Green Industrial Applications of Artificial Intelligence and Internet of Things

This research shows how Hybrid Machine Learning (HML) techniques may be used in real-time to identify an Army’s personal fighting zone or any other specified location in order to reduce safety risks via the detection of an invasion or enemies. Deep Learning (DL) techniques, such as Faster R-CNN, YOLO, and DenseNet, were used to find employees, categorize objects, and detect subtle characteristics in a variety of datasets. Testing showed that a 95% recall rate and a 90% precision rate were possible. This indicates high detection. A cleanness of 85 percent and a correctness of 80 percent were achieved in a real-world construction site application. To some things up: The recommended approach may enhance current safety management methods in conflict zones, borders, and beyond.

A brushless DC (BLDC) motor-based three-wheeled vehicle, known as three-wheeled battery-operated vehicles (TWBOVs), is a suitable alternate to public transportation. The TWBoVs are not only providing efficient short-distance transportation but also are a source of employment generation since 2008 in rural India. The TWBoVs operate mainly through the flooded lead-acid battery. To get the full benefit of lower operating costs, the life, and efficiency of the battery are important aspects. In such a scenario, battery monitoring and management for battery-operated vehicles are a prime aspect. Proper battery management and monitoring enhance the durability of the lead-acid battery in TWBoVs. In this chapter, the monitoring and management of Lead-acid batteries using the Internet of Things (IoT) is capitalized. Depending on the survey in rural Bengal, it is observed that the battery life cycle depreciation process needs to be decreased by properly monitoring the condition of drive-train of TWBoVs and the lead-acid battery ampere-hour discharge in the random drive cycle. A newly applicable design regarding the state of charge (SOC) estimation of the batteries along with terminal voltage and current measurement under different depths of discharge phase has been implemented through IoT-based real-time monitoring system. This developed system relates the distance traveled (in kilometers) by the TWBoVs with the condition of the battery concerning its SOC on an online basis via a Wireless battery management system (WBMS). Experimental analysis through hardware setup and simulation proves the feasibility of the approach in terms of battery utilization and monitoring.

Lack of healthcare or inaccessibility of doctors and caregivers is a major concern. The increase in COVID-19 patients is putting tremendous pressure on hospital management in urban areas. Therefore, the development of IoT (Internet of Things) based patient monitoring systems allows doctors to obtain patient data from remote locations. The Internet of Things is an evolving technology that takes healthcare to the next level by providing affordable, reliable, and convenient devices that can be carried or embedded with patients. There is a growing interest in wearable sensors and medical devices. Therefore, wearable monitoring systems will take patient monitoring to a new level. The IoT allows various devices to be connected over the Internet. Data is collected using sensors and sent to the cloud via IoT channels, where both patients and doctors can access the data (real-time and historical) through a variety of devices. Any deviations from the norm will result in alerts being sent to both doctors and patients. This enables doctors to monitor a large number of patients at once. 

Artificial intelligence (AI) is referred to as machines that can mimic human cognitive functions. It usually engages various digital methods starting from computer programming to deep learning, thus making use of the enormous structured and nonstructured healthcare data. Artificial intelligence is gradually making a change in medical practice by using sophisticated algorithms, assisting clinicians to mitigate diagnostic and therapeutic errors and also using data intensive analysis for early diagnosis of various diseases.

The chapter provides us an insight into the relationship between artificial intelligence and healthcare, origin of artificial intelligence, different categories of artificial intelligence and its applications in our healthcare system, various diseases for screening as well as prognostic evaluation and eventually the issues pertaining to the implementation of AI in medical devices.

The main focus is on the two major categories of AI which includes machine learning and natural language processing. The former analyses the structured data such as genetic or electrophysiological data while the latter deals with unstructured data such as medical notes. In medical practice deep learning is mainly used to explore more complex data. Cardiovascular health, neurological deficits and cancer are the most challenging topics in AI.

AI technologies have created a stir in medical research yet it is facing various hurdles in the form of regulations and data exchange. Thus, ethical and legal concerns need to be addressed before the deployment of AI in the market.

Plant diseases act as a major threat to the both economy and food security of any nation. Despite being of such importance, the identification of plant diseases and approaches deployed to tackle them are mostly conventional/ traditional ones. Incubation of technology and advancement in computer vision and deep learning models have opened new ways for developing much better approaches to tackle such issues. In this work, the native plants of Jammu and Kashmir are taken into consideration. An IoT-based framework is designed for data collection and disease diagnosis. The data involves both diseased and healthy leaf images. A hybrid deep neural network is trained to identify the plant species as well as the diseases associated with it. The trained model achieves an overall accuracy of 96.35%. A comparison with other state of art approaches is also presented, along with suggestions for some related future developments. This approach can be deployed on a global scale to tackle plant diseases and to achieve global diagnosis.

In the present scenario, the contribution of Artificial intelligence (AI) has enhanced considerably in several fields including the healthcare sector. This growing technology has a bright future in medical research as well as in early disease diagnosis and its treatment by minimizing the risk factors and severity. Artificial intelligence is applied in a very smart way so as to make it a more superior and competent technology in comparison to the human brain e.g. by using AI, a robot makes the surgery in a more efficient way than a surgeon by reducing any possibility of failure and severity. Nowadays, AI has evolved as the most competent technique that helps patients and cares for them more efficiently by reducing the cost.

To work more effectively and precisely, AI requires instructions in the form of sets of algorithms. Two major key factors required for AI include natural language processing (NPL) and machine learning (ML). Both these techniques are required to fulfill the various tasks and challenges in the field of the healthcare sector. In the present chapter, an effort has been made to explore the advancements of AI in different fields of the health care system including radiology, dermatology, designing of novel drugs, and the early diagnosis and treatment of various deadly diseases like cancer and neurological disorders. 

By 2050, food production is expected to expand by 70% to feed 2.3 billion people around the world. New agricultural farming technology will be needed to feed the growing global population with safe and healthy foods. With this, in the last few decades, we have witnessed a lot of technological advancements in the farming industry. Agriculture is becoming smarter than ever before thanks to the deployment of disruptive technologies like the Internet of Things (IoT). Farmers have enhanced their control over the process of growing crops and rearing livestock due to the many smart farming IoT gadgets available on the market. The Internet of Things (IoT) is generating a lot of excitement in a variety of industries, including infrastructure, automotive, and retail. Precision agriculture is the IoT's most critical use case, yet it is not often discussed. With our globe on the verge of a food crisis, these new technology breakthroughs to boost harvests could prove life-saving. Precision agriculture is gaining traction as a new farming direction through the Internet of Things. In this chapter, we discuss the IoT technologies that are used to increase data quality, and how they are employed in the field.

Recent developments in data generation, connectivity, and technology have caused the emergence of Internet of Things (IoT) and Artificial Intelligence (AI) programs in different industries. Artificial intelligence and IOT are strengthening current healthcare technologies whether they are employed to discover new relationships between genetic codes and auto control surgical operations assisting robots. This chapter explores and discusses the various modern-day applications of AI within the fitness domain. This paper studies the influences of IoT and AI in healthcare. Artificial Intelligence (AI) and the Internet of Things (IoT) can assist additionally in replacing time-consuming information tracking techniques. The findings also indicate that AI-assisted clinical trials are capable of managing large volumes of facts and producing exceptionally accurate effects. AI expands systems that assist patients at each stage. Patients’ clinical statistics are likewise analyzed by using clinical intelligence, which gives insights to assist them in enhancing their quality of life. This study also highlights key insights into the top technological applications, which include connectivity, diagnosing the disease and discovering its treatment, patient care, defining gaps and further research directions related to modeling, the technology and regulations for data security and privacy, and also systems’ proficiency and security.

Objectives: The accuracy and early diagnosis of abnormalities in fetus Ultra Sound pictures will be improved with the use of a novel automatic segmentation technique. An essential area of study for medical AI is the real-time monitoring of prenatal spine disorders. The Internet of Things and medical AI are directly intertwined (IoT). The objective digital biomarker obtained by IoT devices could represent realtime data. IoT and digital biomarkers can be helpful in the spine based on the attributes. Methods: To increase the accuracy of anomaly detection using the K-means segmentation algorithm, the Curvelet-based Seed Point Selection (S-CSPS) methodology was created. Through seed point evaluation, which lessens the speckle and consequently improves the ability to detect abnormality, it is possible to accurately identify regions for each pixel in US images that belong to the objects. Findings: The ultrasound images of the fetal spine abnormalities dataset are used to build the suggested S-CSPS in the MATLAB environment. As part of the performance analysis, various fetus picture numbers are taken into consideration, along with noise levels, segmentation accuracy, anomaly detection rate, and segmentation time. Improvement: The findings of the simulation analysis demonstrate that, when compared to state-ofthe-art techniques, the S-CSPS method performs better with an increase in segmentation accuracy and an increase in the rate of abnormality detection utilising digital biomarkers. 

The life of an individual, an organization, and a country depends on the movement of products and services across international borders. International trade follows hallowed transportation lines; any disruption to these channels costs countries, organizations, and people millions of dollars and raises the cost of conducting business internationally. In order to ensure smart transportation, this study examined how artificial intelligence (AI), the Internet of things (IoT), and tracking will affect transportation. The introduction of these technologies (AI, IoT, tracking) into the transportation value chain will lead to smart transportation and improve efficiency in the area where they are introduced. The application of these technologies in the private sector of a developing market was the main topic of our study. 100 respondents were surveyed quantitatively in the private sector. SmartPLS was employed as a technique to clarify the ad hoc interaction between smart transportation and the independent and dependent variables of artificial intelligence, the internet of things, and tracking. The findings of this study indicate that tracking, the internet of things, and artificial intelligence have a good impact on smart mobility. The results of this study provide compelling evidence that smart technology investments are necessary if efficiency is to continuously increase. The findings from this study should help governments and businesses make the necessary investments in IoT and AI infrastructure to benefit from smart transportation, as this is the path to the supply of products and services. While considering smart transportation, it is also necessary to shield it from potential cyberattacks. 

The enhancement of supply chain performance is a hot topic in both practice and literature. In order to cut costs and boost efficiency, it is essential to invest in processes that enhance supply chain performance. The interaction between other structures and supply chain performance holds the key to releasing the hidden potential that Supply Chain Management 4.0 holds. The diffusion of “the Internet of Things into supply chain management” would boost productivity and facilitate the supply chain connections that connect industrial input to client delivery of goods and services. Artificial intelligence would improve productivity and efficiency if it were used to supply chain operations, procedures, and activities within and between enterprises. However, putting such devices online runs the risk of exposing performance because of cyber security problems. This paper investigates the beneficial effects of AI and IoT on supply chain efficiency and makes the argument that corporate failings in cyber security might have a detrimental effect on supply chain efficiency. This study employed a quantitative study with 91 respondents from organizations that substantially rely on supply chain operations. To determine the arbitrary associations between the independent and dependent variables, data were analyzed using Smart PLS. The findings imply that while AI and IoT have a beneficial impact on supply chain management performance, cyber security breaches are seen to have a negative impact. 

In our hectic lives, we usually do not have enough time to check our health on a daily basis, and as a result, we disregard our health problems. The smart health prediction system presented in this research uses a new method that could aid us in taking care of ourselves. We can use the symptoms of our health problems as input to our system to help us predict the condition, and then we can contact a medical professional when necessary. The goal of this study is to use data mining techniques to forecast cardiac disease. Due to its ability to effectively forecast outcomes and store vast amounts of data, data mining is increasingly popular nowadays. Here, we examine the information and display each aspect of the dataset. We display the male-to-female patient ratio, the type of cardiovascular disease, type of chest discomfort, and maximum and minimum patient ages. Then, we employ a variety of machine learning approaches, including the Decision Tree Algorithm, Random Forest, Support Vector Machine, Logistic Regression, KNN, and others, to forecast the disease. The majority of the models offer us accuracy rates of over 85%. Additionally, it examines the matrix's recall and precision. Therefore, we can infer that it provides us with a positive outcome that will enable us to take the required precautions and lower the rate of mortality associated with a heart disease or heart attack.

Crack detection has vital importance for monitoring and inspection of buildings. It has great significance for structural safety. This is a challenging task for computer vision and machine learning, as cracks only have low-level features for detection. Convolutional Neural Networks (CNN) is a very promising framework for crack detection from images with high accuracy and precision. This paper is based on a deep-learning methodology to detect and recognize structural defects. The dataset is split into training and testing data which is used to train the model. Then this trained model is used to recognize and classify cracks in images. The dataset consists of concrete crack images. The data set used has two categories, images with cracks and without cracks. A Convolutional Neural Network model using Pytorch will be fit to predict the images if the images have any cracks or not. This paper compares the accuracy of various models. 

As the modern world is progressing towards technological advancements year by year, the human species is endangering other species in land, water, and air. The very existing industrial advancement is focusing on human needs only and now the situation is worsening due to the natural impacts of animal species. Due to these compelling reasons, the Internet of Things has come to the rescue of endangered species. We are replacing IoT with explainable artificial intelligence due to the fact that XAI will address the black box problem of AI. In our paper, we incorporate the specific robust elements of XAI to provide a framework that will give results that are useful for researchers who are responsible for protecting endangered species. The XAI model has higher accuracy and is cost-effective during deployment which makes the proposed approach even more promising.

Agriculture is considered one of the evergreen and blooming sectors which is continuously addressing the needs of the growing population around the world. In a country like India with hundred crore population, 37 million to 118 million still depend on farming. The use of machinery and modern practices in agriculture is still not followed by the majority of farmers. Adoption of modern farm practices can result in increased yield of the crop, reduction in pollution, less water consumption, effective pest management and pesticide usage. There is a need for a lot of research on new inventions that help farmers to overcome these challenges. Artificial intelligence and machine learning are two domains that need to be utilized to address the challenges. Even though many researchers have focused on these issues, it is still way war far behind. In this paper, I would like to propose some of the approaches of Artificial Intelligence and Machine Learning that address the challenges faced by farmers.

Ecological balance is a term describing the co-existence of species with other species and also with the environment ensuring the organization of ecosystems in a state of stability. Each species has a contribution to maintaining the ecological balance. Major disturbances of ecological balance are due to careless activities by human beings like faulty usage of land, soil, water, and forest resources, and industrial and vehicle pollution. The proposed study focuses on two major resources namely soil and water which affect human, animal and plant lives both terrestrial and aquatic to a very large extent. Soil degradation is the loss of soil quality that diminishes yield. Water degradation refers to the quality of water being degraded with the introduction of unwanted chemicals and making it unsuitable for use. The world is surely going to suffer from the problem of hunger if man does not make efforts to conserve the soil and water. The need of the hour is to devise technological solutions that can measure, predict, and analyze the degradation, recommend suitable procedures either to prevent the damage, or control the damage, and suggest the means to achieve better crop productivity. The concept of Precision agriculture using IoT and AI can help in measuring, and analyzing the soil conditions, the requirements of temperature, water, pesticides, and fertilizers and provide guidance on soil management, crop rotation, and optimal planting and harvesting schedules in order to reap better yield and satisfy the food requirements of all species on Earth.

The world has faced a pandemic situation due to COVID-19. The dearth of understanding of germs, the scope of the phenomena, and the rapidity of contamination highlight many points in the new techniques for studying these events. Artificial intelligence approaches could be helpful in assessing data from virus-affected locations. The goal of this research is to look into any links between air quality and pandemic propagation. We also assess how well machine learning algorithms perform when it comes to anticipating new cases. We present a cross-correlation analysis of everyday COVID-19 instances and ecological parameters such as heat, humidification, and contaminants in the atmosphere. Our research reveals a strong link between several environmental factors and the propagation of germs. An intelligent trained model using ecological characteristics may be able to forecast the number of infected cases accurately. This technique may be beneficial in assisting organizations in taking appropriate action about inhabitants’ protection and prevalent response. Temperature and ozone are adversely connected with confirmed cases whereas air particulate matter and nitrogen dioxide are positively correlated. We created and tested three separate predictive models to see if these technologies can be used to forecast the pandemic's progression.