Grzegorz Sokal

ORCID: 0000-0003-1324-7435
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Sensor Technology and Measurement Systems
  • Advanced Measurement and Metrology Techniques
  • Scientific Measurement and Uncertainty Evaluation
  • Advanced Image and Video Retrieval Techniques
  • Composite Material Mechanics
  • Multimodal Machine Learning Applications
  • Advanced Mathematical Modeling in Engineering
  • Theoretical and Computational Physics
  • Video Analysis and Summarization

Uniwersytet Komisji Edukacji Narodowej w Krakowie
2016-2021

Institute of Computer Science
2021

In this paper, we propose using the radial basis functions (RBF) to determine upper bound of absolute dynamic error (UAE) at output a voltage-mode accelerometer. Such can be obtained as result approximating values determined for assumed-in-advance parameter variability associated with mathematical model an This approximation was carried out function neural network (RBF-NN) procedure given number neurons. The Monte Carlo (MC) method also applied related when considering uncertainties...

10.3390/s19194154 article EN cc-by Sensors 2019-09-25

A James Bond’s (JB) catchphrase “shaken, not stirred is explored for the problem of effective conductivity composites. The superconductivity critical index s random non-overlapping disks turns out to be distinctly different shaking and stirring protocols. In case modeled by walks formula ( τ ) = 0.5 + 0.8 3 √ deduced evolution with normalized time 0 ≤ 1, which proportional number serving as disorder measure. Strikingly, coefficient very close protocol regular lattices. obtained based on...

10.24423/aom.2261 article EN Archives of Mechanics 2016-06-29

We propose an algorithm to generate graphical summarising of longer text passages using a set illustrative pictures (TIPS). TIPS is voting process that uses results individual "weak" algorithms. The proposed method includes generates digest the input document. Each sentence summary used as for further processing by transformer separately. A performs embedding and group CLIP similarity-based algorithms trained on different image finds semantic distances between images in illustration database...

10.3390/e23121614 article EN cc-by Entropy 2021-11-30
Coming Soon ...