Sound Model Research Articles

Lung Sound Recognition Method Based on Multi-Resolution Interleaved Net and Time-Frequency Feature Enhancement.

Air pollution and aging population have caused increasing rates of lung diseases and elderly lung diseases year by year. At the same time, the outbreak of COVID-19 has brought challenges to the medical system, which placed higher demands on preventing lung diseases and improving diagnostic efficiency to some extent. Artificial intelligence can alleviate the burden on the medical system by analyzing lung sound signals to help to diagnose lung diseases. The existing models for lung sound recognition have challenges in capturing the correlation between time and frequency information. It is difficult for convolutional neural network to capture multi-scale features across different resolutions, and the fusion of features ignores the difference of influences between time and frequency features. To address these issues, a lung sound recognition model based on multi-resolution interleaved net and time-frequency feature enhancement was proposed, which consisted of a heterogeneous dual-branch time-frequency feature extractor (TFFE), a time-frequency feature enhancement module based on branch attention (FEBA), and a fusion semantic classifier based on semantic mapping (FSC). TFFE independently extracts the time and frequency information of lung sounds through a multi-resolution interleaved net and Transformer, which maintains the correlation between time-frequency features. FEBA focuses on the differences in the influence of time and frequency information on prediction results by branch attention. The proposed model achieved an accuracy of 91.56% on the combined dataset, by an improvement of over 2.13% compared to other models.

Performance of Sound Absorption and Noise Reduction for Dislocation Honeycomb Sandwich Panel With Built-in Coating

The effects of diatom mud coating on characteristic impedance is studied by using the double-thickness method. The parallel relationships among the concave arc column filled with diatom mud, honeycomb cells, the overall core layer, and micro-perforation are considered in using the acousto-electric analogy method. In the case of a series relationship of plates, the sound absorption coefficient of the honeycomb structure of the micro-perforated plate is calculated. The effects of diatom mud coating and dislocation arrangement on the sound absorption coefficient of sandwich panels are numerically simulated by COMSOL. To further verify the reliability of the sound absorption theoretical model, test specimens are made and the effects of dislocation arrangement and diatom mud coating on sound absorption performance are tested by using impedance tube equipment. The effect of dislocation arrangement and diatom mud coating on the sound absorption performance of low-frequency noise of sandwich panels is analysed from the parameters of sound absorption coefficient, resonance frequency, acoustic impedance, and fitting results.

Contextual Gaps in Machine Learning for Mental Illness Prediction: The Case of Diagnostic Disclosures

Getting training data for machine learning (ML) prediction of mental illness on social media data is labor intensive. To work around this, ML teams will extrapolate proxy signals, or alternative signs from data to evaluate illness status and create training datasets. However, these signals' validity has not been determined, whether signals align with important contextual factors, and how proxy quality impacts downstream model integrity. We use ML and qualitative methods to evaluate whether a popular proxy signal, diagnostic self-disclosure, produces a conceptually sound ML model of mental illness. Our findings identify major conceptual errors only seen through a qualitative investigation -- training data built from diagnostic disclosures encodes a narrow vision of diagnosis experiences that propagates into paradoxes in the downstream ML model. This gap is obscured by strong performance of the ML classifier (F1 = 0.91). We discuss the implications of conceptual gaps in creating training data for human-centered models, and make suggestions for improving research methods.

Open-set lung sound recognition model based on conditional Gaussian capsule network and variational time–frequency feature reconstruction

Lung sound auscultation is an essential method for diagnosing lung diseases; however, most existing lung sound recognition methods fail to identify classes that are unknown in training. Thus, we proposed an open-set lung sound recognition model based on the conditional Gaussian capsule network and variational time–frequency feature reconstruction. The proposed model incorporates an inference network, a cubic encoder, an attention module, a classifier, a cubic decoder, and a generative network. First, the inference network is employed to extract the time–frequency features of lung sounds at a single time step. Then, the variational distribution of lung sounds is computed using the capsule network and optimized to approximate the Gaussian model of the class to which the sample belongs according to the labels. Time–frequency synchronized feature extraction and reconstruction are performed on the entire lung sound sample using the cubic encoder and cubic decoder. Finally, we utilize the generative network to refactor the lung sound features for open-set recognition. The proposed model was evaluated experimentally on a combined dataset using two different category assignment schemes. The results demonstrate that the proposed model achieved accuracies of 82.31% and 88.47%, respectively, thereby outperforming existing methods.

Geospatial modelling and socioeconomic inequalities of transportation, human, and nature-based sounds in Accra, Ghana

Geospatial modelling and socioeconomic inequalities of transportation, human, and nature-based sounds in Accra, Ghana

A Sound Velocity Prediction Model for Seafloor Sediments Based on Deep Neural Networks

The acoustic properties of seafloor sediments have always been important parameters in sound field analyses and exploration for marine resources, and the accurate acquisition of the acoustic properties of sediments is one of the difficulties in the study of underwater acoustics. In this study, sediment cores were taken from the northern South China Sea, and the acoustic properties were analyzed. Since traditional methods (such as regression equations or theoretical models) are difficult to apply in practical engineering applications, we applied remote sensing data to sound velocity prediction models for the first time. Based on the influencing mechanism of the acoustic properties of seafloor sediments, the sediments’ source, type and physical properties have a great influence on the acoustic properties. Therefore, we replaced these influencing factors with easily accessible data and remote sensing data, such as parameters of granularity, distance to the nearest coast, decadal average sea surface productivity, water depth, etc., using deep neural networks (DNN) to develop a sound velocity prediction model. Compared with traditional mathematical analyses, the DNN model improved the accuracy of prediction and can be applied to practical engineering applications.

Common risk factors for dental caries and impaired glucose regulation in Guangxi, China.

To assess the prevalence of caries and impaired glucose regulation (IGR) and try to investigate their common risk factors among adult residents in Guangxi province. A cross-sectional study was conducted on a sample of 2993 adults from five different areas of Guangxi province. The sociodemographic data, history of personal habits such as diet and physical activities, physical measurements, oral examination results and biochemical laboratory test data were collected to establish a database and prepare a sound research model. Chi-square test and multiple logistic regression were used to analyse the risk factors for dental caries and IGR. The prevalence rate for caries was 85.9%, and the mean DMFT score was 7.35. In multiple logistic regression, after adjustment, education level, occupation, daily consumption of vegetables, weekly consumption of carbonated beverages and weekly exercise were associated with caries (odds ratio [OR]: 2.10, OR: 1.80, OR: 1.40, OR: 2.45, OR: 2.38). The prevalence of IGR was 33.5%, and after adjustment, results showed that occupation, body mass index, waist circumference, systolic blood pressure, diastolic blood pressure, high-density lipoprotein-C levels and low-density lipoprotein-C levels were significantly associated with IGR (OR: 0.80, OR: 1.70, OR: 1.56, OR: 1.88, OR: 1.60, OR: 1.43, OR: 1.48). The strength of association between caries/IGR and risk factors was a weak association or moderate association. We have not found common risk factors between dental caries and IGR. Therefore, further studies are needed to explore these common risk factors to prevent caries and IGR.

MERGERS AND ACQUISITIONS. AN EVALUATION ANALYSIS OF BANKRUPTCY PRE AND POST OF BOTH EVENTS. EVIDENCE FROM GREECE

The banking sector is one of the most important sectors in economy of the world and occupies a prominent position in the development. The banking system in Greece is regulated by the European Central Bank (ECB) and is composed of various types of banks, including systemic commercial banks, non systemic commercial banks and cooperative banks. The purpose of this study is to study the case of the reduction or not of the occurrence of bank bankruptcy after the acquisition they made of banks with financial difficulties. For this purpose, we study the possible bankruptcy of the acquired banks before their acquisition, as well as the possible bankruptcy of the acquiring banks before and after the acquisition. There are several models for predicting bankruptcy, including financial ratio analysis Z-score model, Zeta model, financial soundness model and other models. In this study to predict bankruptcy for banks we use the Zeta model for banks. This model is one of the commonly used in the international scientific community. The time period of the study is defined after the beginning of the global financial crisis in the year of 2008 and before the pandemic. This global financial crisis as known invaded Greece mainly in year 2010 an the pandemic started at the end of year 2019. The examined time period concerns both a short-term and a long-term period of time for the most rational drawing of conclusions. This specific study is based on the analysis of two of the most characteristic cases involving Greek banks involved in takeovers. One case concerns Greek cooperative banks and the other one concerns Greek systemic banks.
 Keywords: Cooperative Banks, Mergers & Acquisitions, Cash Flows Ratio, Profitability, Insolvency.
 JEL Classifications: G21, G33, G34

Modern Methods of Sound Propagation Modeling Based on the Expansion of Acoustic Fields over Normal Modes

A review of modern methods of modeling acoustic fields based on their representation as a superposition of normal modes is presented. Most of the described methods are based on an approach to calculating mode amplitudes by solving parabolic equations of various types, both narrow-angle and wide-angle. We also consider two-dimensional methods for calculating acoustic fields, to which the above-mentioned three-dimensional approaches are reduced in the absence of dependence of the field and medium parameters on one of the horizontal coordinates. The computation of both time-harmonic acoustic fields and pulsed sound signals is discussed. A number of numerical examples are considered in which such calculations are performed taking into account three-dimensional sound propagation effects. For the first time within the framework of this approach, the calculation of particle accelerations at the pulse signal reception points, as well as the calculation of the energy density flux of the vector field were performed.

Source apportionment of measured volatile organic compounds in Maricopa County, Arizona

ABSTRACT With the goal of corroborating existing emissions inventories of volatile organic compounds (VOCs), a statistical analysis was undertaken on measured ambient VOC concentrations in Maricopa County, Arizona. The Chemical Mass Balance (CMB) model was used to generate emissions source contribution estimates based on ambient VOC concentrations collected at the JLG Supersite in Phoenix, Arizona, and emissions source profiles obtained from EPA’s SPECIATE database. With trial-and-error, optimal model performance using a combination of emissions source profiles yielded source contribution estimates which could be compared to existing regulatory engineering-based emissions inventories. The ultimate objective of this study is to offer a comparison to the “top-down” emissions modeling via CMB and the “bottom-up” modeling traditionally used in preparing emission inventories to identify possible discrepancies and help direct future investigations to better understand local air quality. The methods used to develop the “bottom-up” inventory rely upon sound modeling developed to accurately capture emissions from various source categories. The results show discrepancies between the “bottom-up” and “top-down” emission inventory for VOC emissions from biogenic and natural gas combustion sources, suggesting that the emission strength from these source categories should be further investigated. Implications: The following implication statement has been prepared for the manuscript titled Source Apportionment of Measured Volatile Organic Compounds in Maricopa County, Arizona. The purpose of preparing such a study was to independently corroborate the findings of Maricopa County Air Quality Department (MCAQD) on source contribution estimates of VOC emissions as published in their 2020 Periodic Emissions Inventory for Ozone Precursors. The goal of preparing the findings in the study was to provide additional commentary on the significance of various VOC emissions sources to tropospheric ozone formation in Maricopa County through an alternate air quality modeling approach. The findings from this study are significant to the environment and health of Maricopa County as they offer additional insights into the pathways by which tropospheric ozone may form.

Fuzzy Adaptive PSO-ELM Algorithm Applied to Vehicle Sound Quality Prediction

When dealing with specific tasks, the hidden layer output matrix of an extreme learning machine (ELM) may change, largely due to the random assigned weight matrix of the input layer and the threshold matrix of the hidden layer, which sequentially leads to the corresponding change to output weights. The unstable fluctuations of the output weights increase the structural risk and the empirical risk of ELM. This paper proposed a fuzzy adaptive particle swarm optimization (PSO) algorithm to solve this problem, which could nonlinearly control the inertia factor during the iteration by fuzzy control. Based on the fuzzy adaptive PSO-ELM algorithm, a sound quality prediction model was developed. The prediction results of this model were compared with the other three sound quality prediction models. The results showed that the fuzzy adaptive PSO-ELM model was more precise. In addition, in comparison with two other adaptive inertia factor algorithms, the fuzzy adaptive PSO-ELM model was the fastest model to reach goal accuracy.

The Concept of Spiritual Personality Based on the Sound Heart Model

The theory of Sound Heart in spiritual health was investigated in 2019 in "Chair of Behavioral Sciences" in Shahid Beheshti University by psychology professors. Then it was investigated in the "Chair of Transcendental Sciences" by the clerics of the seminary. It received the permission to perform the "Pre-Semitism". The model was investigated with the presence of ten judges, critics and observers of the "Supreme Council of Cultural Revolution" in the meeting of 2022. Asadzandi, the theorist of the Sound heart model by implementing the suggestions of professors, completed the theory according to the criteria of writing theorizing plans in the "Support Board for Theorizing, Criticism and Scientific Debate Chairs of the Supreme Council of the Cultural Revolution". The final meeting was held in 2023. Sound Heart Model was approved by this important scientific-executive center in Iran. The following content is part of the topics discussed in that meeting.

Sound Identification Method for Gas and Coal Dust Explosions Based on MLP.

To solve the problems of backward gas and coal dust explosion alarm technology and single monitoring means in coal mines, and to improve the accuracy of gas and coal dust explosion identification in coal mines, a sound identification method for gas and coal dust explosions based on MLP in coal mines is proposed, and the distributions of the mean value of the short-time energy, zero crossing rate, spectral centroid, spectral spread, roll-off, 16-dimensional time-frequency features, MFCC, GFCC, short-time Fourier coefficients of gas explosion sound, coal dust sound, and other underground sounds were analyzed. In order to select the most suitable feature vector to characterize the sound signal, the best feature extraction model of the Relief algorithm was established, and the cross-entropy distribution of the MLP model trained with the different numbers of feature values was analyzed. In order to further optimize the feature value selection, the recognition results of the recognition models trained with the different numbers of sound feature values were compared, and the first 35-dimensional feature values were finally determined as the feature vector to characterize the sound signal. The feature vectors are input into the MLP to establish the sound recognition model of coal mine gas and coal dust explosion. An analysis of the feature extraction, optimal feature extraction, model training, and time consumption for model recognition during the model establishment process shows that the proposed algorithm has high computational efficiency and meets the requirement of the real-time coal mine safety monitoring and alarm system. From the results of recognition experiments, the sound recognition algorithm can distinguish each kind of sound involved in the experiments more accurately. The average recognition rate, recall rate, and accuracy rate of the model can reach 95%, 95%, and 95.8%, respectively, which is obviously better than the comparison algorithm and can meet the requirements of coal mine gas and coal dust explosion sensing and alarming.

An inter-model comparison of parabolic equation methods for sound propagation from wind turbines.

The modeling of sound propagation for land-based wind turbines is a complex task that takes various parameters into account. Not only do the wind speed and wind direction affect the noise received at a certain position by changing the refraction of the sound, but also the terrain complexity, ground impedance, and receiver position relative to the source and ground all affect propagation. These effects are seen by the reflections of the sound at the ground surface causing interference of sound waves, or by the receiver being positioned in and out of noise shadow zones in the upwind far field position, or in steep terrain irregularities. Several sound propagation models with different levels of fidelity have been developed through time to account for these effects. This paper will focus on two different parabolic equation models, the Beilis-Tappert Parabolic Equation and the Generalized Terrain Parabolic Equation, through theoretical studies of varying terrain complexity, ground impedance, and sound speed profiles (upwind, downwind, and no wind). In addition, the propagation models are validated through spectral comparisons to noise measurements from two different campaigns considering loudspeaker noise and wind turbine noise, respectively.

FOOD HUBS AS TOOL FOR DEVELOPING ENTREPRENEURSHIP IN GASTRONOMY: THE CASE STUDY OF DUBROVNIK

As the planning profession begins to embrace food and agriculture as important opportunities for sustainable cities and towns, planners are searching for ideas that can be implemented at the local level. Food hubs are gaining popularity as a way to build strong local food systems and healthy communities. Food hubs are innovations in local food systems that serve as an alternative to the conventional food distribution system. Hubs help connect small farmers with local markets and increase food access for local residents. But it is clearly that focusing on the local cuisine as a tourist destination product is worthwhile. Food hub operators are skilled business people who have identified a challenge how to satisfy retail and institutional market demand to source from small and middle size producers and have deftly come up with regionally appropriate solutions that not only result in positive economic outcomes but also provide valuable services to producers and their wider community. Food hub operators represent a new kind of food entrepreneur, one that is increasingly demonstrating a financially sound business model that can be both market and mission driven. This paper examines the importance of the establishment of a food hub for the development of entrepreneurship and innovation in gastronomy, i.e. for the development of the gastronomic offer in Dubrovnik. The survey was conducted in June 2022 among 93 graduates of the School of Tourism and Hospitality to find out their opinion about the establishment of a food hub and whether they are inclined to become its users. Research has proven that most graduates would use food hub services and as such they are necessary for business creation and innovation in the food service industry.

A wearable nanoscale heart sound sensor based on P(VDF-TrFE)/ZnO/GR and its application in cardiac disease detection.

This paper describes a method for preparing flexible composite piezoelectric nanofilms of P(VDF-TrFE)/ZnO/graphene using a high-voltage electrospinning method. Composition and β-phase content of the piezoelectric composite films were analyzed using X-ray diffraction. The morphology of the composite film fibers was observed through scanning electron microscopy. Finally, the P(VDF-TrFE)/ZnO/graphene composite film was encapsulated in a sandwich-structure heart sound sensor, and a visual heart sound acquisition and classification system was designed using LabVIEW. A heart sound classification model was trained based on a fine K-nearest neighbor classification algorithm to predict whether the collected heart sounds are normal or abnormal. The heart sound detection system designed in this paper can collect heart sound signals in real time and predict whether the heart sounds are normal or abnormal, providing a new solution for the diagnosis of heart diseases.

A case study on improving electric bus interior sound quality based on sensitivity analysis of psycho-acoustics parameters

The research on vehicle sound quality is an emerging and highly promising field. This paper proposes a solution for sound quality improvement based on sensitivity analysis of psycho-acoustic parameters, in which the main acoustic techniques involved include noise signal acquisition, subjective and objective evaluations, sound quality modelling and prediction, parameter sensitivity and spectral analysis, and fuzzy comprehensive evaluation. In addition, taking 64 noise samples of electric bus as an application case, the presented sound quality analysis steps are implemented successively, and the obtained test results of improving the whole vehicle sound quality verify the feasibility and effectiveness of the proposed scheme.

On Woven Fabric Sound Absorption Prediction

For building applications, woven fabrics have been widely used as finishing elements of room interior but not in particular aimed for sound absorbers. Considering the micro perforation of the woven fabrics, they should have potential to be used as micro-perforated panel (MPP) absorbers; some measurement results indicated such absorption ability. Hence, it is of importance to have a sound absorption model of the woven fabrics to enable us predicting their sound absorption characteristic that is beneficial in engineering design phase. Treating the woven fabric as a rigid frame, a fluid equivalent model is employed based on the formulation of Johnson-Champoux-Allard (JCA). The model obtained is then validated by measurement results where three kinds of commercially available woven fabrics are evaluated by considering their perforation properties. It is found that the model can reasonably predict their sound absorption coefficients. However, the presence of perturbations in pores give rise to inaccuracy of resistive component of the predicted surface impedance. The use of measured static flow resistive and corrected viscous length in the calculations are useful to cope with such a situation. Otherwise, the use of an optimized simple model as a function of flow resistivity is also applicable for this case.

Development of a Sound Quality Evaluation Model Based on an Optimal Analytic Wavelet Transform and an Artificial Neural Network

The purpose of this study was to develop a sound quality model for real time active sound quality control systems. The model is based on an optimal analytic wavelet transform (OAWT) used along with a back propagation neural network (BPNN) in which the initial weights and thresholds are determined by particle swarm optimisation (PSO). In the model the input signal is decomposed into 24 critical bands to extract a feature matrix, based on energy, mean, and standard deviation indices of the sub signal scalogram obtained by OAWT. The feature matrix is fed into the neural network input to determine the psychoacoustic parameters used for sound quality evaluation. The results of the study show that the present model is in good agreement with psychoacoustic models of sound quality metrics and enables evaluation of the quality of sound at a lower computational cost than the existing models.

A lightweight multi-sensory field-based dual-feature fusion residual network for bird song recognition

Bird song recognition plays an important function in ecosystem balance monitoring, biodiversity detection, and biodiversity conservation. Due to the complexity of the natural environment, based on deep learning, there is a problem of information loss in extracting audio features with a single filter. Identifying bird sounds efficiently and quickly is still a challenge. To address this problem, a lightweight multi-sensory field dual-feature fusion residual network (LDFSRE-NET) is proposed in this paper. Firstly, using the feature extraction filters based on Mel and SincNet to extract birdsong’s low-frequency and timbre information. The proposed dual-feature fusion module (FFMS) is used to fuse the low-frequency and timbre information with the differences between the two feature sets. Secondly, the double-layer residual module (DBNet), connected by basicblock and downblock, is used as the backbone network for bird song recognition to improve the training speed. To improve the different perceptual fields of the backbone network, the 3 × 3 convolutional modules in the basicblocks of the two residual modules are replaced with a Diverse Branch Block. They make the network performs better on recognition tasks under complex situations of multiple branches. Then, the ShuffleAttention attention module is embedded between the two layers of the residual module for transferring its valid information, enhancing the spectrogram ripple feature, and further improving the network’s recognition performance. Finally, extensive experiments are conducted on three datasets: the self-built 30-class bird song dataset (Birdselfdata), the public datasets Birdsdata and Urbansound8K. The model proposed in this paper surpasses the state-of-the-art sound recognition model methods in terms of efficiency and accuracy. The recognition accuracy on these three datasets of this model are 96.75%, 96.46%, and 97.98%, with the F1-score of 96.79%, 96.39%, and 97.88%.