Centre de documentation
scientifique

CDPS: Constrained DTW-Preserving Shapelets / Hussein El Amouri (2023)  

Public Titre : CDPS: Constrained DTW-Preserving Shapelets Type de document : Article/Communication Auteurs : Hussein El Amouri, Auteur ; Thomas Lampert, Auteur ; Pierre Gançarski, Auteur ; Clément Mallet , Auteur Editeur : Berlin, Heidelberg, Vienne, New York, ... : Springer Année de publication : 2023 Collection : Lecture notes in Computer Science Sous-collection : Lecture Notes in Artificial Intelligence num. 13713 Projets : HIATUS / Giordano, Sébastien Conférence : ECML PKDD 2022, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 19/09/2022 23/09/2022 Grenoble France Proceedings Springer Projets : HERELLES / Gançarski, Pierre Importance : pp 21 - 37 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] analyse de données [Termes IGN] analyse de groupement [Termes IGN] classification [Termes IGN] déformation temporelle dynamique (algorithme) [Termes IGN] distance euclidienne [Termes IGN] jeu de données localisées [Termes IGN] série temporelle [Termes IGN] traitement de données localisées [Termes IGN] transformation Résumé : (auteur) The analysis of time series for clustering and classification is becoming ever more popular because of the increasingly ubiquitous nature of IoT, satellite constellations, and handheld and smart-wearable devices, etc. The presence of phase shift, differences in sample duration, and/or compression and dilation of a signal means that Euclidean distance is unsuitable in many cases. As such, several similarity measures specific to time-series have been proposed, Dynamic Time Warping (DTW) being the most popular. Nevertheless, DTW does not respect the axioms of a metric and therefore Learning DTW-Preserving Shapelets (LDPS) have been developed to regain these properties by using the concept of shapelet transform. LDPS learns an unsupervised representation that models DTW distances using Euclidean distance in shapelet space. This article proposes constrained DTW-preserving shapelets (CDPS), in which a limited amount of user knowledge is available in the form of must link and cannot link constraints, to guide the representation such that it better captures the user’s interpretation of the data rather than the algorithm’s bias. Subsequently, any unconstrained algorithm can be applied, e.g. K-means clustering, k-NN classification, etc, to obtain a result that fulfils the constraints (without explicit knowledge of them). Furthermore, this representation is generalisable to out-of-sample data, overcoming the limitations of standard transductive constrained-clustering algorithms. CLDPS is shown to outperform the state-of-the-art constrained-clustering algorithms on multiple time-series datasets. Numéro de notice : C2022-052 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : GEOMATIQUE/INFORMATIQUE/MATHEMATIQUE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1007/978-3-031-26387-3_2 Date de publication en ligne : 17/03/2023 En ligne : https://doi.org/10.1007/978-3-031-26387-3_2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103157