Learn More
We introduce novel profile-based string kernels for use with support vector machines (SVMs) for the problems of protein classification and remote homology detection. These kernels use probabilistic profiles, such as those produced by the PSI-BLAST algorithm, to define position-dependent mutation neighborhoods along protein sequences for inexact matching of(More)
Predicting a protein’s structural class from its amino acid sequence is a fundamental problem in computational biology. Recent machine learning work in this domain has focused on developing new input space representations for protein sequences, that is, string kernels, some of which give state-of-the-art performance for the binary prediction task of(More)
In content-based audio retrieval, the goal is to find sound recordings (audio documents) based on their acoustic features. This content-based approach differs from retrieval approaches that index media files using metadata such as file names and user tags. In this paper, we propose a machine learning approach for retrieving sounds that is novel in that it(More)
We develop a novel multi-class classification method based on <i>output codes</i> for the problem of classifying a sequence of amino acids into one of many known protein structural classes, called <i>folds.</i> Our method learns relative weights between one-vs-all classifiers and encodes information about the protein structural hierarchy for multi-class(More)
  • E Rt A N Sm A N N, M At, +11 authors E R Sc H U L Z
  • 2009
Lifting of dust particles by dust devils and convective plumes may significantly contribute to the global mineral dust budget. During the Saharan Mineral Dust Experiment (SAMUM) in May–June 2006 vertical profiling of dusty plumes was performed for the first time. Polarization lidar observations taken at Ouarzazate (30.9◦N, 6.9◦W, 1133 m height above sea(More)
Predicting a protein's structural class from its amino acid sequence is a fundamental problem in computational biology. Much recent work has focused on developing new representations for protein sequences, called string kernels, for use with support vector machine (SVM) classifiers. However, while some of these approaches exhibit state-of-the-art(More)
  • Pe T E R K N Ippe Rt Z, E Rt A N Sm A N N, +21 authors Ina T E G E N
  • 2009
The SAMUM field campaign in southern Morocco in May/June 2006 provides valuable data to study the emission, and the horizontal and vertical transports of mineral dust in the Northern Sahara. Radiosonde and lidar observations show differential advection of air masses with different characteristics during stable nighttime conditions and up to 5-km deep(More)
  • E Ik, E B Ie, +23 authors R A L Ph K A H N
  • 2009
By EIK E B IERW IRTH 1,6,7∗, M A N FR ED W EN D ISC H 1,6, A N D R É EH R LIC H 1,6, B IR G IT H EESE 1,2, M ATTH IA S TESC H E 1, D IETR IC H A LTH AU SEN 1, A LEX A N D ER SC H LA D ITZ 1, D ETLEF M Ü LLER 1, SEBA STIA N OTTO 3, TH O M A S TR AU TM A N N 3, TILM A N D IN TER 4, W O LFG A N G VO N H OY N IN G EN -H U EN E 4 and R A LPH K A H N 5‡, 1Leibniz(More)
  • R A L Ph K A H N, N Fr E D W E N D Isc H, +4 authors M Ic H A E L E Sse L B O R N
  • 2009
Desert dust aerosol air mass mapping in the western Sahara, using particle properties derived from space-based multi-angle imaging By R A LPH K A H N 1∗, A N D R EA S PETZO LD 2, M A N FR ED W EN D ISC H 3, EIK E B IERW IRTH 3, TILM A N D IN TER 4, M IC H A EL ESSELB O R N 2, M A R C U S FIEB IG 5, B IR G IT H EESE 6, PETER K N IPPERTZ 3, D ETLEF M Ü LLER(More)
  • T Il M A N D In T E R, O L Fg A N, +11 authors D Io
  • 2009
Retrieval of aerosol optical thickness for desert conditions using MERIS observations during the SAMUM campaign By TILM A N D IN TER 1∗, W O LFG A N G VO N H OY N IN G EN -H U EN E 1, JO H N P. B U R ROW S 1, A LEX A N D ER KO K H A N OV SK Y 1, EIK E B IERW IRTH 2, M A N FR ED W EN D ISC H 2, D ETLEF M Ü LLER 3, R A LPH K A H N 4 and M O H A M M ED D IO U(More)