AISSAI Anomaly Detection Workshop

Session

Lightning talks

4 mars 2024, 15:10

Clermont-Ferrand

10. Enhancing Monojet searches with ML

Rafal MASELEK (LPSC (Grenoble))

04/03/2024 15:10

Dark Matter particles could potentially be detected at the Large Hadron Collider (LHC) using the monojet channel, where at least one high pT jet recoils against missing transverse momentum. However, these searches pose a challenge as they require distinguishing subtle differences among similar jets. One way to improve this is by using Machine Learning (ML) methods to analyze correlations...

11. Accelerating the search for mass bumps using the Data-Directed Paradigm

Mlle Bruna Pascual (Université de Montréal)

04/03/2024 15:14

The Data-Directed paradigm (DDP) is a new physics search strategy for efficiently detecting anomalies in a large number of spectra with smoothly-falling SM backgrounds. Unlike the traditional analysis strategy, DDP avoids the need for a simulated or functional-form based background estimate by directly predicting the statistical significance using a convolutional neural network trained to...

12. Integrating Noisy Label Learning and Confidence Estimation

Dr Navid Rabbani (DIA2M, DRCI, CHU Clermont-Ferrand)

04/03/2024 15:18

Training a neural network is challenging when the training dataset is contaminated by labelling errors, which are commonly referred to as label noise. This challenge often coexists with the challenge of predicting confidence, allowing one to flag low-confidence predictions for the main task. Existing techniques tackle one of the two challenges but not both, neglecting their interdependency. We...

13. A deep learning approach for videobased traffic anomaly detection

M. Tom Schumann (RWTH Aachen University – Institute for Highway Engineering)

04/03/2024 15:22

Traffic safety systems especially in critical infrastructure such as road tunnels have garnered the interest of researchers for many years. While traffic managers have used traffic surveillance cameras for some time now, recent advances in computer vision and understanding have enabled more sophisticated automatic incident detection systems. Most state of the art systems consist of modern...

15. Anomaly Detection for Fink

Maria Pruzhinskaya (LPC)

04/03/2024 15:26

48. SEDAF : Prototype of a Real-Time Explainable Anomaly Detection System on Multivariate Data Stream

JIECHIEU KAMENI Florentin Flambeau (CNRS-LIMOS)

04/03/2024 15:30

Anomaly detection refers to the identification of rare events that differ significantly from the normal trend observed in the data distribution. When the number of variables to analyze is large, it can be difficult to understand the detected anomaly without explanation. In this work, we present the prototype of an explainable and real-time anomaly detection system, based on measurements from a...

9. Feet-on-the-ground Deep Anomaly Detection with Images: A real world Industrial case study

M. Francesco Dalmonte (Università di Bologna)

The unsupervised classification of images is a conceptually simple problem, yet it remains a significant challenge in the field of Machine Learning. In fact, despite the development of models that have demonstrated excellent performance on benchmark datasets in recent years, reproducing equally satisfactory results in real-world cases is often very difficult. This study presents a real-world...

14. Indirect estimation of distance of a star from apparent magnitude

Dr Abisa Sinha (Amity University Kolkata)

Space observatory Gaia has prepared a large catalog of 1 billion astronomical objects which consists primarily of stars but also planets, comets, asteroids and quasars among others whose parallaxes are measured instead of distances ($r$). Bailer-Jones (\citet{Bailer-Jones}) established that distance estimation from parallaxes is not trivial once the fractional parallax error is larger than...