[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126830-en":3,"doc-seo-126830-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126830,1099523885074,"Ivy","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Near-infrared spectroscopy and machine learning for classification of food powders during a continuous process","In food production environments, incorrect powder materials can be loaded onto a production line, affecting food safety, product quality, and operating economics. This study evaluates Near Infrared (NIR) spectroscopy combined with machine learning to classify food powders under motion conditions. Two NIR sensors with different wavelength ranges are compared across 25 powder materials, testing spectral preprocessing, feature selection, and multiple algorithms. Best performance uses autoencoder preprocessing with support vector machines and all wavelengths from both sensors, further improved by undersampling and boosting, reaching up to 99.52% accuracy, validated on independent test sets.","Journal of Food Engineering 341 (2023) 111339  \nContents lists available at ScienceDirect Journal of Food Engineering  \njournal [homepage:](homepage: www.elsevier.com/locate/jfoodeng)[ www.elsevier.com/locate/jfoodeng](homepage: www.elsevier.com/locate/jfoodeng)  \n| Near-infrared spectroscopy and machine learning for classification of food   powders during a continuous process\u003Cbr>Samet Ozturk a, b, **, Alexander Bowler a, Ahmed Rady a, Nicholas J. Watson a, *\u003Cbr>a Food, Water, Waste Research Group, Faculty of Engineering, University of Nottingham, University Park, Nottingham, UK b Department of Food Engineering, Gümühane University, Gümühane, Turkey |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Food powders\u003Cbr>Near-infrared spectroscopy In-line sensors\u003Cbr>Machine learning Digital manufacturing. |  | In food production environments, the wrong powder material is occasionally loaded onto a production line which impacts food safety, product quality, and production economics. The aim of this study was to assess the potential of using Near Infrared (NIR) spectroscopy combined with Machine Learning to classify food powders under motion conditions. Two NIR sensors with different wavelength ranges were compared and the ML models were tasked with classifying between 25 food powder materials. Eleven different spectra pre-processing methods, three feature selection methods, and five algorithms were investigated to find the optimal ML pipeline. It was found that pre-processing the spectra using autoencoders followed by using support vector machines with the all spectral wavelengths from both sensors was most accurate. The results were improved further using undersampling and boosting. Overall, this method achieved 99.52, 97.12, 94.08, and 91.68% accuracy for the static, 0.017, 0.036 and 0.068 m s-1 sample speeds. The models were also validated using an independent test sets. |\n\n1. Introduction  \nFood powders including flours, spices, nut or animal derived, play an important role in the production of many food products (Su and Sun, 2018). The quality and safety of these food powders have a significant impact on human health. Therefore, measurements related to chemical composition (e.g., starch or protein content) (Yang et al., 2013), adulteration (such as species or origin) (Lohumi et al., 2014), mycotoxin content (such as aflatoxins) (Teena et al., 2014) -, allergen content (Laborde et al., 2020) or parasitic infection (e.g., red flour beetles or weevils) (Campbell and Arbogast, 2004) are required for quality and safety assurance throughout food production. Previous studies have shown that the most common foods linked to allergen incidents tend tobe prepared dishes, snacks, cereals, bakery, and confectionary (FSA, 2020). These foods are typically more complex as they usually contain a large number of ingredients and are often produced using more complicated processes causing more scope for mistakes. Human errors such as using the wrong ingredient (many powdered food materials have similar appearance) or mislabelling of materials can result in food safety and quality incidents. These kinds of problems may appear unlikely but a  \n2019 UK workshop on food allergens and safety, which included a range of food production stakeholders (manufacturers, regulators, technology providers and academics), concluded that the largest risk to cross-contamination of powdered foods was mislabelling or accidental misuse of materials within production environments (Pauli et al., 2020). In 2020, the Food Standard Agency also reported that 18% of all failures resulting in allergy alerts were production errors associated with either formulation/assembly errors or work in progress labelling errors (FSA, 2020). Therefore, for early detection of these problems, techniques to monitor or confirm the composition of food in production environments in real-time are required. Optical spectroscopic technologies have been develope","cbCaioKurZL5kCCv","https://ap.wps.com/l/cbCaioKurZL5kCCv","pdf",4453324,1,12,"English","en",105,"# Introduction\n# Problem background: food powder safety and quality risks\n# NIR spectroscopy for in-line composition monitoring\n# Study motivation and evaluation approach","[{\"question\":\"What problem does the study address in food production?\",\"answer\":\"The study targets situations where the wrong powder material is loaded onto a production line, which can compromise food safety, quality, and production economics.\"},{\"question\":\"How does the proposed method classify food powders?\",\"answer\":\"It combines near-infrared (NIR) spectroscopy with machine learning to classify powders while accounting for sample motion on a processing line.\"},{\"question\":\"Which model pipeline achieved the highest accuracy?\",\"answer\":\"Preprocessing spectra with autoencoders followed by support vector machines using all wavelengths from both sensors delivered the most accurate results, with further gains from undersampling and boosting.\"}]","Near-infrared spectroscopy and machine learning for classification of food powders during a continuous process | PDF",1785935077,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"near-infrared-spectroscopy-and-machine-learning-for-classification-of-food-powders-during-a-continuous-process","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/near-infrared-spectroscopy-and-machine-learning-for-classification-of-food-powders-during-a-continuous-process/126830/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in food production?","Question",{"text":75,"@type":76},"The study targets situations where the wrong powder material is loaded onto a production line, which can compromise food safety, quality, and production economics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method classify food powders?",{"text":80,"@type":76},"It combines near-infrared (NIR) spectroscopy with machine learning to classify powders while accounting for sample motion on a processing line.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model pipeline achieved the highest accuracy?",{"text":84,"@type":76},"Preprocessing spectra with autoencoders followed by support vector machines using all wavelengths from both sensors delivered the most accurate results, with further gains from undersampling and boosting.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]