Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there m...Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there may be multiple servers and devices that can provide services to the same user simultaneously. This paper proposes a userside adaptive user service deployment algorithm ASD(Adaptive Service Deployment) based on reinforcement learning algorithms. Without relying on complex system information, it can master only a few tasks and users. In the case of attributes, perform effective service deployment decisions, analyze and redefine the key parameters of existing algorithms, and dynamically adjust strategies according to task types and available node types to optimize user experience delay. Experiments show that the ASD algorithm can implement user-side decision-making for service deployment. While effectively improving parameter settings in the traditional Multi-Armed Bandit algorithm,it can reduce user-perceived delay and enhance service quality compared with other strategies.展开更多
Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This ...Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This paper presents the idea of using motifs, subgraphs with higher occurrence in real network than in random ones, to discover two different citation patterns in journal communities. And a further investigation is addressed on both motif granularity and node centrality to figure out some reasons on the differences between two kinds of communities in journal citation network.展开更多
Electrocoagulation(EC)technique was used to investigate the removal performance of aqueous perfluorooctanoic acid(PFOA)with relatively high concentration as simulating the wastewater from organic fluorine industry.A c...Electrocoagulation(EC)technique was used to investigate the removal performance of aqueous perfluorooctanoic acid(PFOA)with relatively high concentration as simulating the wastewater from organic fluorine industry.A comparison was done with the similar amount of coagulant between EC and chemical coagulation process.PFOA removal obtained was higher with EC process,especially for Fe anode.Several factors were studied to optimize the EC process.At the optimal operating parameters including 37.5 mA/cm^2 of current density,initial pH 3.77,and 180 rpm of mixing speed,93%of PFOA could be removed with 100 mg/L of initial concentration after 90-min electrolysis.Furthermore,the remove efficiency could be obviously improved by H2O2 intermittent addition,which removed more than 99%of PFOA within 40-min EC.It could be attributed to that H2O2 facilitated the oxidative transformation from ferrous to ferric ion.In addition,the adsorptive removal of aqueous PFOA on Fe flocs during EC was also verified by fourier transform infrared spectra.展开更多
Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtua...Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual net- works affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evalua- tion, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies （e.g., AT＆T, DFN） and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach.展开更多
Cloud computing as an emerging technology promises to provide reliable and available services on de- mand. However, offering services for mobile requirements without dynamic and adaptive migration may hurt the perform...Cloud computing as an emerging technology promises to provide reliable and available services on de- mand. However, offering services for mobile requirements without dynamic and adaptive migration may hurt the performance of deployed services. In this paper, we propose MAMOC, a cost-effective approach for selecting the server and migrating services to attain enhanced QoS more econom- ically. The goal of MAMOC is to minimize the total operating cost while guaranteeing the constraints of resource de- mands, storage capacity, access latency and economies, including selling price and reputation grade. First, we devise an objective optimal model with multi-constraints, describing the relationship among operating cost and the above con- straints. Second, a normalized method is adopted to calculate the operating cost for each candidate VM. Then we give a de- tailed presentation on the online algorithm MAMOC, which determines the optimal server. To evaluate the performance of our proposal, we conducted extensive simulations on three typical network topologies and a realistic data center net- work. Results show that MAMOC is scalable and robust with the larger scales of requests and VMs in cloud environment. Moreover, MAMOC decreases the competitive ratio by identifying the optimal migration paths, while ensuring the constraints of SLA as satisfying as possible.展开更多
Hunting the advanced threats hidden in the enterprise networks has always been a complex and difficult task.Due to the variety of attacking means,it is difficult for traditional security systems to detect threats.Most...Hunting the advanced threats hidden in the enterprise networks has always been a complex and difficult task.Due to the variety of attacking means,it is difficult for traditional security systems to detect threats.Most existing methods analyze log records,but the amount of log records generated every day is very large.How to find the information related to the attack events quickly and effectively from massive data streams is an important problem.Considering that the knowledge graph can be used for automatic relation calculation and complex relation analysis,and can get relatively fast feedback,our work proposes to construct the knowledge graph based on kernel audit records,which fully considers the global correlation among entities observed in audit logs.We design the construction and application process of knowledge graph,which can be applied to actual threat hunting activities.Then we explore different ways to use the constructed knowledge graph for hunting actual threats in detail.Finally,we implement a LAN-wide hunting system which is convenient and flexible for security analysts.Evaluations based on the adversarial engagement designed by DARPA prove that our platform can effectively hunt sophisticated threats,quickly restore the attack path or assess the impact of attack.展开更多
Long-term prediction is still a difficult problem in data mining.People usually use various kinds of methods of Recurrent Neural Network to predict.However,with the increase of the prediction step,the accuracy of pred...Long-term prediction is still a difficult problem in data mining.People usually use various kinds of methods of Recurrent Neural Network to predict.However,with the increase of the prediction step,the accuracy of prediction decreases rapidly.In order to improve the accuracy of long-term prediction,we propose a framework Variational Auto-Encoder Conditional Generative Adversarial Network(VAECGAN).Our model is divided into three parts.The first part is the encoder net,which can encode the exogenous sequence into latent space vectors and fully save the information carried by the exogenous sequence.The second part is the generator net which is responsible for generating prediction data.In the third part,the discriminator net is used to classify and feedback,adjust data generation and improve prediction accuracy.Finally,extensive empirical studies tested with five real-world datasets(NASDAQ,SML,Energy,EEG,KDDCUP)demonstrate the effectiveness and robustness of our proposed approach.展开更多
基金supported in part by the Industrial Internet Innovation and Development Project "Industrial robot external safety enhancement device"(TC200H030)the Cooperation project between Chongqing Municipal undergraduate universities and institutes affiliated to CAS (HZ2021015)
文摘Mobile edge computing(MEC) is a cloud server running at the edge of a mobile network, which can effectively reduce network communication delay. However, due to the numerous edge servers and devices in the MEC, there may be multiple servers and devices that can provide services to the same user simultaneously. This paper proposes a userside adaptive user service deployment algorithm ASD(Adaptive Service Deployment) based on reinforcement learning algorithms. Without relying on complex system information, it can master only a few tasks and users. In the case of attributes, perform effective service deployment decisions, analyze and redefine the key parameters of existing algorithms, and dynamically adjust strategies according to task types and available node types to optimize user experience delay. Experiments show that the ASD algorithm can implement user-side decision-making for service deployment. While effectively improving parameter settings in the traditional Multi-Armed Bandit algorithm,it can reduce user-perceived delay and enhance service quality compared with other strategies.
文摘Journals and their citation relations are abstracted into journal citation networks, basing on CSTPC journal database from year 2003 to 2006. The network shows some typical characteristics from complex networks. This paper presents the idea of using motifs, subgraphs with higher occurrence in real network than in random ones, to discover two different citation patterns in journal communities. And a further investigation is addressed on both motif granularity and node centrality to figure out some reasons on the differences between two kinds of communities in journal citation network.
基金the National Natural Science Foundation of China(21547011,21177089,21307036)the National High-Tech Research and Development Program of China(863 Program,2013AA062705)+1 种基金the Guangdong Natural Science Foundation(2014A030313761)the Shenzhen Science and Technology Project for Fundamental Research(JCYJ20150324141711622,JCYJ20150529164656097).
文摘Electrocoagulation(EC)technique was used to investigate the removal performance of aqueous perfluorooctanoic acid(PFOA)with relatively high concentration as simulating the wastewater from organic fluorine industry.A comparison was done with the similar amount of coagulant between EC and chemical coagulation process.PFOA removal obtained was higher with EC process,especially for Fe anode.Several factors were studied to optimize the EC process.At the optimal operating parameters including 37.5 mA/cm^2 of current density,initial pH 3.77,and 180 rpm of mixing speed,93%of PFOA could be removed with 100 mg/L of initial concentration after 90-min electrolysis.Furthermore,the remove efficiency could be obviously improved by H2O2 intermittent addition,which removed more than 99%of PFOA within 40-min EC.It could be attributed to that H2O2 facilitated the oxidative transformation from ferrous to ferric ion.In addition,the adsorptive removal of aqueous PFOA on Fe flocs during EC was also verified by fourier transform infrared spectra.
基金This work has been supported by National Science and Technology Major Project of China （NMP） （2010ZX03004-002 and 2012ZX03003-003）, the Strategic Pilot Project of Chinese Academy of Sciences （XDA06010302）, and the National Natural Science Foundation of China （Grant No. 60972083）.
文摘Network virtualization aims to provide a way to overcome ossification of the Internet. However, making efficient use of substrate resources requires effective techniques for embedding virtual networks： mapping virtual nodes and virtual edges onto substrate networks. Previous research has presented several heuristic algorithms, which fail to consider that the attributes of the substrate topology and virtual net- works affect the embedding process. In this paper, for the first time, we introduce complex network centrality analysis into the virtual network embedding, and propose virtual network embedding algorithms based on closeness centrality. Due to considering of the attributes of nodes and edges in the topology, our studies are more reasonable than existing work. In addition, with the guidance of topology quantitative evalua- tion, the proposed network embedding approach largely improves the network utilization efficiency and decreases the embedding complexity. We also investigate our algorithms on real network topologies （e.g., AT＆T, DFN） and random network topologies. Experimental results demonstrate the usability and capability of the proposed approach.
文摘Cloud computing as an emerging technology promises to provide reliable and available services on de- mand. However, offering services for mobile requirements without dynamic and adaptive migration may hurt the performance of deployed services. In this paper, we propose MAMOC, a cost-effective approach for selecting the server and migrating services to attain enhanced QoS more econom- ically. The goal of MAMOC is to minimize the total operating cost while guaranteeing the constraints of resource de- mands, storage capacity, access latency and economies, including selling price and reputation grade. First, we devise an objective optimal model with multi-constraints, describing the relationship among operating cost and the above con- straints. Second, a normalized method is adopted to calculate the operating cost for each candidate VM. Then we give a de- tailed presentation on the online algorithm MAMOC, which determines the optimal server. To evaluate the performance of our proposal, we conducted extensive simulations on three typical network topologies and a realistic data center net- work. Results show that MAMOC is scalable and robust with the larger scales of requests and VMs in cloud environment. Moreover, MAMOC decreases the competitive ratio by identifying the optimal migration paths, while ensuring the constraints of SLA as satisfying as possible.
基金This work is supported in part by the Industrial Internet Innovation and Development Project“Industrial robot external safety enhancement device”(TC200H030)the Cooperation project between Chongqing Municipal undergraduate universities and institutes affiliated to CAS(HZ2021015).
文摘Hunting the advanced threats hidden in the enterprise networks has always been a complex and difficult task.Due to the variety of attacking means,it is difficult for traditional security systems to detect threats.Most existing methods analyze log records,but the amount of log records generated every day is very large.How to find the information related to the attack events quickly and effectively from massive data streams is an important problem.Considering that the knowledge graph can be used for automatic relation calculation and complex relation analysis,and can get relatively fast feedback,our work proposes to construct the knowledge graph based on kernel audit records,which fully considers the global correlation among entities observed in audit logs.We design the construction and application process of knowledge graph,which can be applied to actual threat hunting activities.Then we explore different ways to use the constructed knowledge graph for hunting actual threats in detail.Finally,we implement a LAN-wide hunting system which is convenient and flexible for security analysts.Evaluations based on the adversarial engagement designed by DARPA prove that our platform can effectively hunt sophisticated threats,quickly restore the attack path or assess the impact of attack.
基金the Youth Talent Star of Institute of Information Engineering,Chinese Academy of Sciences(Y7Z0091105)This work was supported in part by National Natural Science Foundation of China under Grant 61771469.
文摘Long-term prediction is still a difficult problem in data mining.People usually use various kinds of methods of Recurrent Neural Network to predict.However,with the increase of the prediction step,the accuracy of prediction decreases rapidly.In order to improve the accuracy of long-term prediction,we propose a framework Variational Auto-Encoder Conditional Generative Adversarial Network(VAECGAN).Our model is divided into three parts.The first part is the encoder net,which can encode the exogenous sequence into latent space vectors and fully save the information carried by the exogenous sequence.The second part is the generator net which is responsible for generating prediction data.In the third part,the discriminator net is used to classify and feedback,adjust data generation and improve prediction accuracy.Finally,extensive empirical studies tested with five real-world datasets(NASDAQ,SML,Energy,EEG,KDDCUP)demonstrate the effectiveness and robustness of our proposed approach.
