2020.09.11., 10:10-10:40

Gerencsér, Balázs RI / Lovas, Attila BME Non-linear state-estimation based traffic modelling relying on sparse measurement data Abstract: We present our approach to the theoretical and computational challenge of traffic data extrapolation, to fit a model via its dynamical system approximations to the real world measurement data available and get …

2020.09.11., 08:00-09:00

Márkus, László ELTE / Baran, Sándor DE / Nedényi, Fanni SZTE / Arató, Miklós ELTE HU-MATHS-IN GE Project In this talk we present a closing draft of the HU-MATHS-IN GE Project. Participation upon signed NDA with GE. Online location: If you wantt to participate please contact the HU-MATHS-IN office.

2020.09.11., 09:00-09:30

Bolla, Marianna BME Spectra of Spectra Abstract: Asymptotic relation is proved between the eigenvalues of the block Toeplitz matrix of autocovariances and the union of spectra of the spectral density matrices at the Fourier frequencies. This result has a lot of important consequences as for the relations between time and …

Stoyan Gisbert Szeminárium Győrben

“A HU-MATHS-IN – Magyar Ipari Innovációs Matematikai Szolgáltatási Hálózat tevékenységének elmélyítése” című projekt keretében (EFOP-3.6.2-16-2017-00015) Győrben, a Széchenyi István Egyetemen a Stoyan Gisbert Szeminárium keretein belül a konzorciumvezető intézmény által koordinált ipari indíttatású rövid futamidejű projektek előadásaira kerül sor 2020.09.09./2020.09.11. napokon. Az esemény programja 2 tematikus napot foglal magába. 2020.09.09-én, …

2020.09.09., 12:05-12:35

Bácsi, Ádám SZE

Highly accurate numerical solution of the Navier-Stokes equations in pipes

Abstract:

The acoustic characterization is one of the key challenges in engineering exhaust systems of vehicles. In the seminar, I will present a numerical study of the exhaust gas flow both in the pipe of a simplified exhaust system and in the exhaust jet. The acoustic noise stems primarily from the highly turbulent fluid flow. To resolve eddies in the turbulent flow up to the levels required for acoustic characterization, Large Eddy Simulation is applied. The simulation results are also compared to experimental measurements.

Online location: https://meet.google.com/ckd-siwc-nvx?authuser=0

Kolumbán, Sándor: Optimizing train re-scheduling with reinforcement learning

Helyszín: Online, https://meet.google.com/pfp-yzpu-cbe?authuser=0 Időpont: 2020.06.30., 17:30 – 17:50 Kivonat: Applying reinforcement learning (RL) methods is a difficult task since these methods usually require a standardization of their inputs and in a similar way a standardization of the output – action – spaces. Usually, when applied to real-world problems, the success …

Kolumbán, Sándor: Improving inventory management using innovative …

Előadás címe: Improving inventory management using innovative market demand prediction Helyszín: Online https://meet.google.com/pfp-yzpu-cbe?authuser=0 Időpont: 2020.06.30., 18:10 – 18:30 Kivonat: The goal of the presented project is to provide state-of-the-art prediction methodologies, using advanced machine learning technology, that can be used to predict demand of certain goods for a foreseeable amount …

Maróti, Miklós: Synthetic foggy scene generation and …

Előadás címe: Synthetic foggy scene generation and evaluation pipeline Helyszín: Online Időpont: 2020.06.30. 17:10-17:30 Kivonat: We present an artificial intelligence based image processing pipeline for generating synthetic foggy scenes from sunny pictures by breaking down the problem into 1) sharp shadow removal, 2) depthmap generation, and 3) fog generation. Then …

Bodó, Zalán: Integrating recommendation systems …

Előadás címe: Integrating recommendation systems into B2B sales processes Helyszín: Online https://meet.google.com/pfp-yzpu-cbe?authuser=0 Időpont: 2020.06.30., 17:50 – 18:10 Kivonat: Evidence, such as the success story of Amazon, shows that an efficient recommendation system can improve sales performance. Recommendation systems play a significant role in online stores, music and video streaming platforms …