个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性...个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性化联邦学习算法(Personalized Federated Learning Based on Sparsity Regularized Bi-level Optimization,pFedSRB),在客户端的个性化更新中引入l 1范数稀疏正则化,提升个性化模型的稀疏度,避免不必要的客户端参数更新,降低模型复杂度.将个性化联邦学习建模为双层优化问题,内层优化采用交替方向乘子法,可提高学习速度.在4个联邦学习基准数据集上的实验表明,pFedSRB在异构数据上表现出色,在提高模型性能的同时有效降低训练用时和空间成本.展开更多
Due to recent legislative incentives and a general change in the public eye towards environmental and energy issues, a renewed interest in building nuclear power plants has taken place in the U.S. The Nuclear Regulato...Due to recent legislative incentives and a general change in the public eye towards environmental and energy issues, a renewed interest in building nuclear power plants has taken place in the U.S. The Nuclear Regulatory Commission has also recently given approvals to build four nuclear reactors in two southeast states, which further indicates the resurging interest in nuclear power in the U.S. Such approvals, however, do not specifically address the impact on having a constrained labor force when manufacturing and constructing multiple reactors. Key findings include the comparison of a constrained and unconstrained workforce on construction and manufacturing completion times, the identification of peak labor requirements based on different construction schedules, and the development of training estimates to ensure the workforce and industry are prepared for the new jobs being created. Results suggest that a shorter planned construction timeline is effective when the workforce is moderately constrained to unconstrained. However, with a severely-constrained starting workforce, a longer construction timeline is preferred. For multiple reactor plans, spreading out the construction start dates outperforms all other construction start date schedules. In particular, heavily compressed start dates could effectively kill a resurgent nuclear industry, especially if workforce expansion is not pursued simultaneously.展开更多
BACKGROUND Oral cancer is the sixth most prevalent cancer worldwide.Public knowledge in oral cancer risk factors and survival is limited.AIM To come up with machine learning(ML)algorithms to predict the length of surv...BACKGROUND Oral cancer is the sixth most prevalent cancer worldwide.Public knowledge in oral cancer risk factors and survival is limited.AIM To come up with machine learning(ML)algorithms to predict the length of survival for individuals diagnosed with oral cancer,and to explore the most important factors that were responsible for shortening or lengthening oral cancer survival.METHODS We used the Surveillance,Epidemiology,and End Results database from the years 1975 to 2016 that consisted of a total of 257880 cases and 94 variables.Four ML techniques in the area of artificial intelligence were applied for model training and validation.Model accuracy was evaluated using mean absolute error(MAE),mean squared error(MSE),root mean squared error(RMSE),R2 and adjusted R2.RESULTS The most important factors predictive of oral cancer survival time were age at diagnosis,primary cancer site,tumor size and year of diagnosis.Year of diagnosis referred to the year when the tumor was first diagnosed,implying that individuals with tumors that were diagnosed in the modern era tend to have longer survival than those diagnosed in the past.The extreme gradient boosting ML algorithms showed the best performance,with the MAE equaled to 13.55,MSE 486.55 and RMSE 22.06.CONCLUSION Using artificial intelligence,we developed a tool that can be used for oral cancer survival prediction and for medical-decision making.The finding relating to the year of diagnosis represented an important new discovery in the literature.The results of this study have implications for cancer prevention and education for the public.展开更多
PRECISION HEALTH AND Digital.Me Continuous monitoring of high-value equipment,such as semiconductor production equipment and jet airplane engines,has become a standard practice across myriad commercial sectors.“Digit...PRECISION HEALTH AND Digital.Me Continuous monitoring of high-value equipment,such as semiconductor production equipment and jet airplane engines,has become a standard practice across myriad commercial sectors.“Digital twin”technologies enable such monitoring by providing sensor data for maintenance and other mission-critical operations in real time.While continuous monitoring has become standard in some industry,its application to monitoring healthy adults globally remains underexplored,with many individuals seeking medical care only when symptomatic.Insights gained from digital twin could be transferred to healthcare,revealing opportunities for more data-driven and personalized care.展开更多
Mobile Edge Computing(MEC)is one of the most promising techniques for next-generation wireless communication systems.In this paper,we study the problem of dynamic caching,computation offloading,and resource allocation...Mobile Edge Computing(MEC)is one of the most promising techniques for next-generation wireless communication systems.In this paper,we study the problem of dynamic caching,computation offloading,and resource allocation in cache-assisted multi-user MEC systems with stochastic task arrivals.There are multiple computationally intensive tasks in the system,and each Mobile User(MU)needs to execute a task either locally or remotely in one or more MEC servers by offloading the task data.Popular tasks can be cached in MEC servers to avoid duplicates in offloading.The cached contents can be either obtained through user offloading,fetched from a remote cloud,or fetched from another MEC server.The objective is to minimize the long-term average of a cost function,which is defined as a weighted sum of energy consumption,delay,and cache contents’fetching costs.The weighting coefficients associated with the different metrics in the objective function can be adjusted to balance the tradeoff among them.The optimum design is performed with respect to four decision parameters:whether to cache a given task,whether to offload a given uncached task,how much transmission power should be used during offloading,and how much MEC resources to be allocated for executing a task.We propose to solve the problems by developing a dynamic scheduling policy based on Deep Reinforcement Learning(DRL)with the Deep Deterministic Policy Gradient(DDPG)method.A new decentralized DDPG algorithm is developed to obtain the optimum designs for multi-cell MEC systems by leveraging on the cooperations among neighboring MEC servers.Simulation results demonstrate that the proposed algorithm outperforms other existing strategies,such as Deep Q-Network(DQN).展开更多
Blockchain implementation in agriculture has begun.Blockchain is recognized as an emerging technology in the agri-foods industry which may provide an efficient and robust mechanism for enhancing food traceability and ...Blockchain implementation in agriculture has begun.Blockchain is recognized as an emerging technology in the agri-foods industry which may provide an efficient and robust mechanism for enhancing food traceability and a transparent and reliable way to validate quality,safety,and sustainability,of agri-foods.However,the technology is in its nascency,therefore,this review was written to foster discussion and encourage the application of blockchain technology,especially in the agri-food industry.In this review,the working principle of blockchain for data recording and tracking is briefly described.The collaborationmodels for the current blockchain applications on agri-foods are summarized.Furthermore,the specific utilization of blockchain to enhance safety and quality of agri-foods is discussed in four aspects:enhance the data transparency,realize data traceability,improve the food safety and quality monitoring,and reduce the cost of financial transactions.A case study on aWalmart pork traceability system has been provided to demonstrate how blockchain may be used to enhance the food traceability.Finally,challenges and future trends of blockchain technology in agri-foods concerning data/cost management,data security,and data integration are discussed.Blockchain technology reveals a promising approach to foster a future of agri-foods system in a way that is safer,healthier,more sustainable,and reliable.展开更多
In fiber laser beam welding(LBW),the selection of optimal processing parameters is challenging and plays a key role in improving the bead geometry and welding quality.This study proposes a multi-objective optimization...In fiber laser beam welding(LBW),the selection of optimal processing parameters is challenging and plays a key role in improving the bead geometry and welding quality.This study proposes a multi-objective optimization framework by combining an ensemble of metamodels(EMs)with the multi-objective artificial bee colony algorithm(MOABC)to identify the optimal welding parameters.An inverse proportional weighting method that considers the leave-one-out prediction error is presented to construct EM,which incorporates the competitive strengths of three metamodels.EM constructs the correlation between processing parameters(laser power,welding speed,and distance defocus)and bead geometries(bead width,depth of penetration,neck width,and neck depth)with average errors of 10.95%,7.04%,7.63%,and 8.62%,respectively.On the basis of EM,MOABC is employed to approximate the Pareto front,and verification experiments show that the relative errors are less than 14.67%.Furthermore,the main effect and the interaction effect of processing parameters on bead geometries are studied.Results demonstrate that the proposed EM-MOABC is effective in guiding actual fiber LBW applications.展开更多
文摘个性化联邦学习侧重于为各客户端提供个性化模型,旨在提高对异构数据的处理性能,然而现有的个性化联邦学习算法大多以增加客户端参数量为代价提高个性化模型的性能,使计算变得复杂.为了解决此问题,文中提出基于稀疏正则双层优化的个性化联邦学习算法(Personalized Federated Learning Based on Sparsity Regularized Bi-level Optimization,pFedSRB),在客户端的个性化更新中引入l 1范数稀疏正则化,提升个性化模型的稀疏度,避免不必要的客户端参数更新,降低模型复杂度.将个性化联邦学习建模为双层优化问题,内层优化采用交替方向乘子法,可提高学习速度.在4个联邦学习基准数据集上的实验表明,pFedSRB在异构数据上表现出色,在提高模型性能的同时有效降低训练用时和空间成本.
文摘Due to recent legislative incentives and a general change in the public eye towards environmental and energy issues, a renewed interest in building nuclear power plants has taken place in the U.S. The Nuclear Regulatory Commission has also recently given approvals to build four nuclear reactors in two southeast states, which further indicates the resurging interest in nuclear power in the U.S. Such approvals, however, do not specifically address the impact on having a constrained labor force when manufacturing and constructing multiple reactors. Key findings include the comparison of a constrained and unconstrained workforce on construction and manufacturing completion times, the identification of peak labor requirements based on different construction schedules, and the development of training estimates to ensure the workforce and industry are prepared for the new jobs being created. Results suggest that a shorter planned construction timeline is effective when the workforce is moderately constrained to unconstrained. However, with a severely-constrained starting workforce, a longer construction timeline is preferred. For multiple reactor plans, spreading out the construction start dates outperforms all other construction start date schedules. In particular, heavily compressed start dates could effectively kill a resurgent nuclear industry, especially if workforce expansion is not pursued simultaneously.
基金The authors sincerely thank the Clinical Outcomes Research and Education at Collegeof Dental Medicine, Roseman University of Health Sciences for supporting this study.
文摘BACKGROUND Oral cancer is the sixth most prevalent cancer worldwide.Public knowledge in oral cancer risk factors and survival is limited.AIM To come up with machine learning(ML)algorithms to predict the length of survival for individuals diagnosed with oral cancer,and to explore the most important factors that were responsible for shortening or lengthening oral cancer survival.METHODS We used the Surveillance,Epidemiology,and End Results database from the years 1975 to 2016 that consisted of a total of 257880 cases and 94 variables.Four ML techniques in the area of artificial intelligence were applied for model training and validation.Model accuracy was evaluated using mean absolute error(MAE),mean squared error(MSE),root mean squared error(RMSE),R2 and adjusted R2.RESULTS The most important factors predictive of oral cancer survival time were age at diagnosis,primary cancer site,tumor size and year of diagnosis.Year of diagnosis referred to the year when the tumor was first diagnosed,implying that individuals with tumors that were diagnosed in the modern era tend to have longer survival than those diagnosed in the past.The extreme gradient boosting ML algorithms showed the best performance,with the MAE equaled to 13.55,MSE 486.55 and RMSE 22.06.CONCLUSION Using artificial intelligence,we developed a tool that can be used for oral cancer survival prediction and for medical-decision making.The finding relating to the year of diagnosis represented an important new discovery in the literature.The results of this study have implications for cancer prevention and education for the public.
基金supported by the Stanford Maternal and Child Health Research Institute through the Stanford Medicine Children’s Health Center for IBD(Inflammatory Bowel Disease)and Celiac Disease and the Stanford Center at the Incheon Global Campus(SCIGC).
文摘PRECISION HEALTH AND Digital.Me Continuous monitoring of high-value equipment,such as semiconductor production equipment and jet airplane engines,has become a standard practice across myriad commercial sectors.“Digital twin”technologies enable such monitoring by providing sensor data for maintenance and other mission-critical operations in real time.While continuous monitoring has become standard in some industry,its application to monitoring healthy adults globally remains underexplored,with many individuals seeking medical care only when symptomatic.Insights gained from digital twin could be transferred to healthcare,revealing opportunities for more data-driven and personalized care.
文摘Mobile Edge Computing(MEC)is one of the most promising techniques for next-generation wireless communication systems.In this paper,we study the problem of dynamic caching,computation offloading,and resource allocation in cache-assisted multi-user MEC systems with stochastic task arrivals.There are multiple computationally intensive tasks in the system,and each Mobile User(MU)needs to execute a task either locally or remotely in one or more MEC servers by offloading the task data.Popular tasks can be cached in MEC servers to avoid duplicates in offloading.The cached contents can be either obtained through user offloading,fetched from a remote cloud,or fetched from another MEC server.The objective is to minimize the long-term average of a cost function,which is defined as a weighted sum of energy consumption,delay,and cache contents’fetching costs.The weighting coefficients associated with the different metrics in the objective function can be adjusted to balance the tradeoff among them.The optimum design is performed with respect to four decision parameters:whether to cache a given task,whether to offload a given uncached task,how much transmission power should be used during offloading,and how much MEC resources to be allocated for executing a task.We propose to solve the problems by developing a dynamic scheduling policy based on Deep Reinforcement Learning(DRL)with the Deep Deterministic Policy Gradient(DDPG)method.A new decentralized DDPG algorithm is developed to obtain the optimum designs for multi-cell MEC systems by leveraging on the cooperations among neighboring MEC servers.Simulation results demonstrate that the proposed algorithm outperforms other existing strategies,such as Deep Q-Network(DQN).
文摘Blockchain implementation in agriculture has begun.Blockchain is recognized as an emerging technology in the agri-foods industry which may provide an efficient and robust mechanism for enhancing food traceability and a transparent and reliable way to validate quality,safety,and sustainability,of agri-foods.However,the technology is in its nascency,therefore,this review was written to foster discussion and encourage the application of blockchain technology,especially in the agri-food industry.In this review,the working principle of blockchain for data recording and tracking is briefly described.The collaborationmodels for the current blockchain applications on agri-foods are summarized.Furthermore,the specific utilization of blockchain to enhance safety and quality of agri-foods is discussed in four aspects:enhance the data transparency,realize data traceability,improve the food safety and quality monitoring,and reduce the cost of financial transactions.A case study on aWalmart pork traceability system has been provided to demonstrate how blockchain may be used to enhance the food traceability.Finally,challenges and future trends of blockchain technology in agri-foods concerning data/cost management,data security,and data integration are discussed.Blockchain technology reveals a promising approach to foster a future of agri-foods system in a way that is safer,healthier,more sustainable,and reliable.
基金supported by the Project of International Cooperation and Exchanges NSFC(Grant No.51861165202)the National Natural Science Foundation of China(Grant Nos.51575211,51705263,51805330)the 111 Project of China(Grant No.B16019).
文摘In fiber laser beam welding(LBW),the selection of optimal processing parameters is challenging and plays a key role in improving the bead geometry and welding quality.This study proposes a multi-objective optimization framework by combining an ensemble of metamodels(EMs)with the multi-objective artificial bee colony algorithm(MOABC)to identify the optimal welding parameters.An inverse proportional weighting method that considers the leave-one-out prediction error is presented to construct EM,which incorporates the competitive strengths of three metamodels.EM constructs the correlation between processing parameters(laser power,welding speed,and distance defocus)and bead geometries(bead width,depth of penetration,neck width,and neck depth)with average errors of 10.95%,7.04%,7.63%,and 8.62%,respectively.On the basis of EM,MOABC is employed to approximate the Pareto front,and verification experiments show that the relative errors are less than 14.67%.Furthermore,the main effect and the interaction effect of processing parameters on bead geometries are studied.Results demonstrate that the proposed EM-MOABC is effective in guiding actual fiber LBW applications.
