Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-12-13 Cooperative journals: 《计算机应用研究》
Abstract： According to the existing research work of location-based social network was not sufficient to mine the user semantic location information related to point-of-interest, Moreover, most recommendation algorithms ignored the influence of the region of point-of-interest on the result of recommendation. This paper proposed a new recommendation model of point-of-interest called USTTGD, first adopted the Latent Dirichlet Allocation(LDA) topic model of time division, based on the semantic location information in check-in records mined the user time preference under the time theme, then devided the region of point-of-interest into grids to evaluate the regional influence. Next, applied Edge-weighted Personalized PageRank(EwPPR) to modeling the successive transitions among point-of-interests. Finally, USTTGD fused user time preference, regional preference and successive transition preference into a unified recommendation framework. Experimental results on real-world datasets show that USTTGD achieves significantly enhance compared with other classical recommendation models on precision and recalling rates.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： The network traffic has sudden changes and dependencies in real-time, and the traditional network traffic prediction model has the disadvantages of weak generalization ability and low prediction accuracy. In order to solve this problem, this paper developed燼 network traffic prediction model based on the Long Short-Term Memory (LSTM) recurrent neural network. Firstly, improved resampling process of Particle Filter (PF) with distance comparison and optimized combination strategy. Then, built a PF-LSTM network model to accurately predict the network traffic. Model training with improved PF algorithm to improved its training rate and overcame the shortcomings of convergence in the traditional LSTM network. Finally, predicted network traffic through proposed models. The experimental results show that the model has better prediction accuracy and convergence efficiency compared with the traditional LSTM model, which can describe the trend of changes better in network traffic.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-20 Cooperative journals: 《计算机应用研究》
Abstract： In order to solve the problems that existing in the maximal frequent itemset mining algorithms, such as the mining time is too long and the memory consumption is too large, this paper presents a maximal frequent itemset mining algorithm BMFI which employs B-list to mining frequent itemsets and employs the whole sequence search tree as the search space, then, the parent equivalence pruning technique is used to reduce the search space. Finally, which combined with the MFI-tree-based projection strategy to achieve superset detection to improve the efficiency of the algorithm. The experimental results show that the performance of BMFI algorithm is superior to FPMAX algorithm and MFIN algorithm in terms of time efficiency and spatial efficiency. The proposed algorithm has good performance when mining the maximal frequent itemset in dense data set and sparse data set.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： In the 5G system, millimeter wave (mmWave) and device to device(D2D) communication is beneficial to improve the system capacity and spectrum utilization. This paper studied the resource allocation for D2D in underlay cellular networks at 73 GHz. In order to reduce the interference between each other, firstly, this paper proposed the regional restrictions on the base station and D2D receiver. Then, it used the method of linear correlation to select reusable cellular users. Finally, in order to improve the system throughput, it proposed a resource allocation based on interference control under meeting the requirements of quality of service (QoS) of cellular communication and D2D communication. The simulation results show that the proposed algorithm outperforms the reference algorithm. The algorithm can effectively improve the system throughput and spectrum efficiency.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-24 Cooperative journals: 《计算机应用研究》
Abstract： Enhanced inter cell interference coordination (eICIC) introduces almost black subframes (ABS) to reduce inter-cell interference in heterogeneous networks. However, excessive ABS can impair macrocell user performance. In order to improve the performance of heterogeneous networks, this paper proposes an interference coordination scheme based on hybrid protected subframes (HPS) considering both ABS and Low Power-ABS (LP-ABS) . The scheme takes into account the resource allocation, HPS density, HPS mixing ratio and user access strategy, in order to maximize the fairness of system proportion as the goal. Simulation results show that the proposed scheme is superior to the traditional enhanced inter-cell interference coordination schemes in terms of system load balancing, user throughput and user fairness.
Hits
Hits
Downloads
Comment