Harnessing Big Data in Food Safety

Description

Big Data technologies have the potential to revolutionize the agriculture sector, in particular food safety and quality practices. This book is designed to provide a foundational understanding of various applications of Big Data in Food Safety. Big Data requires the use of sophisticated approaches for cleaning, processing and extracting useful information to improve decision-making. The contributed volume reviews some of these approaches and algorithms in the context of real-world food safety  studies.  Food safety and quality related data are being generated in large volumes and from a variety of sources such as farms, processors, retailers, government organizations, and other industries. The editors have included examples of how big data can be used in the fields of bacteriology, virology and mycology to improve food safety.  Additional chapters detail how the big data sources are aggregated and used in food safety and quality areas such as food spoilage and quality deterioration along the supply chain, food supply chain traceability, as well as policy and regulations. The volume also contains solutions to address standardization, data interoperability, and other data governance and data related technical challenges. Furthermore, this volume discusses how the application of machine-learning has successfully improved the speed and/or accuracy of many processes in the food supply chain, and also discusses some of the inherent challenges. Included in this volume as well is a practical example of the digital transformation that happened in Dubai, with a particular emphasis on how data is enabling better decision-making in food safety. To complete this volume, researchers discuss how although big data is and will continue to be a major disruptor in the area of food safety, it also raises some important questions with regards to issues such as security/privacy, data control and data governance, all of which must be carefully considered by governments and law makers. Preface Contents 1 Machine Learning Application in Food Safety, Production, and Quality 1.1 Introduction 1.2 An Introduction to Food Supply Chain 1.2.1 Food Safety 1.2.1.1 Foodborne Illness 1.2.1.2 Foodborne Disease Outbreaks 1.2.2 Food Spoilage and Quality 1.2.2.1 Food Authenticity 1.2.2.2 Food Post-harvesting 1.2.3 Food Production Process 1.2.3.1 Food Harvesting 1.2.3.2 Food Packaging 1.2.3.3 Food Traceability 1.2.3.4 Food Distribution 1.2.3.5 Food Storage 1.3 An Introduction to Machine Learning 1.3.1 Machine Learning Applications in Food Safety 1.3.2 Machine Learning Applications in Food Quality 1.3.3 Machine Learning Applications in Food Production 1.4 Conclusion References 2 Foodborne Bacterial PathogenBig Data – Genomic Analysis 2.1 Introduction 2.2 Whole Genome Sequencing 2.2.1 WGS in Source Attribution 2.2.2 WGS in Disease Surveillance 2.2.3 Antimicrobial Resistance, Virulence Potential, and Risk Analysis 2.2.4 WGS Technologies 2.2.4.1 First-Generation Sequencing: Sanger Shotgun Approach 2.2.4.2 Second-Generation Sequencing: The Massively Parallel Approach 2.2.4.3 Third-Generation Sequencing: The Long-Read Approach 2.3 Bioinformatics: Algorithms and Databases 2.4 Future Opportunities and Challenges for WGS 2.4.1 Predicting Emerging Treats 2.4.2 Low- and Middle-Income Countries 2.4.3 Culture-Independent Diagnostic Tests 2.4.3.1 Metagenomic Sequencing References 3 Foodborne Viral Pathogen Big Data: Genomic Analysis 3.1 Introduction 3.1.1 Norovirus 3.1.2 HAV 3.1.3 HEV 3.1.4 SARS-CoV-2 3.1.5 WGS 3.2 Applications 3.2.1 Surveillance and Source Attribution 3.2.2 Analysis of Variants and Viral Evolution 3.2.3 Predictive Analytics 3.3 Conclusion and Future Perspectives References 4 The Use of Big Data in the Field of Food Mycology and Mycotoxins 4.1 Introduction 4.2 Food Mycology: Past and Present 4.3 Evolution of Food Mycological Methods 4.3.1 Methods for Quantifying Fungal Growth 4.3.2 Cultural Methods 4.3.3 The Impact of Polyphasic Approaches on Mycological Studies 4.3.4 Molecular Techniques on Fungal Taxonomy 4.4 The Omic Tools (Genomics, Transcriptomics, Metagenomics, Proteomics, and Metabolomics) in Food Mycology for the Generation of Big Data 4.4.1 Genomics 4.4.2 Transcriptomics 4.4.3 Metagenomics 4.4.4 Metabolomics 4.4.5 Proteomics 4.5 The Usefulness of Big Data Storage 4.6 How to Use Big Data to Find Strategies to Prevent and Control Fungi and Mycotoxins References 5 Big Data and its Role in Mitigating Food Spoilage and Quality Deterioration along the Supply Chain 5.1 Introduction 5.2 Food Spoilage and Shelf Life 5.2.1 Shelf Life Open Dates as Measures of Food Spoilage 5.3 Food Quality and Spoilage Data throughout the Supply Chain 5.3.1 Data Collection 5.3.2 Product Identification 5.3.3 Sensing and Monitoring 5.3.4 Communication, Access, and Processing 5.4 Big Data and Spoilage: Challenges, Uses, and Opportunities 5.5 Final Remarks References 6 Algorithms to Localize Food Contamination Events 6.1 Introduction 6.2 Mathematical Problem Formulation 6.3 The Generalized Jordan Center Estimator 6.3.1 Recall 6.4 Experiments 6.4.1 Random Networks 6.4.2 Synthetic Supply Chain 6.5 Conclusion References 7 The Need for Data Standardization in the Food Supply Chain 7.1 Introduction 7.2 Data in the Food Supply Chain 7.3 Data Interoperability in Food Supply Chain 7.4 Data Standardization 7.4.1 What Is Data Standardization? 7.4.2 The Importance of Data Standardization 7.5 Data Standardization Approaches 7.5.1 Auditing Data Sources 7.5.2 Brainstorming Standards 7.5.3 Standardizing the Data Sources 7.5.4 Standardizing the Database 7.6 Data Standardization Methods in Food Supply Chain 7.7 Data Standardization: A Case Study in Generating Taxonomy in the Field of Foodborne Illnesses 7.8 Conclusion References 8 Big Data Digital Transformation in Food Safety: A DubaiExperience 8.1 Introduction 8.2 Overview of Dubai 8.3 Digital Transformation in Food Safety 8.3.1 Business Information 8.3.2 People Information 8.3.3 Food Safety Information 8.3.4 Information About Facilities and Equipment 8.3.5 Compliance Information 8.4 Supplier Management 8.5 Digital Food Safety and Customized Food Safety Checks 8.6 Instant Action 8.7 Customized Food Safety Checks 8.8 Big Data-Driven Learning 8.9 Future References 9 The Role of Policy and Regulations in the Adoption of Big Data Technologies in Food Safety and Quality 9.1 Introduction 9.2 Regulatory Policies and Regulations 9.3 Data Ethics and Privacy 9.4 Data Governance References Index