In solving many-objective optimization problems(MaO Ps),existing nondominated sorting-based multi-objective evolutionary algorithms suffer from the fast loss of selection pressure.Most candidate solutions become nondo...In solving many-objective optimization problems(MaO Ps),existing nondominated sorting-based multi-objective evolutionary algorithms suffer from the fast loss of selection pressure.Most candidate solutions become nondominated during the evolutionary process,thus leading to the failure of producing offspring toward Pareto-optimal front with diversity.Can we find a more effective way to select nondominated solutions and resolve this issue?To answer this critical question,this work proposes to evolve solutions through line complex rather than solution points in Euclidean space.First,Plücker coordinates are used to project solution points to line complex composed of position vectors and momentum ones.Besides position vectors of the solution points,momentum vectors are used to extend the comparability of nondominated solutions and enhance selection pressure.Then,a new distance function designed for high-dimensional space is proposed to replace Euclidean distance as a more effective distancebased estimator.Based on them,a novel many-objective evolutionary algorithm(MaOEA)is proposed by integrating a line complex-based environmental selection strategy into the NSGAⅢframework.The proposed algorithm is compared with the state of the art on widely used benchmark problems with up to 15 objectives.Experimental results demonstrate its superior competitiveness in solving MaOPs.展开更多
The temporal distance between events conveys information essential for many time series tasks such as speech recognition and rhythm detection.While traditional models such as hidden Markov models(HMMs)and discrete sym...The temporal distance between events conveys information essential for many time series tasks such as speech recognition and rhythm detection.While traditional models such as hidden Markov models(HMMs)and discrete symbolic grammars tend to discard such information,recurrent neural networks(RNNs)can in principle learn to make use of it.As an advanced variant of RNNs.long short-term memory(LSTM)has an alternative(arguably better)mechanism for bridging long time lags.We propose a couple of deep neural network-based models to detect abnormal start-ups,unusual CPU and memory consumptions of the application processes running on smart phones.Experiment results showed that the proposed neural networks achieve remarkable performance at some reasonable computational cost.The speed advantage of neural networks makes them even more competitive for the applications requiring real-time response,offering the proposed models the potential for practical systems.展开更多
The rapid development of Peer-to-Peer(P2P)technologies and applications has a great impact on telecom services and operations.Operators should refine the pipeline operation and develop characteristic P2P services.They...The rapid development of Peer-to-Peer(P2P)technologies and applications has a great impact on telecom services and operations.Operators should refine the pipeline operation and develop characteristic P2P services.They must comply with the rule of Internet services,and design manageable and operational P2P solutions combining the advantages in network,resource and subscriber,providing users with better P2P service experience.ZTE’s manageable and operational P2P solution provides operators with customized authorization and accounting functions.Its development is based on the broadband service management platform widely used in the live networks.ZTE’s P2P system is stable and reliable.展开更多
Along with the deployment of 3G networks and the launch of diversified mobile Internet services,network service modes and operation modes have greatly changed,and now the smart phone plays a key role.Accordingly,the k...Along with the deployment of 3G networks and the launch of diversified mobile Internet services,network service modes and operation modes have greatly changed,and now the smart phone plays a key role.Accordingly,the key technologies for the smart phone,such as the application security management framework,application software authentication mechanism,interoperating capability and dynamic power management should be paid much attention to.The mobile phone vendors are gradually transforming into platform providers who will offer the support for services,including hardware,protocol stacks and storage,instead of providing specific services.Meanwhile,operators and Internet service providers will become the main body of service development.展开更多
Personalized service systems are an effective way to help users obtain recommendations for unseen items, within the enormous volume of information available based on their preferences. The most commonly used personali...Personalized service systems are an effective way to help users obtain recommendations for unseen items, within the enormous volume of information available based on their preferences. The most commonly used personalized service system methods are collaborative filtering, content-based filtering, and hybrid filtering. Unfortunately, each method has its drawbacks. This paper proposes a new method which unified partition-based collaborative filtering and meta-information filtering. In partition-based collaborative filtering the user-item rating matrix can be partitioned into low-dimensional dense matrices using a matrix clustering algorithm. Recommendations are generated based on these low-dimensional matrices. Additionally, the very low ratings problem can be solved using meta-information filtering. The unified method is applied to a digital resource management system. The experimental results show the high efficiency and good performance of the new approach.展开更多
Mobile grid is a branch of grid computing that incorporates mobile devices into the grid infrastructure. It poses new challenges because mobile devices are typically resource-constrained and exhibit unique characteris...Mobile grid is a branch of grid computing that incorporates mobile devices into the grid infrastructure. It poses new challenges because mobile devices are typically resource-constrained and exhibit unique characteristics such as instability in network connections. New scheduling strate- gies are imperative in mobile grid to efficiently utilize the devices. This paper presents a scheduling algorithm that con- siders dynamic properties of mobile devices such as avail- ability, reliability, maintainability, and usage pattern in mo- bile grid environments. In particular, usage patterns caused by voluntarily or involuntarily losing a connection, such as switching off the device or a network interruption could be important criteria for choosing the best resource to execute a job. The experimental results show that our scheduling al- gorithm provides superior performance in terms of execution time, as compared to the other methods that do not consider usage pattern. Throughout the experiments, we found it es- sential to consider usage pattern for improving performance in the mobile grid.展开更多
基金supported in part by the National Natural Science Foundation of China(51775385)the Natural Science Foundation of Shanghai(23ZR1466000)+3 种基金the Shanghai Industrial Collaborative Science and Technology Innovation Project(2021-cyxt2-kj10)the Innovation Program of Shanghai Municipal Education Commission(202101070007E00098)the Innovation Project of Engineering Research Center of Integration and Application of Digital Learning Technology of MOE(1221046)the Program to Cultivate Middle-Aged and Young Cadre Teacher of Jiangsu Province。
文摘In solving many-objective optimization problems(MaO Ps),existing nondominated sorting-based multi-objective evolutionary algorithms suffer from the fast loss of selection pressure.Most candidate solutions become nondominated during the evolutionary process,thus leading to the failure of producing offspring toward Pareto-optimal front with diversity.Can we find a more effective way to select nondominated solutions and resolve this issue?To answer this critical question,this work proposes to evolve solutions through line complex rather than solution points in Euclidean space.First,Plücker coordinates are used to project solution points to line complex composed of position vectors and momentum ones.Besides position vectors of the solution points,momentum vectors are used to extend the comparability of nondominated solutions and enhance selection pressure.Then,a new distance function designed for high-dimensional space is proposed to replace Euclidean distance as a more effective distancebased estimator.Based on them,a novel many-objective evolutionary algorithm(MaOEA)is proposed by integrating a line complex-based environmental selection strategy into the NSGAⅢframework.The proposed algorithm is compared with the state of the art on widely used benchmark problems with up to 15 objectives.Experimental results demonstrate its superior competitiveness in solving MaOPs.
文摘The temporal distance between events conveys information essential for many time series tasks such as speech recognition and rhythm detection.While traditional models such as hidden Markov models(HMMs)and discrete symbolic grammars tend to discard such information,recurrent neural networks(RNNs)can in principle learn to make use of it.As an advanced variant of RNNs.long short-term memory(LSTM)has an alternative(arguably better)mechanism for bridging long time lags.We propose a couple of deep neural network-based models to detect abnormal start-ups,unusual CPU and memory consumptions of the application processes running on smart phones.Experiment results showed that the proposed neural networks achieve remarkable performance at some reasonable computational cost.The speed advantage of neural networks makes them even more competitive for the applications requiring real-time response,offering the proposed models the potential for practical systems.
文摘The rapid development of Peer-to-Peer(P2P)technologies and applications has a great impact on telecom services and operations.Operators should refine the pipeline operation and develop characteristic P2P services.They must comply with the rule of Internet services,and design manageable and operational P2P solutions combining the advantages in network,resource and subscriber,providing users with better P2P service experience.ZTE’s manageable and operational P2P solution provides operators with customized authorization and accounting functions.Its development is based on the broadband service management platform widely used in the live networks.ZTE’s P2P system is stable and reliable.
基金funded by the National High Technology Research and Development Program of China("863"Program)under Grant No.2002AA1Z2306
文摘Along with the deployment of 3G networks and the launch of diversified mobile Internet services,network service modes and operation modes have greatly changed,and now the smart phone plays a key role.Accordingly,the key technologies for the smart phone,such as the application security management framework,application software authentication mechanism,interoperating capability and dynamic power management should be paid much attention to.The mobile phone vendors are gradually transforming into platform providers who will offer the support for services,including hardware,protocol stacks and storage,instead of providing specific services.Meanwhile,operators and Internet service providers will become the main body of service development.
基金the National Natural Science Foundation of China (No. 60473078)
文摘Personalized service systems are an effective way to help users obtain recommendations for unseen items, within the enormous volume of information available based on their preferences. The most commonly used personalized service system methods are collaborative filtering, content-based filtering, and hybrid filtering. Unfortunately, each method has its drawbacks. This paper proposes a new method which unified partition-based collaborative filtering and meta-information filtering. In partition-based collaborative filtering the user-item rating matrix can be partitioned into low-dimensional dense matrices using a matrix clustering algorithm. Recommendations are generated based on these low-dimensional matrices. Additionally, the very low ratings problem can be solved using meta-information filtering. The unified method is applied to a digital resource management system. The experimental results show the high efficiency and good performance of the new approach.
文摘Mobile grid is a branch of grid computing that incorporates mobile devices into the grid infrastructure. It poses new challenges because mobile devices are typically resource-constrained and exhibit unique characteristics such as instability in network connections. New scheduling strate- gies are imperative in mobile grid to efficiently utilize the devices. This paper presents a scheduling algorithm that con- siders dynamic properties of mobile devices such as avail- ability, reliability, maintainability, and usage pattern in mo- bile grid environments. In particular, usage patterns caused by voluntarily or involuntarily losing a connection, such as switching off the device or a network interruption could be important criteria for choosing the best resource to execute a job. The experimental results show that our scheduling al- gorithm provides superior performance in terms of execution time, as compared to the other methods that do not consider usage pattern. Throughout the experiments, we found it es- sential to consider usage pattern for improving performance in the mobile grid.
