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.
The results of numerical computations concerning momentum transfer processes in an air – biophase – liquid system agitated in a bioreactor equipped with baffles and a Smith turbine (CD 6 impeller) are presented in this paper. The effect of sucrose concentration on the distributions of the velocity of the continuous phase, gas hold-up and the size of gas bubbles in the system was analysed. Simulation results were presented in the form of the contours of the analysed magnitudes. The effect of sucrose concentration on the averaged values (i.e. determined on the basis of local values) of gas hold-up and gas bubbles size was evaluated. The results of the numerical computations of gas hold-up were compared with our own experimental data.