Industrial Internet of Things: An Introduction

In this new industrial era, IoT is an emerging technology. Industrialization has entered an entirely novel phase with the fusion or incorporation of deep neural network methods with machine learning (ML). Both sustainable living and economic prosperity have resulted from this. Predictive analysis has been both a boon to humanity and an improvement in the caliber of work produced. It has created an opportunity for people to improve society and assist the poor in numerous ways. IoT and ML integration enables humanity to create a single home on this planet. 

Industry 5.0 is a revolutionary change for the traditional industrial domain with an amalgamation of interactive computational techniques. However, the Industrial Internet of Things (IIoT) is referred to as communication between various batteryenabled physical devices. The present IIoT sector faces issues like complex decisionmaking, enhancement of productivity capabilities, management of the cost of assets, uninterrupted connectivity, and security. Traditional computational techniques were partially successful in finding an appropriate solution for existing issues in IIoT. In this study, the author highlighted a deep learning-based prediction model that further assists the industry while making major decisions. This approach is currently used for various problems in agriculture, healthcare, coal and petroleum, entertainment and sports, surveillance, and retail and marketing industries.

Internet of Things (IoT) technology is a prominent approach for handling present-day issues in various sectors for sustainable development. The agricultural sector is considered the backbone for the sustainability of a nation and plays a vital role in biodiversity sustenance. Precision farming or precision agriculture is the practice of maximizing crop yields and making the agricultural profession more profitable. Precise and timely input of various agricultural parameters through smart and advanced technologies like IoT, AI, image processing, drone-based cameras, computer vision, smart portable devices, GPS, and others provide precision farming a real playground for implementation. The practice of precision farming can boost the efficiency, sustainability, and profitability of farmlands. An automated irrigation system (AIS) is an advanced technology that uses sensors, controllers, and automation to efficiently manage and optimize the watering of plants and crops. While AIS offers numerous benefits, some challenges and problems can also arise, such as in terms of sensor accuracy, connectivity and communication, power supply, maintenance and system updates, cost and implementation, and user understanding and training. Therefore, it is a hard requirement for an intelligent automated system with IoT capabilities that can precisely track and manage water and energy consumption. In today's world, automation dominates human existence. In this chapter, we suggested a comprehensive framework for an IoT-based smart and automated irrigation system to address the drawbacks of conventional systems like drip irrigation and pot irrigation, which cause soil erosion and water wastage. Water is sprayed across the crops in the field by an automated irrigation system to spread it like a downpour. Installing an AIS allows for time- and water-saving water utilization.

In today's interconnected world, where most devices are connected to the internet and constantly sharing data, the increasing number of IoT devices presents challenges for large companies to develop secure IoT systems.. With the progression of interconnected systems, the risk of hampering security is also a big concern. In the current scenario, it is very easy for attackers to initiate any kind of security breach. The attack will be either on its software, firmware, or hardware level. This chapter deals with the hardware security of the IoT system, which is also termed physical security. Various security threats related to the physical security of an IoT device are described. Various consequences have been mentioned that can occur due to these attacks. With these physical attacks, a lot of severe loopholes can be created in the current ongoing research and development of these interconnected systems. 

Inaccurate detection of tumors, fractures, and breast cancer in clinical images has become one of the major issues in the medical field. Variations or errors in medical reports caused by operators, machines, or the environment become a common cause of delay or incorrect diagnosis. Therefore, correct segmentation of areas of interest in clinical images like X-rays and MRIs is highly required. To solve this problem, many researchers have provided various state-of-the-art automatic or semiautomatic methods of segmentation. Artificial neural networks play a significant role in increasing the accuracy of clinical image segmentation. In this chapter, the workings of ANN and the difference between gradient and stochastic gradient descent are discussed. Also, the application of ANN in tumor, fracture, and breast cancer segmentation is discussed using authentic and publically available datasets. This chapter mentions the results and confusion matrix of some state-of-the-art methods. This chapter will help readers know about ANN, the use of gradient and stochastic gradient descent, the application of ANN in segmenting clinical images, and the confusion matrix.

Information technology has shown its presence in every sector that requires automation and intelligence. Traditional healthcare is a major sector in which lots of advancements are needed. AI and IIoT are two main IT-based advanced technologies that are required in many phases to convert traditional healthcare to smart healthcare. The two major requirements of a smart healthcare system are data collection and data analysis, and both of these requirements can be fulfilled by AI and IIoT technologies. IIoT can help collect healthcare data in an automated way using various sensors and other hardware devices. The use of AI-based algorithms and software to replicate human cognition in the analysis, display, and comprehension of complicated medical and healthcare data is referred to as artificial intelligence in healthcare. Artificial intelligence can be utilized to perform the same tasks in a more efficient and costeffective manner. It is always preferable to prevent a disease than to cure it. Artificial intelligence-based apps can assist users in leading a healthy lifestyle and being proactive. When customers realize they have power over their own health, they are more motivated to live a healthy lifestyle. This chapter describes the role of artificial intelligence (AI) and the Industrial Internet of Things (IIoT) in smart healthcare and telemedicine.

One of the latest industrial revolutions is deep transformation and human progress, which has led to the “Automation of Everything”. The physical world, along with digital interfaces and data analysis, is connected via an interconnected network of computers. This change holds the key to unlocking trillions of opportunities in the coming ten years. Productivity has improved greatly in digital and physical industries, which leads to improved quality of life and sustainability. There are loads of challenges due to the massive amount of data being collected by sensors in the current world of IIoT. This chapter aims to review the various deep learning and machine learning technologies, algorithms, and their effect on IIoT. Several applications of machine learning in gaining useful insights from IoT data are also discussed in this chapter.

COVID-19 has shattered existence and implemented a change in the strategies, priorities, and activities of people, organizations, and governments. These progressions are the momentum for the advancement of technology. In this chapter, the discussion is about the pandemic's effect on the reception of the Internet of Things (IoT) in different areas, specifically healthcare, smart cities, smart buildings, smart homes, transportation, and industrial IoT. Industrial IoT (IIoT) healthcare has essentially decreased the expenses for monitoring and safeguarding individuals at home by helping to improve human healthcare quality. Despite its significant convenience and advantages, it faces challenges related to security and protection from the perspective of bilateral fine-grained access control as well as the genuineness and tamper resistance of shared health information.

“The ongoing COVID-19 situation has been challenging for the existence of humans.”It has consistently surpassed the numerous physical and mental activities that humans engage in, compelling them to live within increasingly constrained boundaries. In this chapter, the use of the Internet of Things (IoT) and machine learning (ML)- based framework to tackle pandemic situations in healthcare applications has been discussed. ML and IoT-based monitoring systems track infected individuals using past information, helping with isolation. The system involves parallel computation to track and prevent pandemic diseases through predictions and analysis with artificial intelligence. The execution of ML-based IoT in the pandemic circumstance in healthcare applications has shown performance in tracking and preventing the spread of the pandemic. 

In our day-to-day life, we often refer to transportation as the movement of products or people from one place to another . On the other hand, management is all about controlling resources required by transportation to achieve desired objectives and goals. Transportation management plays a critical role for an individual and company. Applications for transportation management are becoming smarter as a result of the development of technologies like the Internet of Things (IoT), and connected devices are enabling their exploitation in all spheres. Hence, with the use of these technologies, the volume of data is also increasing many-fold. There are many techniques, such as machine learning (ML), deep learning (DL), and artificial intelligence (AI), that can be applied to collected data to get insights into the data and further enhance the capabilities and intelligence of the applications. Nowadays, transportation management is more efficient with the use of both deep learning and Internet of Things techniques. 

The healthcare sector caters to millions of people and makes a significant contribution to the local economy. The inclusion of artificial intelligence and machine learning in healthcare is not only benefiting society but also overcoming various challenges associated with it. Artificial intelligence is a branch of computer science that is used to induce human-like intelligence into machines. Machine learning is a subset of artificial intelligence that makes machines capable of learning and giving the desired conclusions without explicit programming and human support. Machine learning in the healthcare sector is making huge advancements and yielding positive results. The increasing applications of machine learning have earned it a valuable spot in the healthcare sector. From specialized robots in hospitals to automated software for disease prediction and detection, machine learning is taking over almost all areas of healthcare with the aim of reducing the workload of medical experts and also delivering services to individuals at home with cost-effective solutions. With the advancement of technology, the introduction of portable systems has led to the availability of enormous amounts of medical data, which is difficult to analyze by human experts because it takes a lot of time, effort, and analytical costs. Machines are better in speed, endurance, and pattern identification as compared to humans. With the introduction of machine learning in healthcare, the task of managing massive data has become easier as automated machine learning models not only help in data analysis but are also capable of detecting underlying data patterns that may be difficult for clinical experts to come across. Machine learning can ease the task of identifying and detecting various diseases by providing complex algorithms such as Artificial Neural Networks (ANNs). With the introduction of neural networks, the analysis can be done on various data parameters given their ability to self-learn, memorize, and provide quality treatment. Machine learning not just focuses on the physical well-being of an individual but also their mental health by coming up with artificial-intelligence-based mood trackers and self-assessing applications for stress diagnosis. One of the major applications of machine learning is to detect and identify dangerous diseases, such as diabetes and cancer, that are difficult to detect at the initial stage and are detected at subsequent stages when it is too late. The use of early detection systems can save many lives by providing timely treatment of patients. Another important application of machine learning in the healthcare field is the introduction of bionic microchips. The fusion of bionics and machine learning will bring a revolutionary change in the healthcare sector. One such example is implanting bionic chips in the brain to monitor brain activity for the identification of neurological disorders like epilepsy. The AIenabled bionic hand uses a man-machine interface to interpret the patient's intent and send the commands to the artificial limb, thus helping the patient make more natural movements and controlling the prosthetics more precisely. There is a tremendous use of machine learning and artificial intelligence in providing customized solutions to patients, as one solution does not cater to many patients. Therefore, customized solutions according to their medical history are a feasible choice. Machine learning plays an enormous role in drug discovery by improving decision-making in pharmaceutical data through high-quality data. It provides immediate assistance to the patients using the healthcare chatbot systems that suggest immediate solutions to them. There is no area left in the healthcare industry of which machine learning is not a part. Machine learning in the healthcare industry can yield efficient and timely results without any human intelligence. This is just the beginning. Machine learning in healthcare has a bright future that will revolutionize the field of medicine and healthcare.

 Since India gained independence, the number of vehicles in the country has increased by 170 times, while the road infrastructure has only expanded nine times in proportion. The rate of vehicle population growth is approximately two and a half million per year. Road fatalities far exceed those from rail, air, and terrorism, and it is predicted that by 2030, road accidents will be the fifth largest cause of human deaths. Technology, specifically IoT-based intelligent transportation systems (ITS), can address the challenges posed by inadequate road infrastructure and development. International consortia can collaborate to develop solutions tailored to such conditions. This chapter presents facts related to Indian transport and road accidents and proposes an IoT-based intelligent transportation system, termed IoTV, to improve transportation and reduce accident rates. The authors recommend an IoTV solution for ITS in their paper.

 Energy production from fossil fuels is limited as fossil fuel resources are limited on Earth. We have to find alternate resources for energy production. Energy production from waste material or by-products can help us in two major ways: by reducing waste on Earth and by producing energy without affecting conserved resources. Industrial IoT (IIoT) is an advanced IT-based technology that can help us detect the most useful waste and determine its availability in different places. It will also help us automate the complete lifecycle of energy production from by-products and distribute it to the required places.

In this chapter, we will discuss the role of Industrial IoT in the production of consumables from waste products/by-products. We will explain the various applications of IIoT in this whole process and the challenges faced in integrating this technology into it.