Food waste is an important social and environmental issue that the current society faces, where one third of the total food produced is wasted or lost every year while more than 820 million people around the world do not have access to adequate food. However, as we move towards a decentralized Web 3.0 enabled smart city, we can utilize cutting edge technologies such as blockchain, artificial intelligence, cloud computing and many more to reduce food waste in different phases of the supply chain.
In this book, we introduce FoodSQRBlock and SmartNoshWaste - two blockchain based multi-layered frameworks in the food supply chain utilizing cloud computing, QR code and reinforcement learning to reduce food waste.
Contents
1 Preface
2 Introduction
3 Prerequisite: Blockchain, AI, QR Code and Cloud Computing
3.0.1 Blockchain Technology
3.0.2 AI and Reinforcement Learning
3.0.3 QRCode
3.0.4 Cloud Computing
4 FoodSQRBlock: FoodSQRBlock: Digitizing Food Production and the Supply Chain Data
4.1 Proposed Framework: FoodSQRBlock 11
4.2 Experimental evaluation: case study & large scale integration of FoodSQRBlock 15
4.2.1 Experimental Evaluation
4.2.2 Analysis & Discussion
4.3 Future Direction and Discussion
4.4 Summary
5 SmartNoshWaste: Using Blockchain & Machine Learning in Food Supply Chain to Reduce Waste
5.1 Proposed Framework: SmartNoshWaste
5.1.1 Assumptions and data system architecture of SmartNoshWaste
5.1.2 Machine learning module of SmartNoshWaste
5.2 Experimental evaluation: Case study with real food data
5.3 Future Direction and Discussion
5.4 Summary
Bibliography
Acknowledgements
I would like to take this opportunity to extend my thanks to many people who directly and indirectly supported me to improve this book. First of all, I would like to thank my parents - Sudip Dey and Soma Dey, without whom I might never have found my passion to help others using technology. Next, it goes without saying that how lucky I have been to be supervised by Dr. Amit Kumar Singh and Prof. Klaus Dieter McDonald-Maier, who have always supported me and have given me the full freedom to pursue my research during my PhD. I couldn't have asked for any better to be my mentor and advisor during my PhD journey than Dr. Amit Kumar Singh and Prof. Klaus Dieter McDonald-Maier.
Many thanks also to everyone in the Embedded and Intelligent Systems Laboratory at the University of Essex for their continued support, advise and friendship. I would also like to thank Suman Saha, Chief Technology Officer of Nosh Technologies, for his support to build one of the most successful food management and waste reduction startups in the world. Also, without Suman's support this research work would not have been possible.
Abstract
Food waste is an important social and environmental issue that the current society faces, where one third of the total food produced is wasted or lost every year while more than 820 million people around the world do not have access to adequate food. However, as we move towards a decentralized Web 3.0 enabled smart city, wecan utilize cutting edge technologies such as blockchain, artificial intelligence, cloud computing and many more to reduce food waste in different phases of the supply chain. In this book, we introduce FoodSQRBlock and SmartNoshWaste - two blockchain based multi-layered frameworks in the food supply chain utilizing cloud computing, QR code and reinforcement learning to reduce food waste.
List of Figures
2.1 Representational diagram of a smart city using technologies such as Blockchain, Artificial Intelligence (A.I.), Cloud and Edge Computing and many more within the Web 3.0 informationsystem
2.2 UPC barcode for Tropicana Trop50 Blackberry Cherry juice as fetched from BarcodeSpi- der.com [bar, b]
3.1 Representative diagram of intelligent agent
3.2 Representational QR code with “Hello, World!" message embedding
4.1 Overview of the System Architecture of FoodSQRBlock based on Farm-to-Fork supply chain
4.2 Conceptual FoodSQRBlock framework of an agri-food supply chain traceability system based on QR code & blockchain technology
4.3 QR code holding information of a dairy product, which is produced at Boydells Dairy Farm in the UK, generated by FoodSQRBlock
4.4 Time taken to process different number of items (using FoodSQRBlock) in Google Cloud Platform's Compute Engine
5.1 Overview of the Data System Architecture of SmartNoshWaste based on Farm-to-Fork supply chain
5.2 Generic data regarding food in different phases of the supply chain that are digitized to be stored in the blockchain
5.3 Diagramatic representation of Q-Learning based RL method in the Machine Learning Module of SmartNoshWaste
5.4 Consumption and wastage data on potatoes collected via the nosh app [nos, ] where the Y- Axis represents the number of items consumed (C) or wasted (W) and X-Axis represents the months of the year when the data was collected
Chapter 1
Preface
Before I introduce the works on how Blockchain and Artificial Intelligence (AI) are being used in the food supply chain, please allow me to share my story. In 2013, I moved to the U.K. to pursue my master's degree in Advanced Computer Science at the University of Manchester. In 2014, while completing my master's degree, my parents in India went through a tragic car accident that caused severe injuries to my mother and paralyzed my father. To help my parents go through medical procedures, I sent back all my money to them in India without realizing that I didn't have any money to buy food for almost a week. To survive from hunger I ended up salvaging edibles from dustbins on the streets of Manchester. Don't worry, the collected foods were completely edible but were thrown away by others because either of inconvenience or the food were one day past their "best-before" date. This showed me, how much food wastage happens yet we have so many hungry people around the world.
Later in 2014, after graduating with my master's degree with a specialization in Com- puterSystemsEngineering,Ico-developedtheworld'sfirstcrowdfood-sharingplatform that enables users to share their leftovers and food surplus with other people-in-need nearby. This application also won the 3Scale API award at the 2014 Koding's Global Virtual Hackathon and in the following years, it also inspired many other entrepreneurs to join the fight against food waste by developing similar solutions.
Being an early adopter and creator of such a technology that helped build the personal food waste management industry, I have been closely following food waste and related statistics around the world. As the human population grew over the years, food waste also scaled up accordingly. According to the U.S. Food and Agriculture Organization (FAO), more than 1.3 billion tons of food are wasted around the globe, which is worth $2.6 trillion. On the other hand, we have more than 820 million people around the globe who do not have access to proper nutrition. That being said, food wastage is not a social issue but an environmental one as well. Food wastage also contributes to almost 10% of global carbon emissions. Food waste is an issue that is currently plaguing the world and it happens throughout the food supply chain regardless.
Being a technologist and a scientist in the field of AI and Blockchain, I strongly believe that we can use such technologies to reduce waste, improve efficiency and improve sustainability in the food supply chain. So, without further ado let's get started!
Chapter 2
Introduction
Smart cities are often visualized as consortium of technologies including sensors, computing systems and services, across many scales that are connected through multiple networks which provide continuous data regarding the activities of people and objects including devices, buildings and assets in terms of the flow of decisions about the physical, operational and social form of the city [Batty et al., 2012]. On the other hand, as we move towards Web 3.0 with focus on decentralized semantic web [Alabdulwahhab, 2018, Ragnedda and Destefanis, 2019], it is unavoidable to imagine smart cities of the future without decentralized Web 3.0 as the underlying information system.
Abbildung in dieser Leseprobe nicht enthalten
Web 3.0 Information System
Figure 2.1: Representational diagram of a smart city using technologies such as Blockchain, Artificial Intelligence (A.I.), Cloud and Edge Computing and many more within the Web 3.0 information system
Fig. 2.1 shows the diagrammatic representation of a smart city utilizing Web 3.0 information system along with other technologies such as Blockchain, Artificial Intelligence (A.I. or simply, AI) Cloud Computing, Edge Computing and many more, to feed information from each other to optimize the efficiency of city operations and services and connect to the citizens [Peris-Ortiz et al., 2017]. The key goals of information flow within the smart cities could include a plethora of activities including managing traffic and transportation systems, power plants, utilities, water supply networks, waste, crime detection, information systems, schools, libraries, hospitals, and other community services.
On the other hand, one of the most important issues that the modern society faces today is food wastage, which is both a social issue and an environmental one [Schanes et al., 2018, foo, a, foo, b]. Every year one third of total food produced, which weighs approximately 1.3 billion tonnes and is equivalent to $2.6 trillion, is lost or wasted. How- ever,morethan820millionpeoplearoundtheglobedoesn'thaveaccesstopropernutri- tious meal [foo, a]. Moreover, food waste and loss contributes to almost 10% of the total greenhouse gas emissions around the globe, leading to detriment of the environment as well [foo, b]. That being said, the supporting technologies of a Web 3.0 enabled smart city could be the enabler of reducing food waste and to build a more sustainable planet.
Over the decades the food production system - the way to get food from farm to the table in the household - has evolved to a complex network. Today's food production system provides the consumers more variety, convenient, economical and healthier source of food, however, such a system comes with its own challenges, such as the case where ingredients produced by one producer could end up in thousands of other products distributed in many different shops [Yiannas, 2018, Zhao et al., 2019]. This challenge is an issue of food safety, which is potentially detrimental to consumers' health and seriously damage the consumer's trust on the food market. For example, some immoral food producer could use trench oil to produce cooking oil, which is then distributed to thousands of shops, which is retrospectively bought and consumed by the consumer, making them sick in the process. Several cases of such accidents or food safety scandals such as “horsemeat scandal" “Sudan red", “clenbuterol", “Sanlu toxic milk powder" and “trench oil" [Tian, 2016] have happened all over the world. These scandals not just harm the economy of the food market, but at the same time threaten the safety and stability of the society as well. Although there are standards available such as General Food Law in EU [foo, d], Food Safety Modernization Act (FSMA) in US [fms, ], which try to standardize traceability of digital information of food production in some of the stages of food supply chain, these standards are regional and currently there is no holistic standardization of tracking and recording data for food traceability purposes in all stages of food supply chain across the globe. Henceforth, in order to deal with such a challenge related to food safety, Blockchain Technology (BT) [Dey, 2018a,Dey, 2018b] may play a vital role in the traceability of food ingredients in recent times such that the consumers can trace the source of the food ingredients that they are buying/consuming.
Traditionally, many producers still record data of their production on papers, whereas, some producers digitize the production data, which doesn't enable interaction with other parties in the food system. Moreover, traditional food production systems are centralized in nature and could result in the trust problem, such as fraud, corruption, tampering and falsifying information. During a food-borne outbreak, sifting through thousands of documents (digital or paper) to trace food ingredients could be slow and complicated. In recent times, several methodologies [Tian, 2016,Zhao et al., 2019,Astill et al., 2019, Kamble et al., 2020] based on BT have been proposed to solve the challenge of food traceability for food safety purposes. The key strengths of utilizing BT is its decentralized, distributed and trusted nature, which could be advantageously used for food traceability and transparency for consumers at any point of the food production system. However, all the proposed BT frameworks [Tian, 2016, Zhao et al., 2019, Astill et al., 2019, Kamble et al., 2020] only deal with effective traceability of food supply chains, but not with technical solutions to make the food traceability more accessible to consumers such that they can verify and track their bought food items, may be with an easy-to- access device such as a mobile phone [Dey et al., 2019a, Dey et al., 2020a, Dey et al., 2019b,Dey et al., 2020b].
Abbildung in dieser Leseprobe nicht enthalten
Figure 2.2: UPC barcode for Tropicana Trop50 BlackberryCherry juice as fetched from BarcodeSpider.com [bar, b]
On the other hand, a popular way to store food data digitally is by using 1D barcodes such as Universal Product Code barcode [bar, a, Drobnik, 2015]. The Universal Product Code (UPC) barcode consists of 12 numeric digits that are uniquely assigned to each trade/food item. Every region or country maintains a database which holds the record of these trade/food items along with the UPC unique code, which are capable of storing the following data: the type of product, size, manufacturer and the country of origin of the food item. Therefore, if a consumer wants to know more about the bought food item, they have to use a barcode reader (using mobile phone application), which will fetch the unique UPC from the barcode and then fetch the information from an online database using the UPC. Although the information is fetched from an online database, the amount of information available on the item is limited to the type of product, size, manufacturer and the country of origin based on the type of the database. Therefore, no accurate traceability of the item throughout the supply chain is available for the consumer to verify. For example, Fig. 2.2.(a) represents a typical 1D barcode, which accompanies the Tropicana juice's product label [bar, b], and only reflects the following information (see Fig. 2.2.(b)) about the product: UPC number, European Article Number (EAN), Amazon Standard Identification Number (ASIN) product category, brand, model and last scan date-time, as fetched from BarcodeSpider.com. It should be kept in mind that the 1D barcode in Fig. 2.2.(a) only allows to store 12 digit UPC and no other information, therefore, if the correct database is not used to fetch the information on the product using UPC then the information might not get retrieved at all. Moreover, if the consumer is not connected to the Internet, s/he might not even retrieve any information based on the UPC by scanning traditional 1D barcode since a lookup on the online database using UPC is necessary.
Another issue is that many food products have shorter shelf life such as fresh vegetables and fruits should be consumed within few weeks of being produced and the ex- piry/best before date is printed on the label of the food item during the packaging and hence, is not available in the UPC barcode information. Many food management appli- cations[nos,,now,]arenowbeingofferedtoremindtheconsumeroftheexpiry/bestbe- fore dates of the food products to reduce food waste in the household. In these applications (apps), a consumer can record the bought food items along with their expiry/best before dates, to create a reminder to consume the items before they expire. These applications offer barcode scanning to automatically enter the bought food items in to the apps, however, given the lack of information stored in the barcode, the consumer still has to enter the expiry/best before date of each items individually. Therefore, this calls for a technology which enables the consumer not just to be able to verify the source of the bought food items throughout the supply chain for food traceability purposes, but also automatically fetch the respective expiry/best before date.
Several studies [Tian, 2016, Zhao et al., 2019, Astill et al., 2019, Kamble et al., 2020] have been proposed over the years to utilize blockchain and other technologies such as QR code in conjunction to digitize food supply chain data for traceability purposes. Moreover, studies [Yiannas, 2018, Marin et al., 2021] using blockchain to raise awareness of food waste are also being proposed. However, none of the published studies use blockchain, QR code, cloud computing and machine learning in conjunction to develop a framework that could reduce food waste.
To reduce food waste and improve traceability for food safety, we face two distinct challenges:
1. Digitizing food supply chain data such that the food data can be accessed easily for improved traceability.
2. Using machine learning to learn patterns from the digitized food supply chain data and optimize waste.
We overcome the first challenge we propose FoodSQRBlock (F ood S afety Q uick R esponse Block) [Dey et al., 2021], a BT based framework, which digitizes the food production information such that the consumer and producers can trace the food produce at any point of the food production system, and make the information easily accessible using Quick Response code (QR code) such that the information can be retrieved and verified easily by the consumers and producers. In this book, we also provide a proposal for a large scale integration of FoodSQRBlock in the cloud such that the framework could be adopted easily given the improvement and accessibility of cloud technology.
To overcome the second challenge we propose SmartNoshWaste [Dey et al., 2022] - a Blockchain based multi-layered framework utilizing machine learning (more specifically reinforcement learning), cloud computing and QR code in a decentralized Web 3.0 enabled smart city. Blockchain is an excellent technology to digitize and decentralize food supply chain data, whereas, QR code could be utilized in concurrence to make the digitized data more accessible to consumers, especially via smartphones. We have chosen cloud computing for the framework to improve the speed of computation to provide a seamless user experience in validating and accessing the data. Also, cloud computing improves maintainability of software development as the changes in the software could be easily pushed on to the server for it to effect. On the other hand, machine learning being a sub field of AI, where the computing machine improves automatically through experience and by the use of data [Mitchell, 1997], such a mechanism can be utilized to learn from the data and henceforth, optimize food waste.
SmartNoshWaste has two layers: 1) Data System Architecture and 2) Machine Learning Module. The goal of the Data System Architecture is to digitize and store food data on the Blockchain using QR code and cloud computing to improve traceability and accessibility of such data and such that intelligence could be used by agents (machines) to reduce waste in Machine Learning Module. To the best of our knowledge this is the first framework to be proposed using Blockchain, cloud computing, QR code and machine learning in conjunction in a Web 3.0 enabled smart city to reduce food waste.
In the following chapter, we are going to explore some of the key concepts such as Blockchain, AI, QR Code and Cloud Computing that are prerequisite to understanding FoodSQRBlock and SmartNoshWaste frameworks.
Chapter 3 Prerequisite: Blockchain, AI, QR Code and Cloud Computing
In this chapter, we explore some of the key concepts and technologies used to develop the FoodSQRBlock and SmartNoshWaste frameworks.
3.0.1 Blockchain Technology
When Satoshi Nakamoto [Dey, 2018b] released the technology named Bitcoin, he revolutionised the industry not because he had invented a new currency system, which does not require intervention of institutional mediator while transferring money from one entity to another, but because he had gifted one of the most disruptive technologies, which has come to life in decades. With the introduction of Bitcoin, Blockchain got introduced to the world, which is a digital ledger in which all transactions are recorded chronologically and publicly. But the application of blockchain is not just limited to crypto-currencies [blo, a, blo, b] such as Bitcoin and have proved to be useful in tracking ownership, provenance of documents, digital assets, physical assets, voting rights, etc. Blockchain network is traditionally of three types as follows:
1. Public: In this network, everyone can check and verify the transaction made. The network is also open to anyone who wants to participate in the consensus process.
2. Private: In this type of network, strict restrictions are applied on data access and the nodes (user/entity) have restricted access to specific block chains, which are monitored by a governing body.
3. Consortium: Nodes in this type of network can form partnership with businesses or other authorities. This type of network may be public or private and hence, this could be seen as a hybrid approach as partly decentralized.
Blockchain Technology is popular because of its design features, which are composed of six key elements as follows:
1. Decentralized: Blockchain data could be recorded, stored,updatedanddistributed without depending on a central authority or node.
2. Transparency: Data recorded and stored are transparent and are visible. Therefore, leveraging trust among its users.
3. Open Source: The source code as well as the most of the blockchain dependent systems are open to view, free to use and provide the ease of extension for other applications.
4. Autonomous: Blockchain updates are consensus based and thus data could be updated securely from a single user to the whole system. This feature provides autonomy to the system to update data securely.
5. Immutability: All data in the blockchain are reserved forever.
6. Anonymity: Blockchain also provides anonymity to its users and make the system more trust worthy by only using the users' blockchain addresses instead of their personal information.
3.0.2 AI and Reinforcement Learning
Artificial Intelligence or AI [Winston, 1992] is the field of study to enable computing machines to perform tasks that are commonly associated with intelligent beings like humans. On the other hand, Machine Learning or ML [El Naqa and Murphy, 2015] is a sub-field of AI where the computing machine can improve automatically through experience and by the use of data. Traditionally, ML could be broadly categorized into: Supervised [Singh et al., 2016], Unsupervised [Gentleman and Carey, 2008] and Reinforcement learning [ ? ]. Out of these, reinforcement learning has become a popular choice among researchers as we move towards Artificial General Intelligence (AGI) [Goertzel and Pennachin, 2007]. Artificial general intelligence is the hypothetical ability of an intelligent agent (computing machine) that is capable of understanding or learning any intellectual task that a human being can.
Moreover, reinforcement learning (RL) is a type of machine learning algorithm, where an intelligent agent, which is a computing system that perceives its environment to take actions autonomously in order to achieve cumulative rewards based on the knowledge gathered from the environment. Fig. 3.1 shows a representative diagram of an intelligent agent. Here, reward could be optimizing performance or power consumption or thermal efficiency or combination of these together.
3.0.3 QR Code
QR code [Dey et al., 2012b,Huang et al., 2020,Dey, 2012,Dey et al., 2012b,Dey et al., 2013] is an effective information transmission medium, which is widely used in product traceability, advertising, mobile payment, passport verification and other fields. QR code is defined into 40 symbol versions (to carry various data payloads) and 4 user-selectable error correction level (ECL): L, M, Q and H, which can correct up to 7%, 15%, 25% and 30% error codewords respectively when attacked by defacement. The larger QR version can offer higher data payload where the QR code can hold a maximum capacity of 2,956 bytes for a version 40 code. The error correction capability of QR code is one of the key features of this type of barcode introduced by QR code standard and allows the barcode reader to retrieve the data correctly if portions of the barcode are damaged. QR code utilizes Reed-Solomon error correction algorithm to realize this fault tolerance, where the error correction codewords would be generated by Reed-Solomon algorithm and added in the tail of QR code data codewords [Dey et al., 2013, Dey et al., 2012a, Lin, 2016, Dey, 2013]. Usually two error correction codewords could be used to correct codeword data error. Obviously, the larger the QR code version and the error correction level, it can offer higher data payload and reliability.
Fig. 3.2 represents a QR code in which a simple, “Hello, World!" message is embedded.
Abbildung in dieser Leseprobe nicht enthalten
Figure 3.1: Representative diagram of intelligent agent
Abbildung in dieser Leseprobe nicht enthalten
Figure 3.2: Representational QR code with “Hello,World!" message embedding
3.0.4 Cloud Computing
Cloud computing (cloud) [De Donno et al., 2019, Qi and Tao, 2019] is a model to enable ubiquitous, convenient, on-demand network access to a shared pool of configurable computing resources such as networks, servers, storage, applications, and services, which can be rapidly provisioned and released with minimal management effort or service provider interaction [Bohn et al., 2011]. The essential characteristics of Cloud computing are summarized as follows:
1. On-demand self-service: For cloud computing, capabilities can be provided automatically when needed, without requiring any human interaction between the consumer and the service provider.
2. Broad network access: In this type of service, computing capabilities are available over the network and accessible through several mechanisms disposable for a wide range of consumer platforms such as workstations, laptops, and smartphones.
3. Resource pooling: In cloud, computing resources are pooled to accommodate multiple consumers, and hence, dynamically allocating and deallocating them according to consumer's demand. Moreover, the provider resources are location independent, i.e. the consumer does not have any knowledge or control of their exact location.
4. Rapid elasticity: In cloud, computing capabilities can be provided flexibly and released to scale in and out according to the consumer's demand. Therefore, the consumer has the perception of unlimited, and always adequate, computing capabilities.
5. Measured service: In cloud, resource usage can be monitored and reported according to the type of service being offered. This is particularly relevant in pay-per- use, or pay-per-user services because it grants a great transparency between the provider and the consumer of such services.
Cloud services can be provided to consumers in a variety of ways, and one such service is Software as a service (SaaS) [Ali et al., 2019], where the software and its related data are centrally hosted in the cloud computing environment such that the software could be provided to numerous consumers.
In the following chapter, we explore the FoodSQRBlock, which aims to digitize the food supply chain data such that the data could be easily traceable and accessible for improved food safety and to train the machine learning model to optimize waste in the supply chain.
[...]
- Quote paper
- Somdip Dey (Author), 2022, An Introduction to Blockchain and AI in Food Supply Chain in Smart Cities. Reducing Waste, Munich, GRIN Verlag, https://www.grin.com/document/1194960
-
-
-
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X. -
-
Upload your own papers! Earn money and win an iPhone X.