In this paper, a\u00a0neural network approach to the pork farm odour using single-component analysis with the consideration of\u00a0other relevant factors, such as measurement location is proposed. Neural network models and statistical\u00a0models for pork farm odour have been developed and compared for single-component models to determine\u00a0which method produces superior results.\u00a0Non-linear statistical and neural network models were\u00a0developed and compared for single-component pork\u00a0farm odour analysis using NH3 and H2S as odour\u00a0indicators. \u00a0The first set of models considered only a\u00a0single-odour indicator and no other factors. In this case,\u00a0the odour intensity predictions from the neural networks\u00a0were generally better than the predictions produced by\u00a0the non-linear statistical models. \u00a0The second set of models considered asingl e-odour\u00a0indicator (NH3 or H2S) and the odour source (pig\u00a0building or pig manure storage). In this case, both of the\u00a0developed neural network models N5 and N6 performed\u00a0better than their corresponding neural network models\u00a0(N1\u2013N4) for every performance measure considered in\u00a0this paper.\u00a0In general, the use of neural networks to model the pork farm odour\u00a0yields more accurate and precise odour intensity predictions than the statistical models. The measurement\u00a0location for the pork farm odour was considered in several model comparisons. The neural network models\u00a0significantly outperformed the statistical models in this comparison because the statistical models are not able\u00a0to consider the measurement location. This indicates that measurement location is a relevant factor for\u00a0modelling pork farm odour. This also demonstrates that factors other than odour components should be\u00a0considered during modelling.<\/p>\n","protected":false},"excerpt":{"rendered":"
In this paper, a\u00a0neural network approach to the pork farm odour using single-component analysis with the consideration of\u00a0other relevant factors, such as measurement location is proposed. Neural network models and statistical\u00a0models for pork farm odour have been developed and compared for single-component models to determine\u00a0which method produces superior results.\u00a0Non-linear statistical and neural network models were\u00a0developed […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[18120,19],"tags":[213,234,14,309],"class_list":["post-15013","post","type-post","status-publish","format-standard","hentry","category-ontario-pork","category-pork-insight-articles","tag-h2s","tag-nh3","tag-pig","tag-storage"],"_links":{"self":[{"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/posts\/15013","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/comments?post=15013"}],"version-history":[{"count":1,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/posts\/15013\/revisions"}],"predecessor-version":[{"id":15015,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/posts\/15013\/revisions\/15015"}],"wp:attachment":[{"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/media?parent=15013"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/categories?post=15013"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prairieswine.com\/rsc\/wp-json\/wp\/v2\/tags?post=15013"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}