With the emergence of Artificial Intelligence of Things (AIoT), many daily activities have been influenced by the usage of intelligent systems. Many modern applications support a smart environment. A large-scale system may comprise individual IoT systems. The overall system is controlled by Artificial Intelligence, and it serves as the brain that takes decisions. To make effective use of the information stemming from these data using efficient and intelligent data processing techniques is essential that can be analyzed with AI for decision-making or problem-solving. IoT can promote the learning and intelligence of AI; contrarily, AI can multiply the value of IoT. AIoT systems make use of key technologies like deep learning, machine learning, natural language processing, voice recognition, and image analysis. In practice, while deploying AIoT for smart environments, it might come across many challenges. Apart from this, there are other concerns such as security, performance, reliability, efficiency, complexity, accuracy, scalability, and robustness related to the growing state-of-the-art AIoT systems applications for smart environments. All these above concerns are discussed in this chapter along with practical examples.

The concept of smart cities has evolved and is under evolution. Its global implementations face multiple technological, governmental, and economic challenges. Furthermore, the convergence of Artificial Intelligence (AI) and Internet of Things (IoT) technologies might open up hitherto unexplored avenues for smart city development. As a result, the current study seeks to address the essence of smart cities. To that aim, the notion of smart cities is briefly introduced before delving into their features and requirements, as well as generic architecture, compositions, and real-world implementations. The study here investigates the different features and characteristics of a smart city. In addition, potential problems and possibilities in the field of smart cities are discussed. Numerous concerns and challenges, such as analytics and the use of AIoT emerging technologies in smart cities, are addressed in this chapter, which aids in the development of applications for the aforementioned technologies. As a result, this chapter sets the path for future research into the concerns and challenges of applications-oriented smart cities.

The economy of Indian farmers is expected to improve as a result of agricultural production in recent years. Identification of plant diseases is essential for boosting economic yield in agricultural applications. Early detection of disease in leaves is essential to prevent yield loss. Machine learning algorithms can be used to classify diseases at an early stage, allowing farmers to take action to avoid further crop damage. The chapter's major contribution is the creation of an efficient monitoring system for plants that will allow for the categorization of diseases and their early detection. Along with other environmental detection systems, the system under development will have a vision sensor. The camera sensor will be used by the system to capture leaf images in the field whenever the output of the environmental sensor exceeds an ideal threshold. For extracting essential features for classification, a novel segmentation and feature extraction technique is proposed in this chapter. The disease is classified using the random forest algorithm at the monitoring station by an agricultural expert. The effectiveness of the system is gauged by how accurately it can identify and categorize the disease which affects farms. The proposed method discussed in this chapter achieves 99% detection accuracy and 99.75% classification accuracy. According to the research results, the suggested system will be very beneficial for farmers in preventing the disease at an early stage and minimizing the damage done to the crops. When used in the field, the system with the suggested algorithm can function independently.

The agricultural sector allowed for very diverse management in the global economy, where the sector is being strengthened to be part of the commercial growth engine. The firm belief in incorporating information and communication technology (ICT) with agricultural systems influenced the expansion of a mechanized system to classify and organize agricultural products. Conventional farming is based on observations and is highly familiar which is quite laborious and time-consuming, consequently, the need for continuous monitoring of crops can be a difficulty for the farmers. The technologically advanced system initiates the monitoring and mapping process by capturing and predicting the general characterization. The integration of the Internet of Things (IoT) and artificial intelligence (AI) plays a dynamic role in the concept of smart farming, using such applications as monitoring systems to observe crop yield estimation, irrigation, nutrient management, disease identification, and weather forecast. This paper proposes a framework to enable advanced AI according to user-defined variables, of which sensors are an important feature and contributor. As an interface between a sensor and IoT as a medium, it offers great potential for outstanding performance. The results obtained using this integrated approach are very promising and can be used significantly for any other application of precision agriculture.

This study aims to explain the role of AIoT-based (Artificial Intelligence of Things) in the robotics, unmanned aerial vehicles (UAVs)/drones, which can be used for the different types of real-time applications. In recent years, modern advancement in design of robotics and UAVs/drones taking interest in different types of mission, sensors, technologies, and data processing software and a brief understanding of robotics, UAVs/drones. The results show In-depth knowledge about AIoT-based robotics, UAVs, and drones. The aim of this study is to assess the current status, automation, risk mitigation, high efficiency, modernization, and computer-oriented of the UAVs. The overall goal is to elaborate the complete information related to the whole lifecycle of the robotics and UAVs/drones. The digitalization and smart system can be enhanced by carrying out future work. This can increase cyber security by using less human involvement. Also, risky applications can be performed easily by using the AIoT. The proposed strategy is provided in-depth knowledge about the robotics, UAVs/drones. The scope is increased to assess the different fields of application i.e., military, farming, security, transportation, telecommunication, disaster, etc.

To change the gathering of circulated data in worldwide manufacturing services, sharing and managing plenty of information across many participants utilizing a fitting information system plan. Even the forced "trust tax" on manufacturers during their uncountable efforts with clients, providers, merchants, governments, specialist organizations, and other manufacturers tremendously increased. In the information and programming, recollecting can apply some strategies like processing some information with security and privacy; this thing comes under IoT with blockchain technologies. Furthermore, with support to data integration and data handling, blockchain technologies are eager to manage transaction data concerning IoT technologies. In addition to this, blockchain allows a massive "trust tax" using small and medium scale businesses while minimizing the "trust tax" comprehensively compared to accepted manufacturers. This book chapter will investigate the blockchain-based trust mechanism and security. In addition to this, it will also involve blockchain quality assurance, which is an essential part of intelligent manufacturing.

This research will look at an Artificial Intelligence and Internet of Things (IoT) based model of teaching and learning for online course, as well as teaching-learning methodologies design of the curriculum used in the course. The purpose is to offer an "educational curriculum design model" for engineering students. Students in technical courses can learn about small private online courses (SPOC)-AIoT using these modules, and we demonstrated their usefulness through teaching activities. Using a discover, define, develop, deliver double diamond shape strategy, the course and teaching content were designed in order to evaluate students' self-perception and fear of learning during the experimental teaching of AIoT. Students' happiness and effectiveness were studied using a technological acceptance paradigm. During the paradigmatic phase, routes were calculated and hypotheses were validated by bootstrapping, while SPSS was used to analyse measurement and structural models. Using tiny online learning courses in the flipped teaching method immediately gets students' attention and boosts their learning involvement. It is the findings of the study that "self-perception" has a significant positive effect on a user's perception of "usefulness" and "ease of use." According to the study, "fear of learning" is not significantly associated with the "ease of use" and "utility" of flipped learning in combination with online e-learning. There is a positive correlation between the ease of use and the usefulness of digital teaching materials used in flipped teaching that can be associated with predictions of student behaviour. "Perceived ease of use" is the most important factor with a high impact on the "usability" of a product. "Engaged learning" results in a substantial improvement in students' actual "behavioral" attitude toward learning. In comparison to other subjects, science and technology are highly relevant to student learning.

Anomaly detection techniques have attracted more attention in research and industrial areas. Anomaly detection methods have been implemented in many tenders, such as detecting malicious traffic in networks and systems, discovering vulnerabilities in security systems, detecting fraud transactions in credit cards, detecting anomalies in imaging processing, and analyzing and visualizing data in various domains. The IoT ecosystem involves applications like intelligent homes, smart cities, and smart transportation systems. With the increasing necessity for analyzing IoT network behavior, it becomes difficult to efficiently apply traditional anomaly detection techniques. The conventional techniques that use deep learning (DL) or machine learning (ML) do not detect or monitor the IoT ecosystem efficiently and effectively because they do not consider the nature of the IoT ecosystem. Another issue with traditional anomaly detection techniques is that they recalculate training whenever any change from the start points. Furthermore, they depend on a static threshold throughout the training period. This does not fit with the nature of the IoT ecosystem, which is characterized by a dynamic environment. This chapter will discuss the autonomous anomaly detection system for the Internet of Things (IoT) using ML. Specifically, we focus on the dynamic threshold that can be adapted during the training time, such as the local-global ratio technique (LGR) method, which activates the rehabilitating merely when it is essential and precludes any superfluous variations from immaterial differences in the local profiles.