ET-SCS: Error-Tolerant Split Computing System for Internet of Things

Combinations of technical advances in artificial intelligence of things (AIoT) are becoming increasingly fundamental constituents of smart houses, buildings, and factories in cities. In smart grids that ensure the resilient delivery of electrical energy to support cities, effective demand‐side management (DSM) can alleviate ever‐increasing electricity demand from customers in downstream grid sectors. Compared with the traditional intrusive load monitoring (ILM) approach used by energy management systems (EMSs), energy disaggregation, which is an EMS component instead of the ILM approach, can monitor relevant electrical appliances in a nonintrusive manner such that an effective DSM scheme can be achieved. In this study, a distributed horizontal federated learning (HFL)–based energy management framework that implements an active privacy‐preserving and edge–cloud collaborative computing–based energy disaggregation algorithm for smart mains energy disaggregation to energy‐efficient smart houses/buildings is proposed, and its preliminary implementation, in which active two‐stage energy disaggregation considering edge–cloud collaborative computing for autonomous AI modeling is achieved under HFL preserving user data privacy, is demonstrated. In the proposed framework, edge computing that collaborates with the cloud to form edge–cloud computing can serve as converged computing from which load data gathered by distributed on‐site edge devices for online load monitoring/smart energy disaggregation are globally consolidated through an artificial intelligence (AI) model in the cloud (cloud AI) and which the model that realizes global knowledge modeling is then deployed for global AI deployment at the edge (edge AI) via global knowledge sharing. In addition, edge–cloud collaboration based on HFL not only improves data privacy and data security but also enhances network traffic, as it exchanges AI model updates (model weights and biases) for global collaborative AI modeling. This is the promising achievement, instead of transmitting raw private real‐time data to a centralized cloud server for traditional model training. Simulations are conducted and used to demonstrate the feasibility and effectiveness of the proposed framework for smart mains energy disaggregation as an illustrative application paradigm of the framework; the overall load classification rate can be improved by a maximum of approximately 11% as reported from simulation results.

COVID-19 is caused by virus called SARS-CoV-2, which was declared by the WHO as global pandemic. Since the outbreak, there has been a rush to explore Artificial Intelligence (AI) and Internet of Things (IoT) for diagnosing, predicting, and treating infections. At present, individual technologies, AI and IoT, play important roles yet do not impact individually against the pandemic because of constraints like lack of historical data and the existence of biased, noisy, and outlier data. To overcome, balance among data privacy, public health, and human-AI-IoT interaction is must. Artificial Intelligence of Things (AIoT) appears to be a more efficient technological solution that can play a significant role to control COVID-19. IoT devices produce huge data which are gathered and mined for actionable effects in AI. AI converts data into useful results which are utilized by IoT devices. AIoT entails AI through machine learning and decision making to IoT and renovates IoT to add data exchange and analytics to AI. In this chapter, AIoT will serve as a potential analytical tool to fight against the pandemic.

Artificial Intelligence of Things (AIoT) is a term used to describe the integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies. AIoT combines the capabilities of AI algorithms with the data generated by IoT devices to enable real-time decision-making and automation of various processes. Smart buildings refers to a type of building that utilizes advanced technologies to improve its efficiency, performance, and functionality of indoor tasks in a way that provide a safe and comfortable environment for occupants. This paper provides an overview of the research literature on AIoT technologies that is contribute to the development of smart buildings and their functionality. We discuss the benefits of AIoT empowered smart buildings, which include reduced energy consumption and costs, improved occupant comfort and productivity, and increased safety and security. we also discusses the challenges associated with the deployment of AIoT in smart buildings, including data privacy and security concerns, interoperability issues, and the need for specialized expertise. Further, we discuss the promising areas of future research that pave the way for further research on AIoT empowered smart buildings. We concludes our work with a discussion of the potential for AIoT empowered smart buildings to contribute to the sustainability of cities and improve the quality of life for their occupants.

PurposeWith the development of information technology (IT), governments around the globe are using state-of-the-art IT interfaces to implement the so-called 3E’s in public service delivery, that is, economy, efficiency and effectiveness. Two of these IT interfaces relate to Artificial Intelligence (AI) and Internet of Things (IoT). While AI focuses on providing a “human” garb for computing devices, thereby making them “intelligent” devices, IoT relies on interfaces between sensors and the environment to make “intelligent” decisions. Recently, the convergence of AI and IoT – also referred to as Artificial Intelligence of Things (AIoT) – is seen as a real opportunity to refurbish the public service delivery formats. However, there is limited understanding as to how AIoT could contribute to the improvisation of public service delivery. This study aims to create a modular framework for AIoT in addition to highlighting the drivers and barriers for its integration in the public sector.Design/methodology/approachThis descriptive-explanatory study takes a qualitative approach. It entails a thorough examination of the drivers and barriers of integrating AI and IoT in the public sector. A review of literature has led to the development of a conceptual framework outlining the various factors that contribute to creating public value.FindingsValue creation occurs when AI and IoT coalesce in the public service delivery mechanisms.Originality/valueAIoT is a cutting-edge technology revolutionizing health care, agriculture, infrastructure and all other industrial domains. This study adds to the growing body of knowledge on the public sector's use of AI and IoT. Understanding these disruptive technologies is critical to formulating policies and regulations that can maximize the potential benefits for the public-sector organizations.

The Internet of Things (IoT) extend the connectivity into billions of IoT devices around the world. Artificial Intelligence (AI) is the best solution to manage huge data flow and storage in IoT network. Nowadays, IoT is becoming more popular with the invention of high internet speed and many advanced sensors that can be integrated into a microcontroller. Internet of Things relies on Artificial Intelligence technology which gives the term of Artificial Intelligence of Things (AIoT). AIoT is transformational and mutually beneficial for both technologies, as AI adds values to IoT through materials and software. This fusion impacts the revolution of industry 4.0 such as maintenance, production chains, optimization and logistics applied in industries to achieve increased productivity, profitability, efficiency, safety, and security.In this paper we will discuss the merge of Artificial Intelligence and Internet of Things, the soft-hard of AIoT and the impact of AIoT on the industry 4.0 applications.

In recent years, the combination of Artificial Intelligence (AI) and Internet of Things (IoT), known as Artificial intelligence of things (AIoT), has driven significant advancements within crowdsensing paradigms. Under crowdsensing paradigms, a large number of AIoT devices providing local data facilitates the superior completion of complex tasks, but also poses challenges in terms of bandwidth. Semantic communication has emerged as a promising solution to alleviate the bandwidth demands associated with AIoT crowdsensing. However, the substantial computational and energy costs associated with semantic communication make AIoT devices reluctant to participate in crowdsensing tasks or provide low-value semantic information. To address these challenges, we propose a novel crowdsensing incentive architecture designed to motivate smart devices to engage in crowdsensing activities. Our framework leverages contract theory and reputation models to ensure incentive compatibility within the information-asymmetry market between distributed AIoT devices and the crowdsensing platform. Furthermore, to enhance the convergence performance of market strategies in large-scale AIoT environments, we employ a diffusion model to generate contract design from complex data distributions within the market, optimizing the learning of the optimal contract. Simulation results confirm the effectiveness of our proposed architecture in improving the performance of AIoT crowdsensing, demonstrating its potential to overcome the identified challenges.

Artificial intelligence (AI) and internet of things (IoT) have been combined to create the artificial intelligence of things (AIoT), which could revolutionize education. Education has opportunities and difficulties from this growth. The benefits include tailored learning, real-time feedback, and immersive learning. Data privacy, security, and accessibility are problems beyond the digital divide. Strategic decision-making, communication, and stakeholder engagement are needed to maximise productivity and results using AIoT in education. The chapter provides a plan for ethical and equitable usage of the technology while avoiding hazards. This study investigates the role of AIoT in education to provide a much-needed understanding of future perspectives and ramifications. Responsible and ethical AIoT implementation improves learning and outcomes, according to the chapter.

Chapter 8 - A conceptual framework for Artificial Intelligence of Medical Things (AIoMT)

Due to massive and rapid advancement in digital technology, the combination of artificial intelligence (AI) and Internet of Things (IoT) is making a new branch of emerging technology called Artificial Intelligence of Things (AIoT). AIoT is a new and developing branch of computer science with continuous progress being made in this field each day. AIoT helps us achieve more efficient IoT operations, improves human-made interactions with machines, and also enhances data management and data analytics. This emerging technology aims at improving the different industry and service sectors by enabling AI techniques into various infrastructure components. It can provide a viable solution to solve existing problems at different levels of operations ranging from device, software, and platform levels, all connected to IoT networks. Due to the revolution happening in this new technology, this chapter provides an in-depth understanding of different terms related to the emerging technology. This chapter provides the basic understanding of IoT architecture, AI technology, and architecture of AIoT-based systems to the readers. Further, to provide practical exposure about the technology, some proposed systems are also discussed along with their applications in different sectors, i.e., healthcare, transportation, smart homes, and agriculture.

Cloud-edge collaboration provides an efficient way to promote the development and application of the Artificial Intelligence of Things (AIoT) by addressing the limited computing, communication, and storage capabilities of the Internet of Things (IoT) devices. The compute-intensive task of developing an Artificial Intelligence (AI) model is performed on the cloud-server over a public dataset while it is deployed on the edge-server to analyze the IoT data. The merit in processing data locally is the privacy preservation. However, to keep the model relevant to the ever-growing IoT data, it is necessary to share it with the cloud-server, which can raise certain privacy concerns. Also, it is challenging to adapt the model to the IoT data characteristics. Therefore, we propose a privacy-preserving cloud-edge paradigm incorporating personalized context learning and incremental learning strategies to adapt the trained model to the heterogeneous and dynamic IoT environment. To avoid any privacy issues, we propose a lightweight image cryptosystem parameterized to protect image contents according to an application requirement. The simulation results show that our proposed image cryptosystem has favorable encryption properties and the cipher-images are learnable by an AI model. In addition, our incremental learning strategy efficiently kept the model up-to-date, and with proposed personalized context learning strategy, the cloud-server model’s performance improved up to 13% for plain-images and 18% for cipher-images.

SummaryThe power of artificial intelligence of things (AIoT) stems from adapting machine learning (ML) and artificial intelligence (AI) models into abundant intelligent IoT fields, based on a large data stream with different formats, sizes, and timestamps generated by massive numbers of heterogeneous sensors. On the one hand, data acquisition is the fundamental basis for any AIoT systems, but data sensed by massive IoT devices may be noisy and even contain adversarial samples. On the other hand, ensuring the efficiency and robustness in data acquisition is vitally important for data‐driven ML and AI. Recently, besides perceiving ability, the literature has witnessed great development of empowering things with learning and reasoning ability through deep learning models, including recurrent neural networks (RNNs) and/or convolutional neural network (CNNs). However, the existing works have one significant weakness: fail to explicitly leverage the geospatial implications and latent connections among sensors for high‐quality data acquisition and quality control. Graphs are intrinsically suitable for representing the dependencies and inter‐relationships between AIoT data sensing devices. Due to the ability of capturing the complex interactive relationships between nodes and producing high‐level representations of the graph input, graph neural networks (GNNs) have exploded onto various ML and AI fields, to learn from graph‐structured data. Our review covers the latest progresses in GNN for the fundamental atomic task of data acquisition in AIoT. Instead of surveying the abundant GNN schemes in vertically various IoT sensing applications, this paper systematically reviews the horizontal infrastructure that all AIoT fields should have, that is, AIoT data acquisition, based on GNN and other related emerging AI factors. Our contributions include the following aspects: Provide the latest progresses in GNN for the horizontal task of data acquisition in AIoT, propose the unified GNN pipeline based on encoder–decoder paradigm, and systematically categorize and summarize the emerging technologies helpful to address the issues in AIoT data acquisition, especially the noisy and adversarial data, and point out some future directions about GNN‐based AIoT data acquisition.

The Artificial Intelligence and Internet of Things are powerful technologies. Artificial Intelligence is a process in which machines get to work and act like humans. Internet of Things is an enormous network which connects the devices. These devices gather and share data about how they are used and the environment in which they operated. In this research paper we are discussing the differences between the Internet of things and Artificial Intelligence, the need of blending Artificial Intelligence and the Internet of Things. What is the main reason behind this combining Artificial Intelligence and the Internet of Things?

The accelerating convergence of artificial intelligence (AI) and Internet of Things (IoT) has sparked a recent wave of interest in Artificial Intelligence of Things (AIoT). By exploiting the novel paradigm of edge intelligence, emerging computational intensive and resource demanding AIoT applications can be efficiently supported at the network edge. However, due to the limited resource capacity and/or power budget of the edge node, AIoT applications typically deploy compressed AI models to achieve the goal of low-latency and energy-efficient model inference. However, compressed models inherently suffer from the curse of data drift, i.e., the inference data at the deployment stage diverges from the training data at the training stage, leading to reduced model inference accuracy. To handle this issue, continuous learning has been proposed to periodically retrain the AI models on new data in an incremental manner. In this article, we investigate how to coordinate the edge and the cloud resources to perform cost-efficient continuous learning, with the goal of simultaneously optimizing the model performance (in terms of accuracy and robustness) and resource cost. Leveraging the Lyapunov optimization theory, we design and analyze a cost-efficient optimization framework for making online decisions upon admission control, transmission scheduling, and resource provisioning, for the dynamically arrived new data samples of various AIoT applications. We examine the effectiveness of the proposed framework on navigating the performance–cost tradeoff theoretically and empirically through trace-driven simulations.

Artificial Intelligence of Things (AIoT), as a fusion of artificial intelligence (AI) and Internet of Things (IoT), has become a new trend to realize the intelligentization of industry 4.0 and the data privacy and security is the key to its successful implementation. To enhance data privacy protection, the federated learning has been introduced in AIoT, which allows participants to jointly train AI models without sharing private data. However, in federated learning, malicious participants might provide malicious models by launching the poisoning attack, which will jeopardize the convergence and accuracy of the global model. To solve this problem, we propose a malicious model detection mechanism based on the isolation forest (iforest), named D2MIF, for the federated learning-empowered AIoT. In D2MIF, an iforest is constructed to compute the malicious score for each model uploaded by the corresponding participant, and then, the models will be filtered if their malicious scores are higher than the threshold, which is dynamically adjusted using reinforcement learning (RL). The validation experiment is conducted on two public data sets Mnist and Fashion_Mnist. The experimental results show that the proposed D2MIF can effectively detect malicious models and significantly improve the global model accuracy in federated learning-empowered AIoT.

Artificial Intelligence of Things (AIoT) combines Artificial Intelligence (AI) and Internet of Things (IoT) to enable intelligent, real-time decision-making in applications such as healthcare, smart agriculture, and industrial automation. However, ensuring data security in AIoT environments is challenging due to the limited computational resources, memory, and energy constraints of edge devices. Traditional cryptographic algorithms are often too heavy for such settings, while existing lightweight schemes may lack adequate security. This paper proposes LCE-AIoT, a lightweight cryptographic framework based on an optimized version of the Ascon algorithm. Designed for 128-bit authenticated encryption, LCE-AIoT reduces computational overhead by minimizing permutation rounds and memory usage, making it suitable for microcontrollers like ESP32 and STM32. The framework supports both pre-shared and ECC-based key exchange and integrates seamlessly with lightweight IoT operating systems such as Contiki-NG and TinyOS. Experimental results show that LCE-AIoT achieves superior performance compared to existing lightweight algorithms including PRESENT, SIMON, SPECK, and standard Ascon, offering lower execution time, reduced memory footprint, better energy efficiency, and higher throughput. This makes it ideal for secure, low-power AIoT applications. Future enhancements include post-quantum resilience, hardware acceleration, and blockchain integration, ensuring the framework’s adaptability to emerging intelligent systems.