Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "Klaczynski, M." wg kryterium: Autor


Wyświetlanie 1-2 z 2
Tytuł:
Artificial Intelligence and Learning Systems Methods in Supporting Long-Term Acoustic Climate Monitoring
Autorzy:
Kłaczyński, M.
Wszołek, T.
Powiązania:
https://bibliotekanauki.pl/articles/1400078.pdf
Data publikacji:
2013-06
Wydawca:
Polska Akademia Nauk. Instytut Fizyki PAN
Tematy:
43.60.Lq
07.05.Mh
Opis:
Developing effective methods for automatic identification of noise sources is currently one of the most important tasks in long-term acoustical climate monitoring of the environment. Manual verification of recorded data, when it comes to proper determination of noise levels, is time-consuming and costly. A possible solution is to use pattern recognition techniques for acoustic signal recorded by a monitoring station. This paper presents usefulness of special directed measurement techniques, acoustic signal processing, and classification methods using artificial intelligence (the Sammon mapping) and learning systems methods (Support Vector Machines) in the recognition of corona audible noise from ultra-high voltage AC transmission lines.
Źródło:
Acta Physica Polonica A; 2013, 123, 6; 1024-1028
0587-4246
1898-794X
Pojawia się w:
Acta Physica Polonica A
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Automatic Detection of Long-Term Audible Noise Indices from Corona Phenomena on UHV AC Power Lines
Autorzy:
Wszołek, T.
Kłaczyński, M.
Powiązania:
https://bibliotekanauki.pl/articles/1197542.pdf
Data publikacji:
2014-04
Wydawca:
Polska Akademia Nauk. Instytut Fizyki PAN
Tematy:
43.60.Lq
07.05.Mh
Opis:
One of the most important tasks in outdoor acoustic monitoring stations is automatic extraction of the measured signal parameters. In case of corona discharge noise from ultra-high voltage alternating current (UHV AC) power lines it is necessary to select properly the corona audible noise (CAN) parameters to be monitored for noise indicators calculation, as the monitored signal and the background noise strongly fluctuate. A combined selection of distinctive features of CAN is necessary in order to distinguish the actual signal from the external interference. The vast amount of recorded data is difficult to store and process. Therefore, particular attention was devoted to define of the collected parameters used for automatic calculation of the CAN long-term noise indicators. In addition, several new CAN parameters were introduced, including spectral moments, spectral coefficients of tonal components contribution, and power coefficients in selected frequency bands; as it allowed more efficient selection of samples with non-zero contribution from CAN. The artificial neural network was applied for final classification of the measured samples. Selected and properly filtered samples provided the basis for calculations of long-term noise indicators. Efficiency of the said method was tested for the measurement sections with the recorded sound signal and aural qualification of the CAN intensity.
Źródło:
Acta Physica Polonica A; 2014, 125, 4A; A-93-A-98
0587-4246
1898-794X
Pojawia się w:
Acta Physica Polonica A
Dostawca treści:
Biblioteka Nauki
Artykuł
    Wyświetlanie 1-2 z 2

    Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies