Autor: Soszyński, P. - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: The method of underwater object identification using multi-layer perception
Autorzy:: Soszyński, P.
Stateczny, A.
Powiązania:: https://bibliotekanauki.pl/articles/332077.pdf
Data publikacji:: 1999
Wydawca:: Polskie Towarzystwo Akustyczne
Opis:: An algorithm for detection/identification of underwater objects is proposed. The algorithm is based upon the classification ability of a simple multi-layer neural network, also called a Perceptron. A signal recorded by a hydrophone and preprocessed by a computer is supplied to the ANN, which classifies it according to the possessed information encoded within its structure and an array of weighs. Analysis of effectiveness is conducted depending on the variables pertaining to the neural network.
Źródło:: Hydroacoustics; 1999, 2; 161-166
1642-1817
Pojawia się w:: Hydroacoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 2.

Tytuł:: Application of wide bandwidth signals for recognition of sea bedding
Autorzy:: Szulc, D.
Soszyński, P.
Powiązania:: https://bibliotekanauki.pl/articles/332282.pdf
Data publikacji:: 2000
Wydawca:: Polskie Towarzystwo Akustyczne
Opis:: This article presents the results of research on the sea bedding using a measuring set generating wide bandwidth. signals witli linearly modulated frequency - chirp signals. The measurements were conducted in the Gdansk Bay region at locations where geological cores had been drawn.
Źródło:: Hydroacoustics; 2000, 3; 29-34
1642-1817
Pojawia się w:: Hydroacoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 3.

Tytuł:: Improving the quality of noise detection in the Southern Baltic in the aspect of identification
Autorzy:: Soszyński, P.
Cichocki, A.
Powiązania:: https://bibliotekanauki.pl/articles/332622.pdf
Data publikacji:: 2001
Wydawca:: Polskie Towarzystwo Akustyczne
Opis:: Artificial intelligence systems have been more and more used for the purposes of classification and identification. Recently, a lot of attention has been devoted to the exploration of such techniques in combination with the passive acoustic signals of vessels in the sea environment. Although some of the research imply optimistic results it seems necessary to apply the results of investigations regarding the sound propagation in the sea. This paper suggests was of improving the quality of neural classification by narrowing broadband frequency band to some specific narrow bands.
Źródło:: Hydroacoustics; 2001, 4; 217-220
1642-1817
Pojawia się w:: Hydroacoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 4.

Tytuł:: Dynamic normalization of hydroacoustic signals
Autorzy:: Soszyński, P.
Nowak, D.
Powiązania:: https://bibliotekanauki.pl/articles/332041.pdf
Data publikacji:: 2003
Wydawca:: Polskie Towarzystwo Akustyczne
Tematy:: hydroacoustic signals
multidimensional analysis
Opis:: Multidimensional analysis of hydroacoustic data is usually conducted by way of presentation of the signal information decomposed into dimensions of time and frequency using a short term Fourier transform inform of a spectrogram. Same shortfalls of such visual analysis come into place when studying a signal coming from a source changing its distance from the receiver set because of the variations in the signal strength. The proposed method suggests same ways of such normalization scheme that will diminish the influence of these variations by way multiplication of the spectra by a compensation function dependent of time.
Źródło:: Hydroacoustics; 2003, 6; 295-298
1642-1817
Pojawia się w:: Hydroacoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 5.

Tytuł:: Application of PCA as an acoustical signal processing tool for object classification purposes
Autorzy:: Soszyński, P.
Gloza, I.
Powiązania:: https://bibliotekanauki.pl/articles/332669.pdf
Data publikacji:: 2005
Wydawca:: Polskie Towarzystwo Akustyczne
Opis:: The authors presented a technique for an optimal representation of acoustical signals for further object classification purposes using different statistical and neural methods. It is based on principal component analysis (PCA) which is a transformation of vectors localized in k-dimensional observation (feature) space into lower n-dimensional component space retaining majority of included information. The resulting improvement in classification efficiency by a chosen statistical classifier was verified by a numerical experiment.
Źródło:: Hydroacoustics; 2005, 8; 193-198
1642-1817
Pojawia się w:: Hydroacoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Informacja