Overview
- Nominated as an outstanding PhD thesis by The University of Sydney, Australia
- Reports on an improved feature selection technique based on voting
- Offers a comprehensive review of machine learning methods for unsupervised classification and feature selection
Part of the book series: Springer Theses (Springer Theses)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (7 chapters)
-
Front Matter
-
Back Matter
Keywords
- Novelty Detection
- Anomaly Score Based Detector
- Automated Feature Selection
- Feature Selection Based on Voting
- Unsupervised Anomaly Detection
- Unsupervised Artifact Detection
- Learning for Detecting Freezing of Gait Events
- Anomaly Detection for Biomedical Data
- Unsupervised Multi-class Sorting
- Voting Process for Feature Selection
- Improving Classification Performance
- Unsupervised Classification of Biomedical Data
- Subject-independent Classifiers
- Respiratory Artifact Detection
- Forced Oscillation Measurements
- Unsupervised Spike Sorting
- Fog Detection Systems
About this book
This book describes efforts to improve subject-independent automated classification techniques using a better feature extraction method and a more efficient model of classification. It evaluates three popular saliency criteria for feature selection, showing that they share common limitations, including time-consuming and subjective manual de-facto standard practice, and that existing automated efforts have been predominantly used for subject dependent setting. It then proposes a novel approach for anomaly detection, demonstrating its effectiveness and accuracy for automated classification of biomedical data, and arguing its applicability to a wider range of unsupervised machine learning applications in subject-independent settings.
Authors and Affiliations
Bibliographic Information
Book Title: Applying Machine Learning for Automated Classification of Biomedical Data in Subject-Independent Settings
Authors: Thuy T. Pham
Series Title: Springer Theses
DOI: https://doi.org/10.1007/978-3-319-98675-3
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer Nature Switzerland AG 2019
Hardcover ISBN: 978-3-319-98674-6Published: 31 August 2018
Softcover ISBN: 978-3-030-07518-7Published: 25 January 2019
eBook ISBN: 978-3-319-98675-3Published: 23 August 2018
Series ISSN: 2190-5053
Series E-ISSN: 2190-5061
Edition Number: 1
Number of Pages: XV, 107
Number of Illustrations: 3 b/w illustrations, 32 illustrations in colour
Topics: Biomedical Engineering and Bioengineering, Data Mining and Knowledge Discovery, Computational Intelligence, Bioinformatics