10039nam 22004813 450 991104801760332120250829080341.00-443-34594-50-443-34593-7(CKB)40388228400041(MiAaPQ)EBC32271705(Au-PeEL)EBL32271705(OCoLC)1534816481(EXLCZ)994038822840004120250829d2025 uy 0engur|||||||||||txtrdacontentcrdamediacrrdacarrierSpectroscopy and Machine Learning Tools for Food Quality and Safety1st ed.Chantilly :Elsevier Science & Technology,2025.©2025.1 online resource (441 pages)Advances in Food and Nutrition Research Series ;v.Volume 115Front Cover -- Series Page -- Advances in Food &amp -- Nutrition Research -- Copyright -- Contents -- Contributors -- Preface -- Chapter One: Nir spectroscopy for decision-making in the livestock sector: A technological breakthrough -- 1 Introduction -- 1.1 Brief introduction of NIR and instrument evolution -- 1.2 Current control needs in livestock farming systems -- 2 Applications of NIR spectroscopy on animal feeding -- 3 NIR in the meat products: Case of study of iberian pig -- 4 HSI for the analysis of animal feed and meat -- 5 NIR in livestock systems: In vivo analysis -- 6 Conclusions -- 7 Future trends -- References -- Chapter Two: Fluorescence spectroscopy for grape and wine compositional analysis and quality control -- 1 Introduction -- 1.1 Grape and wine history -- 1.2 Grape and wine quality -- 1.3 Wine and grape composition -- 1.3.1 Wine composition -- 1.3.2 Types of phenolics and their effects in wine -- 1.3.3 Grape and grape must composition -- 2 Grape and wine quality measurement, evaluation, and control -- 2.1 Traditional chemical and sensory methods -- 2.2 Instrumental methods -- 2.3 Novel approaches -- 2.4 Chemometrics and machine learning -- 3 Spectroscopic technologies and fluorescence -- 3.1 Specific compounds with fluorophores in grape and wine -- 4 Applications of fluorescence spectroscopy in grape and wine science -- 4.1 Chemometrics for utilizing spectrofluorometric data -- 4.2 Fluorescence spectroscopy in analysis of grape and wine composition -- 4.2.1 Detection and prediction -- 4.3 Fluorescence spectroscopy in grape and wine quality control -- 4.3.1 Classification and authentication -- 4.3.2 Monitoring -- 4.3.3 Addition -- 5 Conclusion and future perspectives -- References -- Chapter Three: From farm to fork: Spectroscopy in meat quality and safety assurance -- 1 Introduction.2 Farm to fork: Key challenges for assessment of quality and safety -- 2.1 On-farm challenges -- 2.2 Post-slaughter challenges -- 2.3 Processing and packaging challenges -- 2.4 Distribution and retail challenges -- 2.5 Consumer-level challenges -- 3 Meat quality -- 4 Meat safety -- 5 Spectroscopy principle -- 5.1 Spectroscopic techniques -- 5.1.1 Point spectroscopy -- 5.1.2 Imaging-based spectroscopy -- 6 Challenges of applying spectroscopy on meat -- 7 Meat Vis-NIR spectra -- 8 Applications -- 8.1 Post-slaughter (pre-rigor) -- 8.2 Post-slaughter (post-rigor) -- 8.3 Packaging and storage -- 9 Challenges, limitations and future -- 10 Conclusion -- References -- Chapter Four: Vibrational spectroscopy (Raman and infrared) and machine learning tools in food safety and composition -- 1 Vibrational spectroscopy -- 1.1 Raman spectroscopy -- 1.2 Fourier transform -- 1.3 Handheld and portable instrumentation -- 1.4 Machine learning -- 1.4.1 Supervised machine learning algorithms -- 1.4.2 Bayesian networks -- 1.4.3 Soft independent modelling of class analogy -- 1.4.4 Support vector machines -- 1.4.5 Decision tree -- 1.4.6 Random forest -- 1.4.7 Gradient boosted trees -- 1.4.8 Levenberg-marquardt -- 1.4.9 Linear discriminant analysis -- 1.4.10 Partial least squares regression -- 1.4.11 Partial least squares discriminant analysis -- 1.4.12 Logistic regression -- 1.4.13 Artificial neural network -- 1.4.14 K-nearest neighbor -- 1.5 Deep learning algorithms -- 1.5.1 Convolutional neural networks -- 1.5.2 Recurrent neural networks -- 1.5.3 Restricted boltzmann machines -- 1.5.4 Autoencoders -- 1.5.5 Transfer learning -- 1.5.6 U-Net -- 1.5.7 Generative adversarial networks -- 1.5.8 Fully convolution neural networks -- 2 Spectroscopy, machine learning, and food applications -- 2.1 AI algorithms used for food applications.2.2 Challenges of applying machine learning for food applications -- 3 Machine learning used for COVID-19 -- 4 Summary -- References -- Chapter Five: Spectroscopy food functionality and safety -- 1 Introduction -- 1.1 Importance of food functionality and safety -- 1.2 Food functionality: enhancing nutritional quality and consumer health -- 1.3 Food safety: a global challenge -- 1.4 The need for advanced analytical methods -- 1.5 Advancing food quality assessment with spectroscopy -- 1.6 Consumer expectations and regulatory demands -- 2 Spectroscopic techniques in food functionality -- 2.1 Chemical composition analysis -- 2.1.1 Identification and quantification of macronutrients by spectroscopic techniques -- 2.1.1.1 Protein analysis -- 2.1.1.2 Fat analysis -- 2.1.1.3 Carbohydrate analysis -- 2.1.2 Detection of bio-active compounds -- 2.1.3 Analysis of food texture and microstructure -- 2.1.4 Functional properties -- 2.1.4.1 Emulsifier -- 2.1.4.2 Stabilizer -- 2.1.5 Application to product development -- 2.1.6 Role in designing functional foods with enhanced health benefits -- 3 Spectroscopic applications in food safety -- 3.1 Contaminant detection -- 3.2 Identification of heavy metals, pesticides, and microbiological hazards -- 3.3 Real-time monitoring of foodborne pathogens -- 3.4 Food adulteration and authenticity -- 3.4.1 Spectroscopic methods -- 3.4.2 Near-infrared spectroscopy (NIR) -- 3.4.3 Fourier transform near-infrared (FT-NIR) spectroscopy -- 3.4.4 Raman spectroscopy -- 3.4.5 NMR spectroscopy -- 3.4.6 UV-Vis spectrophotometry -- 3.4.7 Applications of spectroscopy in food processing -- 3.5 Detection of adulterants in oils, spices and other food products -- 3.5.1 Saffron -- 3.5.2 Pepper -- 3.5.3 Coffee and tea -- 3.5.4 Honey -- 3.5.5 Edible oil -- 3.5.6 Seafood -- 3.5.7 Juice -- 3.6 Authentication of geographic origin and organic claims.3.7 Monitoring shelf life and storage -- 3.8 Evaluation of oxidative changes and microbial activity -- 4 Challenges and future directions -- 4.1 Challenges in spectroscopic analysis for food functionality and safety -- 4.1.1 Limitations in sensitivity and selectivity for complex matrices -- 4.1.2 Need for standardization and calibration in spectroscopic analysis -- 4.1.3 Inadequate resolution of infrared spectroscopy -- 4.1.4 Challenges in quantitative analysis -- 4.2 Future directions -- 4.2.1 Emerging trends: miniaturization, automation, and affordability -- 4.2.2 Innovations in affordability and accessibility -- 4.2.3 Integration of spectroscopy with IoT and blockchain technologies -- 4.2.4 Development of hybrid and multifunctional spectroscopic platforms -- 4.2.5 Sustainability and green analytical chemistry -- 5 Conclusion -- References -- Chapter Six: Handheld NIR spectroscopy for real-time on-site food quality and safety monitoring -- 1 Introduction -- 2 Fundamentals of near-infrared (NIR) spectroscopy -- 3 Data processing, machine learning and NIR spectra interpretation -- 3.1 Basics of data acquisition and preprocessing -- 3.2 Key aspects of chemometrics -- 3.2.1 Exploratory data analysis (EDA) -- 3.2.2 Regression -- 3.2.3 Classification -- 3.2.4 Miscellaneous -- 3.3 Methods for interpretation of NIR Spectra -- 3.4 Modern trends: Deep chemometrics, AI, and big data analytics -- 4 Miniaturization of NIR sensors -- 5 Applications of portable NIR spectroscopy in food analysis -- 5.1 Food quality assessment and composition analysis -- 5.2 Freshness, ripeness, and shelf life assessment -- 5.3 Food safety and contaminant detection -- 5.4 Authentication and anti-fraud measures -- 6 Perspective on miniaturized NIR spectroscopy in food analytics and its future directions -- 7 Summary -- References.Chapter Seven: Food fermentations: NIR spectroscopy as a tool for process analytical technology -- 1 Introduction -- 2 Fermentation in food processing -- 2.1 Advantages of fermentation -- 2.2 Challenges and limitations of fermentation -- 3 Monitoring and control strategies -- 3.1 Traditional monitoring techniques -- 3.2 Advanced monitoring techniques -- 4 NIR spectroscopy as a tool for PAT in food fermentations -- 4.1 Examples of NIR spectroscopy applications in food fermentation -- 4.2 Limitations and challenges -- 5 Conclusions and future perspectives -- References -- Chapter Eight: Spectroscopy grains, beer composition and safety -- 1 Introduction -- 2 The first beer -- 3 The malting and brewing processes -- 4 There more to grain quality than protein -- 5 NIR and cereal breeding -- 6 Grain moisture -- 7 Applications in barley breeding -- 8 Malt traits -- 9 NIR prediction of hop quality -- 10 NIR and wort traits -- 11 Beer traits -- 12 Hyperspectral imaging -- 13 Safety -- 14 Conclusions -- References -- Back Cover.Spectroscopy and Machine Learning Tools for Food Quality and Safety, Volume 115 in the Advances in Food and Nutrition Research series, highlights new advances in the field, with this new volume presenting interesting chapters related to Spectroscopy and Machine Learning Tools.Advances in Food and Nutrition Research Series338.47664Cozzolino Daniel1741199Daniel Cozzolino1882718MiAaPQMiAaPQMiAaPQBOOK9911048017603321Spectroscopy and Machine Learning Tools for Food Quality and Safety4498090UNINA