{"id":117267,"date":"2018-03-11T10:46:42","date_gmt":"2018-03-11T10:46:42","guid":{"rendered":"https:\/\/www.deberes.net\/tesis\/sin-categoria\/modelos-de-exposicion-personal-a-los-contaminantes-del-aire-aplicacion-de-modelos-estada%c2%adsticos-clasicos-y-de-red-neuronal\/"},"modified":"2018-03-11T10:46:42","modified_gmt":"2018-03-11T10:46:42","slug":"modelos-de-exposicion-personal-a-los-contaminantes-del-aire-aplicacion-de-modelos-estada%c2%adsticos-clasicos-y-de-red-neuronal","status":"publish","type":"post","link":"https:\/\/www.deberes.net\/tesis\/contaminacion-atmosferica\/modelos-de-exposicion-personal-a-los-contaminantes-del-aire-aplicacion-de-modelos-estada%c2%adsticos-clasicos-y-de-red-neuronal\/","title":{"rendered":"Modelos de exposici\u00f3n personal a los contaminantes del aire. aplicaci\u00f3n de modelos estad\u00edsticos cl\u00e1sicos y de red neuronal"},"content":{"rendered":"<h2>Tesis doctoral de <strong> Ana Perez Valera <\/strong><\/h2>\n<p>Abstract  the aim of this project is to study the applications of neural networks in the field of personal exposure and to compare the obtained results with the traditional method.   for this application we used data from two different studies. These studies are the european life-macbeth project and the european people project. These studies were performed in various european cities, but for this study, we have collected from life-macbeth project the data of the city of murcia, where personal exposure to benzene, toluene and m, p-xylenes was studied. And to the people project the date of city of Madrid (2003) where concentrations were measured in ambient air and personal exposure. From the data collected, we used those for benzene and aromatics.  the classic method used is the multivariate regression, which is a statistical method that establishes a mathematical relationship between a set of independent variables and a dependent variable. This regression was made using a called &quot;stepwise&quot; procedure.  the neural networks tested for this project has been the following: linear layer, both versions design and training; feed-forward backprop; the cascade-forward backprop, the pure radial basis, probabilistic and generalized regression and also the option &quot;fitting tool&quot;.  the date of the project life-macbeth several conclusions are concluded:  &quot;\tthe classical statistical methods acceptable were those in which personal exposure concentration with different times of exposure to each environment and the concentrations of the different environments related.  &quot;\tclassical statistical study shows that the environments with more influence on personal exposure to the three pollutants are the time spent outdoors and at home (in all the evaluated periods). Also, during periods of weekend and leisure the influence of interiors other than homes is significant.  &quot;\tin case of neural network models, tested options have been considered acceptable methods for linear layer design and generalized regression in which a neural network of four neurons in parallel was designed.  &quot;\tin general, the error obtained with neural networks is smaller than those obtained with the conventional method, especially for toluene and m, p-xylenes.   from the results with the data of the project people several conclusions are concluded too.  &quot;\tthe classic study it is deduced that the environments more influence on personal exposure to the five pollutants are time spent at work and at home; for four of the pollutants also affects the time spent in the car (except for the o-xylene); for three of them also influences the time spent shopping (except benzene and m, p-xylene). For benzene and m,p-xylenes other relevant variable is the number of cigarettes smoked.  &quot;\twith all the contaminants, five neural network simulations and one with the classical statistical multivariate regression method have been made. The simulation for the use of the generalized regression network in two-step option was not acceptable because the percentage of deleted data was very high.  &quot;\tfor all pollutants the networks option linear layer design (lld) 1step improves the classical method. Also generalized regression (gr) 2 steps shows an improvement over the classical estimates. The gr 1 step serves to refine the data, detecting outliers.     el objetivo de este proyecto es el estudio de las aplicaciones de las redes neuronales en el campo de la exposici\u00f3n personal y su comparaci\u00f3n con los resultados obtenidos con el m\u00e9todo tradicional.   pare ello hemos utilizado los datos procedentes de dos estudios distintos que se han realizado. Estos estudios son el proyecto europeo life-macbeth (1996) y el proyecto europeo people. Estos estudios se realizaron en varias ciudades europeas pero para este trabajo se han recopilado los datos de la ciudad de murcia del proyecto life-macbeth, donde se estudi\u00f3 la exposici\u00f3n personal a benceno, tolueno y m, p-xilenos. Y los de la ciudad de Madrid (2003) donde se midi\u00f3 la concentraciones en aire ambiente y la exposici\u00f3n personal, de los datos que se recopilaron hemos utilizado los correspondientes a benceno y compuestos arom\u00e1ticos.  el m\u00e9todo cl\u00e1sico utilizado es el de regresi\u00f3n multivariable, que es un m\u00e9todo estad\u00edstico que establece una relaci\u00f3n matem\u00e1tica entre un conjunto de variables independientes y una variable dependiente. El procedimiento utilizado con esta regresi\u00f3n fue el llamado &quot;paso a paso&quot;.  las redes neuronales ensayadas han sido: capa lineal, las dos versiones  dise\u00f1o y entrenamiento; feed-forward backprop. Cascade-forward backprop., La base radial pura, la probabil\u00edstica y la regresi\u00f3n generalizada y tambi\u00e9n la opci\u00f3n &quot;fitting tool&quot;.  del proyecto life-macbeth pudimos concluir que:  &quot;\tde los m\u00e9todos aceptables cl\u00e1sicos estad\u00edsticos fueron aquellos en donde se relacion\u00f3 la concentraci\u00f3n de exposici\u00f3n personal con los distintos tiempos de exposici\u00f3n a cada ambiente y las concentraciones de los distintos ambientes.   &quot;\tel estudio estad\u00edstico cl\u00e1sico muestra que los tiempos con m\u00e1s influencia en la exposici\u00f3n personal a los tres contaminantes son el tiempo pasado al aire libre y en el hogar (en todos los per\u00edodos evaluados). Tambi\u00e9n, durante los per\u00edodos de fin de semana y de ocio influyen los tiempos pasados en interiores distintos del hogar.  &quot;\ten el caso de modelos de red neuronal, de las opciones ensayadas, se han considerado aceptables las correspondientes a los m\u00e9todos de capa lineal en modo dise\u00f1o y regresi\u00f3n general, en las cuales, tras probar distintas combinaciones l\u00f3gicas, se ha dise\u00f1ado una red neuronal de cuatro neuronas en paralelo, por ser la que mejores resultados aportaba.  &quot;\ten general, los errores obtenidos con redes neuronales son menores que los obtenidos con el m\u00e9todo cl\u00e1sico, especialmente para tolueno y m,p-xilenos.   para los datos del proyecto people tambi\u00e9n se llegaron a varias conclusiones.   &quot;\tdel estudio estad\u00edstico cl\u00e1sico se deduce que las variables con mayor influencia en la exposici\u00f3n personal a los cinco contaminantes son los tiempos pasados en el trabajo y en casa, respectivamente. Para cuatro de los contaminantes tambi\u00e9n influye el tiempo pasado en el coche (excepto para el o-xileno); para tres de ellos el tiempo pasado en tiendas (excepto benceno y m,p-xilenos). Para el benceno y m,p-xilenos otra variable relevante es el n\u00famero de cigarrillos consumidos.  &quot;\tcon todos los contaminantes se ha realizado cinco tipos de simulaci\u00f3n utilizando redes neuronales y un tipo con el m\u00e9todo cl\u00e1sico estad\u00edstico de regresi\u00f3n multivariable. La simulaci\u00f3n correspondiente al uso de la red de regresi\u00f3n generalizada, en su opci\u00f3n de dos pasos no fue aceptable, debido al elevado error que presentaban las estimaciones.   &quot;\tpara todos los contaminantes, la opci\u00f3n de redes de dise\u00f1o de capa lineal (lld) de un paso mejora los resultados obtenidos por m\u00e9todo cl\u00e1sico. Tambi\u00e9n el m\u00e9todo de regresi\u00f3n generalizada (gr) en dos pasos mejora los resultados con respecto a las estimaciones cl\u00e1sicas, aunque el n\u00famero de valores con error elevado es mayor que el m\u00e9todo de capa lineal. El m\u00e9todo de regresi\u00f3n generalizada de un paso se ha demostrado \u00fatil para detectar valores que no siguen la tendencia generalizada del grupo (outliers).<\/p>\n<p>&nbsp;<\/p>\n<h3>Datos acad\u00e9micos de la tesis doctoral \u00ab<strong>Modelos de exposici\u00f3n personal a los contaminantes del aire. aplicaci\u00f3n de modelos estad\u00edsticos cl\u00e1sicos y de red neuronal<\/strong>\u00ab<\/h3>\n<ul>\n<li><strong>T\u00edtulo de la tesis:<\/strong>\u00a0 Modelos de exposici\u00f3n personal a los contaminantes del aire. aplicaci\u00f3n de modelos estad\u00edsticos cl\u00e1sicos y de red neuronal <\/li>\n<li><strong>Autor:<\/strong>\u00a0 Ana Perez Valera <\/li>\n<li><strong>Universidad:<\/strong>\u00a0 Murcia<\/li>\n<li><strong>Fecha de lectura de la tesis:<\/strong>\u00a0 13\/03\/2015<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Direcci\u00f3n y tribunal<\/h3>\n<ul>\n<li><strong>Director de la tesis<\/strong>\n<ul>\n<li>Esther Gonzalez Duperon<\/li>\n<\/ul>\n<\/li>\n<li><strong>Tribunal<\/strong>\n<ul>\n<li>Presidente del tribunal: agustin Mi\u00f1ana aznar <\/li>\n<li>montserrat Hidalgo nu\u00f1ez (vocal)<\/li>\n<li>Rafael Font montesinos (vocal)<\/li>\n<li>Francisco Jos\u00e9 Marzal Martinez (vocal)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Tesis doctoral de Ana Perez Valera Abstract the aim of this project is to study the applications of neural networks [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-gradient":""}},"footnotes":""},"categories":[4520,8235,7953],"tags":[23429,231151,152363,102863,173630,8477],"class_list":["post-117267","post","type-post","status-publish","format-standard","hentry","category-contaminacion-atmosferica","category-murcia","category-redes-neuronales","tag-agustin-minana-aznar","tag-ana-perez-valera","tag-esther-gonzalez-duperon","tag-francisco-jose-marzal-Martinez","tag-montserrat-hidalgo-nunez","tag-rafael-font-montesinos"],"_links":{"self":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/117267","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/comments?post=117267"}],"version-history":[{"count":0,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/posts\/117267\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/media?parent=117267"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/categories?post=117267"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.deberes.net\/tesis\/wp-json\/wp\/v2\/tags?post=117267"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}