Porosity estimation by semi-supervised learning with sparsely available labeled samples

LA Lima, N Görnitz, LE Varella, M Vellasco… - Computers & …, 2017 - Elsevier
This paper addresses the porosity estimation problem from seismic impedance volumes and
porosity samples located in a small group of exploratory wells. Regression methods, trained …

SVM2Motif—reconstructing overlap** DNA sequence motifs by mimicking an SVM predictor

MMC Vidovic, N Görnitz, KR Müller, G Rätsch, M Kloft - PloS one, 2015 - journals.plos.org
Identifying discriminative motifs underlying the functionality and evolution of organisms is a
major challenge in computational biology. Machine learning approaches such as support …

Improved transcript isoform discovery using ORF graphs

WH Majoros, N Lebeck, U Ohler, S Li - Bioinformatics, 2014 - academic.oup.com
Motivation: High-throughput sequencing of RNA in vivo facilitates many applications, not the
least of which is the cataloging of variant splice isoforms of protein-coding messenger RNAs …

[書籍][B] One-class Classification in the presence of Point, Collective, and Contextual Anomalies

N Görnitz - 2019 - search.proquest.com
Anomaly detection has a prominent position in the processing pipeline of any real-world
data-driven application. Its central goal is to detect and separate valid data points from …

[書籍][B] Improving and interpreting machine learning algorithms with applications

MMC Vidovic - 2017 - search.proquest.com
Advancing understanding and interpretation of machine learning algorithms has recently
been receiving much attention. Although classification systems achieve high prediction …