scholarly journals Sound Levels Forecasting in an Acoustic Sensor Network Using a Deep Neural Network

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 903 ◽  
Author(s):  
Juan M. Navarro ◽  
Raquel Martínez-España ◽  
Andrés Bueno-Crespo ◽  
Ramón Martínez ◽  
José M. Cecilia
Keyword(s):  
Neural Network ◽  
Sensor Network ◽  
Sound Pressure Level ◽  
Deep Neural Network ◽  
Sound Pressure ◽  
Noise Pollution ◽  
Pressure Level ◽  
Acoustic Sensor ◽  
Short Term ◽  
Sound Levels

Wireless acoustic sensor networks are nowadays an essential tool for noise pollution monitoring and managing in cities. The increased computing capacity of the nodes that create the network is allowing the addition of processing algorithms and artificial intelligence that provide more information about the sound sources and environment, e.g., detect sound events or calculate loudness. Several models to predict sound pressure levels in cities are available, mainly road, railway and aerial traffic noise. However, these models are mostly based in auxiliary data, e.g., vehicles flow or street geometry, and predict equivalent levels for a temporal long-term. Therefore, forecasting of temporal short-term sound levels could be a helpful tool for urban planners and managers. In this work, a Long Short-Term Memory (LSTM) deep neural network technique is proposed to model temporal behavior of sound levels at a certain location, both sound pressure level and loudness level, in order to predict near-time future values. The proposed technique can be trained for and integrated in every node of a sensor network to provide novel functionalities, e.g., a method of early warning against noise pollution and of backup in case of node or network malfunction. To validate this approach, one-minute period equivalent sound levels, captured in a two-month measurement campaign by a node of a deployed network of acoustic sensors, have been used to train it and to obtain different forecasting models. Assessments of the developed LSTM models and Auto regressive integrated moving average models were performed to predict sound levels for several time periods, from 1 to 60 min. Comparison of the results show that the LSTM models outperform the statistics-based models. In general, the LSTM models achieve a prediction of values with a mean square error less than 4.3 dB for sound pressure level and less than 2 phons for loudness. Moreover, the goodness of fit of the LSTM models and the behavior pattern of the data in terms of prediction of sound levels are satisfactory.

scholarly journals Status of noise pollution in urban area of Dharan Sub- Metropolitan City and Inaruwa Municipality of Sunsari District, Nepal

2017 ◽  
Vol 7 (1) ◽  
pp. 35-40
Author(s):  
Ranij Shrestha ◽  
Alankar Kafle ◽  
Kul Prasad Limbu
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Pollution Assessment ◽  
Noise Pollution ◽  
Pressure Level ◽  
Noise Levels ◽  
Night Time ◽  
Level Measurement ◽  
Standard Value ◽  
Autumn And Winter

The environmental noise level measurement in Dharan and Inaruwa cities of eastern Nepal were conducted and compared with the ambient noise standards provided by Government of Nepal. The noise pollution assessment was performed in autumn and winter seasons by the indicator average day time sound pressure level (Ld, during 7.00 to 22.00 hrs) and average night time sound pressure level (Ln, during 22.00 to 7.00 hrs). The Ld and Ln values at the commercial, silence and residential zones of Dharan were 78 to 82 and 72 to 73, 65 to 73 and 60 to 70, 65 to 76 and 62 to 64 dB(A) in autumn and 78 to 79 and 72 to 76, 64 to 71 and 58 to 68, 63 to 74 and 60 to 62 dB(A) in winter, respectively whereas for Inaruwa, measurement were 75 to 77 and 73 to 75, 59 and 57, 67 and 60 dB(A) in autumn and 66 to 70 and 63 to 68, 55 and 53, 65 and 58 dB(A) in winter, respectively. The results showed that noise levels exceeded the standard value at most of the sites.

scholarly journals Investigation of Noise Pollution Distribution in Different Parts of Yazd Textile Factories

2021 ◽  
Author(s):  
Mohammad Javad Zare Sakhvidi ◽  
Hamideh Bidel ◽  
Ahmad Ali Kheirandish
Keyword(s):  
Occupational Exposure ◽  
Sound Pressure Level ◽  
Textile Industry ◽  
Sound Pressure ◽  
Noise Pollution ◽  
Sound Level ◽  
Pressure Level ◽  
Cross Sectional ◽  
Sound Pressure Levels ◽  
Different Parts

 Background: Chronic occupational exposure to noise is an unavoidable reality in the country's textile industry and even other countries. The aim of this study was to compare the sound pressure level in different parts of the textile industry in Yazd and in different parts of the textile industry. Methods: This cross-sectional study was performed on 930 textile workers in Yazd. A questionnaire was used to obtain demographic information and how to use protective equipment. Then, to obtain the sound pressure level of each unit and device and to use the measurement principles, a calibrated sound level meter was used. Then the results were analyzed using SPSS Ver.29 software. Results: The participants in this study were 714 males and 216 females with a mean age of 35.27 and 33.63 years, respectively. Seven hundred fifty-six participants (81.29%) were exposed to sound pressure levels higher than 85 dB. Among the participants, only 18.39% of the people used a protective phone permanently. Except for factory E, with an average sound pressure level of 77.78 dB, the rest of the factories had an average sound pressure level higher than the occupational exposure limit. The sound measurement results of different devices show that the sound pressure levels above 90 dB are related to the parts of Dolatab, Ring, Kinetting (knitting), Chanel, Autoconer, Dolakni, Open End, MultiLakni, Tabandegi, Texture, and Poy. Conclusion: Based on the results of the present study, noise above 90 dB is considered as one of the main risk factors in most parts of the textile industry (spinning and weaving), which in the absence of engineering, managerial or individual controls on it causes hearing loss in becoming employees of this industry

R-weighting provides better estimation for rat hearing sensitivity

2000 ◽  
Vol 34 (2) ◽  
pp. 136-144 ◽  
Author(s):  
E. Böjrk ◽  
T. Nevalainen ◽  
M. Hakumäki ◽  
H.-M. Voipio
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Sound Level ◽  
Pressure Level ◽  
Sound Studies ◽  
Response Curves ◽  
Acoustic Environment ◽  
High Frequencies ◽  
Hearing Sensitivity ◽  
Sound Levels

Since sounds may induce physiological and behavioural changes in animals, it is necessary to assess and define the acoustic environment in laboratory animal facilities. Sound studies usually express sound levels as unweighted linear sound pressure levels. However, because a linear scale does not take account of hearing sensitivity-which may differ widely both between and within species at various frequencies-the results may be spurious. In this study a novel sound pressure level weighting for rats, R-weighting, was calculated according to a rat's hearing sensitivity. The sound level of a white noise signal was assessed using R-weighting, with H-weighting tailored for humans, A-weighting and linear sound pressure level combined with the response curves of two different loudspeakers. The sound signal resulted in different sound levels depending on the weighting and the type of loudspeaker. With a tweeter speaker reproducing sounds at high frequencies audible to a rat, R- and A-weightings gave similar results, but the H-weighted sound levels were lower. With a middle-range loudspeaker, unable to reproduce high frequencies, R-weighted sound showed the lowest sound levels. In conclusion, without a correct weighting system and proper equipment, the final sound level of an exposure stimulus can differ by several decibels from that intended. To achieve reliable and comparable results, standardization of sound experiments and assessment of the environment in animal facilities is a necessity. Hence, the use of appropriate species-specific sound pressure level weighting is essential. R-weighting for rats in sound studies is recommended.

Average Is the New Loudest

2016 ◽  
Vol 26 ◽  
pp. 56-59
Author(s):  
Johannes Mulder
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Pressure Level ◽  
Audio Engineering ◽  
Sound Levels ◽  
Live Music ◽  
Measurement Strategies ◽  
Audio Production

This article discusses new sound pressure level (SPL) measurement strategies in the context of live music. A brief overview of the introduction of loudness normalization in broadcast audio engineering precedes a discussion of using average sound levels in measurements at concerts. The article closes with a short analysis of the implications of these developments for the notion of agency in the sociotechnical domain of audio production.

scholarly journals Identification and analysis of noise sources in the Noor-Abad gas compressor station, Iran

2015 ◽  
Vol 4 (1) ◽  
pp. 196
Author(s):  
Nader Mohammadi ◽  
Kami Mohammadi
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Acoustic Noise ◽  
Noise Pollution ◽  
Residential Area ◽  
Pressure Level ◽  
Compressor Station ◽  
Noise Condition ◽  
Noise Sources ◽  
Noise Map

The objective of this study is to identify the sources of acoustic noise (noise pollution) in the Noor-Abad gas compressor station and then to prioritize the station equipment based on noise pollution. First, the key locations inside the station as well as in the surrounding residential area, aka the study area, are determined for the measurement of sound pressure level. Then, the sound pressure level is measured at those points, and the related noise map is produced. Based on the noise map, the noise condition in the study area is evaluated by comparing the measured acoustic parameters with allowable standard values. Dangerous regions and critical points are thus identified. The major noise sources consist of main blowdown, units’ blowdowns, scrubbers, and turbo-compressors. The sound pressure level of main blowdown is measured at two intervals from its position: 80 m inside the station and 600 m outside the station (at the edge of the surrounding residential area). Also, the sound pressure level for a unit blowdown and a scrubber is measured at respectively 25 m and 40 m from their positions. Finally, the station equipment is prioritized based on noise pollution. The analysis of measurement results showed that the main noise sources are, respectively, the station main blowdown, units’ scrubbers, units’ blowdowns, turbo-compressors, and gas pipelines.

scholarly journals The relationship of Depression Anxiety and Stress Scale and Harmon Jones with Noise in Isfahan Steel Industry Workers

2021 ◽  
Author(s):  
Hadi ALIMORADI ◽  
Ruhollah FALLAH MADAVARI ◽  
Mahsa NAZARI ◽  
Reza JAFARI NODOSHAN ◽  
Mohammad Javad ZARE SAKHVIDI ◽  
...  
Keyword(s):  
Cognitive Dissonance ◽  
Sound Pressure Level ◽  
Steel Industry ◽  
Sound Pressure ◽  
Noise Pollution ◽  
Pressure Level ◽  
Control Group ◽  
Case Group ◽  
Wide Range ◽  
Relationship Of

Introduction: Loud noise is one of the harmful factors that affects industry workers seriously. In the steel industry, a wide range of equipment and machinery are used in the production processes, which are considered as the sources of annoying noise. Sound has immediate and delayed harmful effects on the process of concentration and increases blood pressure. The aim of this study was to investigate the effect of noise in two different ranges in the control and case groups within the authorized (between 60 to 85 dB) and unauthorized (above 85 dB) categories in the steel industry. Methods: This cross-sectional study was conducted among 300 workers in Isfahan Steel Industries. Environmental sound assessment was performed to determine the distribution of sound pressure level according to the ISO 9612 standard in the company's production units. In this method, the number of exposed people, the exposure time, and the weight factor corresponding to the sound pressure level were calculated in 30 minutes. The DASS-42 and Harmon Jones (DARQ) questionnaires were used to predict the mental state of the participants and to measure the severity of mood swings and arousal. The collected data were analyzed using SPSS statistical software (ver22). Results: Based on the findings, age had a significant effect on depression, marital status had a significant effect on anxiety, and work shift had a significant effect on the level of stress and cognitive dissonance of employees. The stress mean was significantly higher in the case group (14.40 ± 1.66) than the control group (p <0.001). This indicates the effect of sound intensity level on the increase of stress and cognitive dissonance of workers in a noisy environment. With increasing exposure to sound, the participants’ stress decreased (p <0.05). Conclusion: Considering the positive and significant relationship of noise level with stress and cognitive inconsistency of workers in the case group, it is necessary to take effective preventive measures to prevent psychological harm and maintain the workers' health in this industry. In order to reduce noise, a number of applicable solutions have been proposed including spatial planning, selection of suitable materials, control of noise pollution related to outdoor construction, control of noise pollution related to indoor construction, and training.

Case study: Evaluation of noise reduction in frequencies and sound reduction index of construction with variable noise isolation

2020 ◽  
Vol 68 (3) ◽  
pp. 199-208
Author(s):  
Tomas VilniÅ¡kis ◽  
Tomas JanuÅ¡eviÄ?ius ◽  
Pranas BaltrÄ—nas
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Pressure Level ◽  
Glass Wool ◽  
Noise Attenuation ◽  
Engineering Equipment ◽  
Sound Levels ◽  
Air Supply ◽  
Study Evaluation ◽  
Sound Reduction

Intense sound levels produced by engineering equipment have become an acute issue. As most of engineering equipment require air supply, exhaust and good ventilation, it is not possible to control the noise by covering them with tight hoods. Louver with blades covered with acoustic materials and gaps that enable free circu- lation of air are used to this end. Three louver configurations were tested in the semi-anechoic chamber: bare metal louver blades, louver with blades covered with 20-mm-thick polystyrene foam slabs on both sides, and louver with blades covered with 15-mm-thick glass wool slab. According to the test results, louver with blades covered with glass wool slab demonstrated the best noise attenuation characteristics. The reduction of equiv- alent sound pressure level subject to blade inclination angle was from 10.8 to 12.5 dB. Sound pressure level reduction by louver with blades covered with poly- styrene foam slabs was weaker: the reduction of equivalent sound pressure level was from 5.4 to 8.4 dB. Louver with blades not covered with any acoustic material demonstrated the least noise attenuation result from 1.9 to 3.9 dB

Effects of Leisure Activity Related Noise in Residential Zones

2005 ◽  
Vol 12 (4) ◽  
pp. 265-276 ◽  
Author(s):  
J.M. Barrigón Morillas ◽  
V. Gómez Escobar ◽  
J.A. Méndez Sierra ◽  
R. Vílchez-Gómez ◽  
J.M. Vaquero
Keyword(s):  
Sound Pressure Level ◽  
Sound Pressure ◽  
Leisure Activity ◽  
Pressure Level ◽  
Noise Sources ◽  
Sound Levels ◽  
The City

An analysis of two noise surveys of the city of Cáceres is presented. The first was made for 400 inhabitants living throughout the city, and the second for 50 inhabitants of a conflictive zone due to noise during the night, mainly at weekends. The similarity of the two groups of persons interviewed was studied and verified. Then a comparison was made of the responses referring to disturbing noise sources and effects of noise. The results showed appreciable differences between the two surveys. Some continuous sound pressure level measurements made over several days are also presented. They show major differences in the sound levels between the zone and the rest of the city.

Tutorial and Guidelines on Measurement of Sound Pressure Level in Voice and Speech

2018 ◽  
Vol 61 (3) ◽  
pp. 441-461 ◽  
Author(s):  
Jan G. Švec ◽  
Svante Granqvist
Keyword(s):  
Sound Pressure Level ◽  
Background Noise ◽  
Sound Pressure ◽  
Signal To Noise Ratio ◽  
Practical Experience ◽  
Sound Level ◽  
Pressure Level ◽  
Sound Levels ◽  
Frequency Weighting ◽  
Voice And Speech

Purpose Sound pressure level (SPL) measurement of voice and speech is often considered a trivial matter, but the measured levels are often reported incorrectly or incompletely, making them difficult to compare among various studies. This article aims at explaining the fundamental principles behind these measurements and providing guidelines to improve their accuracy and reproducibility. Method Basic information is put together from standards, technical, voice and speech literature, and practical experience of the authors and is explained for nontechnical readers. Results Variation of SPL with distance, sound level meters and their accuracy, frequency and time weightings, and background noise topics are reviewed. Several calibration procedures for SPL measurements are described for stand-mounted and head-mounted microphones. Conclusions SPL of voice and speech should be reported together with the mouth-to-microphone distance so that the levels can be related to vocal power. Sound level measurement settings (i.e., frequency weighting and time weighting/averaging) should always be specified. Classified sound level meters should be used to assure measurement accuracy. Head-mounted microphones placed at the proximity of the mouth improve signal-to-noise ratio and can be taken advantage of for voice SPL measurements when calibrated. Background noise levels should be reported besides the sound levels of voice and speech.

Sign in / Sign up

Export Citation Format

Share Document