{"corpus_id":96709441,"paper_sha":"69b814421d5aecf7f2accda34598f7ee1eb7d0b2","doi":"10.1080/07373930902988247","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2152779201,"dblp_id":null,"acl_id":null,"title":"Comparison of Artificial Neural Network (ANN) and Response Surface Methodology (RSM) in the Prediction of Quality Parameters of Spray-Dried Pomegranate Juice","year":2009,"publication_date":"2009-07-29","venue":"","journal":{"name":"Drying Technology","pages":"910 - 917","volume":"27"},"journal_issn":null,"journal_title":null,"publication_types":[],"pubmed_pub_types":null,"s2_fields_of_study":["Chemistry","Engineering"],"reference_count":41,"citation_count":153,"influential_citation_count":4,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"Response surface methodology (RSM) is a frequently used method for empirical modeling and prediction in the processing of biological media. The artificial neural network (ANN) has recently grown to be one of the most efficient methods for empirical modeling and prediction, especially for nonlinear systems. This article presents comparative studies between an ANN and RSM in the modeling and prediction of quality parameters of spray-dried pomegranate juice. In this study, the effects of the carrier type, carrier concentration, and concentration of crystalline cellulose in a pomegranate juice spray-drying process were investigated on five quality parameters—drying yield, solubility, color change, total anthocyanin content, and antioxidant activity—using RSM and ANN methods. A central composite rotatable experimental design (CCRD) and a feed-forward multilayered perceptron (MLP) ANN trained using back-propagation algorithms for three independent variables were developed to predict the five outputs. The final selected ANN model (3-10-8-5) was compared to the RSM model for its modeling and predictive abilities. The predictive abilities of both the ANN and RSM were compared using a separate dataset of 18 unseen experiments based on RMSE (root mean square error), MAE (mean absolute error), and R2 (correlation coefficient) for each output parameter. The results indicate the superiority of a properly trained ANN in capturing the nonlinear behavior of the system and the simultaneous prediction of five outputs.","claims":[{"public_id":"cl_f3ec546da54ed11f6d17f33fb3321704","status":"active","text":"A central composite rotatable experimental design and a feed-forward multilayer perceptron trained with back-propagation were developed to predict the five quality outputs from three input variables.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_f3ec546da54ed11f6d17f33fb3321704"},{"public_id":"cl_19dca8bef1d3138031ec0541f26e044f","status":"active","text":"A properly trained artificial neural network captured the nonlinear behavior of the spray-drying system better than response surface methodology and enabled simultaneous prediction of five outputs.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_19dca8bef1d3138031ec0541f26e044f"},{"public_id":"cl_51485f2af04dd0a640756355ba093751","status":"active","text":"Carrier type, carrier concentration, and crystalline cellulose concentration were modeled as independent variables affecting drying yield, solubility, color change, total anthocyanin content, and antioxidant activity.","confidence":0.93,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_51485f2af04dd0a640756355ba093751"},{"public_id":"cl_543751e237263e8928fc017c4f997304","status":"active","text":"Model performance was compared on 18 unseen experiments using root mean square error, mean absolute error, and the correlation coefficient.","confidence":0.94,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_543751e237263e8928fc017c4f997304"}],"concepts":[{"public_id":"co_3607ef4d4f7cb50cbf93a8ef501cef8b","status":"active","name":"carrier type","description":"The category of carrier material used during spray drying.","types":["process variable"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_3607ef4d4f7cb50cbf93a8ef501cef8b"},{"public_id":"co_5849a9dc839218d42190c556214fb0e7","status":"active","name":"artificial neural network","description":"A data-driven modeling approach that learns input-output relationships through interconnected processing units.","types":["method"],"aliases":["ANN"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_5849a9dc839218d42190c556214fb0e7"},{"public_id":"co_68726827743895e35a42fae8ca8cb54a","status":"active","name":"carrier concentration","description":"The amount of carrier material used in the spray-drying formulation.","types":["process variable"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_68726827743895e35a42fae8ca8cb54a"},{"public_id":"co_709cf9ed69a841a2d3f75454e5f2da73","status":"active","name":"back-propagation algorithms","description":"Training algorithms that adjust neural-network weights by propagating prediction error backward through the network.","types":["training algorithm"],"aliases":["back-propagation"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_709cf9ed69a841a2d3f75454e5f2da73"},{"public_id":"co_72ea96683d75bf7ddb7e8ca9252e5928","status":"active","name":"central composite rotatable experimental design","description":"A response-surface experimental design used to structure experiments across multiple factors.","types":["experimental design"],"aliases":["CCRD"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_72ea96683d75bf7ddb7e8ca9252e5928"},{"public_id":"co_76f3f32a573985b39e4cb935c5b122a0","status":"active","name":"quality parameters","description":"Measured properties of the spray-dried pomegranate juice used as prediction targets.","types":["outcome"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_76f3f32a573985b39e4cb935c5b122a0"},{"public_id":"co_7ab74fc93557ccb5a124b6d4483a85a7","status":"active","name":"feed-forward multilayered perceptron","description":"A layered neural-network architecture that passes information forward through hidden and output layers.","types":["neural network architecture"],"aliases":["MLP"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_7ab74fc93557ccb5a124b6d4483a85a7"},{"public_id":"co_830f700b50333b70a04c1b3f29e5fb2d","status":"active","name":"crystalline cellulose","description":"A form of cellulose included as an ingredient in the spray-drying process.","types":["ingredient","process variable"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_830f700b50333b70a04c1b3f29e5fb2d"},{"public_id":"co_8576c85a007d722eab425f9f2c8aa66d","status":"active","name":"mean absolute error","description":"A metric that measures the average absolute difference between predicted and observed values.","types":["evaluation metric"],"aliases":["MAE"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_8576c85a007d722eab425f9f2c8aa66d"},{"public_id":"co_c7b473025f1ad4d392d212f92cf6414b","status":"active","name":"correlation coefficient","description":"A statistic used to assess the strength of association between predicted and observed values.","types":["evaluation metric"],"aliases":["R2"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c7b473025f1ad4d392d212f92cf6414b"},{"public_id":"co_d6f0fe023309cc767663fc6a8b287f9b","status":"active","name":"root mean square error","description":"A metric that measures the square root of the average squared prediction error.","types":["evaluation metric"],"aliases":["RMSE"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_d6f0fe023309cc767663fc6a8b287f9b"},{"public_id":"co_dab6598bc896ab05f13caf7f281a3b44","status":"active","name":"18 unseen experiments","description":"A separate test dataset of eighteen experiments used for model evaluation.","types":["evaluation dataset"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_dab6598bc896ab05f13caf7f281a3b44"},{"public_id":"co_ee4c25fef28f8e15b1bb075fa9e0734c","status":"active","name":"response surface methodology","description":"An empirical modeling approach used to estimate relationships between experimental factors and responses.","types":["method"],"aliases":["RSM"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ee4c25fef28f8e15b1bb075fa9e0734c"},{"public_id":"co_ef04d39794c063a1b4f9e71cff466c30","status":"active","name":"spray-dried pomegranate juice","description":"Pomegranate juice processed by spray drying and used as the material being modeled.","types":["material","process material"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ef04d39794c063a1b4f9e71cff466c30"}],"external_ids":{"DOI":"10.1080/07373930902988247","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2152779201,"DBLP":null,"ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/96709441","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":637492,"paper_uid":"9d257747-b5a6-4d1a-a9d7-d7feef392858","canonical_identity":{"paper_id":637492,"paper_uid":"9d257747-b5a6-4d1a-a9d7-d7feef392858","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/96709441"}