To provide diversified services in the intelligent transportation systems,smart vehicles will generate unprecedented amounts of data every day.Due to data security and user privacy issues,Federated Learning(FL)is cons...To provide diversified services in the intelligent transportation systems,smart vehicles will generate unprecedented amounts of data every day.Due to data security and user privacy issues,Federated Learning(FL)is considered a potential solution to ensure privacy-preserving in data sharing.However,there are still many challenges to applying the traditional synchronous FL directly in the Internet of Vehicles(Io V),such as unreliable communications and malicious attacks.In this paper,we propose a Directed Acyclic Graph(DAG)based Swarm Learning(DSL),which integrates edge computing,FL,and blockchain technologies to provide secure data sharing and model training in Io Vs.To deal with the high mobility of vehicles,the dynamic vehicle association algorithm is introduced,which could optimize the connections between vehicles and road side units to improve the training efficiency.Moreover,to enhance the anti-attack property of the DSL algorithm,a malicious attack detection method is adopted,which could recognize malicious vehicles by the site confirmation rate.Furthermore,an accuracy-based reward mechanism is developed to promote vehicles to participate in the model training with honest behaviors.Finally,simulation results demonstrate that the proposed DSL algorithm could achieve better performance in terms of model accuracy,convergence rates and security compared with existing algorithms.展开更多
Although Federated Deep Learning(FDL)enables distributed machine learning in the Internet of Vehicles(IoV),it requires multiple clients to upload model parameters,thus still existing unavoidable communication overhead...Although Federated Deep Learning(FDL)enables distributed machine learning in the Internet of Vehicles(IoV),it requires multiple clients to upload model parameters,thus still existing unavoidable communication overhead and data privacy risks.The recently proposed Swarm Learning(SL)provides a decentralized machine learning approach for unit edge computing and blockchain-based coordination.A Swarm-Federated Deep Learning framework in the IoV system(IoV-SFDL)that integrates SL into the FDL framework is proposed in this paper.The IoV-SFDL organizes vehicles to generate local SL models with adjacent vehicles based on the blockchain empowered SL,then aggregates the global FDL model among different SL groups with a credibility weights prediction algorithm.Extensive experimental results show that compared with the baseline frameworks,the proposed IoV-SFDL framework reduces the overhead of client-to-server communication by 16.72%,while the model performance improves by about 5.02%for the same training iterations.展开更多
Engine data management is of great significance for ensuring data security and sharing,as well as facilitating multi-party collaborative learning.Traditional data management approaches often involve decentralized data...Engine data management is of great significance for ensuring data security and sharing,as well as facilitating multi-party collaborative learning.Traditional data management approaches often involve decentralized data storage that is vulnerable to tampering,making it challenging to conduct multi-party collaborative learning under privacy protection conditions and fully leverage the value of data.Moreover,data with compromised integrity can lead to incorrect results if used for model training.Therefore,this paper aims to break down data sharing barriers and fully utilize decentralized data for multi-party collaborative learning under privacy protection conditions.We propose a trustworthy engine data management method based on blockchain technology to ensure data immutability and non-repudiation.To address the issue of limited data samples for some users resulting in poor model performance,we introduce swarm learning techniques based on centralized machine learning and design a trustworthy data management method for swarm learning,achieving trustworthy regulation of the entire process.We conduct research on engine models under swarm learning based on the NASA open dataset,effectively organizing decentralized data samples for collaborative training while ensuring data privacy and fully leveraging the value of data.展开更多
Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero....Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero.As a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec separately.Nevertheless,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables Mask.However,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is optimized.In data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between data.Inspired by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these SLMOPs.TELSO mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast convergence.Experi-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.展开更多
To maximize the power density of the electric propulsion motor in aerospace application,this paper proposes a novel Dynamic Neighborhood Genetic Learning Particle Swarm Optimization(DNGL-PSO)for the motor design,which...To maximize the power density of the electric propulsion motor in aerospace application,this paper proposes a novel Dynamic Neighborhood Genetic Learning Particle Swarm Optimization(DNGL-PSO)for the motor design,which can deal with the insufficient population diversity and non-global optimal solution issues.The DNGL-PSO framework is composed of the dynamic neighborhood module and the particle update module.To improve the population diversity,the dynamic neighborhood strategy is first proposed,which combines the local neighborhood exemplar generation mechanism and the shuffling mechanism.The local neighborhood exemplar generation mechanism enlarges the search range of the algorithm in the solution space,thus obtaining highquality exemplars.Meanwhile,when the global optimal solution cannot update its fitness value,the shuffling mechanism module is triggered to dynamically change the local neighborhood members.The roulette wheel selection operator is introduced into the shuffling mechanism to ensure that particles with larger fitness value are selected with a higher probability and remain in the local neighborhood.Then,the global learning based particle update approach is proposed,which can achieve a good balance between the expansion of the search range in the early stage and the acceleration of local convergence in the later stage.Finally,the optimization design of the electric propulsion motor is conducted to verify the effectiveness of the proposed DNGL-PSO.The simulation results show that the proposed DNGL-PSO has excellent adaptability,optimization efficiency and global optimization capability,while the optimized electric propulsion motor has a high power density of 5.207 kW/kg with the efficiency of 96.12%.展开更多
Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swa...Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swarm optimization (PSO) algorithm is presented. Firstly, an improved version of the original PSO, cooperative random learning particle swarm optimization (CRPSO), is put forward to enhance the performance of the conventional PSO. Secondly, the way of finding PID coefficient will be studied by using this algorithm. Finally, the experimental results and practical works demonstrate that the CRPSO-PID controller achieves a good performance.展开更多
1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves ...1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves privacy,enhances responsiveness,and saves bandwidth.However,current ondevice DL relies on predefined patterns,leading to accuracy and efficiency bottlenecks.It is difficult to provide feedback on data processing performance during the data acquisition stage,as processing typically occurs after data acquisition.展开更多
Purpose–The purpose of this paper is to propose distributed learning-based three different metaheuristic algorithms for the identification of nonlinear systems.The proposed algorithms are experimented in this study t...Purpose–The purpose of this paper is to propose distributed learning-based three different metaheuristic algorithms for the identification of nonlinear systems.The proposed algorithms are experimented in this study to address problems for which input data are available at different geographic locations.In addition,the models are tested for nonlinear systems with different noise conditions.In a nutshell,the suggested model aims to handle voluminous data with low communication overhead compared to traditional centralized processing methodologies.Design/methodology/approach–Population-based evolutionary algorithms such as genetic algorithm(GA),particle swarm optimization(PSO)and cat swarm optimization(CSO)are implemented in a distributed form to address the system identification problem having distributed input data.Out of different distributed approaches mentioned in the literature,the study has considered incremental and diffusion strategies.Findings–Performances of the proposed distributed learning-based algorithms are compared for different noise conditions.The experimental results indicate that CSO performs better compared to GA and PSO at all noise strengths with respect to accuracy and error convergence rate,but incremental CSO is slightly superior to diffusion CSO.Originality/value–This paper employs evolutionary algorithms using distributed learning strategies and applies these algorithms for the identification of unknown systems.Very few existing studies have been reported in which these distributed learning strategies are experimented for the parameter estimation task.展开更多
To solve the data island problem,federated learning(FL)provides a solution paradigm where each client sends the model parameters but not the data to a server for model aggregation.Peer-to-peer(P2P)federated learning f...To solve the data island problem,federated learning(FL)provides a solution paradigm where each client sends the model parameters but not the data to a server for model aggregation.Peer-to-peer(P2P)federated learning further improves the robustness of the system,in which there is no server and each client communicates directly with the other.For secure aggregation,secure multi-party computing(SMPC)protocols have been utilized in peer-to-peer manner.However,the ideal SMPC protocols could fail when some clients drop out.In this paper,we propose a robust peer-to-peer learning(RP2PL)algorithm via SMPC to resist clients dropping out.We improve the segmentbased SMPC protocol by adding a check and designing the generation method of random segments.In RP2PL,each client aggregates their models by the improved robust secure multi-part computation protocol when finishes the local training.Experimental results demonstrate that the RP2PL paradigm can mitigate clients dropping out with no significant degradation in performance.展开更多
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 62371082,61831002,and 62001076in part by the Natural Science Foundation of Chongqing under Grant CSTB2023NSCQ-MSX0726 and cstc2020jcyj-msxmX0878。
文摘To provide diversified services in the intelligent transportation systems,smart vehicles will generate unprecedented amounts of data every day.Due to data security and user privacy issues,Federated Learning(FL)is considered a potential solution to ensure privacy-preserving in data sharing.However,there are still many challenges to applying the traditional synchronous FL directly in the Internet of Vehicles(Io V),such as unreliable communications and malicious attacks.In this paper,we propose a Directed Acyclic Graph(DAG)based Swarm Learning(DSL),which integrates edge computing,FL,and blockchain technologies to provide secure data sharing and model training in Io Vs.To deal with the high mobility of vehicles,the dynamic vehicle association algorithm is introduced,which could optimize the connections between vehicles and road side units to improve the training efficiency.Moreover,to enhance the anti-attack property of the DSL algorithm,a malicious attack detection method is adopted,which could recognize malicious vehicles by the site confirmation rate.Furthermore,an accuracy-based reward mechanism is developed to promote vehicles to participate in the model training with honest behaviors.Finally,simulation results demonstrate that the proposed DSL algorithm could achieve better performance in terms of model accuracy,convergence rates and security compared with existing algorithms.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant 62071179.
文摘Although Federated Deep Learning(FDL)enables distributed machine learning in the Internet of Vehicles(IoV),it requires multiple clients to upload model parameters,thus still existing unavoidable communication overhead and data privacy risks.The recently proposed Swarm Learning(SL)provides a decentralized machine learning approach for unit edge computing and blockchain-based coordination.A Swarm-Federated Deep Learning framework in the IoV system(IoV-SFDL)that integrates SL into the FDL framework is proposed in this paper.The IoV-SFDL organizes vehicles to generate local SL models with adjacent vehicles based on the blockchain empowered SL,then aggregates the global FDL model among different SL groups with a credibility weights prediction algorithm.Extensive experimental results show that compared with the baseline frameworks,the proposed IoV-SFDL framework reduces the overhead of client-to-server communication by 16.72%,while the model performance improves by about 5.02%for the same training iterations.
文摘Engine data management is of great significance for ensuring data security and sharing,as well as facilitating multi-party collaborative learning.Traditional data management approaches often involve decentralized data storage that is vulnerable to tampering,making it challenging to conduct multi-party collaborative learning under privacy protection conditions and fully leverage the value of data.Moreover,data with compromised integrity can lead to incorrect results if used for model training.Therefore,this paper aims to break down data sharing barriers and fully utilize decentralized data for multi-party collaborative learning under privacy protection conditions.We propose a trustworthy engine data management method based on blockchain technology to ensure data immutability and non-repudiation.To address the issue of limited data samples for some users resulting in poor model performance,we introduce swarm learning techniques based on centralized machine learning and design a trustworthy data management method for swarm learning,achieving trustworthy regulation of the entire process.We conduct research on engine models under swarm learning based on the NASA open dataset,effectively organizing decentralized data samples for collaborative training while ensuring data privacy and fully leveraging the value of data.
基金supported by the Scientific Research Project of Xiang Jiang Lab(22XJ02003)the University Fundamental Research Fund(23-ZZCX-JDZ-28)+5 种基金the National Science Fund for Outstanding Young Scholars(62122093)the National Natural Science Foundation of China(72071205)the Hunan Graduate Research Innovation Project(ZC23112101-10)the Hunan Natural Science Foundation Regional Joint Project(2023JJ50490)the Science and Technology Project for Young and Middle-aged Talents of Hunan(2023TJ-Z03)the Science and Technology Innovation Program of Humnan Province(2023RC1002)。
文摘Traditional large-scale multi-objective optimization algorithms(LSMOEAs)encounter difficulties when dealing with sparse large-scale multi-objective optimization problems(SLM-OPs)where most decision variables are zero.As a result,many algorithms use a two-layer encoding approach to optimize binary variable Mask and real variable Dec separately.Nevertheless,existing optimizers often focus on locating non-zero variable posi-tions to optimize the binary variables Mask.However,approxi-mating the sparse distribution of real Pareto optimal solutions does not necessarily mean that the objective function is optimized.In data mining,it is common to mine frequent itemsets appear-ing together in a dataset to reveal the correlation between data.Inspired by this,we propose a novel two-layer encoding learning swarm optimizer based on frequent itemsets(TELSO)to address these SLMOPs.TELSO mined the frequent terms of multiple particles with better target values to find mask combinations that can obtain better objective values for fast convergence.Experi-mental results on five real-world problems and eight benchmark sets demonstrate that TELSO outperforms existing state-of-the-art sparse large-scale multi-objective evolutionary algorithms(SLMOEAs)in terms of performance and convergence speed.
基金supported by the National Natural Science Foundation of China(No.:52177028)Aeronautical Science Foundation of China(No.201907051002)+1 种基金the Fundamental Research Funds for the Central Universities,China(No.YWF21BJJ522)the Major Program of the National Natural Science Foundation of China(No.51890882).
文摘To maximize the power density of the electric propulsion motor in aerospace application,this paper proposes a novel Dynamic Neighborhood Genetic Learning Particle Swarm Optimization(DNGL-PSO)for the motor design,which can deal with the insufficient population diversity and non-global optimal solution issues.The DNGL-PSO framework is composed of the dynamic neighborhood module and the particle update module.To improve the population diversity,the dynamic neighborhood strategy is first proposed,which combines the local neighborhood exemplar generation mechanism and the shuffling mechanism.The local neighborhood exemplar generation mechanism enlarges the search range of the algorithm in the solution space,thus obtaining highquality exemplars.Meanwhile,when the global optimal solution cannot update its fitness value,the shuffling mechanism module is triggered to dynamically change the local neighborhood members.The roulette wheel selection operator is introduced into the shuffling mechanism to ensure that particles with larger fitness value are selected with a higher probability and remain in the local neighborhood.Then,the global learning based particle update approach is proposed,which can achieve a good balance between the expansion of the search range in the early stage and the acceleration of local convergence in the later stage.Finally,the optimization design of the electric propulsion motor is conducted to verify the effectiveness of the proposed DNGL-PSO.The simulation results show that the proposed DNGL-PSO has excellent adaptability,optimization efficiency and global optimization capability,while the optimized electric propulsion motor has a high power density of 5.207 kW/kg with the efficiency of 96.12%.
基金the National Basic Research Program (973) of China (No. 2004CB720703)
文摘Cryogenic ground support equipment (CGSE) is an important part of a famous particle physics experiment - AMS-02. In this paper a design method which optimizes PID parameters of CGSE control system via the particle swarm optimization (PSO) algorithm is presented. Firstly, an improved version of the original PSO, cooperative random learning particle swarm optimization (CRPSO), is put forward to enhance the performance of the conventional PSO. Secondly, the way of finding PID coefficient will be studied by using this algorithm. Finally, the experimental results and practical works demonstrate that the CRPSO-PID controller achieves a good performance.
基金supported by the National Science Fund for Distinguished Young Scholars(62025205)the National Natural Science Foundation of China(Grant Nos.62032020,62102317)CityU APRC Grant(9610633).
文摘1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves privacy,enhances responsiveness,and saves bandwidth.However,current ondevice DL relies on predefined patterns,leading to accuracy and efficiency bottlenecks.It is difficult to provide feedback on data processing performance during the data acquisition stage,as processing typically occurs after data acquisition.
文摘Purpose–The purpose of this paper is to propose distributed learning-based three different metaheuristic algorithms for the identification of nonlinear systems.The proposed algorithms are experimented in this study to address problems for which input data are available at different geographic locations.In addition,the models are tested for nonlinear systems with different noise conditions.In a nutshell,the suggested model aims to handle voluminous data with low communication overhead compared to traditional centralized processing methodologies.Design/methodology/approach–Population-based evolutionary algorithms such as genetic algorithm(GA),particle swarm optimization(PSO)and cat swarm optimization(CSO)are implemented in a distributed form to address the system identification problem having distributed input data.Out of different distributed approaches mentioned in the literature,the study has considered incremental and diffusion strategies.Findings–Performances of the proposed distributed learning-based algorithms are compared for different noise conditions.The experimental results indicate that CSO performs better compared to GA and PSO at all noise strengths with respect to accuracy and error convergence rate,but incremental CSO is slightly superior to diffusion CSO.Originality/value–This paper employs evolutionary algorithms using distributed learning strategies and applies these algorithms for the identification of unknown systems.Very few existing studies have been reported in which these distributed learning strategies are experimented for the parameter estimation task.
基金supported by the National Key R&D Program of China(2022YFB3102100)Shenzhen Fundamental Research Program(JCYJ20220818102414030)+2 种基金the Major Key Project of PCL(PCL2022A03)Shenzhen Science and Technology Program(ZDSYS20210623091809029)Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies(2022B1212010005).
文摘To solve the data island problem,federated learning(FL)provides a solution paradigm where each client sends the model parameters but not the data to a server for model aggregation.Peer-to-peer(P2P)federated learning further improves the robustness of the system,in which there is no server and each client communicates directly with the other.For secure aggregation,secure multi-party computing(SMPC)protocols have been utilized in peer-to-peer manner.However,the ideal SMPC protocols could fail when some clients drop out.In this paper,we propose a robust peer-to-peer learning(RP2PL)algorithm via SMPC to resist clients dropping out.We improve the segmentbased SMPC protocol by adding a check and designing the generation method of random segments.In RP2PL,each client aggregates their models by the improved robust secure multi-part computation protocol when finishes the local training.Experimental results demonstrate that the RP2PL paradigm can mitigate clients dropping out with no significant degradation in performance.
