In recent years,intelligent data-driven prognostic methods have been successfully developed,and good machinery health assessment performance has been achieved through explorations of data from multiple sensors.However...In recent years,intelligent data-driven prognostic methods have been successfully developed,and good machinery health assessment performance has been achieved through explorations of data from multiple sensors.However,existing datafusion prognostic approaches generally rely on the data availability of all sensors,and are vulnerable to potential sensor malfunctions,which are likely to occur in real industries especially for machines in harsh operating environments.In this paper,a deep learning-based remaining useful life(RUL)prediction method is proposed to address the sensor malfunction problem.A global feature extraction scheme is adopted to fully exploit information of different sensors.Adversarial learning is further introduced to extract generalized sensor-invariant features.Through explorations of both global and shared features,promising and robust RUL prediction performance can be achieved by the proposed method in the testing scenarios with sensor malfunctions.The experimental results suggest the proposed approach is well suited for real industrial applications.展开更多
In wireless networks current standard MAC layer protocols don’t provide any error correction scheme for broadcast/multicast. In this paper, we enhance a Leader Based Protocol (LBP) and propose a Beacon-driven Leader ...In wireless networks current standard MAC layer protocols don’t provide any error correction scheme for broadcast/multicast. In this paper, we enhance a Leader Based Protocol (LBP) and propose a Beacon-driven Leader Based Protocol (BLBP) for the MAC layer multicast error control. To guarantee a very low Packet Loss Ratio (PLR) under strict delay constraints for video multicast over a Gilbert-Elliott (GE) channel, we analyze BLBP and compare it with LBP and different application layer multicast error control schemes via simulation experiments. Both the theoretical analysis and simulation results show that BLBP can correct nearly all the errors for all receivers in the MAC layer and is more efficient than LBP. BLBP is also more efficient than the application layer Automatic Repeat request (ARQ) scheme and the total multicast delay is much shorter. BLBP is very good for real-time multicast applications with strict delay constraints.展开更多
Desertification process as a great problem affects most of the countries in the world. This process has a high rate in arid and semiarid areas. Today, human societies are en- countering the desertification phenomenon ...Desertification process as a great problem affects most of the countries in the world. This process has a high rate in arid and semiarid areas. Today, human societies are en- countering the desertification phenomenon as a serious problem which causes various ir- reparable damages to economic and social sectors. In order to assess desertification results in production of different regional models for their application in another region the indices should be re-investigated and adjusted to local conditions. Several models have been de- veloped for desertification evaluation. The present study, attempts to assess quantitatively the desertification process has in an area located at Sistan plain of Iran （Niatak region as a case study） by using Modified MEDALUS method. The obtained results indicated that of the whole studied region （comprising 4819.6 acres）, 2651.56 acres （55%） are located in medium de- sertification intensity class, 1269.48 acres （26.34%） are positioned in severe desertification intensity class, and 898.54 acres （18.64%） are placed in vary severe desertification intensity class.展开更多
This study presents a comprehensive analysis of the current energy landscape and the imperative transition toward renewable energy.It begins with an overview of current energy sources and trends,highlighting the dispa...This study presents a comprehensive analysis of the current energy landscape and the imperative transition toward renewable energy.It begins with an overview of current energy sources and trends,highlighting the disparity between supply and increasing demand.Adverse impacts of reliance on fossil fuels such as environmental degradation,economic volatility,and health hazards underscore the urgent need for a transition.The study then explores the vast potential of renewable energy sources(RES)such as solar,wind,hydrogen,and hydro,emphasizing their feasibility in the Southern African context.The positive impacts of integrating renewables are examined,including reduced greenhouse gas emissions,enhanced energy security,and economic diversification.Through case studies of regional examples,the success and failures of transitioning efforts are analyzed,providing valuable insights into best practices and pitfalls.The study identifies significant challenges in transitioning,particularly in grid-tied and off-grid scenarios,and discusses infrastructural,financial,and regulatory obstacles.The recommendations section outlines strategic steps for achieving a feasible transition,proposing either a full transition or specific percentages of renewable energy integration to meet energy demands.In conclusion,the study emphasizes the critical importance of adopting these strategies for sustainable development and global climate goals,advocating for continuous innovation and localized solutions to maximize the benefits of renewable energy.Key findings are that the environmental and economic effects of fossil fuel usage strain economies by increasing fossil fuel subsidies.RES are abundant in the Southern African region,and some projects have already been successfully implemented,especially in South Africa.Economic growth and technological advancement are some of the benefits of fully transitioning to renewables,but lack of skilled labor,infrastructure,necessary technology,and most importantly,high capital requirements,etc.,are some challenges being faced.Hence,the need for regional cooperation,policy frameworks,and infrastructure enhancement,and investment mobilization for an accelerated transition.展开更多
Since years, online social networks have evolved from profile and communication websites to online portals where people interact with each other, share and consume multimedia-enriched data and play different types of ...Since years, online social networks have evolved from profile and communication websites to online portals where people interact with each other, share and consume multimedia-enriched data and play different types of games. Due to the immense popularity of these online games and their huge revenue potential, the number of these games increases every day, resulting in a current offering of thousands of online social games. In this paper, the applicability of neighborhood-based collaborative filtering （CF） algorithms for the recommendation of online social games is evaluated. This evaluation is based on a large dataset of an online social gaming platform containing game ratings （explicit data） and online gaming behavior （implicit data） of millions of active users. Several similarity metrics were implemented and evaluated on the explicit data, implicit data and a combination thereof. It is shown that the neighborhood-based CF algorithms greatly outperform the content-based algorithm, currently often used on online social gaming websites. The reslflts also show that a combined approach, fie, taking into account both implicit and explicit data at the same time, yields overall good results on all evaluation metrics for all scenarios, while only slightly performing worse compared to the strengths of the explicit or implicit only approaches. The best performing algorithms have been implemented in a live setup of the online game platform.展开更多
Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private ...Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central server.Unlike most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model training.Our primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained budget.To this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL system.Based on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)problem.Next,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple subproblems.Finally,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected clients.In addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.展开更多
基金supported by the National Science Fund for Distinguished Young Scholars of China(52025056)Fundamental Research Funds for the Central Universities(xzy012022062)。
文摘In recent years,intelligent data-driven prognostic methods have been successfully developed,and good machinery health assessment performance has been achieved through explorations of data from multiple sensors.However,existing datafusion prognostic approaches generally rely on the data availability of all sensors,and are vulnerable to potential sensor malfunctions,which are likely to occur in real industries especially for machines in harsh operating environments.In this paper,a deep learning-based remaining useful life(RUL)prediction method is proposed to address the sensor malfunction problem.A global feature extraction scheme is adopted to fully exploit information of different sensors.Adversarial learning is further introduced to extract generalized sensor-invariant features.Through explorations of both global and shared features,promising and robust RUL prediction performance can be achieved by the proposed method in the testing scenarios with sensor malfunctions.The experimental results suggest the proposed approach is well suited for real industrial applications.
文摘In wireless networks current standard MAC layer protocols don’t provide any error correction scheme for broadcast/multicast. In this paper, we enhance a Leader Based Protocol (LBP) and propose a Beacon-driven Leader Based Protocol (BLBP) for the MAC layer multicast error control. To guarantee a very low Packet Loss Ratio (PLR) under strict delay constraints for video multicast over a Gilbert-Elliott (GE) channel, we analyze BLBP and compare it with LBP and different application layer multicast error control schemes via simulation experiments. Both the theoretical analysis and simulation results show that BLBP can correct nearly all the errors for all receivers in the MAC layer and is more efficient than LBP. BLBP is also more efficient than the application layer Automatic Repeat request (ARQ) scheme and the total multicast delay is much shorter. BLBP is very good for real-time multicast applications with strict delay constraints.
文摘Desertification process as a great problem affects most of the countries in the world. This process has a high rate in arid and semiarid areas. Today, human societies are en- countering the desertification phenomenon as a serious problem which causes various ir- reparable damages to economic and social sectors. In order to assess desertification results in production of different regional models for their application in another region the indices should be re-investigated and adjusted to local conditions. Several models have been de- veloped for desertification evaluation. The present study, attempts to assess quantitatively the desertification process has in an area located at Sistan plain of Iran （Niatak region as a case study） by using Modified MEDALUS method. The obtained results indicated that of the whole studied region （comprising 4819.6 acres）, 2651.56 acres （55%） are located in medium de- sertification intensity class, 1269.48 acres （26.34%） are positioned in severe desertification intensity class, and 898.54 acres （18.64%） are placed in vary severe desertification intensity class.
文摘This study presents a comprehensive analysis of the current energy landscape and the imperative transition toward renewable energy.It begins with an overview of current energy sources and trends,highlighting the disparity between supply and increasing demand.Adverse impacts of reliance on fossil fuels such as environmental degradation,economic volatility,and health hazards underscore the urgent need for a transition.The study then explores the vast potential of renewable energy sources(RES)such as solar,wind,hydrogen,and hydro,emphasizing their feasibility in the Southern African context.The positive impacts of integrating renewables are examined,including reduced greenhouse gas emissions,enhanced energy security,and economic diversification.Through case studies of regional examples,the success and failures of transitioning efforts are analyzed,providing valuable insights into best practices and pitfalls.The study identifies significant challenges in transitioning,particularly in grid-tied and off-grid scenarios,and discusses infrastructural,financial,and regulatory obstacles.The recommendations section outlines strategic steps for achieving a feasible transition,proposing either a full transition or specific percentages of renewable energy integration to meet energy demands.In conclusion,the study emphasizes the critical importance of adopting these strategies for sustainable development and global climate goals,advocating for continuous innovation and localized solutions to maximize the benefits of renewable energy.Key findings are that the environmental and economic effects of fossil fuel usage strain economies by increasing fossil fuel subsidies.RES are abundant in the Southern African region,and some projects have already been successfully implemented,especially in South Africa.Economic growth and technological advancement are some of the benefits of fully transitioning to renewables,but lack of skilled labor,infrastructure,necessary technology,and most importantly,high capital requirements,etc.,are some challenges being faced.Hence,the need for regional cooperation,policy frameworks,and infrastructure enhancement,and investment mobilization for an accelerated transition.
文摘Since years, online social networks have evolved from profile and communication websites to online portals where people interact with each other, share and consume multimedia-enriched data and play different types of games. Due to the immense popularity of these online games and their huge revenue potential, the number of these games increases every day, resulting in a current offering of thousands of online social games. In this paper, the applicability of neighborhood-based collaborative filtering （CF） algorithms for the recommendation of online social games is evaluated. This evaluation is based on a large dataset of an online social gaming platform containing game ratings （explicit data） and online gaming behavior （implicit data） of millions of active users. Several similarity metrics were implemented and evaluated on the explicit data, implicit data and a combination thereof. It is shown that the neighborhood-based CF algorithms greatly outperform the content-based algorithm, currently often used on online social gaming websites. The reslflts also show that a combined approach, fie, taking into account both implicit and explicit data at the same time, yields overall good results on all evaluation metrics for all scenarios, while only slightly performing worse compared to the strengths of the explicit or implicit only approaches. The best performing algorithms have been implemented in a live setup of the online game platform.
基金supported by the National Natural Science Foundation of China under Grant No.62172386the Natural Science Foundation of Jiangsu Province of China under Grant No.BK20231212the Teaching Research Project of the Education Department of Anhui Province of China under Grant No.2021jyxm1738.
文摘Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central server.Unlike most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model training.Our primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained budget.To this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL system.Based on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)problem.Next,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple subproblems.Finally,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected clients.In addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.
