Fast Detection and Classification of Dangerous Urban Sounds Using Deep Learning

Video analytics is an integral part of surveillance cameras. Comparedto video analytics, audio analytics offers several benefits, includingless expensive equipment and upkeep expenses. Additionally, the volume ofthe audio datastream is substantially lower than the video camera datastream,especially concerning real-time operating systems, which makes it lessdemanding of the data channel’s bandwidth needs. For instance, automaticlive video streaming from the site of an explosion and gunshot to the policeconsole using audio analytics technologies would be exceedingly helpful forurban surveillance. Technologies for audio analytics may also be used toanalyze video recordings and identify occurrences. This research proposeda deep learning model based on the combination of convolutional neuralnetwork (CNN) and recurrent neural network (RNN) known as the CNNRNNapproach. The proposed model focused on automatically identifyingpulse sounds that indicate critical situations in audio sources. The algorithm’saccuracy ranged from 95% to 81% when classifying noises from incidents,including gunshots, explosions, shattered glass, sirens, cries, and dog barking.The proposed approach can be applied to provide security for citizens in openand closed locations, like stadiums, underground areas, shopping malls, andother places.

Recognition System for Diagnosing Pneumonia and Bronchitis Using Children’s Breathing Sounds Based on Transfer Learning

Respiratory infections in children increase the risk of fatal lung disease,making effective identification and analysis of breath sounds essential.However,most studies have focused on adults ignoring pediatric patients whose lungs are more vulnerable due to an imperfect immune system,and the scarcity of medical data has limited the development of deep learning methods toward reliability and high classification accuracy.In this work,we collected three types of breath sounds from children with normal(120 recordings),bronchitis(120 recordings),and pneumonia(120 recordings)at the posterior chest position using an off-the-shelf 3M electronic stethoscope.Three features were extracted from the wavelet denoised signal:spectrogram,mel-frequency cepstral coefficients(MFCCs),and Delta MFCCs.The recog-nition model is based on transfer learning techniques and combines fine-tuned MobileNetV2 and modified ResNet50 to classify breath sounds,along with software for displaying analysis results.Extensive experiments on a real dataset demonstrate the effectiveness and superior performance of the proposed model,with average accuracy,precision,recall,specificity and F1 scores of 97.96%,97.83%,97.89%,98.89%and 0.98,respectively,achieving superior performance with a small dataset.The proposed detection system,with a high-performance model and software,can help parents perform lung screening at home and also has the potential for a vast screening of children for lung disease.

Introduction to the Special Issue on Perspectives on Soundscape and Challenges of Noise Pollution: A Multidisciplinary Approach to Sustainable Environmental Solutions

Over the past two decades,research on the subject of noise pollution and urban soundscapes has seen significant growth[1,2].The goal of these studies was to gain a better understanding of the urban acoustic environment by employing various methodologies and techniques to delve into the complexity of this topic.These research efforts have primarily revolved around two fundamental axes[3].On one hand,the first axis focused on combating noise pollution[4–6],emphasizing the reduction of unwanted sounds and compliance with sound levels set by environmental and health protection organizations[7,8].

Spectral Soundscapes in Elfriede Jelinek’s Post-Holocaust Novel The Children of the Dead and Its 2019 Film Adaptation

How should we approach Die Kinder der Toten by the Austrian Nobel Prize winner Elfriede Jelinek today?And how does the 2019 film adaptation by the Nature Theatre of Oklahoma change the text’s reception through focus on intermedial and intertextual elements?So far,the most insightful reviews have centered on the conceptual,contextual and textual-and thus also political aspects of this work.By focusing on intertextual and intermedial components,I hope to illustrate a few aspects of the novel that have yet to be analyzed in the scholarship on Jelinek.Drawing on Derrida’s Specters of Marx and on elements of sound studies,literature studies,and film studies,I hope to demonstrate how sound can have a significant spectral presence that connects with other literary texts and media,different world regions in the past,the present and the future.

Soundscape Design of Old Urban Residential Districts

This paper introduced the concept of soundscape, investigated sound environment of old urban residential districts, and explored soundscape elements and soundscape designs. In view of current sound environment features of old urban residential districts and different population groups' preferences for different sound elements, this paper proposed soundscape design methods to improve sound environment of old urban residential districts.

OMP-BASED MULTI-BAND SIGNAL RECONSTRUCTION FOR ECOLOGICAL SOUNDS RECOGNITION

The paper proposes a new method of multi-band signal reconstruction based on Orthogonal Matching Pursuit(OMP),which aims to develop a robust Ecological Sounds Recognition(ESR)system.Firstly,the OMP is employed to sparsely decompose the original signal,thus the high correlation components are retained to reconstruct in the first stage.Then,according to the frequency distribution of both foreground sound and background noise,the signal can be compensated by the residual components in the second stage.Via the two-stage reconstruction,high non-stationary noises are effectively reduced,and the reconstruction precision of foreground sound is improved.At recognition stage,we employ deep belief networks to model the composite feature sets extracted from reconstructed signal.The experimental results show that the proposed approach achieved superior recognition performance on 60 classes of ecological sounds in different environments under different Signal-to-Noise Ratio(SNR),compared with the existing method.

Sounds of Home

The weather had been unusually warm for May in Brandon, Miss. My wife Pat and I were nursing aSunday-morning cup of coffee on our deck and watch-ing thunderheads build rapidly into mountainous cloudson the southern horizon. There was barely any breeze,and the humidity was so thick you could almost rollit in your palms. By the time we finished our second cup, the

Ultrastructure of stridulating organ of Xylotrechus rusticus L. (Coleoptera, Cerambycidae) and behavioral responses to alarm sounds

We used scanning electron microscope （SEM） to observe the ultrastructure of stridulating organs in Xylotrechus rusticus L. We com- pared the morphological structure and size of stridulating organs, the numbers of a tooth-like part used in stridulation and its presence in fe- males and males of this beetle. The alarm sound of X.. rusticus was re- corded first when it was stimulated, then we tested behavioral responses to this alarm sound. The alarm sound ofX. rusticus has a warning effect on conspecifics.

Sounds Synthesis with Slime Mould of Physarum Polycephalum

This paper introduces a novel application of bionic engineering： a bionic musical instrument using Physarum polycephalum. Physarum polycephalum is a huge single cell with thousands of nuclei, which behaves like a giant amoeba. During its foraging behavior this plasmodium produces electrical activity corresponding to different physiological states. We developed a method to render sounds from such electrical activity and thus represent spatio-temporal behavior of slime mould in a form apprehended auditorily. The electrical activity is captured by various electrodes placed on a Petri dish containing the cultured slime mold. Sounds are synthesized by a bank of parallel sinusoidal oscillators connected to the electrodes. Each electrode is responsible for one partial of the spectrum of the resulting sound. The behavior of the slime mould can be controlled to produce different timbres.

Wavelet packet feature selection for lung sounds based on optimization

In this paper, a wavelet packet feature selection method for lung sounds based on optimization is proposed to obtain the best feature set which maximizes the differences between normal lung sounds and abnormal lung sounds(sounds with wheezes or rales). The proposed method includes two main steps: Firstly, the wavelet packet transform(WPT) is used to extract the original features of lung sounds; then the genetic algorithm(GA) is used to select the best feature set. The obtained optimal feature set is sent to four different classifiers to evaluate the performance of the proposed method. Experimental results show that the feature set obtained by the proposed method provides a higher classification accuracy of 94.6% in comparison with the best wavelet packet basis approach and multi-scale principal component analysis(PCA) approach. Meanwhile, the proposed method has effective generalization performance and can obtain the best feature set without priori knowledge of lung sounds.

A new method of lung sounds filtering using modulated least mean square—Adaptive noise cancellation

Advanced processing of lung sound (LS) recording is a significant means to separate heart sounds (HS) and combined low frequency noise from instruments (NI), with saving its characteristics. This paper proposes a new method of LS filtering which separates HS and NI simultaneously. It focuses on the application of least mean squares (LMS) algorithm with adaptive noise cancelling (ANC) technique. The second step of the new method is to modulate the reference input r1(n) of LMS-ANC to acquiesce combining HS and NI signals. The obtained signal is removed from primary signal (original lung sound recording-LS). The original signal is recorded from subjects and derived HS from it and it is modified by a band pass filter. NI is simulated by generating approximately periodic white gaussian noise (WGN) signal. The LMS-ANC designed algorithm is controlled in order to determine the optimum values of the order L and the coefficient convergence μ. The output results are measured using power special density (PSD), which has shown the effectiveness of our suggested method. The result also has shown visual difference PSD (to) normal and abnormal LS recording. The results show that the method is a good technique for heart sound and noise reduction from lung sounds recordings simultaneously with saving LS characteristics.

The Apple and the Ear, Grasping Sounds in Space—A Theory of Sound Localization

Sensing the direction of origin of a sound in space has long been attributed to the delay between arrival times between the two ears. This, now discredited two dimensional theory, was put to rest by the observation that a person deaf in one ear can locate sounds in three dimensional space. We present here a new theory of sound localization that has the re-quired three dimensional measurement. It is a theory that interprets the well researched biological structure of the mammalian cochlea in a new and logical way, which leads to a deeper understanding of how sound localization functions.

Snoring sounds’ statistical characteristics depend on anthropometric parameters

Snoring is common in people with obstructive sleep apnea (OSA). Although not every snorer has OSA or vice-versa, many studies attempt to use snoring sounds for classification of people into two groups of OSA and simple snorers. This paper discusses the relationship between snorers’ anthropometric parameters and statistical characteristics of snoring sound (SS) and also reports on classification accuracies of methods using SS features for screening OSA from simple snorers when anthropometric parameters are either matched or unmatched. Tracheal respiratory sounds were collected from 60 snorers simultaneously with full-night Polysomnography (PSG). Energy, formant frequency, Skewness and Kurtosis were calculated from the SS segments. We also defined and calculated two features: Median Bifrequency (MBF), and projected MBF (PMBF). The statistical relationship between the extracted features and anthropometric parameters such as height, Body Mass Index (BMI), age, gender, and Apnea-Hypopnea Index (AHI) were investigated. The results showed that the SS features were not only sensitive to AHI but also to height, BMI and gender. Next, we performed two experiments to classify patients with Obstructive Sleep Apnea (OSA) and simple snorers: Experiment A: a small group of participants (22 OSA and 6 simple snorers) with matched height, BMI, and gender were selected and classified using Na?ve Bayes classifier, and Experiment B: the same number of participants with unmatched height, BMI, and gender were chosen for classification. A sensitivity of 93.2% (87.5%) and specificity of 88.4% (86.3%) was achieved for the matched (unmatched) groups.

Sound Quality of Turn Indicator Sounds-Use of aMultidimensional Approach in the Automotive ProductDevelopment

Vehicle sounds are important factors of customer satisfaction and have a decisive influence on the product automobile andits quality impression. It becomes more and more important to connect customer requirements and technical specifications to developa vehicle sound with high quality. The turn indicator sound can be described as one sound, which gives the customer an importantfeedback of correct function performance and can be seen as one of the sounds, which play a role in the customer＇s perception ofvehicle quality. In a laboratory experimental study, the question was investigated, how a turn indicator sound must be designed to beperceived as pleasant and high-quality. A multidimensional approach was chosen to combine subjective customer assessments,objective psychophysiological responses of the study participants and physical parameters of the sounds. In total, 15 different tumindicator sounds were assessed by 48 subjects. The study shows how the connection of subjective and objective parameters cansupport product development. The multi-dimensional approach helps to derive recommendations for action to improve the soundquality of the product automobile. Also, the study shows a possibility to involve the human factor in a highly technical environment.

From dBA to soundscape indices: Managing our sound environment

While in the EU alone 80 million citizens are suffering from excessive environmental noise, the conventional approach, i.e., reduction of ‘sound level', does not always deliver the required improvements in quality of life. The growing field of ‘soundscape studies' is addressing this gap by considering the sound environment as perceived, in context, with an interdisciplinary approach. However, soundscapes are hugely complex,and measuring them as a basis for environmental design requires a step change to the discipline. This paper explores the need for developing ‘soundscape indices', in the movement from noise control to soundscape creation,adequately reflecting levels of human comfort, the impact of which will be reminiscent of that of the Decibel scale created by Bell Systems a century ago. By analysing the soundscape design of urban open public spaces, the coherent steps for achieving this are also discussed,including characterising soundscapes by capturing soundscapes and establishing a comprehensive database; determining key factors and their influence on soundscape quality based on the database; developing, testing and validating soundscape indices; and demonstrating the applicability of the soundscape indices in the management of our sound environment.

Can urban forests provide acoustic refuges for birds?Investigating the influence of vegetation structure and anthropogenic noise on bird sound diversity

As a crucial component of terrestrial ecosystems,urban forests play a pivotal role in protecting urban biodiversity by providing suitable habitats for acoustic spaces.Previous studies note that vegetation structure is a key factor influencing bird sounds in urban forests;hence,adjusting the frequency composition may be a strategy for birds to avoid anthropogenic noise to mask their songs.However,it is unknown whether the response mechanisms of bird vocalizations to vegetation structure remain consistent despite being impacted by anthropogenic noise.It was hypothesized that anthropogenic noise in urban forests occupies the low-frequency space of bird songs,leading to a possible reshaping of the acoustic niches of forests,and the vegetation structure of urban forests is the critical factor that shapes the acoustic space for bird vocalization.Passive acoustic monitoring in various urban forests was used to monitor natural and anthropogenic noises,and sounds were classified into three acoustic scenes(bird sounds,human sounds,and bird-human sounds)to determine interconnections between bird sounds,anthropogenic noise,and vegetation structure.Anthropogenic noise altered the acoustic niche of urban forests by intruding into the low-frequency space used by birds,and vegetation structures related to volume(trunk volume and branch volume)and density(number of branches and leaf area index)significantly impact the diversity of bird sounds.Our findings indicate that the response to low and high frequency signals to vegetation structure is distinct.By clarifying this relationship,our results contribute to understanding of how vegetation structure influences bird sounds in urban forests impacted by anthropogenic noise.

From understanding to designing soundscapes

Soundscape represents a step change in the field of environmental acoustics in that it combines physical,social,and psychological approaches.Although the term soundscape was introduced in the 1960s,significant attention to it has mainly been paid in the last decade or so in the community of environmental acoustics by researchers and recently by practitioners including policy makers.This paper explores the current situation and future challenges in soundscape.Starting with a framework on research and practical needs in soundscape and a brief introduction of some recent/current networks,activities,projects,and publications,this paper then presents a systematic review of recent progress in soundscape research and practice.A short review of the soundscape research in China is also given.

Sound preferences of the dense urban environment： Soundscape of Cairo

A questionnaire study was conducted to investigate the soundscape preferences of the sonic environment in Cairo. Participants, who were Cairo residents, were questioned about their appraisal of fami（iar urban soundscapes in a dose- and open-ended format questionnaire. Psycholinguistic data analysis of verbal descriptions expressed by respondents was conducted to identify the re（evance of semantic categories of environmental sounds and quantitative soundscape aspects for the urban sonic environment of Cairo. Resu（ts confirmed a direct retevance of the linguistic semantic auditory judgment and of the outputs of the quantitative dose-ended questions. Cairenes were also found to express their sonic environment （inguisti- cal（y based on physical properties rather than semantic features and values. Analyzing the relative annoyance increase （RAI） of the dose-ended part, overall positive RAI va（ues for all sound categories reveal how sensitive to noise Cairo residents are. Results further showed that at an RAI value of approximately 27%, sound category perception transforms from positive to negative.