An Integration-Based Approach to Pattern Clustering and Classification

Sani, Laura; D’Addese, Gianluca; Pecori, Riccardo; Mordonini, Monica; Villani, Marco; Cagnoni, Stefano

doi:10.1007/978-3-030-03840-3_27

Cited by 5 publications

(3 citation statements)

References 12 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach still has some limitations [2]. First, the definition of the relevance index in Equation (1) is somehow empirical: the choice of dividing the integration by the mutual information is not based on any theory or any specific motivation.…”

Section: Integration As a Relevance Index Metricmentioning

confidence: 99%

“…Similar to the other metrics in the same family, its computation relies on the approximation of the statistical distribution of the variables based on the analysis of a sample of the system states observed over a given time interval, possibly in response to a previous perturbation. The higher the zI(V), the more relevant V [2].…”

Section: Introductionmentioning

confidence: 99%

“…The RI metrics have been applied to feature extraction [3], as well as to pattern clustering and classification [2] with promising preliminary results. In [2], one can find the first definition of the zI index, the metric that we used in this study.…”

mentioning

confidence: 99%

See 2 more Smart Citations

From Complex System Analysis to Pattern Recognition: Experimental Assessment of an Unsupervised Feature Extraction Method Based on the Relevance Index Metrics

et al. 2019

Self Cite

View full text Add to dashboard Cite

The so-called Relevance Index (RI) metrics are a set of recently-introduced indicators based on information theory principles that can be used to analyze complex systems by detecting the main interacting structures within them. Such structures can be described as subsets of the variables which describe the system status that are strongly statistically correlated with one another and mostly independent of the rest of the system. The goal of the work described in this paper is to apply the same principles to pattern recognition and check whether the RI metrics can also identify, in a high-dimensional feature space, attribute subsets from which it is possible to build new features which can be effectively used for classification. Preliminary results indicating that this is possible have been obtained using the RI metrics in a supervised way, i.e., by separately applying such metrics to homogeneous datasets comprising data instances which all belong to the same class, and iterating the procedure over all possible classes taken into consideration. In this work, we checked whether this would also be possible in a totally unsupervised way, i.e., by considering all data available at the same time, independently of the class to which they belong, under the hypothesis that the peculiarities of the variable sets that the RI metrics can identify correspond to the peculiarities by which data belonging to a certain class are distinguishable from data belonging to different classes. The results we obtained in experiments made with some publicly available real-world datasets show that, especially when coupled to tree-based classifiers, the performance of an RI metrics-based unsupervised feature extraction method can be comparable to or better than other classical supervised or unsupervised feature selection or extraction methods.

show abstract

Section: Integration As a Relevance Index Metricmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%