{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Authorea, Inc."}],"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T16:38:36Z","timestamp":1748968716028,"version":"3.41.0"},"posted":{"date-parts":[[2022,8,30]]},"group-title":"Preprints","reference-count":0,"publisher":"Wiley","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2022,8,30]]},"abstract":"<jats:p id=\"p1\">Due to the complexity of biological transformations, developing\nmodel-based strategies to optimize and control bioprocesses is\nnontrivial. Hybrid models combining a mechanistic description of known\ninfluential factors with machine learning to infer the missing\ninfluential factors from data have been reported as powerful tools for\nbioprocesses applications. The artificial neural network is one of the\nmost popular machine learning methods in this case. This paper presents\na systematic literature review by computerized search across two\ndatabases: Scopus and Web of Science, and backward citation. The PRISMA\nmethod was applied to selecting the publications and 159 research\narticles were categorized as hybrid model applications to bioprocesses\nproblems. It was found that hybrid models were mainly applied in\nupstream operation steps with a predominance of bioreaction steps. In\ndownstream processing, chromatography appeared as a more recent research\ntopic, with a relatively small number of publications. Furthermore,\nholistic hybrid modeling applications that integrate data and knowledge\nfrom several bioprocess steps will likely emerge in the future, enabling\nbetter optimization and control of the bioprocess\u2019s platform. The\ncombination of other machine learning methods with the hybrid neural\nnetwork model is another opportunity that could improve the output of\nthe model.<\/jats:p>","DOI":"10.22541\/au.166188605.56941100\/v1","type":"posted-content","created":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T19:01:23Z","timestamp":1661886083000},"source":"Crossref","is-referenced-by-count":0,"title":["Trend of the Application of Hybrid Artificial Neural Network Models in Bioprocesses"],"prefix":"10.22541","author":[{"given":"Roshanak","family":"Agharafeie","sequence":"first","affiliation":[{"name":"Universidade Nova de Lisboa"}]},{"given":"Rui","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Universidade NOVA de Lisboa Faculdade de Ciencias e Tecnologia"}]},{"given":"Jorge M.","family":"Mendes","sequence":"additional","affiliation":[{"name":"Universidade Nova de Lisboa"}]}],"member":"311","container-title":[],"original-title":[],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T19:01:23Z","timestamp":1661886083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.authorea.com\/users\/504767\/articles\/584020-trend-of-the-application-of-hybrid-artificial-neural-network-models-in-bioprocesses?commit=ae191869a01bf98c0d2fd161bd94b616b1fb967a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,30]]},"references-count":0,"URL":"https:\/\/doi.org\/10.22541\/au.166188605.56941100\/v1","relation":{},"subject":[],"published":{"date-parts":[[2022,8,30]]},"subtype":"preprint"}}