Trust-Aware Federated Learning with Differential Privacy for Secure AIoT in Critical Infrastructures

Purpose Smart cities are an attempt to recognize the pioneering projects designed to make the cities livable, sustainable, functional and viable. The purpose of this paper is to evaluate funding released by the government city wise and sources available for finance for the development of the smart cities. The impact of fund released by the government for the development of smart cities (Chandigarh, Karnal, Faridabad, Pune, Chennai, Ahmedabad, Kanpur, Delhi, Lucknow and Agra) in India has been studied in detail. Urbanization is a continuous process, which is taking place throughout the globe, especially in developing countries like India. Design/methodology/approach The research is descriptive in nature. The sources of funding for smart cities in India have been taken into consideration, and χ2 test of independence has been employed to study the impact of fund released by the government for smart city development in India by using IBM SPSS. Findings The total investment, area-based projects, pan-city initiatives and O&M costs for smart cities ranged between Rs 133,368 and Rs 203,979 lakh crores, Rs 105,621 and Rs 163,138 lakh crores, Rs 26,141 and Rs 38,840 lakh crores, and Rs 1,604 and Rs 1,999 lakh crores, respectively, in the year 2016 (for 60 smart cities) to 2017 (for 99 smart cities), which shows an increasing trend. The investment in retrofitting projects, redevelopment projects, greenfield projects and area-based projects ranged between Rs 94,419 and Rs 131,003 lakh crores, Rs 8,247 and Rs 23,119 lakh crores, Rs 2,955 and Rs 8,986 lakh crores, and Rs 105,621 and Rs 163,138 lakh crores, respectively, in the year 2016 (60 smart cities) to 2017 (99 smart cities), which shows the division of projects funding for smart city development in India. The funding released for smart city development such as other sources, loans from the financial institution, private investment, convergence, state government share funding and Central Government Funding ranged between Rs 14,828 and Rs 15,930 lakh crores, Rs 7,775 and Rs 9,795 lakh crores, Rs 30,858 and Rs 43,622 lakh crores, Rs 25,726 and Rs 43,088 lakh crores, Rs 27,260 and Rs 45,695 lakh crores, and Rs 29,207 and Rs 47,858 lakh crores, respectively, in the year 2016 (60 smart cities) to 2017 (99 smart cities), which reflects the different sources of funding for the development of smart cities in India. The χ2 test of independence has been applied, which shows that there is no impact of fund released by the government on cities for smart city development in India as the p-values of Chandigarh (0.213), Karnal (0.199), Faridabad (0.213), Pune (0.199), Chennai (0.213), Ahmadabad (0.199), Kanpur (0.199), Delhi (0.199), Kolkata, Lucknow (0.213) and Agra (0.199) are greater than 0.05. Research limitations/implications For the Smart Cities Mission to be financially sustainable, the right policy and institutional framework should be implemented for modernization and aggregation of government landholding. Consolidation of all the landholdings under the smart city project should be properly implemented, and the role of private sectors should be encouraged for public‒private partnership projects to make Smart City Mission more successful. Practical implications The benefits of smart cities development will help provide affordable, cleaner and greener housing infrastructure for all, especially the inclusive group of developers belonging to the lower middle-income strata of India, and the benefits will be replicated when adopted on a smaller scale in the rural part of the country. Originality/value The research paper is original and χ2 test has been used to study the impact of fund released by the government for smart city development in India.

The smart urbanization is getting popular in international urban planning for the last decade. The smart city word is to combine information and communication technology to define smart living. A smart city has an infrastructure to provide life quality, a safe and clean environment to its citizens by smart technology. These days people want to live a smart life. So, the urban planner/researcher is evolving “smart city models” based on the following six dimensions, economy, environment, people, governance, mobility, and living. This model was developed based on “American” and “European” cities. In the Indian smart city development scheme taken by India in 2014 to urbanized 100 smart cities. So, the requirement to developed “Indian smart city model” arises. This paper used the “Indian smart city model” define with eight dimensions matching to cities of India. The model takes a smart data-driven decision based on 80 indicators of the city. The “Indian smart cities” are ranking according to the calculated distance of optimal indicators values. The Taxicab Distance-Based Approach (TDBA) is purposed to ranking the “Indian smart city.” The TDBA find the optimal solution on the bases of “Indian smart city” indicators multiple values. The approach calculates the optimal distance solution to find the best result. The result shows the ranking of “Indian smart cities” on the bases of a defined model using TDBA. The ranking gives a status of growth by comparing the cities’ rank. The cities can change and update their planning according to cities rank. The data gathering from different departments and surveys of the cities. This information used for evaluation of city rank using the TDBA approach. TDBA is a mathematical tool that has been used to aggregate and convert data into a standard form that is used to rank “Indian smart cities”. The result clarifies cities vision and makes a blueprint of the cities it wants to be in the future.

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.

New sustainable ideas for materialistic solutions of smart city in India: A review from allahabad city

The exponential growth of Artificial Intelligence of Things (AIoT) has resulted in an unparalleled fusion of AI with IoT technologies, giving rise to intricate systems that present vast opportunities for automation, productivity, and data-centric decision-making. Nevertheless, this amalgamation also poses substantial obstacles regarding safeguarding online information and upholding confidentiality. The chapter extensively examines the difficulties associated with these issues and the tactics employed to surmount them. The chapter commences by delineating the distinctive susceptibilities inherent in AIoT systems, with a particular emphasis on how the interconnection of AI and IoT technologies gives rise to novel avenues for data breaches and privacy infringements. It then explores the most recent approaches and technologies used to protect data sent over AIoT networks. These include improved encryption methods, secure data transfer protocols, and solutions based on blockchain technology. A substantial chunk of the chapter focuses on privacy-preserving strategies in AIoT. The text examines the equilibrium between data usefulness and privacy protection. It delves into techniques like anonymization, differential privacy, and federated learning as means to safeguard user data while ensuring the effectiveness of AIoT systems. The chapter also examines regulatory and ethical factors, thoroughly examining current and developing legislation and regulations that oversee data security and privacy in AIoT. The content incorporates case studies and real-world examples to demonstrate the pragmatic implementation of theoretical principles. Ultimately, the chapter predicts forthcoming patterns and difficulties in this swiftly progressing domain, providing valuable perspectives on possible AIoT security and privacy protocol advancements. This resource is vital for professionals, researchers, and students engaged in AIoT, cybersecurity, and data privacy. It provides them with the necessary information and tools to protect against the ever-changing threats in this dynamic field.

In dealing with the impacts of our changing climate, the sun, air, and water are the three main factors that will affect our ability to maintain a healthy and livable living environment. The two United Nations' Sustainable Development Goals (SDGs) of "health welfare" and "sustainable city" relate closely to how societies face climate change. Applying smart technologies such as the Artificial Intelligence of Things (AIoT), big data, blockchains, and the Internet of Things (IoT), cloud calculation, and network management allows designers to access information on relational and adaptive environmental designs. Moreover, these technologies help us learn evolutionary computation information in order to provide advanced mechanisms. Models that help promote the implementation of smart neighborhoods and cities integrate smart technologies and IoT in order to improve air quality and living convenience and achieve living environments that are livable and healthy. This article primarily addresses the impacts of climate change on our living environment and how we may use green and smart buildings to ameliorate the effects of this change on daily life, promote the efficient use of water resources, and make living spaces significantly more environmentally friendly. In addition, we hope to apply the idea of smart IoT and big data analysis to design "passive toughness adaptation" and "automatic sensing prevention" into healthy living environments, which may facilitate our ability to handle the problems of super-ageing societies and to adapt to the diminishing birthrate. An intelligent and resilient environment that is appropriate for all age groups may provide a valuable path forward for preparing effectively for the impacts of climate change.

Indian cities have frequently observed intense and severe heat waves for the last few years. It will be primarily due to a significant increase in the variation in heat wave characteristics like duration, frequency, and intensity across the urban regions of India. This study will determine the impact of future climate scenarios like SSP 245 and 585 over the heat wave characteristics. It will present the comparison between heat waves characteristics in the historical time (1981 to 2020) with future projections, i.e., D1 (2021–2046), D2 (2047–2072), and D3 (2073–2098) for different climate scenarios across Indian smart cities. It is observed that the Coastal, Interior Peninsular, and North-Central regions will observe intense and frequent heat waves in the future under SSP 245 and 585 scenarios. A nearly two-fold increase in heat wave' mean duration will be observed in the smart cities of the Interior Peninsular, Coastal, and North Central zones. Thiruvananthapuram city on the west coast has the maximum hazard associated with heat waves among all the smart cities of India under both SSPs. This study assists smart city policymakers in improving the planning and implementation of heat wave adaptation and mitigation plans based on the proposed framework for heat action plans and heat wave characteristics for improving urban health well-being under hot weather extremes in different homogeneous temperature zones.

The Internet of Things (IoT) has expanded to a diverse network of interconnected electronic components, including processors, sensors, actuators, and software throughout several sectors such as healthcare, agriculture, smart cities, other industries. Despite offering simplified solutions, it introduces significant challenges, specifically data security and privacy. Machine Learning (ML), particularly the Federated Learning (FL) framework has demonstrated a promising approach to handle these challenges, specifically by enabling collaborative model training for Intrusion Detection Systems (IDS). However, FL faces some security and privacy issues, including adversarial attacks, poisoning attacks, and privacy leakages during model updates. Since the encryption, mechanisms poses issues like computational overheads and communication costs. Hence, there is need for exploring of alternative mechanism such as Differential Privacy (DP). In this research, we demonstrate an experimental study aiming exploring of FL with DP to secure IoT environment. This study analyzes the effectiveness of DP in horizontal FL setup under Independent and Identically Distributed (IID) pattern. Results on MNIST dataset show promising outcomes; FL with and without employing DP mechanism achieve an accuracy of 98.92% and 98.2%, respectively. Furthermore, the accuracy rate achieved with complex cybersecurity dataset is 93% and 91% before and after employing the DP mechanism. These findings outlines the efficiency of DP in FL framework for improving security and privacy in IoT environment.

The 100 Smart Cities Mission in India have received significant attention from the researchers and policymakers globally. This chapter examines the imposing challenge of development of command and control centres that are at the focal point of the smart cities discourse in India with as many as 83 cities investing substantially to capture and use big data through such technologically advanced facilities. A thorough account of the genesis of the Smart Cities Mission in India is presented here to establish the context behind the development of centralised big data command and control centres. This chapter presents the very first analysis of the technical architecture and systems being adopted by the Indian smart cities for creating the command and control centres and highlights their innovations in collecting and integrating big data through a range of audio, video, sound, sensing and crowdsourcing devices. While identifying the domain and application areas incorporated within the command and control centre projects, this research reveals that the focus by the Indian smart cities is more on controlling and surveilling rather than improving the delivery of public services. This chapter also critically assesses the potential of building synergy between different local and state agencies through the command and control centres and how much they can influence the urban planning processes in rapidly growing Indian cities. The outcomes from the research suggest that the command and control centres in Indian smart cities are predominantly privatised and there is an inclination towards big data corporatisation. The chapter argues for public ownership over these big data and command and control centres so that publicly funded high-value datasets can be made openly available for use by the app developers, businesses, innovators, startups and citizens that could open up opportunities for creative collaborations and the development of a data-driven innovation ecosystem.

This study presents basic concepts and applications of Artificial Intelligence System (AIS) for development of intelligent transport systems in smart cities in India. With growing urbanization the government has now realized the need for developing smart cities that can cope with the challenges of urban living and also be magnets for investment in India. Transport system in smart cities should be accessible, safe, environmentally friendly, faster, comfortable and affordable without compromising the future needs. The Indian cities largely lacks of Intelligent Transport System in India and there are various problems such as inefficient public transport system, severe congestion, increasing incidence of road accidents, inadequate parking spaces and a rapidly increasing energy cost etc. Therefore, development of Intelligent Transportation System is essential for smart cities due to concerns regarding the environmental, economic, and social equity. Artificial Intelligence is a key technology to resolve these issues. Therefore, there is an urgent need to adopt Artificial Intelligence system for development of Intelligent Transport System to better understand and control its operations in smart cities. Hence, the main objective of this study is to present some basic concepts of Artificial Intelligence and its applications for development of Intelligent Transport System in smart cities in India. This study concludes that Artificial Intelligence system needs to be adopted to develop smart public transport system, intelligent traffic management and control, smart traveller information system, smart parking management and safe mobility & emergency system in smart cities. It is expected that this study will pave the way for development of Intelligent Transport System in smart cities in India.

The extant international literature on smart cities, which are conceptualized and designed to enhance the quality of well-being, fails to provide a homogeneously unifying definition of smart city. This lack of comprehensive knowledge manifests into a critical policy challenge to policy managers responsible for creating and managing complex contours of evolution of smart cities. Smart cities, however, are increasingly becoming a subject to public debate worldwide, which appears to be a strong value-enhancing approach to managing future cities. This paper critically reviews the existing definitional conceptualization of smart cities and their changing frames in global setting across a range of criteria borrowed from literature. Further, the research maps a potential Indian smart city (case of GIFT City) on comparable framework of global smart cities with an objective of developing insights into planned efficiency of smart cities in India. The study also examines different strategies of smart city development with a spatial approach and understanding the way in which these strategies can fit into India’s urban scenario. The second part of the paper delves into financing of smart cities in India. Having taken into account India’s budgetary plans to develop 100 smart cities, we assess the scale and effectiveness of the plans. Given the potential economic profiles of such cities and associated financial outlays, we also explore likely sources of financing for smart cities with a strong focus on risk-return trade-offs.

Three decadal urban drought variability risk assessment for Indian smart cities

The artificial intelligence of things (AIoT) is an emerging technology that enables numerous AIoT devices to participate in big data analytics and machine learning (ML) model training, providing various customized intelligent services for industry manufacturing. Federated learning (FL) empowers AIoT applications with privacy-preserving distributed model training without sharing raw data. However, due to IoT devices’ limited computing and memory resources, existing FL approaches for AIoT applications cannot support efficient large-scale model training. Federated synergy learning (FSyL) is a promising collaborative paradigm that alleviates the computation and communication overhead on resource-constrained AIoT devices via offloading part of the ML model to the edge server for end-to-edge collaborative training. Existing FSyL works neither efficiently address the inter-round device selection to improve model diversity nor determine the intra-round edge association to reduce the training cost, which hinders the applications of FSyL-enable AIoT. Motivated by this issue, this article first investigates the bottlenecks of executing FSyL in AIoT. It builds an optimization model of joint inter-round device selection and intra-round edge association for balancing model diversity and training cost. To tackle the intractable coupling problem, we present a framework named Online DEvice SelectIon and EdGe AssociatioN for Cost-Diversity Tradeoffs FSyL (DESIGN). First, the edge association subproblem is extracted from the original problem, and game theory determines the optimal association decision for an arbitrary device selection. Then, based on the optimal association decision, device selection is modeled as a combinatorial multi-armed bandit (CMAB) problem. Finally, we propose an online mechanism to obtain joint DESIGN decisions. The performance of DESIGN is theoretically analyzed and experimentally evaluated on real-world datasets. The results show that DESIGN can achieve up to \(84.3\%\) in cost-saving with an accuracy improvement of \(23.6\%\) compared with the state-of-the-art.

Functionality between the size and indicators of smart cities: A research challenge with policy implications

in the year 2015, the newly elected Political-party of India started the smart-cities project. The main purpose of enlightening the governance is corporal and governmental structures and facilities (e.g. constructions of buildings, roads, and power supplies, etc.) dearth that outbreak Indian cities. The Operation emphatically, conditions that there is no standard definition of a ‘smart city’ and indicates immeasurable freedom for cities to self-define their thoughtful of ‘smart-ness’. It is also the innovative footstep by the Indian Government to construct smart-cities in India to permit monetary development and eminence people’s life by permitting confined expansion and using smart technologies to make it’s resident’s life healthier. For this purpose, the government of India firstly covering five years plan for hundreds of cities in India. After five years the evaluation process takes care by the MoUD and fascinating the existence of smart cities criteria and also will apply outside of the cities. This paper presented the challenges on the operation, implementation strategy and achieving objectives of smart cities in India.