, considérons les 7 jours de la semaine indépendamment. Nous disposons alors de 7 variables séquentielles X 1
, agit de partitionner le domaine temporel en intervalles successifs et de considérer la moyenne des mesures sur chaque intervalle. Là encore, cela permet de réduire la dimensionalité de la variable séquentielle tout en synthétisant l'information. Le travail décrit ici l'est au titre de perspectives avancées. Il n'a pas donné lieu à une implantation ou été soumis à des expérimentations. L'objectif est de montrer que notre démarche est générique et se
, Unsupervised Curve Clustering using B-Splines, Scandinavian Journal of Statistics, vol.78, issue.3, pp.581-595, 2003.
DOI : 10.1111/1467-9469.00350
, Mining sequential patterns Efficient similarity search in sequence databases Mining association rules between sets of items in large databases Fast similarity search in the presence of noise, scaling, and translation in time-series databases Querying shapes of histories Instance-based learning algorithms, Proceedings of the 4th international conference of foundations of data organization and algorithms (FODO) Proceedings of the ACM SIGMOD conference on management of data Twenty-first international conference on very large data bases Twenty-first international conference on very large databases (VLDB '95), pp.3-14, 1991.
, MDL and MML : similarities and differences (introduction to minimum encoding inference -part iii), 1994.
, Bayesian theory, 2000.
DOI : 10.1002/9780470316870
, Finding patterns in time series : a dynamic programming approach Advances Knowledge Discovery Data Mining Similarity-based clustering of sequences using hidden markov models, Bibliographie Machine learning and data mining in pattern recognition, pp.86-97, 1996.
, UCI repository of machine learning databases, 1996.
, Selection of relevant features and examples in machine learning Optimal bayesian 2D-discretization for variable ranking in regression A bayes optimal approach for partitioning the values of categorical attributes MODL : a bayes optimal discretization method for continuous attributes Time series analysis, forecasting and control, Ninth international conference on discovery science, pp.245-271, 1994.
, Advances in instance selection for instance-based learning algorithms, Data Mining and Knowledge Discovery, vol.6, issue.2, pp.153-172, 2002.
DOI : 10.1023/A:1014043630878
, A general probabilistic framework for clustering individuals and objects, Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining , KDD '00, pp.140-149, 2000.
DOI : 10.1145/347090.347119
, Instance selection by encoding length heuristic with random mutation hill climbing Machine learning with data dependent hypothesis classes, Proceedings of the eighth australian joint conference on artificial intelligence, pp.99-106335, 1995.
, Efficient time series matching by wavelets Finding prototypes for nearest neighbor classifiers CRISP-DM 1.0 : step-by-step data mining guide Modélisation supervisée de données fonctionnelles par perceptron muli-couches, IEEE Transactions on Computers, vol.23, issue.13, pp.126-1331179, 1967.
, Rule discovery from time series A probabilistic theory of pattern recognition, Knowledge Discovery and Data Mining, pp.16-22, 1996.
, Supervised and Unsupervised Discretization of Continuous Features, International conference on machine learning, pp.194-202, 1995.
DOI : 10.1016/B978-1-55860-377-6.50032-3
, Knowledge discovery and data mining : towards a unifying framework, KDD, pp.82-88, 1996.
, Utilisation des graphes de proximité dans le cadre de l'apprentissage basé sur les voisins, Actes des 4èmes journées francophones extraction et gestion des connaissances Cépaduès-Editions, pp.355-366, 2004.
, Multivariate Discretization by Recursive Supervised Bipartition of Graph, Machine learning and data mining in pattern recognition, pp.253-264, 2005.
DOI : 10.1007/11510888_25
URL : https://hal.archives-ouvertes.fr/hal-00324795
, Supervised Evaluation of Dataset Partitions: Advantages and Practice, Machine learning and data mining in pattern recognition, pp.600-609, 2005.
DOI : 10.1007/11510888_59
URL : https://hal.archives-ouvertes.fr/hal-00324794
, Efficient instance selection for the nearest neighbor rule, Machine learning, 2006.
, Illustration d'une méthode d'évaluation supervisée par un problème de classification de courbes, Actes des 13èmes rencontres de la société francophone de classification, 2006.
, Sélection supervisée d'instances : une approche descriptive, Actes des 6èmes journées francophones extraction et gestion des connaissances (EGC'06), pp.421-432, 2006.
, Supervised evaluation of voronoi partitions, Journal of intelligent data analysis, vol.10, issue.3, pp.269-284, 2006.
URL : https://hal.archives-ouvertes.fr/hal-00324793
, Supervised Selection of Dynamic Features, with an Application to Telecommunication Data Preparation, Proceedings of the 6 th industrial conference on data mining, 2006.
DOI : 10.1007/11790853_19
URL : https://hal.archives-ouvertes.fr/hal-00324796
, THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS, Annals of Eugenics, vol.59, issue.2, pp.179-188, 1936.
DOI : 10.1111/j.1469-1809.1936.tb02137.x
, Discriminatory Analysis. Nonparametric Discrimination: Consistency Properties, International Statistical Review / Revue Internationale de Statistique, vol.57, issue.3, 1951.
DOI : 10.2307/1403797
, The reduced nearest neighbor rule, Gavrilov et al., 2000 ] M. Gavrilov, D. Anguelov, P. Indyk, and R. Motwani. Mining the stock market : which measure is best ? In Knowledge discovery in databases, pp.431-433, 1972.
, Deformable Markov model templates for time-series pattern matching, Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining , KDD '00, pp.81-90, 2000.
DOI : 10.1145/347090.347109
, Noisy time series prediction using a recurrent neural network and grammatical inference, Machine Learning, pp.161-183, 2001.
, Séries temporelles et modèles dynamiques Advances in minimum description length : theory and applications Event detection from time series data, Guralnik and Srivastava Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining, pp.33-42, 1995.
, An introduction to variable and feature selection Features extraction : foundations and applications Data mining : statistics and more ? The American Statistician, Journal of machine learning research, vol.3, issue.522, pp.1157-1182112, 1998.
, Variable neighborhood search: Principles and applications, European Journal of Operational Research, vol.130, issue.3, pp.449-467, 2001.
DOI : 10.1016/S0377-2217(00)00100-4
, Model Selection and the Principle of Minimum Description Length, Journal of the American Statistical Association, vol.96, issue.454, pp.746-774515, 1968.
DOI : 10.1198/016214501753168398
, The elements of statistical learning Représentation symbolique de longues séries temporelles Generalized linear models with functional predictors Relative neighborhood graphs and their relatives Kaddous and C. Sammut. Classification of multivariate time series and structured data using constructive induction, Jaromczyk and Toussaint, pp.411-4321502, 1992.
, An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback, Fourth international conference on knowledge discovery and data mining (KDD'98), pp.239-241, 1998.
, Scaling up Dynamic Time Warping to Massive Datasets, 3rd European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD'99), pp.1-11, 1999.
DOI : 10.1007/978-3-540-48247-5_1
, A probabilistic approach to fast pattern matching in time series databases, Third international conference on knowledge discovery and data mining, pp.24-30, 1997.
, Wrappers for feature subset selection, Artificial Intelligence, vol.97, issue.1-2, pp.273-324, 1997.
DOI : 10.1016/S0004-3702(97)00043-X
, Error-based and entropy-based discretization of continuous features Self-organizing maps, KDD ] A.D. Lanterman. Schwarz, Wallace, and Rissanen : intertwining themes in theories of model selection. International statistical review, pp.114-119185, 1996.
, An introduction to Kolmogorov complexity and its applications A bayesian approach to temporal data clustering using the hidden markov model methodology [ MacQueen, 1967 ] J. MacQueen. Some methods for classification and analysis of multivariate observations, Fifth Berkeley Symposium on Mathematical Statistics and Probability, pp.281-297, 1967.
, MML and bayesianism : similarities and differences (introduction to minimum encoding inference -part ii), 1994.
, Introduction to minimum encoding inference Department of computer science, Monash university, 1994. [ Pavlidis, 1974 ] T. Pavlidis. Waveform segmentation through functional approximation, IEEE Trans. Comp, issue.7, pp.22689-697, 1974.
, Computational geometry : an introduction, 1986.
DOI : 10.1007/978-1-4612-1098-6
, Supporting fast search in time series for movement patterns in multiple scales, Proceedings of the seventh international conference on Information and knowledge management , CIKM '98, pp.251-258, 1998.
DOI : 10.1145/288627.288664
, Inferring decision trees using the minimum description lenght principle, Proceedings of the IEEE, pp.227-248257, 1989.
DOI : 10.1016/0890-5401(89)90010-2
, Functional data analysis, 1997.
, Modeling by shortest data description, Rissanen, 1989 ] J. Rissanen. Stochastic complexity in statistical inquiry, pp.465-471, 1978.
DOI : 10.1016/0005-1098(78)90005-5
, Clustering functional data with the SOM algorithm [ Salzberg, 1991 ] S. Salzberg. A nearest hyperrectangle learning method Learning with kernels : support vector machines, regularization, optimization, and beyond Estimating the dimension of a model, Proceedings of the ESANN Probabilités et analyse des données statistiques. Technip Scholkopf and Smola, pp.305-312277, 1978.
, Stopping criterion for boostingbased data reduction techniques : from binary to multiclass problem A mathematical theory of communication, systems technical journal, pp.863-885, 1948.
, Item sets that compress Discriminative clustering : optimal contingency tables by learning metrics Agglomerative information bottleneck Clustering sequences with hidden markov models, SIAM Conference on data mining Proceedings of the 13 th european conference on machine learning Slonim and Tishby Proceedings of neural information processing system Advances in neural information processing systems, pp.393-404, 1997.
, Probabilistic model-based clustering of multivariate and sequential data Proceedings of artificial intelligence and statistics A formal theory of inductive inference, I and II. Information and control On solving ill-posed problem and method of regularization Le grand fossé, The nature of statistical learning theory, pp.299-3041, 1963.
, Minimum description length induction, Bayesianism, and Kolmogorov complexity, IEEE Transactions on Information Theory, vol.46, issue.2, pp.446-464, 2000.
DOI : 10.1109/18.825807
, An information measure for classification An experimental comparison of the nearest neighbor and nearest hyperrectangle algorithms, Wettschereck and Dietterich, pp.185-1945, 1968.
, Improved heterogeneous distance functions, Journal of artificial intelligence research, vol.6, issue.1, pp.1-34, 1997.
, Instance pruning techniques, Proceedings of the 14 th international conference on machine learning, pp.403-411, 1997.
, Asymptotic properties of nearest neighbor rules using edited data A decision-theoretic extension of stochastic complexity and its applications to learning, IEEE Transactions on systems, man and cybernetics IEEE Transactions on Information Theory, vol.2, issue.444, pp.408-4211424, 1972.
, Efficient retrieval of similar time sequences under time warping, ICDE, pp.201-208, 1998.