them this research would not have been possible. I would like also to thank many faculty members of the University of Waterloo, most notably my committee members, Prof. Chrysanne DiMarco, Prof. Krzysztof Czarnecki and Prof. Kostas Kontogiannis for their valuable input and suggestions.

2010

Concept lattices built on noisy data tend to be large and hence hard to interpret. We introduce several measures that can be used in selecting relevant concepts and discuss how they can be combined together. We study their performance in a series of experiments.

Information Sciences, 2018

Formal concepts and closed itemsets proved to be of big importance for knowledge discovery, both as a tool for concise representation of association rules and a tool for clustering and constructing domain taxonomies and ontologies. Exponential explosion makes it difficult to consider the whole concept lattice arising from data, one needs to select most useful and interesting concepts. In this paper interestingness measures of concepts are considered and compared with respect to various aspects, such as efficiency of computation and applicability to noisy data and performing ranking correlation.

Lecture Notes in Computer Science, 2011

The field of association rule mining has long been dominated by algorithms that search for patterns based on their frequency of occurrence in a given dataset. The birth of weighted association rule mining caused a fundamental paradigm shift in the way that patterns are identified. Consideration was given to the "importance" of an item in addition to its frequency of occurrence. In this research we propose a novel measure which we term Discriminatory Confidence that identifies the extent to which a given item can segment a dataset in a meaningful manner. We devise an efficient algorithm which is driven by an Information Scoring model that identifies items with high discriminatory power. We compare our results with the classical approach to association rule mining and show that the Information Scoring model produces widely divergent results. Our research reveals that mining on the basis of frequency alone tends to exclude some of the most informative patterns that are discovered using discriminatory power.

Lecture Notes in Computer Science

The paper presents a clustering method which can be applied to populated ontologies for discovering interesting groupings of resources therein. The method exploits a simple, yet effective and language-independent, semi-distance measure for individuals, that is based on their underlying semantics along with a number of dimensions corresponding to a set of concept descriptions (discriminating features committee). The clustering algorithm is a partitional method and it is based on the notion of medoids w.r.t. the adopted semi-distance measure. Eventually, it produces a hierarchical organization of groups of individuals. A final experiment demonstrates the validity of the approach using absolute quality indices. We propose two possible exploitations of these clusterings: concept formation and detecting concept drift or novelty.

International Journal of General Systems, 2018

The effective use of the concept lattice in large datasets has been always limited by the large volume of extracted knowledge. The stability measure has been shown to be of valuable help for knowledge selection. In this paper, we introduce the SC-MG algorithm to efficiently compute both types of stability, i.e. extensional and intensional. The guiding idea is to exploit the relationship between stability and minimal generators in order to compute both measures. The performed experiments show the efficiency of the SC-MG algorithm. In addition, it sharply outperforms the pioneering approaches of the literature.

J. Netw. Intell., 2018

In recent years, concept drift has become a popular research topic in data mining because of its wide range of practical applications. Concept drift discusses the significant change of concepts along with time or location movement. It can thus be used to derive the purchasing behavior of customers from a database at different times or locations. In the past, most of the research focuses on concept drift from traditional transaction databases. However, quantities of purchased items usually exist in databases and can provide more information in concept drift. In this paper, we integrate fuzzy data mining with concept drift and generalize the similarity measures for achieving the purpose. These measures are used for defining fuzzy concept-drift patterns derived from quantitative transaction databases at different time. The proposed approach can thus fully utilize the results from fuzzy mining and provide effective information about customers behavior change to managers for tuning the b...