CID: an efficient complexity-invariant distance for time series

The ubiquity of time series data across almost all human endeavors has produced a great interest in time series data mining in the last decade. While dozens of classification algorithms have been applied to time series, recent empirical evidence strongly suggests that simple nearest neighbor classification is exceptionally difficult to beat. The choice of distance measure used by the nearest neighbor algorithm is important, and depends on the invariances required by the domain. For example, motion capture data typically requires invariance to warping, and cardiology data requires invariance to the baseline (the mean value). Similarly, recent work suggests that for time series clustering, the choice of clustering algorithm is much less important than the choice of distance measure used.In this work we make a somewhat surprising claim. There is an invariance that the community seems to have missed, complexity invariance. Intuitively, the problem is that in many domains the different classes may have different complexities, and pairs of complex objects, even those which subjectively may seem very similar to the human eye, tend to be further apart under current distance measures than pairs of simple objects. This fact introduces errors in nearest neighbor classification, where some complex objects may be incorrectly assigned to a simpler class. Similarly, for clustering this effect can introduce errors by “suggesting” to the clustering algorithm that subjectively similar, but complex objects belong in a sparser and larger diameter cluster than is truly warranted.We introduce the first complexity-invariant distance measure for time series, and show that it generally produces significant improvements in classification and clustering accuracy. We further show that this improvement does not compromise efficiency, since we can lower bound the measure and use a modification of triangular inequality, thus making use of most existing indexing and data mining algorithms. We evaluate our ideas with the largest and most comprehensive set of time series mining experiments ever attempted in a single work, and show that complexity-invariant distance measures can produce improvements in classification and clustering in the vast majority of cases.

Las terrazas del rio Miño en el tramo Chantada-As Neves (límite de Galicia Portugal)

[ES] La cartografía geomorfológica es especialmente difícil en áreas con depósitos escasos, poco significativos y de cronología incierta,con formas multiedad y multiorigen. Tal es el caso de Galicia. Este trabajo es un intento de reconstruir la historia geomorfológica de Galicia durante el Cenozoico en un área especialmente relevante por su situación geodinámica. Se ha hecho un inventario exhaustivo de los niveles de terrazas erosivas y de acumulación en un tramo específico, por sus características morfológicas del curso principal del río Miño. Se presentan aquí los sistemas de terrazas entre Chantada y As Neves y se relacionan con las tres superficies de corrosión química (etched surfaces) más relevantes en la zona: R800, R600 y R400. Se analiza también su relación con el perfil longitudinal del río. Utilizando los únicos criterios existentes (continuidad topográfica y altitud), se propone para el sector estudiado un modelo evolutivo esencialmente determinado por la incisión fluvial asociada a la colisión entre la Placa Euroasiática y la Ibérica durante el Paleógeno y que geomorfológicamente se inicia a partir de la formación del aplanamiento R600, equivalente en Galicia a la Superficie Fundamental Peninsular.

Mio-pliocene crustaceans from the Canary Islands, Spain

[EN] There are few previous references to fossil crustaceans for the Neogene marine layers of the Canary Islands (Spain). The Mio-Pliocene marine sedimentary layers in the eastern islands (Gran Canaria, Fuerteventura and Lanzarote) were previously characterised by the presence of numerous fossil fauna, mainly anthozoans and molluscs, which correspond to an equatorial-typepalaeoclimate, warmer than the present climate. This Mio-Pliocene transition dated between 9.3 and 4.1 Ma. In this paper, 12 fossil crustacean taxa are identified and classified, including decapods and barnacles: Balanus concavus Bronn, 1831, Balanus spongicola Brown, 1827, Balanus perforatus Bruguière, 1789, Chenolobia testudinaria Linnè, 1767, Tetraclita cf. rubescens Darwin, 1854, Callianassa matsoni Rathbun, 1935, Callianassa sp., Upogebia sp, Eriphia aff. verrucosa (Forskal, 1775) , Maja sp., Scylla michelini Milne-Edwards, 1861 and Ocypode sp. [...]

Lazaru Belelē Hoi mnēsteres tēs en tō Ethnikō Panepistēmio edras tes Ebrai͏̈kēs : elenchos tōn hypoblētheisōn diatribōn

In griech. Schr.

Maria Malibran, Hüftbild : il mio soggiorno in Venezia, forma per me un' epoca faustissima di mia vita, 31. Marzo 1835

Signatur des Originals: S 36/G04629

Giuseppina Strepponi als Nina, Rollenbild, Hüftbild, in: Giovanni Paisiello: Nina o sia la pazza per amore : Nina: T'amo, fu il primo accento Che disse a te il mio core,

Signatur des Originals: S 36/G04409

Le Cid : tragédie

par P. Corneille. Mit grammatikalischen Regeln ... bearb. von Georg Kißling ...

Maríateresa Fumagalli Beonio Brocchieri. Tres historias góticas. Ideas y hombres de la Edad Media, trad. Gustavo Fernández Walker, Colección Lejos y Cerca, Miño y Dávila editores, Buenos Aires, 2006. ISBN-13: 978-84-96571-28-0. 112 págs.

Fil: Peretó Rivas, Rubén.

Azucena Adelina Fraboschi, Bajo la mirada de Hildegarda, abadesa de Bingen, Miño y Dávila editores, Buenos Aires-Argentina, 2010, ISBN: 978-84-92613-44-1, 271 p.

Fil: Benavides, Cristian.