Wyniki wyszukiwania - BazTech

1

Zastosowanie struktur sieci neuronowych typu transformer do detekcji anomalii danych

Krasiński Kamil, Piotrowski Zbigniew

Elektronika : konstrukcje, technologie, zastosowania

|

2024

|

Vol. 65, Nr 8

30--32

PL

Celem niniejszego artykułu jest przegląd metod i narzędzi wykorzystujących różne architektury sztucznych sieci neuronowych w celu wykrywania anomalii w dostarczonych ciagach danych, ze szczególnym naciskiem na architekturę sieci typu transformer. Przegląd ten ma na celu zaprezentowanie aktualnego stanu wiedzy, jak również wskazanie kierunków dalszych badań i rozwoju w tej wciąż rozwijającej się dziedzinie.

EN

The aim of this article is to review methods and tools utilizing various artificial neural network architectures of artificial intelligence for detecting anomalies in provided data sequences, with a particular emphasis on transformer network architecture. This review aims to present the current state of knowledge, as well as to indicate directions for further research and development in this still evolving field.

2

Szacowanie parametrów projektu w metodyce zwinnej

Krasiński Kamil, Piotrowski Zbigniew

Elektronika : konstrukcje, technologie, zastosowania

|

2024

|

Vol. 65, Nr 8

26--29

PL

W artykule dokonano przeglądu metod i narzędzi stosowanych do szacowania czasu realizacji projektu w ramach metodyki zarządzania projektami Scrum. W artykule przedstawiono nie tylko różnorodność dostępnych technik szacowania parametrów projektu, ale również oceniono ich przydatność w różnych sytuacjach projektowych.

EN

The article reviews the methods and tools used for estimating project completion time within the Scrum project management methodology. The article not only presents the diversity of available techniques for estimating project parameters but also assesses their usefulness in various project situations.

3

Strategic analysis of implementation assets and threats

Piech Henryk, Grodzki Grzegorz

Journal of Applied Mathematics and Computational Mechanics

|

2019

|

Vol. 18, nr 2

65--74

EN

The main goal of the work is to support the marketing strategy using the characteristics created on the base of the game theory and uncertain knowledge. We want to elaborate algorithm, which does not require game-playing investigation. The additional aim consists in adaptating the game strategy to the concrete e.g. economic situation, described by selected, specific parameters. The next aim consists in exploitation uncertain knowledge as a data also. Game theory is the part of mathematics approach extended by Nash and adopted to psychology, sociology, politics, economics and informatics (artificial intelligence) problems. Game Theory provides mathematical tools for analyzing situations in which parties, called players, make decisions that are interdependent. This causes each player to consider the other player’s possible decisions, or strategies, in formulating his own strategy. This approach based on the assumption, that a solution to a game describes the optimal decisions of the players, who may have similar, opposed, or mixed interests, and the outcomes that may result from these decisions. This will be described as an example.

4

Probabilistic and Fuzzy Process Classifiers for Operating Systems Scheduler

Bagchi S.

Fundamenta Informaticae

|

2016

|

Vol. 145, nr 4

405--427

EN

The schedulers residing in kernel of Operating Systems employ patterns of resource affinities of concurrent processes in order to make scheduling decisions. The scheduling decisions affect overall resource utilization in a system. Moreover, the resource affinity patterns of a process may not be possible to profile statically in all cases. This paper proposes a novel probabilistic estimation model and a classifier algorithm to queuing processes based on respective resource affinities. The proposed model follows probabilistic estimation using execution traces, which can be either online or statically profiled. The algorithm tracks the resource affinities of processes based on periodic estimation and classifies the processes accordingly for scheduling. The effects of variations of estimation periods are investigated and fuzzy refinements are introduced. Experimental results indicate that the classifier algorithm successfully determines resource affinities of a set of processes online. However, the algorithm can determine inherent affinity pattern of a process in the presence of uniform distribution having enhanced IO frequency.