Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： There is a certain internal relationship between user links and location links in location-based social network(LBSN) , and different users also have different behaviors in the network. Therefore, view of the above problem, a Cooperation based personalized link prediction algorithm(CPP) is proposed in LBSN. For the user's personalized features, the kernel density estimation method is used to model the user's time and spatial dimensions. The interest groups were used to divide the users into overlapping communities, and the personalized user link prediction was performed through the community, friends and sign-in relationships. Based on the prediction of the personalized user link, a personalized link relationship between users and locations was predicted via the algorithm of the random walk with community restarting. The CPP algorithm improves the performance by the iteration of the user link prediction and the location link prediction. The experimental results show that the CPP algorithm has better prediction performance than that of the existing algorithm.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract： Concern the problem that multi-channel Motor Imagery (MI) of Brain-Computer Interface (BCI) based on 3D visual guidance with more redundancy information and poor classification accuracy, this paper proposed a pattern classification method based on wavelet packet decomposition(WPD)-common spatial pattern(CSP)-adaptive differential evolution(ADE) for feature extraction of electroencephalogram（EEG）.Firstly, this algorithm used WPD to divide the multi-channel motion imagery EEG signals into fine sub-bands. Secondly, it used CSP to obtain the eigenvectors corresponding to each subspace of WPD transformation. Finally, it selected the feature vectors through the ADE algorithm to obtain the best feature subsets for classification. Using WPD-CSP-ADE mode for feature extraction and selection, it had better performance in classification accuracy and number of features than the classic WPD-CSP method. At the same time, the classification performance of the proposed algorithm was significantly better than the genetic algorithm and particle swarm optimization algorithm. The experiments show that the WPD-CSP-ADE method can effectively improve the classification accuracy and reduce the number of features used for classification.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-11-29 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the security problems existing in the process of the data aggregation and transmission in crowd sensing networks, such as privacy leakage, incomplete information, data tampering. this paper proposed a data aggregation privacy protection algorithm based on distributed compressive sensing and hash function. Firstly, it used distributed compressive sensing method to sparsely observe the sensed data and remove the redundant data. Then, it utilized one-way hash function to obtain hash value of the observation data and filled the hash value with the unconstrained camouflage data into the observation data of sensory data to reach the aim of concealing the true sensor data. Finally, after extracting the camouflage data at the sink node, it obtained the hash value of the observation data again to verify the integrity of data. Simulation results show that the algorithm takes into account the privacy preserving and integrity protecting of data, and also can reduce the communication overhead greatly, which means the strong applicability and scalability in practical applications.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： The existing privacy protection strategies in crowd sensing networks used the same privacy policies for all locations which overprotected led to the problems that some locations, others were not adequately protected and the sensing data was less accurate. In order to solve this problem, this paper proposed a location privacy protection algorithm to meet the users’ personalized privacy and security requirements. First, it mined users’ access duration, frequency and regularity at different locations according to the user's historical movement trajectory, which used to predict the social attributes of the locations to the users. Then, it combined the location’s social attributes and natural attributes to predict user-location sensitivity levels. Finally, considering the different privacy security requirements of users in different locations, it set a dynamic privacy decision scheme. Users with less sensitivity at each location were selected to participate in sensing tasks to ensure that users, in the safe privacy context, could contribute the accurate data with a higher level of spatiotemporal correlation. The simulation results show that the algorithm can improve the privacy protection level and the accuracy of the sensing data.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-12 Cooperative journals: 《计算机应用研究》
Abstract： In view of the current D2D multicast content delivery mechanism has a large amount of transmission redundancy, lead to low energy efficiency and low spectrum efficiency. This paper proposed a novel demand-aware D2D video distribution mechanism. By predicting users’ video service requests, the video is pushed to potential service users while distributing video for service request users. Firstly, the willingness of potential service users to accept video push is estimated based on the users’ interests, the popularity of the video and the residual-energy of the users’ devices. Secondly, the utility measure of video distribution service was proposed to measure the value of video distribution service, and the issue on energy efficiency of the optimal cluster heads was modeled. Finally, this paper proposed a D2D video distribution mechanism that optimizes the energy efficiency of cluster heads. Simulation results show that the proposed mechanism is superior to the traditional ones with regard to the energy efficiency of the cluster head and system throughput.
Hits
Hits
Downloads
Comment