Showing papers in "Applied Acoustics in 2021"

TL;DR: The authors proposed a method for feature extraction: SMOFS-NFC (Shortened Method of Frequencies Selection Nearest Frequency Components), which is very useful for diagnosis of bearings, ventilation faults and other mechanical faults of power tools.

TL;DR: In this paper, a composite porous metamaterial (CPM) consisting in a porous polyurethane sponge with embedded multi-layer I-plates is proposed to mitigate the slow wave phenomenon and/or insufficient sub-wavelength sound absorption.

TL;DR: The results show the effectiveness, robustness, and high accuracy of the proposed approach to have meaningful data augmentation by considering variations applied to the audio clips directly.

TL;DR: A model of classification is proposed by the use of a discrete wavelet transform DWT to transform the signal and the GA and the classifier SVM algorithm is applied, which achieves the best accuracy.

TL;DR: In this article, the double-leaf acoustic black hole beam embedded mass oscillator is used for vibration isolation, and different elastic wave modulation effects are discussed, such as strong wave trapping region corresponds to the anti-symmetrical vibration attenuation (Fano-like resonance) and the weak wave trapping regions correspond to the symmetrical vibration scattering (Bragg scattering).

TL;DR: In this paper, the periodic nested acoustic black hole phononic structure is presented, and different complex band structures and corresponding evanescent Bloch wave propagation are discussed, which can be used in the vibration reduction design of lightweight structure and enrich the relevant research experience on acoustic black holes.

TL;DR: Mel frequency magnitude coefficient is found to be the better spectral feature for the identification of emotion from speech compared to the conventional features.

TL;DR: The PSO-Improve-CNN model presents the highest diagnostic accuracy, less time in training and testing, and greater robustness, and the comprehensive performance of the proposed model is demonstrated to be much stronger.

TL;DR: This work shows that the combined use of CNNs and LSTMs by integrating spatial and temporal context along with time–frequency domain signals can significantly improve the accuracy of seizure detection.

TL;DR: The proposed model contains three steps to deal with the recognition of underwater targets: feature extraction, data augmentation and deep neural network, which uses the convolutional recurrent neural network for acoustic target recognition.

TL;DR: In this article, the authors focus on the application of acoustic and ultrasonic techniques for the detection and assessment of leaks, blockages and defect in buried pipes, and explore the future application of autonomous robotics to deploy these sensors in water distribution and sewerage pipes.

TL;DR: Two new substitution schemes for digital audio watermarking based on the Fourier transform are proposed and show that this approach offers good imperceptibility and generates watermarked audio sample robust against various attacks with a high-quality watermark.

TL;DR: A novel approach, based on attention guided 3D convolutional neural networks (CNN)-long short-term memory (LSTM) model, is proposed for speech based emotion recognition and it is seen that the proposed method outperforms the compared methods.

TL;DR: In this article, a low-frequency acoustic metamaterial based on a micro-perforated panel coupled to a multi-cavity of coiled-up spaces that is similar to a symmetrical labyrinth is presented.

TL;DR: In this article, the authors evaluated the perception of the indoor acoustic environment in relation to traditional and new activities performed at home, i.e., relaxation, and working from home (WFH).

TL;DR: A feature selection approach which modifies the initial population generation stage of metaheuristic search algorithms, is proposed and shows that the presented feature selection algorithms reduce the number of features significantly and are still effective for emotion classification from speech.

TL;DR: RPS of EEG signals can be used as a biomarker for psychiatrists which are simpler than the EEG signals in visual depression diagnostics, and it is found that EEG signals from the right hemisphere are significant for depression detection than the left hemisphere.

TL;DR: In this paper, an underwater acoustic metamaterial was developed, which can serve to absorb broadband low-frequency underwater sound under high hydrostatic pressure ranging from 200 to 2000 Hz.

TL;DR: The integration of multi-sensor information in conjunction with ANFIS as a classification algorithm, owing to its efficiency in predicting every possible detail about the health/condition of the different gearbox components, demonstrates its potential to be used as an adaptive condition monitoring as it.

TL;DR: In this article, the authors proposed an NDE method for accurate characterization of the elastic properties of wood using the Lamb wave propagation method and three-point bending tests were performed on the green poplar wood specimens with different moisture content (MC) levels.

TL;DR: In this article, the performance of PMN-PT piezoelectric single crystal elements under different pressures is compared with PZT-4 PZE ceramic elements.

TL;DR: In this article, the authors presented an overview on advancement made in designing of a digital infinite impulse response (IIR) filter, which is found to be challenging due to presence of poles in its transfer function.

TL;DR: A new heart sound classification model is proposed based on Local Binary Pattern (LBP) and Local Ternary (LTP) Pattern features and deep learning that surpasses the up-to-date methods according to the classification accuracy rate.

TL;DR: In this article, the authors investigated how the environmental sound quality influence visitors' soundscape perceptions, preferences, and behavior and found that the visitors' loudness and satisfaction perceptions were associated with the maximum sound levels (LAmax and Nmax) instead of the time-equivalent sound levels of the environment.

TL;DR: In this study, propeller, eccentric and bearing failures, which are frequently seen in UAV motors, were created and the fault diagnosis was made by applying the recommended method on the sound data received from the motors.

TL;DR: In this paper, a method combining signal feature extraction with genetic algorithm optimization support vector machine (GA-SVM) was proposed to realize quantitatively testing of near-surface defects, and three kinds of neural network classifiers were used to identify the size and depth of defects by the features database.

TL;DR: In this paper, the authors investigated phenolic resin-bonded recycled denim as a potential replacement to synthetic sound absorbers and found that the mechanism of sound absorption for samples is viscosity resistance, in which SAC at low frequencies is low, however at high frequencies is quite significant.

TL;DR: Results clearly show how different types of personal protection equipment do affect speech transmission and sound pressure level especially at mid-high frequency and that the source emission lobes vary when wearing certain type of personal devices.

TL;DR: The proposed CNN algorithm has higher accuracy and shorter estimation time in small SNR environment, therefore, the method proposed can effectively identify the incoming wave direction of the unknown signal in water after training.

TL;DR: In this paper, an innovative natural fibro-granular composite made of kenaf fibers and waste rice husk granules is developed and presented in the impedance tube method.