{"publication_status":"published","article_type":"original","publication_identifier":{"eissn":["0723-1520"],"issn":["1866-5195"]},"publication":"Brewing science ","main_file_link":[{"open_access":"1","url":"https://www.researchgate.net/publication/355735532_Determination_of_free_amino_nitrogen_in_beer_mash_with_an_inline_NIR_transflectance_probe_and_data_evaluation_by_machine_learning_algorithms"}],"intvolume":"        74","citation":{"havard":"P. Wefing, F. Conradi, J. Rämisch, P. Neubauer, J. Schneider, Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms, Brewing Science . 74 (2021) 107–121.","chicago-de":"Wefing, Patrick, Florian Conradi, Johannes Rämisch, Peter Neubauer und Jan Schneider. 2021. Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms. <i>Brewing science </i> 74, Nr. 9/10: 107–121. doi:<a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>, .","ufg":"<b>Wefing, Patrick u. a.</b>: Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms, in: <i>Brewing science </i> 74 (2021), H. 9/10,  S. 107–121.","din1505-2-1":"<span style=\"font-variant:small-caps;\">Wefing, Patrick</span> ; <span style=\"font-variant:small-caps;\">Conradi, Florian</span> ; <span style=\"font-variant:small-caps;\">Rämisch, Johannes</span> ; <span style=\"font-variant:small-caps;\">Neubauer, Peter</span> ; <span style=\"font-variant:small-caps;\">Schneider, Jan</span>: Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms. In: <i>Brewing science </i> Bd. 74, Carl (2021), Nr. 9/10, S. 107–121","mla":"Wefing, Patrick, et al. “Determination of Free Amino Nitrogen in Beer Mash with an Inline NIR Transflectance Probe and Data Evaluation by Machine Learning Algorithms.” <i>Brewing Science </i>, vol. 74, no. 9/10, 2021, pp. 107–21, <a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>.","short":"P. Wefing, F. Conradi, J. Rämisch, P. Neubauer, J. Schneider, Brewing Science  74 (2021) 107–121.","ama":"Wefing P, Conradi F, Rämisch J, Neubauer P, Schneider J. Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms. <i>Brewing science </i>. 2021;74(9/10):107-121. doi:<a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>","van":"Wefing P, Conradi F, Rämisch J, Neubauer P, Schneider J. Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms. Brewing science . 2021;74(9/10):107–21.","bjps":"<b>Wefing P <i>et al.</i></b> (2021) Determination of Free Amino Nitrogen in Beer Mash with an Inline NIR Transflectance Probe and Data Evaluation by Machine Learning Algorithms. <i>Brewing science </i> <b>74</b>, 107–121.","apa":"Wefing, P., Conradi, F., Rämisch, J., Neubauer, P., &#38; Schneider, J. (2021). Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms. <i>Brewing Science </i>, <i>74</i>(9/10), 107–121. <a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>","ieee":"P. Wefing, F. Conradi, J. Rämisch, P. Neubauer, and J. Schneider, “Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms,” <i>Brewing science </i>, vol. 74, no. 9/10, pp. 107–121, 2021, doi: <a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>.","chicago":"Wefing, Patrick, Florian Conradi, Johannes Rämisch, Peter Neubauer, and Jan Schneider. “Determination of Free Amino Nitrogen in Beer Mash with an Inline NIR Transflectance Probe and Data Evaluation by Machine Learning Algorithms.” <i>Brewing Science </i> 74, no. 9/10 (2021): 107–21. <a href=\"https://doi.org/10.23763/BrSc21-10wefing\">https://doi.org/10.23763/BrSc21-10wefing</a>."},"publisher":"Carl","_id":"6689","oa":"1","status":"public","doi":"https://doi.org/10.23763/BrSc21-10wefing","author":[{"full_name":"Wefing, Patrick","last_name":"Wefing","id":"68976","first_name":"Patrick"},{"full_name":"Conradi, Florian","id":"68967","last_name":"Conradi","first_name":"Florian"},{"full_name":"Rämisch, Johannes","first_name":"Johannes","last_name":"Rämisch"},{"full_name":"Neubauer, Peter","first_name":"Peter","last_name":"Neubauer"},{"last_name":"Schneider","id":"13209","first_name":"Jan","full_name":"Schneider, Jan","orcid":"0000-0001-6401-8873"}],"language":[{"iso":"eng"}],"keyword":["mashing","NIR","machine learning","FAN"],"abstract":[{"text":"Free amino nitrogen (FAN) concentrations in beer mash can be determined with machine learning algorithms\r\nfrom near-infrared (NIR) spectra. NIR spectroscopy is an alternative to a classical chemical analysis and\r\nallows for the application of inline process quality control. This study investigates the capabilities of\r\ndifferent machine learning techniques such as Ordinary Least Squares (OLS) regression, Decision Tree\r\nRegressor (DTR), Bayesian Ridge Regression (BRR), Ridge Regression (RR), K-nearest neighbours (KNN)\r\nregression as well as Support Vector Regression (SVR) to predict the FAN content in beer mash from NIR\r\nspectra. Various pre-processing strategies such as principal component analysis (PCA) and data\r\nstandardization were used to process NIR data that were used to train the machine learning algorithms.\r\nAlgorithm training was conducted with NIR data obtained from 16 beer mashes with varying FAN\r\nconcentrations. The trained models were then validated with 4 beer mashes that were not used for model\r\ntraining. Machine learning algorithms based on linear regression showed the highest prediction accuracy on\r\nunpre-processed data. BRR reached a root mean square error of calibration (RMSEC) of 2.58 mg/L (R2 = 0.96)\r\nand a prediction accuracy (RMSEP) of 2.81 mg/L (R2 = 0.96). The FAN concentration range of the investigated\r\nsamples was between approx. 180 and 220 mg/L. Machine learning based NIR spectra analysis is an alternative\r\nto classical chemical FAN level determination methods and can also be used as inline sensor system.","lang":"eng"}],"date_updated":"2025-01-30T15:43:53Z","date_created":"2021-11-02T10:06:04Z","quality_controlled":"1","volume":74,"year":"2021","issue":"9/10","user_id":"83781","type":"journal_article","page":"107 - 121","department":[{"_id":"DEP1308"},{"_id":"DEP4028"}],"title":"Determination of free amino nitrogen in beer mash with an inline NIR transflectance probe and data evaluation by machine learning algorithms"}