With the number of users that use mobile devices for frequent transactions increasing rapidly, it is a great challenge to guarantee the credibility of transactions. Blockchain is regarded as a practical technology for...
With the number of users that use mobile devices for frequent transactions increasing rapidly, it is a great challenge to guarantee the credibility of transactions. Blockchain is regarded as a practical technology for such demand, however, the limited computing capacity of each user's device becomes a bottleneck. In this paper, the edge computing pattern is introduced to support complex computing for mobile devices of users by renting computing resource from computing service providers. By considering demands of both the user and the service provider, we propose a two-level game approach based on the Stackelberg Game for multiple users and multiple service providers on computing resources renting and pricing. The simulation results show that the proposed mechanism is feasible and effective.
With the rapid development of Internet and constant improvement of informationization degree, all kinds of security problems become increasingly prominent. Especially computersystem security is faced with serious cha...
详细信息
With the rapid development of Internet and constant improvement of informationization degree, all kinds of security problems become increasingly prominent. Especially computersystem security is faced with serious challenges. In such case, whether the course of computersystem security taught in colleges and universities can be advanced with the times plays an important role in dealing with the challenge. Based on the current situation of computersystem security course, this thesis analyzed and studied how to realize the innovative reform of computersystem security course.
As an extended computing paradigm of cloud computing, Mobile Edge Computing (MEC) facilitates real-time service responses by deploying resources near network edges. However, services should frequently move among multi...
As an extended computing paradigm of cloud computing, Mobile Edge Computing (MEC) facilitates real-time service responses by deploying resources near network edges. However, services should frequently move among multiple edge computing servers because of the mobility of most users, which accordingly leads to increased network operation costs and influences service quality. In this paper, we formulate the service migration problem as a Markov Decision Process (MDP) and introduce the dueling Deep Q-Network (DQN) to solve the problem, so as to reduce the network operating cost without lowering the service quality. We also propose a trajectory prediction approach to further optimize the service migration. Simulation experimental results demonstrate that the proposed mechanism can achieve a lower network operation cost without reducing the service quality.
With the fast development of 3D imaginations becomes more and more fascination, multi-view stereo based 3D reconstruction is a significant technique for those application. To facilitate the subsequent processing of 3D...
详细信息
In this work, a novel framework is proposed to improve air traffic safety from the perspective of human factors by detecting possible risks from air-ground speech communication. In the proposed framework, the automati...
详细信息
With the increasingly extensive applications of the network, the security of internal network of enterprises is facing more and more threats from the outside world, which implies the importance to master the network r...
详细信息
In view of the fact that some attacks have low detection rates in intrusion detection dataset, a two-level feature selection method based on minimal-redundancy-maximal-relevance (mRMR) and information gain (IG) was pr...
详细信息
A new based on Semi-supervised classification theory for SAR images in contourlet domain is proposed, in this paper. Attempting to get better and faster performance, the PSO algorithm (Particle swarm optimization algo...
详细信息
To implement the interoperation of different ontologies in medical informatics domain and achieve the goal of the sharing and multiplexing of domain knowledge, the heterogeneous problem between ontologies must be solv...
详细信息
ISBN:
(纸本)9781424458721;9781424458745
To implement the interoperation of different ontologies in medical informatics domain and achieve the goal of the sharing and multiplexing of domain knowledge, the heterogeneous problem between ontologies must be solved. Now the best method of resolving ontology heterogeneous is establishing ontology mapping, that is founding the semantic relations between ontologies and making corresponding mapping rules firstly, and then integrating all independent ontologies into a whole to be operated. In order to produce mapping-pairs and implement ontology mapping and realizing knowledge sharing, a concept similarity algorithm combining semantic similarity with semantic relativity is adopted to estimate the similarity between concepts. It has been proved that the evaluation of concept similarity between ontologies is more accurate by considering both semantic similarity and semantic relativity, and it has laid a good foundation for establishing mapping-pairs and knowledge sharing model based on ontology mapping.
In recent years, the deep learning method has been widely used in the financial field, promoting the development of stock price forecasting. The time series data in reality has complex characteristics, and the traditi...
详细信息
In recent years, the deep learning method has been widely used in the financial field, promoting the development of stock price forecasting. The time series data in reality has complex characteristics, and the traditional single model has great limitations in prediction. For the problem that the time series data is too complicated, this paper proposes a time series mixed prediction model based on decomposition and synthesis. The time series is decomposed by empirical mode decomposition(EMD). For the problem that the calculation complexity becomes larger after decomposition, and the prediction error of each subcomponent leads to the total error is still large. In this paper, the sampled entropy(SE) method is used to combine the decomposed subsequences, which reduces the computational complexity and total error of the algorithm. The combined sequence is predicted by the LSTM neural network. The experimental result show that the prediction accuracy of the model is significantly improved compared with the traditional model.
暂无评论