[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126994-en":3,"doc-seo-126994-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},126994,687207024643,"Oliver","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Detection of Antibiotic Residues in Milk Using Near-Infrared Spectra - Thesis Overview","The study evaluates a novel alternative screening approach that combines Near-InfraRed (NIR) milk spectra with machine learning models to detect residues of common, approved veterinary drugs in milk. Qualitative and statistics-based analyses, including ML clustering, identify detection thresholds at the mg/L level across antibiotic targets in 0% and 2% milk. ML classification shows limited separation between adulterated and unadulterated samples (612 samples), with performance metrics not meeting practical application requirements. Results also confirm external factors such as antibiotic concentration variation and milk temperature affect NIR spectral amplitude.","Detection of Antibiotic Residues in Milk Using Near-Infrared Spectra  \nand Machine Learning Modelling  \nby  \nKaitlyn Rodriguez  \nA Thesis  \npresented to  \nThe University of Guelph  \nIn partial fulfilment of requirements  \nfor the degree of  \nMaster of Science  \nin  \nBioinformatics  \nGuelph, Ontario, Canada  \n© Kaitlyn Rodriguez , April , 2024  \nAbstract  \nDetection of Antibiotic Residues in Milk Using Near-Infrared Spectra and Machine  \nLearning Modelling  \nKaitlyn Rodriguez  \nUniversity of Guelph, 2024  \nAdvisor(s):  \nDr. Dan Tulpan  \nThe aim of this study was to evaluate the viability of a novel, alternative screening method that pairs Near-InfraRed (NIR) milk spectra with Machine Learning (ML) modelling for the detection of residues of common, approved veterinary drugs in milk. Analyses (qualitative, statistics-based and ML clustering) revealed thresholds of detection at the mg/L level for all antibiotics of interest in 0% and 2% milk. Moreover, ML classification algorithms demonstrated limited capability to differentiate adulterated from unadulterated samples (datasets of 612 samples) at thresholds of 1160 mg/L and 0.01 mg/L with accuracies and F1-scores between 0.72 and 0.74. However, these scores do not meet requirements for practical applications. Furthermore, variations in antibiotic contamination levels and sample temperature fluctuations were both verified to influence NIR spectral amplitude. To prevent the misinterpretation of spectral changes as evidence of antibiotic contamination, it is vital that the control of external experimental factors is conducted and well-documented.  \nAcknowledgements  \nI would first like to thank my advisor, Dr. Dan Tulpan, for his unwavering support and guidance through all of the unexpected hurdles I’ve had overcome throughout my time as a graduate student. I cannot begin to express how grateful I am to have worked with an advisor who is so dedicated to doing everything he can to ensure that his students succeed. I have learned so much from him and have made incredible connections with peers and mentors through his introduction. I would also like to thank him for taking a chance on this project. While it hasn’t been the easiest experience, I cherish everything that came out of this project. Not only the final product and the potential for more in the future, but also my growth as a person and a researcher.  \nA profound thank-you to my advisory committee, Dr. Ricardo Ventura, Dr. Stephen LeBlanc, and Dr. Christine Baes, as well as Dr. Julio Balieiro from the BIOMA Lab of the University of São Paulo. Thank you all for your mentorship, support and for offering the invaluable and insightful perspectives that brought this project to life. Thank you to Dr. Ventura and Dr. Balieiro for the time and hard work that was dedicated towards the pilot study that got this project off the ground. Thank you, Dr. LeBlanc, for your help and generosity in providing the antibiotics that made our experiments possible. Dr. Baes, thank you for being so kind and encouraging through the trials and tribulations of this project.  \nI would also like to thank my peers within the Tulpan Lab and beyond. I would especially like to thank Esther, Elena, Saeed, Harry, Jihao, Ben, Lucas and Julia for being really incredible people to work with and learn from. I can’t wait to see where life takes everyone, and I look forward to continuing to celebrate each other’s successes. Furthermore, I would like to thank Dr. Julang Li and especially Lauren Fletcher for all the wet lab support they provided to make this project possible. Thank you so much for your time, help and expertise. You were such a delight to get to know. Thank you for meeting me during those early mornings and for bringing some light to those long lab days.  \nFinally, thank you to my mom and dad for unconditionally supporting me as I chase my dreams. To Alex and Julie, thank you for being the absolute best siblings I could ever ask for and lean on. There are t","cbCaijdYVhGjFvxX","https://ap.wps.com/l/cbCaijdYVhGjFvxX","pdf",7725621,1,205,"English","en",105,"# Abstract\n# Acknowledgements\n# Table of Contents\n# List of Tables\n# List of Figures\n# List of Symbols, Abbreviations or Nomenclature\n# List of Appendices\n# General Introduction\n## Veterinary Antibiotic Use in the Canadian Dairy Industry\n## Use of Near-Infrared Spectroscopy and Mid-Infrared Spectroscopy in the Determination of Food Quality and Safety\n## Statistical Analysis and Machine Learning Modelling\n## Study Objectives","[{\"question\":\"What screening method does the thesis evaluate for antibiotic residues in milk?\",\"answer\":\"It evaluates an alternative screening approach that pairs near-infrared (NIR) milk spectra with machine learning (ML) modelling to detect residues of approved veterinary drugs in milk.\"},{\"question\":\"How effective were the ML models at distinguishing adulterated from unadulterated samples?\",\"answer\":\"ML classification produced limited differentiation between adulterated and unadulterated samples (612 samples), with accuracies and F1-scores between 0.72 and 0.74 at specified thresholds, which did not meet practical application needs.\"},{\"question\":\"What factors can affect NIR spectral results besides antibiotic contamination?\",\"answer\":\"The study verifies that variations in antibiotic contamination levels and fluctuations in sample temperature both influence NIR spectral amplitude, so external experimental factors must be controlled and well-documented.\"}]","Detection of Antibiotic Residues in Milk Using Near-Infrared Spectra - Thesis Overview | PDF",1785936093,517,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"detection-of-antibiotic-residues-in-milk-using-near-infrared-spectra-thesis-overview","",{"@graph":36,"@context":86},[37,54,69],{"@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/detection-of-antibiotic-residues-in-milk-using-near-infrared-spectra-thesis-overview/126994/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What screening method does the thesis evaluate for antibiotic residues in milk?","Question",{"text":76,"@type":77},"It evaluates an alternative screening approach that pairs near-infrared (NIR) milk spectra with machine learning (ML) modelling to detect residues of approved veterinary drugs in milk.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How effective were the ML models at distinguishing adulterated from unadulterated samples?",{"text":81,"@type":77},"ML classification produced limited differentiation between adulterated and unadulterated samples (612 samples), with accuracies and F1-scores between 0.72 and 0.74 at specified thresholds, which did not meet practical application needs.",{"name":83,"@type":74,"acceptedAnswer":84},"What factors can affect NIR spectral results besides antibiotic contamination?",{"text":85,"@type":77},"The study verifies that variations in antibiotic contamination levels and fluctuations in sample temperature both influence NIR spectral amplitude, so external experimental factors must be controlled and well-documented.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]