James Kahn

James Kahn

Auto-generated profile, based on publicly available information

James Kahn

Helmholtz AI, Scientific Computing Centre, Karlsruhe Institute of Technology, Karlsruhe, Germany

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 December 2022 in Automation in Construction
Verified
Journal Article
Open access
ZMZoe Mayer
Zoe Mayer
JKJames Kahn
James Kahn
Yu HouYu Hou
Yu Hou
MGMarkus Götz
Markus Götz
Rebekka VolkRebekka Volk
Rebekka Volk
FSFrank Schultmann
Frank Schultmann

24 May 2023 in Solar Energy
Verified
Journal Article
Open access
ABAlex Brenner
Alex Brenner
JKJames Kahn
James Kahn
THTobias Hirsch
Tobias Hirsch
MRMarc Röger
Marc Röger
RPRobert Pitz-Paal
Robert Pitz-Paal

1 September 2022 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
JKJames Kahn
James Kahn
ITIlias Tsaklidis
Ilias Tsaklidis
OTOskar Taubert
Oskar Taubert
LRLea Reuter
Lea Reuter
GDGiulio Dujany
Giulio Dujany
MGMarkus Götz
Markus Götz
In this work, we present a neural approach to reconstructing rooted tree graphs describing hierarchical interactions, using a novel representation we term the lowest common ancestor generations (LCAG) matrix. This compact formulation is equivalent to the adjacency matrix, but enables learning a tree’s structure from its leaves alone without the prior assumptions required if using the adjacency matrix directly. Employing the LCAG therefore enables the first end-to-end trainable solution which learns the hierarchical structure of varying tree sizes directly, using only the terminal tree leaves to do so. In the case of high-energy particle physics, a particle decay forms a hierarchical tree structure of which only the final products can be observed experimentally, and the large combinatorial space of possible trees makes an analytic solution intractable. We demonstrate the use of the LCAG as a target in the task of predicting simulated particle physics decay structures using both a Transformer encoder and a neural relational inference encoder graph neural network. With this approach, we are able to correctly predict the LCAG purely from leaf features for a maximum tree-depth of 8 in 92.5 % of cases for trees up to 6 leaves (including) and 59.7 % for trees up to 10 in our simulated dataset.

12 December 2024 in Safety Science
Verified
Journal Article
Open access
AGAlexandros Gazos
Alexandros Gazos
JKJames Kahn
James Kahn
IKIsabel Kusche
Isabel Kusche
CBChristian Büscher
Christian Büscher
MGMarkus Götz
Markus Götz

18 August 2023 in Journal of High Energy Physics
Verified
Journal Article
Open access
PDF file
TCThe Belle collaboration
The Belle collaboration
JYJ. H. Yin
J. H. Yin
YLY. B. Li
Y. B. Li
EWE. Won
E. Won
IAI. Adachi
I. Adachi
VZV. Zhukova
V. Zhukova
We measure the cross section of e+e− → ηcJ/ψ at the Υ(nS)(n = 1–5) on-resonance and 10.52 GeV off-resonance energy points using the full data sample collected by the Belle detector with an integrated luminosity of 955 fb−1. We also search for double charmonium production in e+e− → ηcJ/ψ via initial state radiation near the ηcJ/ψ threshold. No evident signal of the double charmonium state is found, but evidence for the e+e−→ ηcJ/ψ process is found with a statistical significance greater than 3.3σ near the ηcJ/ψ threshold. The average cross section near the threshold is measured and upper limits of cross sections are set for other regions.

10 May 2023 in Scientific Data
Verified
Journal Article
Open access
PDF file
ZMZoe Mayer
Zoe Mayer
JKJames Kahn
James Kahn
MGMarkus Götz
Markus Götz
Yu HouYu Hou
Yu Hou
TBTobias Beiersdörfer
Tobias Beiersdörfer
Frank SchultmannFrank Schultmann
Frank Schultmann
Thermal Bridges on Building Rooftops (TBBR) is a multi-channel remote sensing dataset. It was recorded during six separate UAV fly-overs of the city center of Karlsruhe, Germany, and comprises a total of 926 high-resolution images with 6927 manually-provided thermal bridge annotations. Each image provides five channels: three color, one thermographic, and one computationally derived height map channel. The data is pre-split into training and test data subsets suitable for object detection and instance segmentation tasks. All data is organized and structured to comply with FAIR principles, i.e. being findable, accessible, interoperable, and reusable. It is publicly available and can be downloaded from the Zenodo data repository. This work provides a comprehensive data descriptor for the TBBR dataset to facilitate broad community uptake.