{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T15:13:11Z","timestamp":1777043591597,"version":"3.51.4"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T00:00:00Z","timestamp":1530748800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61503104"],"award-info":[{"award-number":["61503104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Hangzhou Smart City Research Center of Zhejiang\/Zhejiang Smart City Regional Collaborative Innovation Center","award":["GK150906299001\/019"],"award-info":[{"award-number":["GK150906299001\/019"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11042-018-6295-8","type":"journal-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T16:20:15Z","timestamp":1530807615000},"page":"29021-29041","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["Urban noise recognition with convolutional neural network"],"prefix":"10.1007","volume":"78","author":[{"given":"Jiuwen","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianzhong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre-Paul","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,5]]},"reference":[{"issue":"10","key":"6295_CR1","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TASLP.2014.2339736","volume":"22","author":"O Abdel-Hamid","year":"2014","unstructured":"Abdel-Hamid O, Mohamed AR et al. (2014) Convolutional neural networks for speech recognition. IEEE-ACM Trans Audio Speech Language Process 22(10):1533\u20131545","journal-title":"IEEE-ACM Trans Audio Speech Language Process"},{"key":"6295_CR2","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.apacoust.2016.05.025","volume":"117","author":"A Agha","year":"2016","unstructured":"Agha A, Ranjan R, Gan WS (2016) Noisy vehicle surveillance camera: A system to deter noisy vehicle in smart city. Appl Acoust 117:236\u2013245","journal-title":"Appl Acoust"},{"key":"6295_CR3","doi-asserted-by":"crossref","unstructured":"Ahmad K, Thosarz A, Jagannath H (2015) A unique approach in text independent speaker recognition using MFCC feature sets and probabilistic neural network. In: IEEE eighth international conference on advances in pattern recognition, pp 1\u20136","DOI":"10.1109\/ICAPR.2015.7050669"},{"key":"6295_CR4","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.apacoust.2016.11.013","volume":"117","author":"C Asensio","year":"2017","unstructured":"Asensio C (2017) Acoustics in Smart Cities. Appl Acoust 117:191\u2013192","journal-title":"Appl Acoust"},{"issue":"1","key":"6295_CR5","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0264-2751(02)00093-8","volume":"20","author":"A Calixto","year":"2003","unstructured":"Calixto A, Diniz FB, Zannin PHT (2003) The statistical modeling of road traffic noise in an urban setting. Cities 20(1):23\u201329","journal-title":"Cities"},{"issue":"5","key":"6295_CR6","doi-asserted-by":"publisher","first-page":"2839","DOI":"10.1007\/s11042-014-2424-1","volume":"75","author":"J Cao","year":"2016","unstructured":"Cao J, Chen T, Fan J (2016) Landmark recognition with compact BoW histogram and ensemble ELM. Multimed Tools Appl 75(5):2839\u20132857","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"6295_CR7","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1007\/s11045-015-0374-z","volume":"28","author":"J Cao","year":"2017","unstructured":"Cao J, Huang W, Zhao T, Wang J, Wang R (2017) An enhance excavation equipments classification algorithm based on acoustic spectrum dynamic feature. Multidim Syst Sign Process 28(3):921\u2013943","journal-title":"Multidim Syst Sign Process"},{"key":"6295_CR8","doi-asserted-by":"publisher","unstructured":"Cao J, Shang L, Wang J, Vong C, Yin C, Cheng Y, Huang X (2017) A novel distance estimation algorithm for periodic surface vibrations based on frequency band energy percentage feature. Mechanical Systems and Signal Processing. https:\/\/doi.org\/10.1016\/j.ymssp.2017.10.016","DOI":"10.1016\/j.ymssp.2017.10.016"},{"issue":"12","key":"6295_CR9","doi-asserted-by":"publisher","first-page":"4392","DOI":"10.1109\/TCYB.2016.2609999","volume":"47","author":"J Cao","year":"2017","unstructured":"Cao J, Wang W, Wang J, Wang R (2017) Excavation equipment recognition based on novel acoustic statistical Features. IEEE Trans Cybern 47(12):4392\u20134404","journal-title":"IEEE Trans Cybern"},{"key":"6295_CR10","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.neunet.2016.06.001","volume":"81","author":"J Cao","year":"2016","unstructured":"Cao J, Zhang K, Luo M, Yin C, Lai X (2016) Extreme learning machine and adaptive sparse representation for image classification. Neural Netw 81:91\u2013102","journal-title":"Neural Netw"},{"key":"6295_CR11","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.neucom.2016.03.113","volume":"261","author":"J Cao","year":"2017","unstructured":"Cao J, Zhao T, Wang W, Wang J, Wang R (2017) Excavation equipments classification based on improved MFCC features and ELM. Neurocomputing 261:231\u2013241","journal-title":"Neurocomputing"},{"key":"6295_CR12","doi-asserted-by":"crossref","unstructured":"Cao M, Wang J, Cao J, Zeng H (2017) Acoustics recognition of excavation equipment based on MF-PLPCC features and RELM. In: Proceedings of the 36th Chinese control conference, pp 5400\u20135404","DOI":"10.23919\/ChiCC.2017.8028211"},{"key":"6295_CR13","doi-asserted-by":"publisher","unstructured":"Chutani S, Goyal A (2017) Improved universal quantitative steganalysis in spatial domain using ELM ensemble. Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-017-4656-3","DOI":"10.1007\/s11042-017-4656-3"},{"issue":"4","key":"6295_CR14","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"B Davis","year":"1980","unstructured":"Davis B, Mermelstein P (1980) Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans Acoust Speech Signal Process 28(4):357\u2013366","journal-title":"IEEE Trans Acoust Speech Signal Process"},{"issue":"3-4","key":"6295_CR15","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng L, Yu D (2014) Deep learning: Methods and applications. Found Trends Signal Process 7(3-4):197\u2013387","journal-title":"Found Trends Signal Process"},{"key":"6295_CR16","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez LPS, Fern\u00e1ndez XLAS, Hern\u00e1ndez JJC et al. (2015) Methods of analysis for urban environmental noise. In: IEEE Sai intelligent systems conference, pp 381\u2013389","DOI":"10.1109\/IntelliSys.2015.7361170"},{"issue":"1","key":"6295_CR17","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1109\/TASLP.2016.2632307","volume":"25","author":"Y Han","year":"2017","unstructured":"Han Y, Kim J, Lee K (2017) Deep convolutional neural networks for predominant instrument recognition in polyphonic music. IEEE\/ACM Trans Audio Speech Language Process 25(1):208\u2013221","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"6295_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of IEEE international conference on computer vision (ICCV), pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"issue":"2","key":"6295_CR19","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1109\/72.991427","volume":"13","author":"CW Hsu","year":"2002","unstructured":"Hsu CW, Lin CJ (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw 13(2):415\u2013425","journal-title":"IEEE Trans Neural Netw"},{"key":"6295_CR20","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.apacoust.2015.06.004","volume":"99","author":"B Huang","year":"2015","unstructured":"Huang B, Pan Z, Zhang B (2015) A virtual perception method for urban noise: The calculation of noise annoyance threshold and facial emotion expression in the virtual noise scene. Appl Acoust 99:125\u2013134","journal-title":"Appl Acoust"},{"issue":"1-3","key":"6295_CR21","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"G-B Huang","year":"2006","unstructured":"Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1-3):489\u2013501","journal-title":"Neurocomputing"},{"key":"6295_CR22","doi-asserted-by":"crossref","unstructured":"Huang Y, Yu D, Liu C, Gong Y (2014) A comparative analytic study on the gaussian mixture and context dependent deep neural network hidden Markov models, Interspeech","DOI":"10.21437\/Interspeech.2014-429"},{"issue":"2","key":"6295_CR23","first-page":"1097","volume":"60","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 60(2):1097\u20131105","journal-title":"Adv Neural Inf Process Syst"},{"issue":"7553","key":"6295_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521 (7553):436\u2013444","journal-title":"Nature"},{"key":"6295_CR25","doi-asserted-by":"crossref","unstructured":"Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, pp 2278\u20132324","DOI":"10.1109\/5.726791"},{"issue":"10","key":"6295_CR26","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1016\/S0003-682X(02)00024-5","volume":"63","author":"B Li","year":"2002","unstructured":"Li B, Tao S, Dawson RW (2002) Evalution and analysis of traffic noise from the main urban roads in Beijing. Appl Acoust 63(10):1137\u20131142","journal-title":"Appl Acoust"},{"issue":"10","key":"6295_CR27","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1016\/S0003-682X(02)00030-0","volume":"63","author":"JMB Morillas","year":"2002","unstructured":"Morillas JMB, Escobar VG, Sierra JAM et al. (2002) An environmental noise study in the city of C\u00e1ceres. Spain Appl. Acoust. 63(10):1061\u20131070","journal-title":"Spain Appl. Acoust."},{"key":"6295_CR28","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.apacoust.2016.06.010","volume":"117","author":"C Mydlarz","year":"2016","unstructured":"Mydlarz C, Salamon J, Bello JP (2016) The implementation of low-cost urban acoustic monitoring devices. Appl Acoust 117:207\u2013218","journal-title":"Appl Acoust"},{"key":"6295_CR29","unstructured":"Nair V, Hinton G (2010) Rectified linear units improve restricted boltzmann machines. In: ICML, 2010, pp 807\u2013814"},{"issue":"1","key":"6295_CR30","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/TNNLS.2015.2504382","volume":"28","author":"S Nan","year":"2017","unstructured":"Nan S, Sun L, Chen B, Lin Z, Toh K-A (2017) Density-dependent quantized least squares support vector machine for large data sets. IEEE Trans Neural Netw Learn Syst 28(1):94\u2013106","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6295_CR31","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.dsp.2014.05.003","volume":"31","author":"S Ntalampiras","year":"2014","unstructured":"Ntalampiras S (2014) Universal background modeling for acoustic surveillance of urban traffic. Digital Signal Process 31:69\u201378","journal-title":"Digital Signal Process"},{"key":"6295_CR32","unstructured":"Piczak KJ (2015) Environmental sound classification with convoltional neural networks. In: IEEE international workshop on machine learning for signal processing, pp 1\u20136"},{"issue":"12","key":"6295_CR33","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1109\/TASLP.2016.2602884","volume":"24","author":"Y Qian","year":"2016","unstructured":"Qian Y et al. (2016) Very deep convolutional neural networks for noise robust speech recognition. IEEE\/ACM Trans Audio Speech Language Process 24(12):2263\u20132276","journal-title":"IEEE\/ACM Trans Audio Speech Language Process"},{"key":"6295_CR34","unstructured":"Rezazadeh Azar E, McCabe B (2011) Vision-based equipment detection in construction images.. In: The 3rd international\/9th construction specialty conference, Ottawa ON, Canada, Accepted"},{"issue":"7","key":"6295_CR35","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.autcon.2012.03.003","volume":"24","author":"E Rezazadeh Azar","year":"2012","unstructured":"Rezazadeh Azar E, McCabe B (2012) Part based model and spatialtemporal reasoning to recognize hydraulic excavators in construction images and videos. Autom Constr 24(7):194\u2013202","journal-title":"Autom Constr"},{"key":"6295_CR36","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neunet.2014.08.005","volume":"64","author":"TN Sainath","year":"2015","unstructured":"Sainath TN, Kingsbury B, Saon G, Soltau H et al. (2015) Deep convolutional neural networks for large-scale speech tasks. Neural Netw 64:39\u201348","journal-title":"Neural Netw"},{"key":"6295_CR37","unstructured":"Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. Computer Science, pp 338\u2013342"},{"issue":"1","key":"6295_CR38","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.landurbplan.2012.06.017","volume":"108","author":"EM Salomons","year":"2012","unstructured":"Salomons EM, Pont MB (2012) Urban traffic noise and the relation to urban desity, form, and traffic elasticity. Landsc Urban Plan 108(1):2\u201316","journal-title":"Landsc Urban Plan"},{"issue":"8","key":"6295_CR39","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MCOM.1985.1092631","volume":"23","author":"M Schroeder","year":"1985","unstructured":"Schroeder M (1985) Linear predictive coding of speech: review and current directions. IEEE Commun Mag 23(8):54\u201361","journal-title":"IEEE Commun Mag"},{"key":"6295_CR40","unstructured":"Sermanet P, Chintala S, LeCun Y (2012) Convolutional neural networks applied to house numbers digit classification. In: IEEE international conference on pattern recognition, pp 3288\u20133291"},{"issue":"5","key":"6295_CR41","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/j.compenvurbsys.2011.06.001","volume":"35","author":"LCLD Souza","year":"2011","unstructured":"Souza LCLD, Giunta MB (2011) Urban indices as environmental noise indicators. Comput Environ Urban Syst 35(5):421\u2013430","journal-title":"Comput Environ Urban Syst"},{"issue":"1","key":"6295_CR42","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A et al. (2014) Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"6295_CR43","doi-asserted-by":"crossref","unstructured":"Stoeckle S, Path N, Kumar DK et al. (2001) Environmental sound sources classification using neural networks. In: IEEE intelligent information systems conference, the 7th Australian and New Zealand, pp 399\u2013403","DOI":"10.1109\/ANZIIS.2001.974112"},{"key":"6295_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.eswa.2016.01.011","volume":"53","author":"AJ Torija","year":"2016","unstructured":"Torija AJ, Ruiz DP (2016) Automated classification of urban locations for environmental noise impact assessment on the basis of road-traffic content. Expert Syst Appl 53:1\u201313","journal-title":"Expert Syst Appl"},{"issue":"7","key":"6295_CR45","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1016\/j.apacoust.2008.11.001","volume":"70","author":"KT Tsai","year":"2009","unstructured":"Tsai KT, Lin MD, Chen YH (2009) Noise mapping in urban environments: A Taiwan study. Appl Acoust 70(7):964\u2013972","journal-title":"Appl Acoust"},{"key":"6295_CR46","doi-asserted-by":"crossref","unstructured":"Yang S, Cao J, Wang J, Wang R (2016) Linear prediction of one-sided autocorrelation sequence for noisy acoustics recognition of excavation equipment. In: 12th world congress on intelligent control and automation, pp 924\u2013928","DOI":"10.1109\/WCICA.2016.7578544"},{"key":"6295_CR47","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1016\/j.apacoust.2016.08.002","volume":"117","author":"J Ye","year":"2016","unstructured":"Ye J, Kobayashi T, Murakawa M (2016) Urban sound event classification based on local and global features aggregation. Appl Acoust 117:246\u2013256","journal-title":"Appl Acoust"},{"issue":"2","key":"6295_CR48","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/S0195-9255(02)00092-6","volume":"23","author":"PHT Zannin","year":"2003","unstructured":"Zannin PHT, Calixto A, Diniz FB et al. (2003) A survey of urban noise annoyance in a large Brazilian city: the importance of a subjective analysis in conjunction with an objective analysis. Environ Impact Assess Rev 23(2):245\u2013255","journal-title":"Environ Impact Assess Rev"},{"key":"6295_CR49","doi-asserted-by":"publisher","unstructured":"Zhang Y, Zhao G, Sun J et al. (2017) Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and Jaya algorithm, Multimedia Tools and Applications. https:\/\/doi.org\/10.1007\/s11042-017-5023-0","DOI":"10.1007\/s11042-017-5023-0"},{"issue":"3","key":"6295_CR50","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.apacoust.2011.09.003","volume":"73","author":"J Zhao","year":"2012","unstructured":"Zhao J, Zhang X, Chen Y (2012) A novel traffic-noise prediction method for nonstraight roads. Appl Acoust 73(3):276\u2013280","journal-title":"Appl Acoust"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6295-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-018-6295-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-6295-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,27]],"date-time":"2022-08-27T00:48:58Z","timestamp":1661561338000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-6295-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,5]]},"references-count":50,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["6295"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-6295-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,5]]},"assertion":[{"value":"25 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}