Überwachte Methoden für die spektrale Entmischung mit künstlichen neuronalen Netzen / / Johannes Anastasiadis.
In this work, artificial neural networks trained in a supervised manner for spectral unmixing are investigated. For this purpose, a suitable network architecture is determined first. After that, the focus lies on the generation of suitable training data. Model-based methods that generate training da...
Saved in:
VerfasserIn: | |
---|---|
Place / Publishing House: | Karlsruhe : : KIT Scientific Publishing,, 2023. |
Year of Publication: | 2023 |
Language: | German |
Series: | Karlsruher Institut für Technologi
|
Physical Description: | 1 online resource (xii, 171 pages). |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 01930nam a2200325 i 4500 | ||
---|---|---|---|
001 | 993661675904498 | ||
005 | 20240322153802.0 | ||
006 | m o d | ||
007 | cr ||||||||||| | ||
008 | 240322s2023 gw ob 000 0 ger d | ||
024 | 7 | |a 10.5445/KSP/1000159281 |2 doi | |
035 | |a (CKB)5590000001150234 | ||
035 | |a (NjHacI)995590000001150234 | ||
035 | |a (EXLCZ)995590000001150234 | ||
040 | |a NjHacI |b eng |e rda |c NjHacl | ||
050 | 4 | |a QA76.87 |b .A537 2023 | |
082 | 0 | 4 | |a 006.32 |2 23 |
100 | 1 | |a Anastasiadis, Johannes, |e author. | |
245 | 1 | 0 | |a Überwachte Methoden für die spektrale Entmischung mit künstlichen neuronalen Netzen / |c Johannes Anastasiadis. |
264 | 1 | |a Karlsruhe : |b KIT Scientific Publishing, |c 2023. | |
300 | |a 1 online resource (xii, 171 pages). | ||
336 | |a text |b txt |2 rdacontent | ||
337 | |a computer |b c |2 rdamedia | ||
338 | |a online resource |b cr |2 rdacarrier | ||
490 | 0 | |a Karlsruher Institut für Technologi | |
588 | |a Description based on publisher supplied metadata and other sources. | ||
520 | |a In this work, artificial neural networks trained in a supervised manner for spectral unmixing are investigated. For this purpose, a suitable network architecture is determined first. After that, the focus lies on the generation of suitable training data. Model-based methods that generate training data from real pure spectra and data-based methods that augment existing training data are presented and evaluated. | ||
504 | |a Includes bibliographical references. | ||
505 | 0 | |a Vorwort -- Symbotverzeichnis -- Einleitung -- Spektrale Enlmischung -- Kunstliche neuronale Netze -- Verwandte Aibeiten -- Faltungsnetz fur fie spektrale Entmischung -- Modellbasierte Trainingsdatenerzeugung -- aus Reinspektren -- Augmentierung spektraler Datensatze -- Umsetzung und Analyse -- Zusammenfassung und -- Ausblick -- Herleilung: Stochastische Mischmodelle -- Literaturverzeichnis. | |
650 | 0 | |a Neural networks (Computer science) | |
776 | |z 1000159281 | ||
906 | |a BOOK | ||
ADM | |b 2024-04-24 04:17:43 Europe/Vienna |f System |c marc21 |a 2023-09-07 12:04:59 Europe/Vienna |g false | ||
AVE | |i DOAB Directory of Open Access Books |P DOAB Directory of Open Access Books |x https://eu02.alma.exlibrisgroup.com/view/uresolver/43ACC_OEAW/openurl?u.ignore_date_coverage=true&portfolio_pid=5354332880004498&Force_direct=true |Z 5354332880004498 |b Available |8 5354332880004498 |