The book aims to take the reader on a technological voyage of deep learning (DL) highlighting the associated challenges and opportunities in Industry 4.0. The competence of DL for automation and manufacturing sector has received astonishing attention during past decade. The manufacturing industry has recently experienced a revolutionary advancement despite several issues. One of the prime hindrances is enormous increase in the data comprising of various formats, semantics, qualities and features. DL enables detection of meaningful features that were far difficult to perform through traditional methods so far. The goal of this book "Challenges and Opportunities for Deep Learning Applications in Industry 4.0" is to present the challenges and opportunities in smart industry. The book also discusses the prospective research directions that focus on the theory and practical applications of DL in industrial automation. Hence, the book aims to serve as a complete handbook and research guide to the readers working in this domain. The target audience of this book will include Researchers, IT Industry, Research Agencies, and industrialists etc.
ORGANIZATION OF THE BOOK
The book is organized so as to include related rudiments and applications of deep learning in various industries viz. healthcare, transportation and agriculture etc. The book comprises of nine chapters. A brief description of each of the chapters of this book is as follows:
Chapter 1 discusses the Machine Learning Approaches to Industry 4.0. Inclusion of this chapter in the book augments the belief that Manufacturing plays a prominent role in the development and economic growth of countries. However, transformation in the Industry 4.0 also faces several challenges. Fortunately, Machine Learning can prove to be the essential tool and optimize the production process owing to its capability to respond quickly to the changes and market demand. Hence, it can predict certain aspects to improve performance and thus Machine Learning can prove its effectiveness by enabling 'Predictive quality and yield' and 'Predictive maintenance.'
Chapter 2 provides a comprehensive survey of IOT in Industry 4.0. IoT becomes a topic of paramount importance as we are entering into the new generation of computing technology where IOT plays a crucial role impacting the life around us in homes, healthcare, education, and transportation etc. There are more than 14 billion digital devices which are interconnected in the world in IOT which is more than twice the population of the world. IoT makes our lives more comfortable as it does not require any physical interaction between the machine and humans. IoT is widely used to exchange information either remotely or locally with the help of sensors. These IoT devices, then process the information according to their needs. The chapter provides an overview about the recent technologies in the field of IOT and discusses some of its very relevant applications. It also provides an opportunity for the young researchers to gather more and more information in this domain.
Chapter 3 discusses the scope of cloud computing in Industry 4.0 as it has transformed the traditional mass production model to mass customization model. The vision of Industry 4.0 is to make machines that have the capability of self- learning and self-awareness for improving the planning, performance, operations and maintenance of manufacturing units. This chapter discusses the fundamental technologies behind success of cloud computing in great detail. The chapter additionally presents numerous applications along with various issues and challenges.
Chapter 4 presents the Deep Learning Models for Covid19 Diagnosis and Prediction, a current pandemic that has shaken the entire world. The motive behind employing deep learning is its competence to improve the advanced computing power across the globe in various industries. In this chapter, authors provide a review of existing deep learning models to study the impact of artificial intelligent techniques on the development of intelligent models in healthcare sector specifically in dealing with SARS-CoV-2 coronavirus. Additionally, authors also highlight major challenges and open issues.
Chapter 5 presents a model for Air Pollution Analysis using Machine Learning and Artificial Intelligence. Here, authors focus on discovering patterns and trends, making forecasts, finding relationships and possible explanations, mapping different causes of Air Pollution in Delhi with various demographics and detecting patterns. During the implementation, some interesting results have been obtained related to COVID-19 pandemic.
Chapter 6 predicts the current trend using machine learning. The release of cryptocurrency like Bitcoin has started a new era in the financial sector. Here, authors examine the prediction of prices and the model predicts prices of Bitcoin using machine learning. The current work is described in detail in the chapter.
Chapter 7 performs a Bibliometric Analysis of Fault Prediction System using Machine Learning Techniques. Software fault prediction (SFP) is crucial for the software quality assurance process and is applied to identify the faulty modules of the software. Software metric based fault prediction reflects several aspects of the software. Several Machine Learning (ML) techniques have been implemented to eliminate faulty and unnecessary data from faulty modules. This chapter gives a brief introduction to SFP and includes a bibliometric analysis. This chapter can be beneficial for young researchers to locate attractive and relevant research insights within SFP.
Chapter 8 presents a COVID-19 Forecasting model using machine learning. The epidemiological dataset of coronavirus is used to forecast a future number of cases using various machine learning models. This chapter presents a comparative study of the existing forecasting machine models used on the COVID-19 dataset to predict worldwide growth cases. The machine learning models, namely polynomial regression, linear regression, support vector regression (SVR), were applied on the dataset that was outperformed by Holt's linear and winter model in predicting the worldwide cases.
Chapter 9 discusses the application of AI in agriculture as it has the potential to boost the social and economic wellbeing of farmers within the medium to long run. The study highlights that AI-based farm advisory systems play an immense role in solving the farmers' problems by enabling them to require proactive decisions in their respective farms. Various applications of Artificial Intelligence (AI in harvesting, plant disease detection, pesticide usage, AI-based mobile applications for farmer support etc.) have been discussed in this survey in detail.
Thus, the aim of this book is to familiarize researchers with the latest trends in deep learning ranging from rudiments to its applications in Industry 4.0.