The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （a...The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （and related problems） are becoming more complex and uncertain. Researchers have therefore turned to artificial intelligence （AI） to efficiently deal with the problems ereated by big data.展开更多
Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related p...Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related problems arc becoming more complex and uncer tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data.展开更多
Internet of Things has received much attention over the past de- cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather- ing and related...Internet of Things has received much attention over the past de- cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather- ing and related problems are becoming more complex and uncer- tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data. This special issue of ZTE Communications will be dedicated to development, trends, challenges, and current practices in artificial intelligence for the Internet of Things. Position papers, technology overviews, and case studies are all welcome. Appropriate topics include but are not limited to：展开更多
With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performan...With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.展开更多
With the advent of the sixth-generationwireless technology,the importance of using artificial intelligence of things(AIoT)devices is increasing to enhance efficiency.As massive volumes of data are collected and stored...With the advent of the sixth-generationwireless technology,the importance of using artificial intelligence of things(AIoT)devices is increasing to enhance efficiency.As massive volumes of data are collected and stored in these AIoT environments,each device becomes a potential attack target,leading to increased security vulnerabilities.Therefore,intrusion detection studies have been conducted to detect malicious network traffic.However,existing studies have been biased toward conducting in-depth analyses of individual packets to improve accuracy or applying flow-based statistical information to ensure real-time performance.Effectively responding to complex andmultifaceted threats in large-scale AIoT environments is challenging.This study proposes a hybrid multivariate network traffic(HyMNeT)feature-based intrusion detection system that applies a hybrid meta-heuristic feature selection approach to create a secure and efficient AIoT environment.The HyMNeT system selects critical features by applying mutual information maximization(MIM)and the maximal information coefficient(MIC)based on statistical features of the network traffic flow and raw packet features.This system employs the reference vector-guided evolutionary algorithm to search for optimal thresholds that maximizeMIMscores whileminimizingMIC scores.An evaluation of the selected multivariate network traffic feature set using four machine learning models on the BoT-IoT and ToN-IoT datasets resulted in average accuracy,precision,recall,and F1-score values of 0.9844,0.9897,0.9844,and 0.9859,respectively.This work demonstrates that HyMNeT performs detection consistently and stably across all models.展开更多
Rapid urbanization,alongside escalating resource depletion and ecological degradation,underscores the urgent need for innovative paradigms in urban development.In response,sustainable smart cities are increasingly lev...Rapid urbanization,alongside escalating resource depletion and ecological degradation,underscores the urgent need for innovative paradigms in urban development.In response,sustainable smart cities are increasingly leveraging advanced technological frameworks—most notably the convergence of Artificial Intelligence of Things(AIoT)and Cyber-Physical Systems(CPS)—as critical enablers for transforming their management and planning processes.Within this dynamic landscape,Urban Brain(UB)and Urban Digital Twin(UDT)have emerged as prominent AIo T-powered city platforms.Defined by their complex functionalities and multi-layered architectures,these systems exemplify Cyber-Physical Systems of Systems(CPSoS),offering a cohesive foundation for integrating real-time operational responsiveness with strategic predictive foresight.Despite notable technological progress,a critical gap persists in effectively integrating the distinct yet complementary capabilities of UB and UDT within a structured and scalable framework.To the best of our knowledge,research on the explicit fusion of UB's real-time analytics—enabled through stream processing—with UDT's predictive analytics—driven by simulation modeling—is scant,if not absent.Most existing studies continue to treat UB and UDT as siloed systems,failing to recognize the critical need to synchronize their respective operational and strategic functions.This fragmentation limits the ability of urban systems to respond both adaptively and proactively to the complex,interrelated challenges of environmental sustainability.To address this critical gap,this study introduces a novel foundational framework—Artificial Intelligence of Things for Sustainable Smart City Brain and Digital Twin Systems—designed to synergistically integrate UB and UDT as AIo T-enabled platforms within a unified CPSo S architecture.This framework addresses the critical disconnect between real-time operational management and strategic predictive planning,delivering an integrated pathway for advancing environmentally sustainable smart city development goals.Harnessing the complementary strengths of UB and UDT,it empowers cities to respond dynamically to immediate urban demands while ensuring consistent alignment with long-term sustainability goals.UB's real-time analytics enhance the efficiency of daily urban operations,whereas UDT's predictive modeling anticipates and simulates future scenarios.Together,they establish a synergistic feedback loop:UB's real-time insights continuously inform UDT's strategic simulations,while UDT's long-range forecasts iteratively refine UB's operational decision-making.The framework thus equips researchers,practitioners,and policymakers with a robust methodology for designing and implementing adaptive,efficient,and resilient urban ecosystems.It facilitates the development of intelligent urban environments that can advance environmental sustainability by integrating solid theoretical foundations with actionable strategies.展开更多
With the ongoing advancement of urban-rural integration,traditional villages are encountering challenges such as fragmented spatial patterns,the erosion of cultural landscapes,and the diminishing of distinctive featur...With the ongoing advancement of urban-rural integration,traditional villages are encountering challenges such as fragmented spatial patterns,the erosion of cultural landscapes,and the diminishing of distinctive features.Current landscape protection and utilization methods often exhibit limitations,including a narrow identification dimension,fragmented activation strategies,and a disconnect from modern development.To address these issues,this paper introduced the“landscape gene”theory from the perspective of urban and rural planning.It integrated artificial intelligence and Internet of Things technologies to construct a pathway for the inheritance and activation of landscape genes,centered around the concepts of Specifically,through remote sensing image recognition,village texture deconstruction,cultural element extraction,and a dynamic monitoring system,the core genes of traditional village spatial texture,historical sites,cultural symbols,and more were accurately identified and dynamically tracked.In terms of activation strategy,an AI-driven participatory planning platform guided the community in co-building and co-managing,thereby achieving adaptive regeneration and sustainable use of landscape genes in contemporary contexts.Empirical results indicated that this method could increase the retention rate of core landscape elements by 22%,enhance villager participation by 35%,and achieve an 87%satisfaction rate with landscape activation,effectively promote the cultural continuity and morphological renewal of traditional villages.展开更多
The recent advancements made in the realms of Artificial Intelligence(AI)and Artificial Intelligence of Things(AIoT)have unveiled transformative prospects and opportunities to enhance and optimize the environmental pe...The recent advancements made in the realms of Artificial Intelligence(AI)and Artificial Intelligence of Things(AIoT)have unveiled transformative prospects and opportunities to enhance and optimize the environmental performance and efficiency of smart cities.These strides have,in turn,impacted smart eco-cities,catalyzing ongoing improvements and driving solutions to address complex environmental challenges.This aligns with the visionary concept of smarter eco-cities,an emerging paradigm of urbanism characterized by the seamless integration of advanced technologies and environmental strategies.However,there remains a significant gap in thoroughly understanding this new paradigm and the intricate spectrum of its multifaceted underlying dimensions.To bridge this gap,this study provides a comprehensive systematic review of the burgeoning landscape of smarter eco-cities and their leadingedge AI and AIoT solutions for environmental sustainability.To ensure thoroughness,the study employs a unified evidence synthesis framework integrating aggregative,configurative,and narrative synthesis approaches.At the core of this study lie these subsequent research inquiries:What are the foundational underpinnings of emerging smarter eco-cities,and how do they intricately interrelate,particularly urbanism paradigms,environmental solutions,and data-driven technologies?What are the key drivers and enablers propelling the materialization of smarter eco-cities?What are the primary AI and AIoT solutions that can be harnessed in the development of smarter eco-cities?In what ways do AI and AIoT technologies contribute to fostering environmental sustainability practices,and what potential benefits and opportunities do they offer for smarter eco-cities?What challenges and barriers arise in the implementation of AI and AIoT solutions for the development of smarter eco-cities?The findings significantly deepen and broaden our understanding of both the significant potential of AI and AIoT technologies to enhance sustainable urban development practices,as well as the formidable nature of the challenges they pose.Beyond theoretical enrichment,these findings offer invaluable insights and new perspectives poised to empower policymakers,practitioners,and researchers to advance the integration of eco-urbanism and AI-and AIoT-driven urbanism.Through an insightful exploration of the contemporary urban landscape and the identification of successfully applied AI and AIoT solutions,stakeholders gain the necessary groundwork for making well-informed decisions,implementing effective strategies,and designing policies that prioritize environmental well-being.展开更多
The rapid expansion of artificial intelligence(AI)applications has raised significant concerns about user privacy,prompting the development of privacy-preserving machine learning(ML)paradigms such as federated learnin...The rapid expansion of artificial intelligence(AI)applications has raised significant concerns about user privacy,prompting the development of privacy-preserving machine learning(ML)paradigms such as federated learning(FL).FL enables the distributed training of ML models,keeping data on local devices and thus addressing the privacy concerns of users.However,challenges arise from the heterogeneous nature of mobile client devices,partial engagement of training,and non-independent identically distributed(non-IID)data distribution,leading to performance degradation and optimization objective bias in FL training.With the development of 5G/6G networks and the integration of cloud computing edge computing resources,globally distributed cloud computing resources can be effectively utilized to optimize the FL process.Through the specific parameters of the server through the selection mechanism,it does not increase the monetary cost and reduces the network latency overhead,but also balances the objectives of communication optimization and low engagement mitigation that cannot be achieved simultaneously in a single-server framework of existing works.In this paper,we propose the FedAdaSS algorithm,an adaptive parameter server selection mechanism designed to optimize the training efficiency in each round of FL training by selecting the most appropriate server as the parameter server.Our approach leverages the flexibility of cloud resource computing power,and allows organizers to strategically select servers for data broadcasting and aggregation,thus improving training performance while maintaining cost efficiency.The FedAdaSS algorithm estimates the utility of client systems and servers and incorporates an adaptive random reshuffling strategy that selects the optimal server in each round of the training process.Theoretical analysis confirms the convergence of FedAdaSS under strong convexity and L-smooth assumptions,and comparative experiments within the FLSim framework demonstrate a reduction in training round-to-accuracy by 12%–20%compared to the Federated Averaging(FedAvg)with random reshuffling method under unique server.Furthermore,FedAdaSS effectively mitigates performance loss caused by low client engagement,reducing the loss indicator by 50%.展开更多
More devices in the Intelligent Internet of Things(AIoT)result in an increased number of tasks that require low latency and real-time responsiveness,leading to an increased demand for computational resources.Cloud com...More devices in the Intelligent Internet of Things(AIoT)result in an increased number of tasks that require low latency and real-time responsiveness,leading to an increased demand for computational resources.Cloud computing’s low-latency performance issues in AIoT scenarios have led researchers to explore fog computing as a complementary extension.However,the effective allocation of resources for task execution within fog environments,characterized by limitations and heterogeneity in computational resources,remains a formidable challenge.To tackle this challenge,in this study,we integrate fog computing and cloud computing.We begin by establishing a fog-cloud environment framework,followed by the formulation of a mathematical model for task scheduling.Lastly,we introduce an enhanced hybrid Equilibrium Optimizer(EHEO)tailored for AIoT task scheduling.The overarching objective is to decrease both the makespan and energy consumption of the fog-cloud system while accounting for task deadlines.The proposed EHEO method undergoes a thorough evaluation against multiple benchmark algorithms,encompassing metrics likemakespan,total energy consumption,success rate,and average waiting time.Comprehensive experimental results unequivocally demonstrate the superior performance of EHEO across all assessed metrics.Notably,in the most favorable conditions,EHEO significantly diminishes both the makespan and energy consumption by approximately 50%and 35.5%,respectively,compared to the secondbest performing approach,which affirms its efficacy in advancing the efficiency of AIoT task scheduling within fog-cloud networks.展开更多
Power Line Communications-Artificial Intelligence of Things(PLC-AIo T)combines the low cost and high coverage of PLC with the learning ability of Artificial Intelligence(AI)to provide data collection and transmission ...Power Line Communications-Artificial Intelligence of Things(PLC-AIo T)combines the low cost and high coverage of PLC with the learning ability of Artificial Intelligence(AI)to provide data collection and transmission capabilities for PLC-AIo T devices in smart parks.With the development of smart parks,their emerging services require secure and accurate time synchronization of PLC-AIo T devices.However,the impact of attackers on the accuracy of time synchronization cannot be ignored.To solve the aforementioned problems,we propose a tampering attack-aware Deep Q-Network(DQN)-based time synchronization algorithm.First,we construct an abnormal clock source detection model.Then,the abnormal clock source is detected and excluded by comparing the time synchronization information between the device and the gateway.Finally,the proposed algorithm realizes the joint guarantee of high accuracy and low delay for PLC-AIo T in smart parks by intelligently selecting the multi-clock source cooperation strategy and timing weights.Simulation results show that the proposed algorithm has better time synchronization delay and accuracy performance.展开更多
The dynamic landscape of sustainable smart cities is witnessing a significant transformation due to the integration of emerging computational technologies and innovative models.These advancements are reshaping data-dr...The dynamic landscape of sustainable smart cities is witnessing a significant transformation due to the integration of emerging computational technologies and innovative models.These advancements are reshaping data-driven planning strategies,practices,and approaches,thereby facilitating the achievement of environmental sustainability goals.This transformative wave signals a fundamental shift d marked by the synergistic operation of artificial intelligence(AI),artificial intelligence of things(AIoT),and urban digital twin(UDT)technologies.While previous research has largely explored urban AI,urban AIoT,and UDT in isolation,a significant knowledge gap exists regarding their synergistic interplay,collaborative integration,and collective impact on data-driven environmental planning in the dynamic context of sustainable smart cities.To address this gap,this study conducts a comprehensive systematic review to uncover the intricate interactions among these interconnected technologies,models,and domains while elucidating the nuanced dynamics and untapped synergies in the complex ecosystem of sustainable smart cities.Central to this study are four guiding research questions:1.What theoretical and practical foundations underpin the convergence of AI,AIoT,UDT,data-driven planning,and environmental sustainability in sustainable smart cities,and how can these components be synthesized into a novel comprehensive framework?2.How does integrating AI and AIoT reshape the landscape of datadriven planning to improve the environmental performance of sustainable smart cities?3.How can AI and AIoT augment the capabilities of UDT to enhance data-driven environmental planning processes in sustainable smart cities?4.What challenges and barriers arise in integrating and implementing AI,AIoT,and UDT in data-driven environmental urban planning,and what strategies can be devised to surmount or mitigate them?Methodologically,this study involves a rigorous analysis and synthesis of studies published between January 2019 and December 2023,comprising an extensive body of literature totaling 185 studies.The findings of this study surpass mere interdisciplinary theoretical enrichment,offering valuable insights into the transformative potential of integrating AI,AIoT,and UDT technologies to advance sustainable urban development practices.By enhancing data-driven environmental planning processes,these integrated technologies and models offer innovative solutions to address complex environmental challenges.However,this endeavor is fraught with formidable challenges and complexities that require careful navigation and mitigation to achieve desired outcomes.This study serves as a comprehensive reference guide,spurring groundbreaking research endeavors,stimulating practical implementations,informing strategic initiatives,and shaping policy formulations in sustainable urban development.These insights have profound implications for researchers,practitioners,and policymakers,providing a roadmap for fostering resiliently designed,technologically advanced,and environmentally conscious urban environments.展开更多
To tackle the challenge of applying convolutional neural network(CNN)in field-programmable gate array(FPGA)due to its computational complexity,a high-performance CNN hardware accelerator based on Verilog hardware desc...To tackle the challenge of applying convolutional neural network(CNN)in field-programmable gate array(FPGA)due to its computational complexity,a high-performance CNN hardware accelerator based on Verilog hardware description language was designed,which utilizes a pipeline architecture with three parallel dimensions including input channels,output channels,and convolution kernels.Firstly,two multiply-and-accumulate(MAC)operations were packed into one digital signal processing(DSP)block of FPGA to double the computation rate of the CNN accelerator.Secondly,strategies of feature map block partitioning and special memory arrangement were proposed to optimize the total amount of off-chip access memory and reduce the pressure on FPGA bandwidth.Finally,an efficient computational array combining multiplicative-additive tree and Winograd fast convolution algorithm was designed to balance hardware resource consumption and computational performance.The high parallel CNN accelerator was deployed in ZU3 EG of Alinx,using the YOLOv3-tiny algorithm as the test object.The average computing performance of the CNN accelerator is 127.5 giga operations per second(GOPS).The experimental results show that the hardware architecture effectively improves the computational power of CNN and provides better performance compared with other existing schemes in terms of power consumption and the efficiency of DSPs and block random access memory(BRAMs).展开更多
Artificial intelligence of things systems equipped with flexible sensors can autonomously and intelligently detect the condition of the surroundings.However,current intelligent monitoring systems always rely on an ext...Artificial intelligence of things systems equipped with flexible sensors can autonomously and intelligently detect the condition of the surroundings.However,current intelligent monitoring systems always rely on an external computer with the capability of machine learning rather than integrating it into the sensing device.The computer-assisted intelligent system is hampered by energy inefficiencies,privacy issues,and bandwidth restrictions.Here,a flexible,large-scale sensing array with the capability of low-power in-sensor intelligence based on a compression hypervector encoder is proposed for real-time recognition.The system with in-sensor intelligence can accommodate different individuals and learn new postures without additional computer processing.Both the communication bandwidth requirement and energy consumption of this system are significantly reduced by 1,024 and 500 times,respectively.The capability for in-sensor inference and learning eliminates the necessity to transmit raw data externally,thereby effectively addressing privacy concerns.Furthermore,the system possesses a rapid recognition speed(a few hundred milliseconds)and a high recognition accuracy(about 99%),comparing with support vector machine and other hyperdimensional computing methods.The research holds marked potential for applications in the integration of artificial intelligence of things and flexible electronics.展开更多
文摘The Internet of Things （IoT） has received much attention over the past decade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gathering （and related problems） are becoming more complex and uncertain. Researchers have therefore turned to artificial intelligence （AI） to efficiently deal with the problems ereated by big data.
文摘Interact of Things has received much attention over the past de cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather ing and related problems arc becoming more complex and uncer tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data.
文摘Internet of Things has received much attention over the past de- cade. With the rapid increase in the use of smart devices, we are now able to collect big data on a daily basis. The data we are gather- ing and related problems are becoming more complex and uncer- tain. Researchers have therefore turned to AI as an efficient way of dealing with the problems created by big data. This special issue of ZTE Communications will be dedicated to development, trends, challenges, and current practices in artificial intelligence for the Internet of Things. Position papers, technology overviews, and case studies are all welcome. Appropriate topics include but are not limited to：
基金supported by the Natural Science Foundation of China No.62362008the Major Scientific and Technological Special Project of Guizhou Province([2024]014).
文摘With the rapid development of the Artificial Intelligence of Things(AIoT),convolutional neural networks(CNNs)have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks.However,the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices.Therefore,this paper proposes an efficient privacy-preserving CNN framework(i.e.,EPPA)based on the Fully Homomorphic Encryption(FHE)scheme for AIoT application scenarios.In the plaintext domain,we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain.Within the encryption domain,we integrate batch normalization(BN)into the convolutional layers to simplify the computation process.For nonlinear activation functions,we use composite polynomials for approximate calculation.Regarding the noise accumulation caused by homomorphic multiplication operations,we realize the refreshment of ciphertext noise through minimal“decryption-encryption”interactions,instead of adopting bootstrapping operations.Additionally,in practical implementation,we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain.Finally,we conduct extensive experiments on four IoT datasets,different CNN architectures,and two platforms with different resource configurations to evaluate the performance of EPPA in detail.
基金supported by the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(RS-2023-00267476)by the Ministry of Trade,Industry and Energy(MOTIE)and the Korea Institute for Advancement of Technology(KIAT)through the International Cooperative R&D program(No.P0028271).
文摘With the advent of the sixth-generationwireless technology,the importance of using artificial intelligence of things(AIoT)devices is increasing to enhance efficiency.As massive volumes of data are collected and stored in these AIoT environments,each device becomes a potential attack target,leading to increased security vulnerabilities.Therefore,intrusion detection studies have been conducted to detect malicious network traffic.However,existing studies have been biased toward conducting in-depth analyses of individual packets to improve accuracy or applying flow-based statistical information to ensure real-time performance.Effectively responding to complex andmultifaceted threats in large-scale AIoT environments is challenging.This study proposes a hybrid multivariate network traffic(HyMNeT)feature-based intrusion detection system that applies a hybrid meta-heuristic feature selection approach to create a secure and efficient AIoT environment.The HyMNeT system selects critical features by applying mutual information maximization(MIM)and the maximal information coefficient(MIC)based on statistical features of the network traffic flow and raw packet features.This system employs the reference vector-guided evolutionary algorithm to search for optimal thresholds that maximizeMIMscores whileminimizingMIC scores.An evaluation of the selected multivariate network traffic feature set using four machine learning models on the BoT-IoT and ToN-IoT datasets resulted in average accuracy,precision,recall,and F1-score values of 0.9844,0.9897,0.9844,and 0.9859,respectively.This work demonstrates that HyMNeT performs detection consistently and stably across all models.
基金financial support provided by Innosuisse for the Blue City Flagship Project(Flagship ID#PFFS21-03)。
文摘Rapid urbanization,alongside escalating resource depletion and ecological degradation,underscores the urgent need for innovative paradigms in urban development.In response,sustainable smart cities are increasingly leveraging advanced technological frameworks—most notably the convergence of Artificial Intelligence of Things(AIoT)and Cyber-Physical Systems(CPS)—as critical enablers for transforming their management and planning processes.Within this dynamic landscape,Urban Brain(UB)and Urban Digital Twin(UDT)have emerged as prominent AIo T-powered city platforms.Defined by their complex functionalities and multi-layered architectures,these systems exemplify Cyber-Physical Systems of Systems(CPSoS),offering a cohesive foundation for integrating real-time operational responsiveness with strategic predictive foresight.Despite notable technological progress,a critical gap persists in effectively integrating the distinct yet complementary capabilities of UB and UDT within a structured and scalable framework.To the best of our knowledge,research on the explicit fusion of UB's real-time analytics—enabled through stream processing—with UDT's predictive analytics—driven by simulation modeling—is scant,if not absent.Most existing studies continue to treat UB and UDT as siloed systems,failing to recognize the critical need to synchronize their respective operational and strategic functions.This fragmentation limits the ability of urban systems to respond both adaptively and proactively to the complex,interrelated challenges of environmental sustainability.To address this critical gap,this study introduces a novel foundational framework—Artificial Intelligence of Things for Sustainable Smart City Brain and Digital Twin Systems—designed to synergistically integrate UB and UDT as AIo T-enabled platforms within a unified CPSo S architecture.This framework addresses the critical disconnect between real-time operational management and strategic predictive planning,delivering an integrated pathway for advancing environmentally sustainable smart city development goals.Harnessing the complementary strengths of UB and UDT,it empowers cities to respond dynamically to immediate urban demands while ensuring consistent alignment with long-term sustainability goals.UB's real-time analytics enhance the efficiency of daily urban operations,whereas UDT's predictive modeling anticipates and simulates future scenarios.Together,they establish a synergistic feedback loop:UB's real-time insights continuously inform UDT's strategic simulations,while UDT's long-range forecasts iteratively refine UB's operational decision-making.The framework thus equips researchers,practitioners,and policymakers with a robust methodology for designing and implementing adaptive,efficient,and resilient urban ecosystems.It facilitates the development of intelligent urban environments that can advance environmental sustainability by integrating solid theoretical foundations with actionable strategies.
文摘With the ongoing advancement of urban-rural integration,traditional villages are encountering challenges such as fragmented spatial patterns,the erosion of cultural landscapes,and the diminishing of distinctive features.Current landscape protection and utilization methods often exhibit limitations,including a narrow identification dimension,fragmented activation strategies,and a disconnect from modern development.To address these issues,this paper introduced the“landscape gene”theory from the perspective of urban and rural planning.It integrated artificial intelligence and Internet of Things technologies to construct a pathway for the inheritance and activation of landscape genes,centered around the concepts of Specifically,through remote sensing image recognition,village texture deconstruction,cultural element extraction,and a dynamic monitoring system,the core genes of traditional village spatial texture,historical sites,cultural symbols,and more were accurately identified and dynamically tracked.In terms of activation strategy,an AI-driven participatory planning platform guided the community in co-building and co-managing,thereby achieving adaptive regeneration and sustainable use of landscape genes in contemporary contexts.Empirical results indicated that this method could increase the retention rate of core landscape elements by 22%,enhance villager participation by 35%,and achieve an 87%satisfaction rate with landscape activation,effectively promote the cultural continuity and morphological renewal of traditional villages.
基金funding from the European Union's Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No.101034260.
文摘The recent advancements made in the realms of Artificial Intelligence(AI)and Artificial Intelligence of Things(AIoT)have unveiled transformative prospects and opportunities to enhance and optimize the environmental performance and efficiency of smart cities.These strides have,in turn,impacted smart eco-cities,catalyzing ongoing improvements and driving solutions to address complex environmental challenges.This aligns with the visionary concept of smarter eco-cities,an emerging paradigm of urbanism characterized by the seamless integration of advanced technologies and environmental strategies.However,there remains a significant gap in thoroughly understanding this new paradigm and the intricate spectrum of its multifaceted underlying dimensions.To bridge this gap,this study provides a comprehensive systematic review of the burgeoning landscape of smarter eco-cities and their leadingedge AI and AIoT solutions for environmental sustainability.To ensure thoroughness,the study employs a unified evidence synthesis framework integrating aggregative,configurative,and narrative synthesis approaches.At the core of this study lie these subsequent research inquiries:What are the foundational underpinnings of emerging smarter eco-cities,and how do they intricately interrelate,particularly urbanism paradigms,environmental solutions,and data-driven technologies?What are the key drivers and enablers propelling the materialization of smarter eco-cities?What are the primary AI and AIoT solutions that can be harnessed in the development of smarter eco-cities?In what ways do AI and AIoT technologies contribute to fostering environmental sustainability practices,and what potential benefits and opportunities do they offer for smarter eco-cities?What challenges and barriers arise in the implementation of AI and AIoT solutions for the development of smarter eco-cities?The findings significantly deepen and broaden our understanding of both the significant potential of AI and AIoT technologies to enhance sustainable urban development practices,as well as the formidable nature of the challenges they pose.Beyond theoretical enrichment,these findings offer invaluable insights and new perspectives poised to empower policymakers,practitioners,and researchers to advance the integration of eco-urbanism and AI-and AIoT-driven urbanism.Through an insightful exploration of the contemporary urban landscape and the identification of successfully applied AI and AIoT solutions,stakeholders gain the necessary groundwork for making well-informed decisions,implementing effective strategies,and designing policies that prioritize environmental well-being.
基金supported in part by the National Natural Science Foundation of China under Grant U22B2005,Grant 62372462.
文摘The rapid expansion of artificial intelligence(AI)applications has raised significant concerns about user privacy,prompting the development of privacy-preserving machine learning(ML)paradigms such as federated learning(FL).FL enables the distributed training of ML models,keeping data on local devices and thus addressing the privacy concerns of users.However,challenges arise from the heterogeneous nature of mobile client devices,partial engagement of training,and non-independent identically distributed(non-IID)data distribution,leading to performance degradation and optimization objective bias in FL training.With the development of 5G/6G networks and the integration of cloud computing edge computing resources,globally distributed cloud computing resources can be effectively utilized to optimize the FL process.Through the specific parameters of the server through the selection mechanism,it does not increase the monetary cost and reduces the network latency overhead,but also balances the objectives of communication optimization and low engagement mitigation that cannot be achieved simultaneously in a single-server framework of existing works.In this paper,we propose the FedAdaSS algorithm,an adaptive parameter server selection mechanism designed to optimize the training efficiency in each round of FL training by selecting the most appropriate server as the parameter server.Our approach leverages the flexibility of cloud resource computing power,and allows organizers to strategically select servers for data broadcasting and aggregation,thus improving training performance while maintaining cost efficiency.The FedAdaSS algorithm estimates the utility of client systems and servers and incorporates an adaptive random reshuffling strategy that selects the optimal server in each round of the training process.Theoretical analysis confirms the convergence of FedAdaSS under strong convexity and L-smooth assumptions,and comparative experiments within the FLSim framework demonstrate a reduction in training round-to-accuracy by 12%–20%compared to the Federated Averaging(FedAvg)with random reshuffling method under unique server.Furthermore,FedAdaSS effectively mitigates performance loss caused by low client engagement,reducing the loss indicator by 50%.
基金in part by the Hubei Natural Science and Research Project under Grant 2020418in part by the 2021 Light of Taihu Science and Technology Projectin part by the 2022 Wuxi Science and Technology Innovation and Entrepreneurship Program.
文摘More devices in the Intelligent Internet of Things(AIoT)result in an increased number of tasks that require low latency and real-time responsiveness,leading to an increased demand for computational resources.Cloud computing’s low-latency performance issues in AIoT scenarios have led researchers to explore fog computing as a complementary extension.However,the effective allocation of resources for task execution within fog environments,characterized by limitations and heterogeneity in computational resources,remains a formidable challenge.To tackle this challenge,in this study,we integrate fog computing and cloud computing.We begin by establishing a fog-cloud environment framework,followed by the formulation of a mathematical model for task scheduling.Lastly,we introduce an enhanced hybrid Equilibrium Optimizer(EHEO)tailored for AIoT task scheduling.The overarching objective is to decrease both the makespan and energy consumption of the fog-cloud system while accounting for task deadlines.The proposed EHEO method undergoes a thorough evaluation against multiple benchmark algorithms,encompassing metrics likemakespan,total energy consumption,success rate,and average waiting time.Comprehensive experimental results unequivocally demonstrate the superior performance of EHEO across all assessed metrics.Notably,in the most favorable conditions,EHEO significantly diminishes both the makespan and energy consumption by approximately 50%and 35.5%,respectively,compared to the secondbest performing approach,which affirms its efficacy in advancing the efficiency of AIoT task scheduling within fog-cloud networks.
基金supported by the Science and Technology Project of the State Grid Corporation of China under Grant Number 5400202199541A-0-5-ZN。
文摘Power Line Communications-Artificial Intelligence of Things(PLC-AIo T)combines the low cost and high coverage of PLC with the learning ability of Artificial Intelligence(AI)to provide data collection and transmission capabilities for PLC-AIo T devices in smart parks.With the development of smart parks,their emerging services require secure and accurate time synchronization of PLC-AIo T devices.However,the impact of attackers on the accuracy of time synchronization cannot be ignored.To solve the aforementioned problems,we propose a tampering attack-aware Deep Q-Network(DQN)-based time synchronization algorithm.First,we construct an abnormal clock source detection model.Then,the abnormal clock source is detected and excluded by comparing the time synchronization information between the device and the gateway.Finally,the proposed algorithm realizes the joint guarantee of high accuracy and low delay for PLC-AIo T in smart parks by intelligently selecting the multi-clock source cooperation strategy and timing weights.Simulation results show that the proposed algorithm has better time synchronization delay and accuracy performance.
文摘The dynamic landscape of sustainable smart cities is witnessing a significant transformation due to the integration of emerging computational technologies and innovative models.These advancements are reshaping data-driven planning strategies,practices,and approaches,thereby facilitating the achievement of environmental sustainability goals.This transformative wave signals a fundamental shift d marked by the synergistic operation of artificial intelligence(AI),artificial intelligence of things(AIoT),and urban digital twin(UDT)technologies.While previous research has largely explored urban AI,urban AIoT,and UDT in isolation,a significant knowledge gap exists regarding their synergistic interplay,collaborative integration,and collective impact on data-driven environmental planning in the dynamic context of sustainable smart cities.To address this gap,this study conducts a comprehensive systematic review to uncover the intricate interactions among these interconnected technologies,models,and domains while elucidating the nuanced dynamics and untapped synergies in the complex ecosystem of sustainable smart cities.Central to this study are four guiding research questions:1.What theoretical and practical foundations underpin the convergence of AI,AIoT,UDT,data-driven planning,and environmental sustainability in sustainable smart cities,and how can these components be synthesized into a novel comprehensive framework?2.How does integrating AI and AIoT reshape the landscape of datadriven planning to improve the environmental performance of sustainable smart cities?3.How can AI and AIoT augment the capabilities of UDT to enhance data-driven environmental planning processes in sustainable smart cities?4.What challenges and barriers arise in integrating and implementing AI,AIoT,and UDT in data-driven environmental urban planning,and what strategies can be devised to surmount or mitigate them?Methodologically,this study involves a rigorous analysis and synthesis of studies published between January 2019 and December 2023,comprising an extensive body of literature totaling 185 studies.The findings of this study surpass mere interdisciplinary theoretical enrichment,offering valuable insights into the transformative potential of integrating AI,AIoT,and UDT technologies to advance sustainable urban development practices.By enhancing data-driven environmental planning processes,these integrated technologies and models offer innovative solutions to address complex environmental challenges.However,this endeavor is fraught with formidable challenges and complexities that require careful navigation and mitigation to achieve desired outcomes.This study serves as a comprehensive reference guide,spurring groundbreaking research endeavors,stimulating practical implementations,informing strategic initiatives,and shaping policy formulations in sustainable urban development.These insights have profound implications for researchers,practitioners,and policymakers,providing a roadmap for fostering resiliently designed,technologically advanced,and environmentally conscious urban environments.
基金supported by the National Natural Science Foundation of China(61871132,62171135)。
文摘To tackle the challenge of applying convolutional neural network(CNN)in field-programmable gate array(FPGA)due to its computational complexity,a high-performance CNN hardware accelerator based on Verilog hardware description language was designed,which utilizes a pipeline architecture with three parallel dimensions including input channels,output channels,and convolution kernels.Firstly,two multiply-and-accumulate(MAC)operations were packed into one digital signal processing(DSP)block of FPGA to double the computation rate of the CNN accelerator.Secondly,strategies of feature map block partitioning and special memory arrangement were proposed to optimize the total amount of off-chip access memory and reduce the pressure on FPGA bandwidth.Finally,an efficient computational array combining multiplicative-additive tree and Winograd fast convolution algorithm was designed to balance hardware resource consumption and computational performance.The high parallel CNN accelerator was deployed in ZU3 EG of Alinx,using the YOLOv3-tiny algorithm as the test object.The average computing performance of the CNN accelerator is 127.5 giga operations per second(GOPS).The experimental results show that the hardware architecture effectively improves the computational power of CNN and provides better performance compared with other existing schemes in terms of power consumption and the efficiency of DSPs and block random access memory(BRAMs).
基金supported by the National Key R&D Program of China(grant no.2020YFA0405700)the NationalNatural Science Foundation of China(grant no.51925503 to Y.H.and grant no.52375568 to F.Z.)+1 种基金the Tencent Foundation(XPLORER Prize to Y.H.)the Science and Technology Innovation Team of Hubei Province.
文摘Artificial intelligence of things systems equipped with flexible sensors can autonomously and intelligently detect the condition of the surroundings.However,current intelligent monitoring systems always rely on an external computer with the capability of machine learning rather than integrating it into the sensing device.The computer-assisted intelligent system is hampered by energy inefficiencies,privacy issues,and bandwidth restrictions.Here,a flexible,large-scale sensing array with the capability of low-power in-sensor intelligence based on a compression hypervector encoder is proposed for real-time recognition.The system with in-sensor intelligence can accommodate different individuals and learn new postures without additional computer processing.Both the communication bandwidth requirement and energy consumption of this system are significantly reduced by 1,024 and 500 times,respectively.The capability for in-sensor inference and learning eliminates the necessity to transmit raw data externally,thereby effectively addressing privacy concerns.Furthermore,the system possesses a rapid recognition speed(a few hundred milliseconds)and a high recognition accuracy(about 99%),comparing with support vector machine and other hyperdimensional computing methods.The research holds marked potential for applications in the integration of artificial intelligence of things and flexible electronics.
