Skip to main content

2023 | Book

Deep Learning Technologies for the Sustainable Development Goals

Issues and Solutions in the Post-COVID Era

Editors: Virender Kadyan, T. P. Singh, Chidiebere Ugwu

Publisher: Springer Nature Singapore

Book Series : Advanced Technologies and Societal Change


About this book

This book provides insights into deep learning techniques that impact the implementation strategies toward achieving the Sustainable Development Goals (SDGs) laid down by the United Nations for its 2030 agenda, elaborating on the promises, limits, and the new challenges. It also covers the challenges, hurdles, and opportunities in various applications of deep learning for the SDGs. A comprehensive survey on the major applications and research, based on deep learning techniques focused on SDGs through speech and image processing, IoT, security, AR-VR, formal methods, and blockchain, is a feature of this book. In particular, there is a need to extend research into deep learning and its broader application to many sectors and to assess its impact on achieving the SDGs. The chapters in this book help in finding the use of deep learning across all sections of SDGs. The rapid development of deep learning needs to be supported by the organizational insight and oversight necessary for AI-based technologies in general; hence, this book presents and discusses the implications of how deep learning enables the delivery agenda for sustainable development.

Table of Contents

Chapter 1. How Deep Learning Can Help in Regulating the Subscription Economy to Ensure Sustainable Consumption and Production Patterns (12th Goal of SDGs)
In today’s rapidly changing world, the importance of sustainable consumption cannot be underestimated. Businesses are taking part in the subscription economy because of the economic and social benefits it provides, as well as its role in sustainable consumption. With the help of deep learning, the businesses can offer the optimum level of service exposure which allows them to earn consistent revenues and ensure customer retention in the long term. Deep learning can assist businesses to minimize the adverse effects of under and overconsumption and have a balanced consumption in the subscription economy. It can also help them to decrease their material footprint and reduce pressure on natural resources. This chapter discusses the applications of deep learning as a cross-disciplinary approach to regulate subscription-based offerings and ensuring sustainable consumption.
Yogesh Sharma, Rajeev Sijariya, Priya Gupta
Chapter 2. Deep Technologies Using Big Data in: Energy and Waste Management
The potential of big data is growing exponentially, and over the next decade, it will almost change every business and industry. The diverse applications of big data have opened new dimensions for industrialization and urbanization. This leads to a huge energy crisis and environmental wastes. The conventional methods are incapable of handling energy crises and wastes. Moreover, the methods require a lot of manpower and resources which make them more costly. Thus, the ultimate solution of handling this computationally expensive and complex issue is by analyzing the demand of energy, classification, and identification of the source of wastes at every step of technological advances. Big data analytics is capable of analyzing these large datasets, still faces major setbacks because of high-dimensional, imbalance, and dynamic datasets. These difficulties lead to various other problems, such as search-based data analytics problems, multi-objective optimization problems, uncertain data problems, and classification and clustering problems. To address these issues, various data analytics tools and statistical techniques were designed by the researchers; but, the literature shows strong evidence that deep learning techniques are efficient in solving these complex and computationally expensive problems very well. This chapter attempts to exploit deep learning techniques to solve energy and waste management issues through big data analytics. Finally, the chapter concludes with the discussion and prospects of deep learning in big data analytics for energy and waste management.
Jyotsna Verma
Chapter 3. QoS Aware Service Provisioning and Resource Distribution in 4G/5G Heterogeneous Networks
The Fourth Generation (4G) wireless communication network is widely implemented with standardized framework of operation and QoS constraints. Emergence of enhanced mobile broadband (eMBB) and user demand for ultra-reliable and low latency communication, research interests are now shifted to the Fifth Generation (5G) network. With rapid increase in number of mobile devices and associated user’s demand of diverse services, the 5G network is expected to improve overall spectrum efficiency. However, latency, energy efficiency, QoS, throughput, are some of the challenges to be addressed for a reliable network. The chapter discusses congestion control algorithms and delay bounded QoS provisioning framework. This QoS provisioning can be deployed in LTE 4G and 5G network with differential baud rate and fading parameters. Hybrid scheduling with QoS class identifier is discussed for LTE access network.
Rintu Nath
Chapter 4. Leveraging Fog Computing for Healthcare
The Internet of Things (IoT) links various gadgets all around the world. Remote monitoring of health and tracking, exercise program, and remote medical support are all examples of a developing sector in the healthcare system. With the advent of IoT-based healthcare technology, it is possible to relieve pressure on healthcare systems, minimize healthcare costs, and enhance rate of computation and execution. The cloud was utilized to handle the complicated and massive amounts of medical information produced by IoT devices. Delay, bandwidth use, real-time reaction latencies, security, and confidentiality are all important considerations when integrating IoT cloud services. To overcome the above-mentioned issues, the concept of fog computing came into existence. Fog computing facilitates on-time, consistent delivery of services despite overcoming difficulties such as interruptions or disturbances, as well as overhead expenses associated with data transport to the cloud. The chapter covers an introduction to fog computing, its architecture and characteristics. The chapter provides detailed information about the use of fog computing in the domain of healthcare and concludes with the case studies and research challenges in this domain.
Avita Katal
Chapter 5. Intelligent Self-tuning Control Design for Wastewater Treatment Plant Based on PID and Model Predictive Methods
To design an intelligent controller which can automatically adopt its parameters according to the real-time requirement. To maintain plant’s optimal behaviour is continuous researcher’s interest. Optimization problems often arise in real-world situation concerning engineering and design, chemical operation, and so forth. In this situation, obtaining a single optimal solution will result in certain compromises on one or more of the others, and in such cases, we will end up with a more than one equally good solutions rather than just one. It is in continuous interest of researchers to address the multivariable optimization problems since its optimal goals are frequently hard to satisfy all variable in best way. Objective function of plant should be designed with consideration of range of variable and different states of the plant. To design an intelligent adaptive sludge model in multivariable treatment plant to reduce the organic contents and improve the fluid quality of effluent is the focus of this work. Intelligent analytics of water treatment plant is highly required for optimal desired performance. In this work, control techniques such as decentralized PI controller, conventional PID controller, and model adaptive control have been implemented. All control techniques have been given satisfactory results of dissolve oxygen and substrate with give constant values. But model predictive control has been given the best simulation results. Then at last simulation, results from different techniques have been compared, and model predictive control has been given the better results as compared to other techniques in MATLAB Simulink.
Ujjwal, Neelam Verma, Anjali Jain
Chapter 6. Impact of Deep Learning Models for Technology Sustainability in Tourism Using Big Data Analytics
Over the last decade, tourism industry is exploring the latest technologies to improve the customer experience and enhance customer satisfaction. In order to address the customer demands and business, tourism industry embraces to redefine their products and services using deep learning models and big data analytics. Deep learning-based model can be used to measure customer satisfaction, perception and behavior utilizing sentiment analysis, emotion analysis, and data analysis. Big data analytics in tourism can improve the overall tourism business operations and services. Deep learning techniques with big data analytics not only helps in developing the economical tourism models but also analyze the impact of various environmental factors on tourism planning and travel demand. In addition, these techniques are helpful in estimation of tourist seasonal demands, market price strategies and data analysis automation. Deep learning using data analytics can bring a paradigm shift in the tourism industry by offering personalized recommendations with budget specific packages based on customer past travel, reviews and experience. In this chapter, we will briefly analyze the impact of deep learning in tourism sector in terms of innovation, commercialization and profitability of the business. In addition, we will also review the advancement and potential of the deep learning-based methods with big data analytics in tourism industry in terms of customer overall experience.
Ashish Kumar, Rubeena Vohra
Chapter 7. Study of UAV Management Using Cloud-Based Systems
Unmanned aerial vehicles (UAVs) are considered to be recent developing technology having ability of making various basic public and private processes better. UAVs help in speeding up the recovery and rescue activities and also helpful in delivery systems. Development of UAV systems by traditional techniques needs large amount of effort, time, and cost. Management of UAV systems using conventional techniques has many limitations. As the UAV airspace turn out to be more restrictive, it is significant to manage UAV systems by utilizing innovative methods of collision avoidance. In this chapter, cloud-web-application study is presented which offers real-time flight managing and regulating UAVs. For every linked UAV, exhaustive reading of the accelerometer UAV sensor, GPS and provides ultrasonic sensor as well as visual cameras in addition to status reports from small inner elements of UAVs. The flexible map overlap looks at current routes and existing UAV sites, letting users easily manage all aircraft operations. The system perceives and avoids major impacts by auto-adjusting the UAV flight modes and notifying users about changes. The main aim is to streamline efforts, reduction in time, and cost of collaborative applications for UAVs which are heterogenous. This chapter deliberates how UAVs are unified with the cloud computing standard for providing universal access to their services. UAV resources are tracked in a novel flexible web-service design and has integrated communication amid services known as resource oriented architecture. The UAV-cloud framework to facilitate the design of pervasive UAV viewpoints, also the trivial integrated design of UAV resources is also discussed in this chapter.
Sonali Vyas, Sourabh Singh Verma, Ajay Prasad
Chapter 8. Contemporary Role of Blockchain in Industry 4.0
Everything around us is transforming with advancement in time, as a result, new technologies are developing with upcoming industry revolution which is widely popular as Industry 4.0. It includes new trends related to cyber-physical system, Augmented Reality, artificial intelligence, Internet of Things (IoT), cloud computing, and many more. Many physical infrastructures are transformed to virtual ones which allows decision making and planning in a decentralized form. It also enabled users to accomplish real-time communications with help of integrated computing algorithms with the challenge of decentralization and heterogeneous systems. Progressive web technologies are involving varied characteristics in order to make technology very easy for the manufacturer communal. Blockchain version 4.0 is aiding business in terms of ensuring clearness in terms of supply, besides it promises conviction amongst the transaction establishments, and supply chain management is inculcating blockchain technology completely. The significant segment which is benefited with the adoption of Industry 4.0 moralities besides machineries is industrial or manufacturing business which will be generating smart industrial era involving progressive knowledge in addition to systems in Industry 4.0 which will be enhancing varied progressions amongst business value chain plus up surging proficiency and productivity. Though, Industry 4.0 necessitates actual incorporation of countless machineries and arrangements involving unified procedures amongst its constituents which generates numerous trials during creation of applications for smart industrial and manufacturing units which involves various factors like safety, conviction, traceability, dependability, and contract automation amongst manufacturing value chain. This chapter discusses various solutions correlated to union of blockchain as well as Industry 4.0. It also explores various pros and cons of traditional security solutions and provides evaluation of present blockchain-based security solutions. It also deliberates blockchain-based application areas of Industry 4.0.
Shaurya Gupta, Sonali Vyas, Vinod Kumar Shukla
Chapter 9. SDGs Laid Down by UN 2030 Document
As the era of globalization and international trade has reached to all nations of the world, there is a need to make some provision so that every nation should enjoy the benefits of globalization. With this speed of industrial development, the nations with developed infrastructure are getting high benefits while others are facing difficulties and inequalities. This gap in the income leads to lopsided development. There are regions that are still facing extreme poverty and hunger, while the producing countries are creating high emissions. This made serious effect on the environment and society. To provide some feasible solution to this problem, UNDP has set 17 goals with 169 targets for its member countries. This provides a step by step guide to end poverty, safeguard environment, ensure peace and disseminate equality and inclusiveness in the society. The development in the deep technologies can help in achieving these goals. Emergence of technology has given a new dimension to many sectors and thus SDGs can be applied with cost effectiveness. To understand the application of deep technologies in achieving SDG, it is important to understand the basic formulation of these 17 SDGs.
Vishakha Goyal, Mridul Dharwal
Chapter 10. Healthcare 4P: Systematic Review of Applications of Decentralized Trust Using Blockchain Technology
Sharing of Global Healthcare information using secure digital channels will be a key accelerator in developing a knowledge society with improved health care. Sharing of information brings both risks and benefits to Healthcare institutes. Blockchain technology provides an immutable and decentralized based platform. However, as highlighted by the scalability Trilemma there is a balance to be achieved between scalability, security, and decentralization. There are different Blockchain industry standard models, each of which provides a varying degree of reliability, investment cost, and security. This chapter focusses on information sharing challenges in IoT-enabled health care and analysing the effectiveness of Blockchain frameworks to resolve the same. It goes further to create a repeatable framework of trust requirements of the use cases in health care for verifying the Blockchain capability matrix.
Deepika Sachdev, Shailendra Kumar Pokhriyal, Sylesh Nechully, Sai Shrinvas Sundaram
Chapter 11. Implementation of an IoT-Based Water and Disaster Management System Using Hybrid Classification Approach
As a result of floods in the past, infrastructure worth millions of dollars has been destroyed. However, despite all the study, there is currently no universal, worldwide system that can be used to gather, store, evaluate, and predict floods. Worldwide, researcher’s are striving to discover a solution that can collect, store and analyze huge data on flooding in order to forecast the outcomes of flood-based prediction systems. Using a deep learning model and a hybrid classification technique, this study has built an IoT-based water and disaster management system. First, the input data is derived from the flood big data set of information. To build the system, four IoT sensors were used: the Water Flow (WF) sensor, the Water Level sensor (WL), the Rain Sensor (RS), and the Humidity sensor (HS). HDFS map-reduce is then used to decrease the repetitive data from the IoT sensed data. The data are pre-processed using missing value imputation and a normalizing algorithm after the repetitive data has been removed. As a result of this, a rule is created utilizing a mix of attributes and attributes technique. A hybrid classifier that incorporates Convolutional Deep Neural Network (CDNN) and Artificial Neural Network (ANN) classifiers classifies the rules as (a) odds of a flood are occurring and (b) chances of no flooding occurring at the final stage. Using criteria such as sensitivity, specificity, accuracy, precision, recall, and F-score, the results of the suggested approach are compared. Aside from that, when compared to other algorithms, the suggested system gives a far more accurate result than those other approaches.
Abhishek Badholia, Anurag Sharma, Gurpreet Singh Chhabra, Vijayant Verma
Chapter 12. ANN: Concept and Application in Brain Tumor Segmentation
Medical expert analyses, brain MR images to segment the tumor area. The report may vary according to the machines or the experience of operators. Automating the process of brain tumor segmentation based on MRIs is a greater need to maintain uniformity. In addition, provide a report to the doctor with high accuracy to proceed with the diagnosis of the patient. Many researchers have applied ANN in training the model to segment the tumorous cells in the MR images. Using ANN, multiple state-of-art methods have been proposed with promising results. Motivated with architecture and performance of Neural Network. In this chapter we discussed the working of ANN (Artificial Neural Network) and its application in brain tumor segmentation.
Amit Verma
Chapter 13. Automation of Brain Tumor Segmentation Using Deep Learning
Today also, radiologist analyze the MR images manually based on their experience and knowledge for segmenting the tumor. Use some graphical software to make the report about the presence of the tumor, its size, and other features. Based on this report doctors diagnose the patient, it is the main source for any doctor to start the treatment of the patient. However, as the MRI reports are based on the experience of the radiologist so it is a big challenge to maintain uniformity in the reports generated from the different MR imaging centers. Therefore, automation in this particular field is very much required for better precision and to maintain uniformity in the report. Therefore, doctor can diagnose the patient in much better way. Deep learning playing a vital role in automating the process of brain tumor and other organ segmentation using MR images. Many researchers developed various state-of-art methods to automate the process of brain tumor segmentation in MR images. There are multiple deep learning methods such as stacked auto- encoder, artificial neural network, convolutional neural network, and Unet used for the process of segmenting the medial images, where CNN is the most successful method for segmenting. In this chapter, the importance of automatic brain tumor segmentation approach. CNN and process of convolution, max pooling discussed in detail. Moreover, application of CNN for automatically segmenting brain tumor also discussed with some state-of-art methods.
Amit Verma
Chapter 14. Transportation Management Using IoT
Deep Learning to Predict Various Traffic States
One of the largest issues in terms of road traffic, transportation costs, car parking, service types, etc., is moving people and basic goods between locations. The transportation system is the foundation of supply chain management, and effective management of the aforementioned issues is referred to as transportation management. The development of the Internet of Things (IoT), which makes ordinary physical things or gadgets smart, has recently attracted a lot of interest. IoT is increasingly being used to control local and international transportation systems. Vehicle-to-vehicle communication is made possible by Industry 4.0, which lowers traffic and, as a result, accidents, congestion, pollution, etc. The Internet of Things (IoT) is used in this chapter to improve the shipping and movement of cars and cargoes across various transportation management segments. It increases the vigilance and level of scrutiny for both the product and human movement. The chapter also discusses how deep learning technologies have recently advanced to handle IoT problems in transportation management.
Amit Singh
Chapter 15. Enhancing Shoppers’ Loyalty by Prioritizing Customer-Centricity Drivers in the Retail Industry
The objective of this research chapter is to identify, analyze, and record the priority of shoppers toward the factors which drive the customer-centric approach of modern retail houses. 92 customer-centricity driving variables have been identified from concomitant literature. These variables are examined in 1024 respondents of metro and urban shoppers. Exploratory factor analysis and analytic hierarchy process (AHP) have been used to identify customer priority among significant drivers. After analyzing another survey of 142 respondents, the AHP three categories of drivers, namely essential drivers, experience influencing drivers, and moderating drivers. As this study involved metro and urban shoppers majorly, it may not reflect the opinion of whole retail customers. The study helps retails to focus on shoppers’ priority and minimize their efforts on non-acclaimed factors to position themselves as a customer-centric organization.
Vishal Srivastava, Manoj Kumar Srivastava, R. K. Singhal
Deep Learning Technologies for the Sustainable Development Goals
Virender Kadyan
T. P. Singh
Chidiebere Ugwu
Copyright Year
Springer Nature Singapore
Electronic ISBN
Print ISBN

Premium Partner