Challenges and Opportunities for Deep Learning Applications in Industry 4.0

Manufacturing plays a prominent role in the development and economic growth of countries. A dynamic shift from a manual mass production model to an integrated automated industry towards automation includes several stages. Along with the boost in the economy, manufacturers also face several challenges, including several aspects. Machine Learning can prove to be an essential tool and optimize the production process, respond quickly to the changes and market demand respectively, predict certain aspects of the particular industry to improve performance, maintain machine health and other aspects. Machine Learning technology can prove its effectiveness when applied to a specific issue in the sector— such as filtering out the primary use cases of Machine Learning manufacturing specifically, 'Predictive quality and yield' and 'Predictive maintenance.' Supervised Machine Learning and Unsupervised Machine Learning may provide the accuracy to predict the outputs and the underlying patterns.

Internet of Things (IoT) is surely a term that gives us the thought that everything is related to the internet. IoT is an assembly of machines that can share and transfer data. In this way, IoT can make our lives more convenient and easy because no physical interaction is required between machines and humans. As there are so many benefits of this technology there arise some challenges too. In today’s scenario, humans rely very much on the smart applications of the IoT, which will affect our lives to the core. IoT is widely used to exchange information either remotely or locally with the help of sensors. These IoT devices can then process the information according to their needs and can take necessary steps as well. For example, IoT devices can sense the temperature and if the temperature rises above a certain level, they can act as actuators. This chapter provides us with an overview of the recent technologies in the field of IoT and to learn more about some of its very relevant applications. However, this document provides an opportunity for young researchers to gather more and more information about the Internet of things.

The latest advancements in the manufacturing industry due to ICT (Information and Communication Technologies) has promoted the wave of Industry 4.0 in today's world. This has transformed the traditional mass-production model into the 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 paper analyses the fundamental technologies behind the success of I4.0, namely Cloud computing and big data analysis, in great detail. The Cloud is the heart of Industry 4.0. It is the primary enabler of innovative, more efficient, and practical strategies in business processes by using artificial intelligence, intelligent sensors, and robotics. It has additionally examined numerous applications where this concept is being used along with various issues and challenges.

Recent advancements in artificial intelligence and machine learning, specifically in the domain of natural language and computer vision, involve deep neural networks. Deep learning technology is evolving rapidly to enhance the advanced computing power across the globe in every industry. The uses of deep learning technology are becoming more apparent as the amount of available data is increasing enormously. It is being used to solve numerous complicated applications in real life with surprising levels of accuracy. Besides all the benefits, the large-scale deployment of artificial intelligence and deep learning-based models has several associated challenges due to the huge and rapidly changing data and its accessibility to common people. In this study, the authors provide a review of existing deep learning models to study the impact of artificial intelligence on the development of intelligent models in the healthcare sector, specifically in dealing with the SARS-CoV-2 coronavirus. In addition to reviewing the significant developments, the authors also highlight major challenges and open issues.

The field of cryptocurrency has witnessed exponential growth in popularity in recent years. Almost ten years ago, the release of Bitcoin marked the beginning of a new era of innovation in the financial sector. In this work, we outline what exactly defines a cryptocurrency, describing fundamental concepts, underlying technologies such as the blockchain, and subsequently the viability of this new digital financial asset. Building on this knowledge, we examine the infamous volatility of cryptocurrency prices, analyzing pricing data and the likelihood of these currencies, specifically Bitcoin, being in the midst of a financial bubble. We examine the prediction of prices, or rather the inability to do so, before introducing the Currency Analyzer web application developed as part of this work. Containing up to date prices, this application predicts the prices of Bitcoin using machine learning. The research, planning methodologies, technologies, and design and evaluation of this application are described in detail in this chapter, followed by a conclusion and future scope.

Fault prediction in software is an important aspect to be considered in software development because it ensures reliability and the quality of a software product. A high-quality software product consists of a few numbers of faults and failures. Software fault prediction (SFP) is crucial for the software quality assurance process as it examines the vulnerability of software products towards failures. Fault detection is a significant aspect of cost estimation in the initial stage, and hence, a fault predictor model is required to lower the expenses used during the development and maintenance phase. SFP is applied to identify the faulty modules of the software in order to complement the development as well as the testing process. 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. The objective of the bibliometric analysis is to analyze research trends of ML techniques that are used for predicting software faults. This chapter uses the VOSviewer software and Biblioshiny tool to visually analyze 1623 papers fetched from the Scopus database for the past twenty years. It explores the distribution of publications over the years, top-rated publishers, contributing authors, funding agencies, cited papers and citations per paper. The collaboration of countries and cooccurrence analysis as well as over the year’s trend of author keywords are also explored. This chapter can be beneficial for young researchers to locate attractive and relevant research insights within SFP.

The global pandemic due to the novel coronavirus (2019-nCoV) is responsible for millions of deaths worldwide. It has been caused by a syndrome related to respiratory organs, namely Coronavirus 2 (SARS-CoV-2), believed to have originated in Wuhan. Pattern analysis of the spread of COVID-19 is critical to provide proper guidelines to the public for their safety and health. The epidemiological dataset of coronavirus is used to forecast a future number of cases using various machine learning models and validated concerning the complete count of globally present cases. The dataset has been compiled using different datasets from Johns Hopkins University, National Health Commission, and the World Health Organization (WHO). The prediction has been able to observe the total cases in 222 nations globally. This paper 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, and Support vector regression (SVR), were applied to the dataset that was outperformed by Holt's linear and winter model in predicting the worldwide cases. However, Facebook's Prophet Model gave the best results. The value of the Root means square error (RMSE) was observed to be 5387.741339, with the Mean absolute percentage error (MAPE) value and correlation coefficient calculated to be 0.0020933 and 0.99998, respectively. Hence, Facebook's Prophet Model is the most promising approach and this prediction of COVID-19 cases can be used for the risk evaluation and safety measures to be taken in corresponding areas globally.

Progression in technology and innovation increases internet users, who post their perspectives on social media platforms regarding any product or service. It brings forth significant terms, i.e.,”feedback of users,” termed as sentiments and plays a substantial role for commercial organizations to analyze and find polarity related to their respective services. In Sentiment Analysis, the feature extraction phase is a crucial one that affects the entire process's processing. In the case of high dimensional Real- Time data, it leads to a sparse feature matrix and gives rise to steady processing. In this exploration work, we have proposed an Improved Optimized Feature Sentiment Classifier for Big Data (IOFSCBD) System, which deals with advancing the classifiers by giving improved values in each sort of dataset. Results show better execution of the Improved Optimized Feature Sentiment Classifier for Big Data system System.

AI based applications are used for farm-based advisories regarding sprays, forecasting, usage of drones within the farms, infrastructure for humidity and temperature updates to the farmers, etc. Thanks to this, the losses of farmers have begun to decline. Therefore, considering the aims of the government regarding doubling the farmers’ income, the losses of the farmers must be minimized using AI practices. AI intervention has the potential to boost the social and economic well-being of farmers within the medium to long run. The adoption of AI is useful in agriculture as it can bring industrial revolution and explosion in agriculture to feed the growing human population of the world. The study highlights that AI based farm advisory systems are playing an immense role in solving the problems of the farmers by enabling them to require proactive decisions on 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. Finally, the overview of Deep Learning and its application in agriculture is given.