Autor: Zhang, W J - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: Numerical Study of the Effect of Furrows on Biosonar Beamforming in Aselliscus Stoliczkanus Bat
Autorzy:: He, W.
Feng, J.
Gao, L.
Zhang, Z.
Lu, H.
Powiązania:: https://bibliotekanauki.pl/articles/176802.pdf
Data publikacji:: 2017
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:: Aselliscus Stoliczkanus bat
furrows
frequency-selective characteristics
finite element method
beam pattern
Opis:: The Aselliscus Stoliczkanus bat, studied here, has intricately shaped structures surrounding the nostrils. These structures are hypothesised to have influence on animals’ acoustic radiation patterns. Using micro-tomography scanning technique, a 3D digital model of the noseleaf is reconstructed and biosonar beam pattern is analysed using a finite element method based on the 3D noseleaf model. The present research focuses on the conspicuous furrows in noseleaf, and our analysis allows to conclude the followings: a) structural details in noseleaf of Aselliscus Stoliczkanus bat can produce acoustic effects even if it is not adjacent to the nostrils, b) the furrows possess frequency-selective characteristics, c) the furrows have the function to manipulate the direction and width of the outgoing ultrasound wave.
Źródło:: Archives of Acoustics; 2017, 42, 3; 395-399
0137-5075
Pojawia się w:: Archives of Acoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Skocz do pozycji: 2.

Tytuł:: Teaching Machines on Snoring : A Benchmark on Computer Audition for Snore Sound Excitation Localisation
Autorzy:: Qian, K.
Janott, C.
Zhang, Z.
Deng, J.
Baird, A.
Heiser, C.
Hohenhorst, W.
Herzog, M.
Hemmert, W.
Schuller, B.
Powiązania:: https://bibliotekanauki.pl/articles/177964.pdf
Data publikacji:: 2018
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:: snore sound
obstructive sleep apnea
acoustic features
machine learning
Opis:: This paper proposes a comprehensive study on machine listening for localisation of snore sound excitation. Here we investigate the effects of varied frame sizes, and overlap of the analysed audio chunk for extracting low-level descriptors. In addition, we explore the performance of each kind of feature when it is fed into varied classifier models, including support vector machines, k-nearest neighbours, linear discriminant analysis, random forests, extreme learning machines, kernel-based extreme learning machines, multilayer perceptrons, and deep neural networks. Experimental results demonstrate that, wavelet packet transform energy can outperform most other features. A deep neural network trained with subband Energy ratios reaches the highest performance achieving an unweighted average recall of 72.8% from four types for snoring.
Źródło:: Archives of Acoustics; 2018, 43, 3; 465-475
0137-5075
Pojawia się w:: Archives of Acoustics
Dostawca treści:: Biblioteka Nauki

Artykuł

Informacja