Hochschulbibliothekszentrum des Landes Nordrhein-Westfalen
Institutionelles Repositorium der Hochschule DüsseldorfNot a member yet
4344 research outputs found
Sort by
Examining the Impact of Optical Aberrations to Image Classification and Object Detection Models
No full textDeep neural networks (DNNs) have proven to be successful in various computer vision applications such that models even infer in safety-critical situations. Therefore, vision models have to behave in a robust way to disturbances such as noise or blur. While seminal benchmarks exist to evaluate model robustness to diverse corruptions, blur is often approximated in an overly simplistic way to model defocus, while ignoring the different blur kernel shapes that result from optical systems. To study model robustness against realistic optical blur effects, this paper proposes two datasets of blur corruptions, which we denote OpticsBench and LensCorruptions. OpticsBench examines primary aberrations such as coma, defocus, and astigmatism, i.e. aberrations that can be represented by varying a single parameter of Zernike polynomials. To go beyond the principled but synthetic setting of primary aberrations, LensCorruptions samples linear combinations in the vector space spanned by Zernike polynomials, corresponding to 100 real lenses. Evaluations for image classification and object detection on ImageNet and MSCOCO show that for a variety of different pre-trained models, the performance on OpticsBench and LensCorruptions varies significantly, indicating the need to consider realistic image corruptions to evaluate a model's robustness against blur
UNITY: Multistrategische Intervention zur Förderung von Radmobilität, Gesundheit und Nachhaltigkeit im Rahmen der Stadtentwicklung Düsseldorf [Vortragsabstract]
No full textEpisodic evolution and active tectonics of the Karamık Graben in the apex of Isparta Angle, SW Türkiye
No full text
Bericht zur Vorstudie: IMAI Intermediale Sammlungsforschung mit Artificial Intelligence 2024
No full textModelle der sogenannten Künstlichen Intelligenz (KI) ermöglichen eine systematische Strukturierung von riesigen Datenmengen zum Zweck der Erkenntnisgewinnung aus bestehenden Informationen. Ein Verfahren wie das Maschinelle Lernen kann dabei unterstützen, einen neuen Blick auf vorhandenes Wissen in digitalen Archiven zu werfen. Diese lernfähigen Maschinen sollen im Projekt „IMAI – Intermediale Sammlungsforschung mit Artificial Intelligence“ untersucht werden, um Archivar*innen sowie Kunst- und Medienhistoriker*innen bei der Sichtung des audiovisuellen Materials zu unterstützen und den Umgang mit Sammlungen zeitbasierter Medien effizienter sowie komfortabler zu machen. In einer ersten Projektphase (2024) sollten durch die Erprobung verfügbarer Prototypen und durch die Sichtung des Videoarchivs des Inter Media Art Institute Anwendungsoptionen abgewogen werden. Die bislang genutzten Werkzeuge zur Erschließung von Archiven wurden dabei genauso betrachtet wie die Arbeitsweisen weiterer betroffener Anwender*innen. Der Bericht fasst die Erkenntnisse aus der Vorstudie zusamme
»Playing with Possibilities«: Skateboarding als Spielen mit den Möglichkeitsräumen des Urbanen
No full text
Translating community-wide spectral library into actionable chemical knowledge: a proof of concept with monoterpene indole alkaloids
No full textWith over 3000 representatives, the monoterpene indole alkaloids (MIAs) class is among the most diverse families of plant natural products. The MS/MS spectral space exploration of these complex compounds using chemoinformatic and computational mass spectrometry tools offers a valuable opportunity to extract and share chemical insights from this emblematic family of natural products (NPs). In this work, we first present a substantially updated version of the MIADB, a database now containing 422 MS/MS spectra of MIAs that has been uploaded to the GNPS library versus 172 initial entries. We then introduce an innovative workflow that leverages hundreds of fragmentation spectra to support the FAIRification, extraction and dissemination of chemical knowledge. This workflow aims at the extraction of spectral patterns matching finely defined MIA skeletons. These extracted signatures can then be queried against complex biological extract datasets using MassQL. By applying this strategy to an LC-MS/MS dataset of 75 plant extracts, our results demonstrated the efficiency of this approach in identifying the diversity of MIA skeletons present in the analyzed samples. Additionally, our work enabled the digitization of structural data for diverse MIA skeletons by converting them into machine-readable formats and thereby enhancing their dissemination for the scientific community.
Scientific contribution
A comprehensive investigation of the monoterpene indole alkaloid chemical space, aiming to highlight skeleton-dependent fragmentation similarity trends and to generate valuable spectrometric signatures that could be used as queries
