Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： In order to apply neural network to urban LiDAR point clouds data classification, and to decrease large computation and long time consuming in the training process of large scale point clouds data, this paper improved the original Point-Net neural network by adding neighborhood characteristics of point clouds, and it proposed a new classification algorithm for point clouds based on the improved Point-Net. This algorithm compressed the original point clouds data volume through grid clustering and resampling, and then it extracted multi-scale neighborhood point clouds data and classified urban point clouds by using improved Point-Net. This paper verified the classification algorithm with data from different regions. The results show that the algorithm has good classification effect, high classification accuracy and less calculation. Therefore, the algorithm can realize effective classification of airborne LiDAR data in urban areas.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problem of low data transmission rate of traditional single path routing protocol in resource-constrained LEO satellite network, based on GEO/LEO double-layer satellite network model, a new multi-path routing protocol (N-NCMR) for double-layer satellite network based on network coding (NC) is proposed. Firstly, GEO satellite is used to calculate routing for LEO satellite network, and NC technology is used to transmit different parts of data stream along multiple disjoint paths dynamically, thus reducing the burden of LEO satellite. Secondly, a delayed acknowledgment mechanism is designed to accelerate data transmission. Source nodes can send subsequent groups continuously before receiving the previous set of acknowledgment (ACK) messages. The simulation results show that the routing protocol significantly improves the throughput and data transmission efficiency of LEO satellite network.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-03 Cooperative journals: 《计算机应用研究》
Abstract： In order to improve the accuracy of radar target recognition, this paper proposes a high resolution range profile (HRRP) recognition method based on deep belief network (DBN) . Firstly, the method uses a restricted Boltzmann machine (RBM) to perform layer-by-layer unsupervised training on HRRP data. The network parameters are updated according to the contrast divergence (CD) algorithm, and the DBN depth is designed by the reconstruction error method. Then, the DBN model parameters are supervised and fine-tuned through a back propagation (BP) mechanism. Finally, based on the model, the classification and recognition of HRRP is realized. The experimental results show that compared with the traditional neural network, the recognition accuracy and noise robustness of the deep belief network based on this paper are significantly improved, and the recognition accuracy can be improved by 8.5%.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： For the problem of high peak-to-average power ratio (PAPR) of transform domain communication system (TDCS) and the slow convergence of the PAPR of the traditional iterative clipping and filtering method, this paper proposed an improved iterative clipping and filtering method for TDCS signal PAPR reduction. By filtering the clipping noise introduced, this method reduced the PAPR regrowth and effectively eliminated out-of-band spectrum spread, and got better PAPR suppression effect in iteration. The simulation results show that on the one hand, this method can obtain better PAPR suppression effect, the first iteration can obtain about 1 dB performance gain compared with the traditional method and the third iteration has better effect than the fourth iteration of traditional method. On the other hand, it can improve the out-of-band spectrum performance, after filtering, the out-of-band spectrum power reduces by about 5 dB. The comparison of BER shows that the performance of system lost by the improved method is very low.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》
Abstract： Due to the presence of irrelevant features and redundant features in the fine feature set of frequency hopping radio stations, the large amount of calculation and low recognition accuracy are existed for radio stations identification. This paper proposed an individual identification method for frequency hopping radio stations based on CMFS-MIC feature selection. Firstly, the fine feature sets of each collected signal sample of frequency hopping radio were calculated, and then using the association information entropy to measure the combination effect of the feature subsets, taking into account the features’ relationship and the redundant relationship to sort each feature in descending order. On this basis, the approximate Markov blanket method using the largest information coefficient metric is used to remove redundant and irrelevant features. This process achieves the purpose of optimizing and reducing the dimension of feature subsets. Finally, it designed a voting combination classifier to realize the identification of four frequency-hopping radio signals. Simulation results show that proposed algorithm has higher sorting recognition rate.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-06-19 Cooperative journals: 《计算机应用研究》
Abstract： To safeguard the efficient implementation of airborne communications missions, this paper developed a coding aware opportunistic routing scheme which had advantages of both SDN and network coding, aiming at the insufficient of timeliness, reliability and overhead in the interaction of routing information for the airborne backbone networks. Following the basic idea of coding aware opportunistic routing, this routing scheme structured a forwarding consumption function combining the distance of nodes and the coding gains to assign priorities of candidate nodes, thus it could improve the network transmission efficiency. Besides, this routing scheme designed the feedback mechanism of the control message and the structure of flow table, thus it could reduce the control overhead. The simulation results show that this routing scheme can adapt to airborne communication, in addition, it can reduce the transmission delay and routing overhead while it can greatly improve the network throughput and transmission rate.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-06-19 Cooperative journals: 《计算机应用研究》
Abstract： To solve the problem of clustering of platform resources in C2 organization, firstly, each element in process of decision-making entity configuration is defined, then the work load are defined by two aspects as inside workload and outside workload. The root mean square (RMS) of work load are established as the objective function of configuration model, and platform scheduling scheme is taken as the input information, global updating rule based ant colony algorithm is applied to solve this problem. Finally, the method are verified and analyzed by simulation example, results show that a greater clustering scheme are obtained by this method, and it has advantages over traditional methods in terms of clustering results and convergence speed.
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 problem of low channel utilization and throughput because of burstiness on high-priority service accessing the satellite channel on account of long-range combat aircraft transmitting different priority service when it accesses satellite channel, the paper proposed a dynamic channel access strategy supporting service with priority for satellite communication network. The access strategy constructed the spectrum pool to share channel through introducing the cognitive radio technology. It set the high-priority service accessing channel freely, meanwhile, it ensured low priority business access the channel successfully through reserving spare channel. When there is some service not accessing channel, the service uses the queuing model for access. The simulation results show that this strategy can effectively guarantee the successful ratio of high-priority service accessing channel, meanwhile, it effectively reduces the access delay. When the access strategy is applied, it can effectively reduce the impact of burstiness on high-priority service accessing the satellite channel , which leads to improving the comprehensive utilization rate of the satellite channel, reducing the access delay of low-priority service and guaranteeing the throughput on low-priority service accessing the satellite network.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-18 Cooperative journals: 《计算机应用研究》
Abstract： In order to deal with the complexity and uncertainty of battlefield environment, the research on adaptive adjustment of command and control structure has become a hotspot. The basic entity and command and control structure of army organization are introduced. The method of decision-making entity’s load measurement is given. And, the optimization model of adaptive adjustment of command and control structure is established under two kinds of battlefield condition respectively. Then, artificial bee colony algorithm is used to solve this optimization problem. The concrete steps and process of the artificial bee colony algorithm are given. Finally, the case simulation is carried out. The adjustment method based on the artificial bee colony algorithm has obtained a good effect of the adjustment of command and control structure, which proves the feasibility of the artificial bee colony algorithm in adapting and adjusting the command and control structure.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-02 Cooperative journals: 《计算机应用研究》
Abstract： Aiming at the problem of poor precision in the application of compressed sensing theory in the field of broadband spectrum sensing, and according to the sparse characteristics of the stationary signal in the frequency domain, this paper developed a broadband compression spectrum sensing method based on P-Ifourier (Partial-Inverse fourier) observation matrix. The new method translated the spectrum sensing problem into a typical compressed sensing problem, and used the standard orthogonal Fourier basis observation matrix which has the excellent incoherence performance to build the observation matrix in order to have good reconstruction performance and reconstruction precision. The simulation results show that compared with the Gaussian random observation matrix and the embedded chaotic sequence - cyclic Toeplitz structure observation matrix, this method can significantly reduce the mean square error of signal reconstruction in the lower SNR environment, and under the same conditions it can significantly improves the probability of reconstruction.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-24 Cooperative journals: 《计算机应用研究》
Abstract： In order to carry out research of locating the source of GNSS spoofing interference, this paper built a model of multiple GNSS spoofing interference noise. Firstly, this paper analyzed the theory of spoofing and gave the mathematic models of signals. Then, it built a model of cross correlation interference of PRNs based on the analysis to composing and regular of the noise. Finally, this paper applied SNR and distribution of azimuth to depict the noise model. The simulation results indicated that the weight of the cross correlation noise of multiple GNSS spoofing in the noise of receiver tended to 100%. It reveals that the direction precision contradicts multiple GNSS spoofing power, and the result of direction finding can be optimized by SNR of the spoofing.
Hits
Hits
Downloads
Comment