Les outils de l’analyse en ligne (OLAP) permettent à l’utilisateur de
réaliser des tâches explora... more Les outils de l’analyse en ligne (OLAP) permettent à l’utilisateur de réaliser des tâches exploratoires dans les cubes de données. Cependant, ils n’offrent aucun moyen pour la prédiction ou l’explication des faits. En vue de renforcer le processus de l’aide à la décision, plusieurs travaux ont proposé l’extension de l’analyse en ligne à des capacités plus avancées. Dans cet article, nous pro- posons une nouvelle approche d’extension de l’analyse en ligne à des capacités de prédiction à deux phases. La première est une phase de réduction des dimen- sions des cubes de données, qui repose sur l’analyse en composantes principales (ACP). La deuxième est une phase de prédiction dans laquelle nous introdui- sons une nouvelle architecture de percéptrons multicouches (PMC). Notre étude expérimentale a montré une capacité de prédiction prometteuse, ainsi qu’une bonne robustesse dans le cas d’un cube épars.
On-line Analytical Processing (OLAP) represents a good applications package to explore and naviga... more On-line Analytical Processing (OLAP) represents a good applications package to explore and navigate into data cubes. Though, it is limited to exploratory tasks. It does not assist the decision maker in performing information investigation. Thus, various studies have been trying to extend OLAP to new capabilities by coupling it with data mining algorithms. Our current proposal stands within this trend. It has two major contributions. First, a Multi-perspectives Cube Exploration Framework (MCEF) is introduced. It is a generalized framework designed to assist the application of classical data mining algorithm on OLAP cubes. Second, a Neural Approach for Prediction over High-dimensional Cubes (NAP-HC) is also introduced, which extends Modular Neural Networks (MNN)s architecture to multidimensional context of OLAP cubes, to predict non-existent measures. A preprocessing stage is embedded in NAP-HC to assist it in facing up the challenges arising from the particu-larity of OLAP cubes. It consists of an OLAP oriented cube exploration strategy coupled with a dimensions reduction step that reposes on the Principal Component Analysis (PCA). Carried out experiments highlight the efficiency of MCEF in assisting the application of MNNs on OLAP cubes and the high predictive capabilities of NAP-HC.
OLAP techniques provide efficient solutions to navigate through
data cubes. However, they are not... more OLAP techniques provide efficient solutions to navigate through data cubes. However, they are not equipped with frameworks that empower user investigation of interesting information. They are restricted to exploration tasks. Recently, various studies have been trying to extend OLAP to new capabilities by coupling it with data mining algorithms. However, most of these algorithms are not designed to deal with sparsity, which is an unavoidable consequence of the multidimensional structure of OLAP cubes. In [1], we proposed a novel approach that embeds Multilayer Perceptrons into OLAP environment to extend it to prediction. This approach has largely met its goals with limited sparsity cubes. However, its performances have decreased progressively with the increase of cube sparsity. In this paper, we propose a substantially modified version of our previous approach called NAP-SC (Neural Approach for Prediction over Sparse Cubes). Its main contribution consists in minimizing sparsity effect on measures prediction process through the application of a cube transformation step, based on a dedicated aggregation technique. Carried out experiments demonstrate the effectiveness and the robustness of NAP-SC against high sparsity data cubes.
The steady growth in the size of data has encouraged the emergence of advanced main memory trie-b... more The steady growth in the size of data has encouraged the emergence of advanced main memory trie-based data structures. Concurrently, more acute knowledge extraction techniques are devised for the discovery of compact and lossless knowledge formally expressed by generic bases. In this paper, we present an approach for deriving generic bases of association rules. Using this approach, we construct small partially ordered sub-structures. Then, these ordered sub-structures are parsed to derive, in a straightforward manner, local generic association bases. Finally, local bases are merged to generate the global one. Extensive experiments carried out essentially showed that the proposed data structure allows to generate a more compact representation of an extraction context comparatively to existing approaches in literature.
Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569), 2000
... The function Gen-next takes as argument the set of fuzzy concepts FC; and computes the set CF... more ... The function Gen-next takes as argument the set of fuzzy concepts FC; and computes the set CFCi+l containing all (i + 1)-fuzzy itemsets, which will be used as fuzzy generators, during the next its-eration. Function Gen-next Input : CFi Begin CFCi+l = Apriori-Gen(CFi) 1 ...
Les outils de l’analyse en ligne (OLAP) permettent à l’utilisateur de
réaliser des tâches explora... more Les outils de l’analyse en ligne (OLAP) permettent à l’utilisateur de réaliser des tâches exploratoires dans les cubes de données. Cependant, ils n’offrent aucun moyen pour la prédiction ou l’explication des faits. En vue de renforcer le processus de l’aide à la décision, plusieurs travaux ont proposé l’extension de l’analyse en ligne à des capacités plus avancées. Dans cet article, nous pro- posons une nouvelle approche d’extension de l’analyse en ligne à des capacités de prédiction à deux phases. La première est une phase de réduction des dimen- sions des cubes de données, qui repose sur l’analyse en composantes principales (ACP). La deuxième est une phase de prédiction dans laquelle nous introdui- sons une nouvelle architecture de percéptrons multicouches (PMC). Notre étude expérimentale a montré une capacité de prédiction prometteuse, ainsi qu’une bonne robustesse dans le cas d’un cube épars.
On-line Analytical Processing (OLAP) represents a good applications package to explore and naviga... more On-line Analytical Processing (OLAP) represents a good applications package to explore and navigate into data cubes. Though, it is limited to exploratory tasks. It does not assist the decision maker in performing information investigation. Thus, various studies have been trying to extend OLAP to new capabilities by coupling it with data mining algorithms. Our current proposal stands within this trend. It has two major contributions. First, a Multi-perspectives Cube Exploration Framework (MCEF) is introduced. It is a generalized framework designed to assist the application of classical data mining algorithm on OLAP cubes. Second, a Neural Approach for Prediction over High-dimensional Cubes (NAP-HC) is also introduced, which extends Modular Neural Networks (MNN)s architecture to multidimensional context of OLAP cubes, to predict non-existent measures. A preprocessing stage is embedded in NAP-HC to assist it in facing up the challenges arising from the particu-larity of OLAP cubes. It consists of an OLAP oriented cube exploration strategy coupled with a dimensions reduction step that reposes on the Principal Component Analysis (PCA). Carried out experiments highlight the efficiency of MCEF in assisting the application of MNNs on OLAP cubes and the high predictive capabilities of NAP-HC.
OLAP techniques provide efficient solutions to navigate through
data cubes. However, they are not... more OLAP techniques provide efficient solutions to navigate through data cubes. However, they are not equipped with frameworks that empower user investigation of interesting information. They are restricted to exploration tasks. Recently, various studies have been trying to extend OLAP to new capabilities by coupling it with data mining algorithms. However, most of these algorithms are not designed to deal with sparsity, which is an unavoidable consequence of the multidimensional structure of OLAP cubes. In [1], we proposed a novel approach that embeds Multilayer Perceptrons into OLAP environment to extend it to prediction. This approach has largely met its goals with limited sparsity cubes. However, its performances have decreased progressively with the increase of cube sparsity. In this paper, we propose a substantially modified version of our previous approach called NAP-SC (Neural Approach for Prediction over Sparse Cubes). Its main contribution consists in minimizing sparsity effect on measures prediction process through the application of a cube transformation step, based on a dedicated aggregation technique. Carried out experiments demonstrate the effectiveness and the robustness of NAP-SC against high sparsity data cubes.
The steady growth in the size of data has encouraged the emergence of advanced main memory trie-b... more The steady growth in the size of data has encouraged the emergence of advanced main memory trie-based data structures. Concurrently, more acute knowledge extraction techniques are devised for the discovery of compact and lossless knowledge formally expressed by generic bases. In this paper, we present an approach for deriving generic bases of association rules. Using this approach, we construct small partially ordered sub-structures. Then, these ordered sub-structures are parsed to derive, in a straightforward manner, local generic association bases. Finally, local bases are merged to generate the global one. Extensive experiments carried out essentially showed that the proposed data structure allows to generate a more compact representation of an extraction context comparatively to existing approaches in literature.
Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Cat. No. 01TH8569), 2000
... The function Gen-next takes as argument the set of fuzzy concepts FC; and computes the set CF... more ... The function Gen-next takes as argument the set of fuzzy concepts FC; and computes the set CFCi+l containing all (i + 1)-fuzzy itemsets, which will be used as fuzzy generators, during the next its-eration. Function Gen-next Input : CFi Begin CFCi+l = Apriori-Gen(CFi) 1 ...
Uploads
réaliser des tâches exploratoires dans les cubes de données. Cependant, ils n’offrent
aucun moyen pour la prédiction ou l’explication des faits. En vue de renforcer
le processus de l’aide à la décision, plusieurs travaux ont proposé l’extension
de l’analyse en ligne à des capacités plus avancées. Dans cet article, nous pro-
posons une nouvelle approche d’extension de l’analyse en ligne à des capacités
de prédiction à deux phases. La première est une phase de réduction des dimen-
sions des cubes de données, qui repose sur l’analyse en composantes principales
(ACP). La deuxième est une phase de prédiction dans laquelle nous introdui-
sons une nouvelle architecture de percéptrons multicouches (PMC). Notre étude
expérimentale a montré une capacité de prédiction prometteuse, ainsi qu’une
bonne robustesse dans le cas d’un cube épars.
data cubes. However, they are not equipped with frameworks that empower
user investigation of interesting information. They are restricted
to exploration tasks.
Recently, various studies have been trying to extend OLAP to new capabilities
by coupling it with data mining algorithms. However, most of
these algorithms are not designed to deal with sparsity, which is an unavoidable
consequence of the multidimensional structure of OLAP cubes.
In [1], we proposed a novel approach that embeds Multilayer Perceptrons
into OLAP environment to extend it to prediction. This approach has
largely met its goals with limited sparsity cubes. However, its performances
have decreased progressively with the increase of cube sparsity.
In this paper, we propose a substantially modified version of our previous
approach called NAP-SC (Neural Approach for Prediction over Sparse
Cubes). Its main contribution consists in minimizing sparsity effect on
measures prediction process through the application of a cube transformation
step, based on a dedicated aggregation technique.
Carried out experiments demonstrate the effectiveness and the robustness
of NAP-SC against high sparsity data cubes.
réaliser des tâches exploratoires dans les cubes de données. Cependant, ils n’offrent
aucun moyen pour la prédiction ou l’explication des faits. En vue de renforcer
le processus de l’aide à la décision, plusieurs travaux ont proposé l’extension
de l’analyse en ligne à des capacités plus avancées. Dans cet article, nous pro-
posons une nouvelle approche d’extension de l’analyse en ligne à des capacités
de prédiction à deux phases. La première est une phase de réduction des dimen-
sions des cubes de données, qui repose sur l’analyse en composantes principales
(ACP). La deuxième est une phase de prédiction dans laquelle nous introdui-
sons une nouvelle architecture de percéptrons multicouches (PMC). Notre étude
expérimentale a montré une capacité de prédiction prometteuse, ainsi qu’une
bonne robustesse dans le cas d’un cube épars.
data cubes. However, they are not equipped with frameworks that empower
user investigation of interesting information. They are restricted
to exploration tasks.
Recently, various studies have been trying to extend OLAP to new capabilities
by coupling it with data mining algorithms. However, most of
these algorithms are not designed to deal with sparsity, which is an unavoidable
consequence of the multidimensional structure of OLAP cubes.
In [1], we proposed a novel approach that embeds Multilayer Perceptrons
into OLAP environment to extend it to prediction. This approach has
largely met its goals with limited sparsity cubes. However, its performances
have decreased progressively with the increase of cube sparsity.
In this paper, we propose a substantially modified version of our previous
approach called NAP-SC (Neural Approach for Prediction over Sparse
Cubes). Its main contribution consists in minimizing sparsity effect on
measures prediction process through the application of a cube transformation
step, based on a dedicated aggregation technique.
Carried out experiments demonstrate the effectiveness and the robustness
of NAP-SC against high sparsity data cubes.