Explore projects

Jupyter Notebooks für die Summer School Step Forward

A multimedia dataset for object-centric business process mining in IT asset management

Interference signals cause position errors and outages to global navigation satellite system (GNSS) receivers. However, to solve these problems, the interference needs to be detected, classified, its purpose determined, and localized, such that it can be eliminated. Several interference monitoring solutions exist, but these are expensive, resulting in fewer nodes that may miss spatially sparse interference signals. This paper introduces a low-cost commercial-off-the-shelf (COTS) GNSS interference monitoring, detection, and classification receiver. It employs machine learning (ML) on tailored signal pre-possessing of the raw signal samples and GNSS measurements to facilitate a generalized, high-performance architecture that does not require human in the loop (HIL) calibration. Therefore, the low-cost receivers with high performance can justify significantly more receivers to be deployed, resulting in a significantly higher probability of intercept (POI). The initial results of controlled interference scenarios demonstrate detection and classification capabilities exceeding conventional approaches.

In this demostrator, we illustrate not only the general procedure of building a QNN via quantum circuit, but also showcase using QNN to predict 2D solution of Poisson equation. To accelerate the convergence, the physics informed NN is introduced. We also show the convergence comprison between QNN and PIQNN.

In this demonstration, we present a Quantum Alternating Algorithm designed to address Mixed Integer Linear Problems (MILP). The algorithm's efficacy is showcased through the resolution of an energy use case, employing CPU and GPU quantum simulators, as well as the IBM Quantum System at Ehningen.

Link zur Doku: http://fre10753.pages.fraunhofer.de/mkdocs-example

Public mirror of internal repository

We propose a quantum version of the deterministic annealing algorithm to verify the input-output relations of a neural network. We apply the algorithm to traffic sign recognition, an important task for self-driving vehicles.