Multiclass classification and gene selection with a stochastic algorithm
Microarray technology allows for the monitoring of thousands of gene expressions in various biological conditions, but most of these genes are irrelevant for classifying these conditions. Feature selection is consequently needed to help reduce the...
mehr
|
Microarray technology allows for the monitoring of thousands of gene expressions in various biological conditions, but most of these genes are irrelevant for classifying these conditions. Feature selection is consequently needed to help reduce the dimension of the variable space. Starting from the application of the stochastic meta algorithm ``Optimal Feature Weighting" (OFW) for selecting features in various classification problems, focus is made on the multiclass problem that wrapper methods rarely handle. From a computational point of view, one of the main difficulties comes from the commonly unbalanced classes situation when dealing with microarray data. From a theoretical point of view, very few methods have been developed to minimize any classification criterion, compared to the 2-class situation (e.g. SVM, lo SVM, RFE.). The OFW approach is developed to handle multiclass problems using CART and \textit{one-vs-one} SVM as classifiers. The results are then compared with those obtained with other multiclass selection algorithm (Random Forests and the filter method F-test), on five public microarray data sets with various complexities. Statistical relevancy of the results is assessed by measuring and comparing the performances of these different approaches. The aim of this study is to heuristically evaluate which method would be the best to select genes classifying the minority classes. Application and biological interpretation are then given in the case of a pig folliculogenesis study.
|
| Export in Literaturverwaltung |
|
On board in stormy weather : symbolism of psycho-physiological conditions in K. Munk’s sketch "Lette Bølge naar du blaaner"
In the article, a travel sketch of Danish playwright Kaj Munk (1898 – 1944) is analytically considered. The analysis of this text allows drawing at least three conclusions: 1. Explicit motive of seasickness, figuring here as antithetic modification...
mehr
|
Volltext:
|
|
|
Zitierfähiger Link:
|
|
|
In the article, a travel sketch of Danish playwright Kaj Munk (1898 – 1944) is analytically considered. The analysis of this text allows drawing at least three conclusions: 1. Explicit motive of seasickness, figuring here as antithetic modification of implicite present free-standing posture motive, symbolizes idea of disintegrating personality. 2. Such a symbolism is deeply rooted in that of Danish identity. 3. From literary styles and trends history point of view, the sketch appears to be typical of that line in expressionism, which continues tradition of symbolism as artistic and literary trend of late 19th century. ; BEI STURMWETTER AM BORD: Symbolik der psychophysiologischen Zustände in K. Munks "Reiseskizze Lette Bølge naar du blaaner". (Kurzfassung in Deutsch) Die in diesem Aufsatz vorgenommene Analyse einer von dem dänischen Bühnenschriftsteller K. Munk (1898 – 1944) geschriebenen Reiseskizze ermöglicht, wenigstens drei Schlussfolgerungen zu ziehen: 1. Explizites Seekrankheitsmotiv, die hier als antithetische Modifikation der implizit anwesenden Motivs der freistehenden Figur auftritt, versinnbildlicht in diesem Kontext die Idee der sich zerfallenden Persönlichkeit. 2. Diese Symbolik ist tief eingewurzelt im hergebrachten Sinnbildsystem der dänischen Identität. 3. Von dem Standpunkt der Stil- und Richtungsgeschichte aus betrachtet erscheint diese Reiseskizze als typisches Beispiel jener Linie in Expressionismus, die die Tradition des Symbolismus weiterentwickelt.
|
| Export in Literaturverwaltung |
|
Pre- and post-positioning of wenn-clauses in spoken and written German
This paper is concerned with the distinction between pre- and postpositioned (initial and final) wenn-clauses in German, and with the distinction between written and spoken language. A simple cross-tabulation of the two features [spoken/written] and...
mehr
|
This paper is concerned with the distinction between pre- and postpositioned (initial and final) wenn-clauses in German, and with the distinction between written and spoken language. A simple cross-tabulation of the two features [spoken/written] and [pre-/ postpositioned] (section 3) shows that initial wenn-clauses are preferred in spoken German, but final wenn-clauses are preferred in written German. These findings are in need of an explanation, which will be given in sections 4 and 5. Section 2 sketches the main characteristics of German wenn-clauses as compared to English conditional (if-) clauses. The findings and discussions in this paper are corpus-based. They are partly quantitative, partly qualitative. With respect to both dimensions, the claim is that a full understanding of the syntax of (particularly) spoken language eludes the possibilities of a purely introspective methodology. Of course, no (quantitative or qualitative) corpus-based investigation can do without a strong reliance on the analyst's knowledge ( intuition') about the language being researched; in fact, finding valid generalizations always involves Gedankenexperimente playing with structural changes in and recontextualizations of the examples' ; published
|
| Export in Literaturverwaltung |
|
