USING ANN TO STUDY SOUND PREFERENCE EVALUATION IN URBAN OPEN SPACES

Lei Yu,Jian Kang

doi:10.3846/16486897.2015.1050399

Abstract

In soundscape research, subjective preference evaluation of a sound is crucial. Based on a series of field studies and laboratory experiments, influence of sound category and psychoacoustic parameters on sound preference evaluation is examined. It has been found that sound category and loudness and sharpness are important. Regarding a previous study, age and education level are also important to influence sound preference evaluation. In order to understand user’s preference in terms of sound at a design stage, prediction of sound preference evaluation is essential. As sound preference evaluation is complicated and influenced by various factors linearly and non-linearly, artificial neural network (ANN) has been explored to make predictions of sound preference evaluation. A number of developed ANN models have been demonstrated, and it has been found that the models including input factors of sound category, loudness and sharpness produce better predictions than others. The best prediction model is the one that is based on an individual case study site. Based on the best prediction model, a mapping tool for sound preference evaluation has been developed and its usefulness for aiding landscape architects and urban designers has been demonstrated.

Highlights

A1,b2s,t4rIancstt.iItnutseouonf dEsccaopleogreyseaanrcdhE, saurbtjhecSticvieenprceefse,reFnacecuelvtayluoaftioSncioefncaesoaunnddTisecchruncoilaol.gBy,asUedniovnerasisteyrioefs oTfafriteuld, studies and laboratory experiments,4in6flVueannceemouf issoeunsdtr.c,at5e1g0or1y4aTndarptsuy,chEosatcoonuisatic parameters on sound preference evaluatio3n, 8Iisnesxtiatmutineeodf
It can be seen that all models give a very good prediction, compared with the models based on field studies
A possible reason for the better performance of the laboratory models is that the evaluation was made from the same group of subjects and the input variables including loudness and sharpness closely related with output – sound preference evaluation, which was not the case in the field studies

Summary

Introduction

A1,b2s,t4rIancstt.iItnutseouonf dEsccaopleogreyseaanrcdhE, saurbtjhecSticvieenprceefse,reFnacecuelvtayluoaftioSncioefncaesoaunnddTisecchruncoilaol.gBy,asUedniovnerasisteyrioefs oTfafriteuld, studies and laboratory experiments,4in6flVueannceemouf issoeunsdtr.c,at5e1g0or1y4aTndarptsuy,chEosatcoonuisatic parameters on sound preference evaluatio3n, 8Iisnesxtiatmutineeodf. DR.e,garding a previous study, age and education level are alLsoVi-m1p5o8r6taRntigtoa,inLfluaetvnicae sound preference evaluation. In order to understand 4u,s5e,r6’sInpsrteifteuretencoefinFoteordmsSoaffestoyu,nAd natima adlesHigenaslttahgea,npdreEdincvtiiornonomf seonutn(dBpIrOefeRre)n,c3e eLvealjuuapteiosnsitsr.e,ssential. As sound preference evaluation is complicatedLaVn-d10in7f6lueRnicgead, bLyavtavriiaous factors linearly and non-linearly, artificial neural network (ANN) has beenSeuxbpmloritetdedto 6maMkeapr.re2d0ic1t2io;nascocfespoutendd p1r4efAeruengc.e2e0v1al2uation. ANN models have been demonstrated, and it has been found that the models including input factors of sound catego-. Abrys,trlaocutd.nTerssinaintrdotsohlaurepnnees(sTpNroTd)u,cae bceotmtermpornedlyictuisoends tehxapnloostihveersf.oTrhme bileitsatrpyreadnicdtioinndmusotdrieallisatphpeliocnateiothnast, icsabnasceaduse seorinouans eindvivroidnumalencatasel pstouldluytsioitne. B2a8s-eddayonlatbhoerabteostryprpeodticetxiopnermimoednelt, wa amsacpaprirniegdtoooultfoarppsolyuinndg pbrieofaeuregnmceenetvaatliuoantiounsing labhoasrabteoerny dseevleelcotpeded baancdteitrsiaulsesfturlaninesss faosr ianidoicnuglulamn,dsbcaiopsetiamrcuhliatteicotns awndithurbmaonladsesseigsnearnsdhacsabbbeeangedelmeaofnsetxrtartaedct., and pinhKysetooyiwrleommrdeicdsr:ioastboiuioannlducpsoirmnefgmerrueynneciateynedvraeblsulpuaoetinofseninb, uulegrrbefaoenkr otcpooennsttuaspdmayicnetha, neAtNefdNfeecgmtraooddf aetlthliieonsnge. Treatments Chemical on TNT removal and changes analyses revealed significant decreases in TNT concentrations, including reduction of some of the TNT to its amino derivates during the 28-day

Results

Discussion

Conclusion