Entity

Time filter

Source Type

Luoyang Henan, China

Guan X.,National University of Defense Technology | Guan X.,Yantai Naval Aeronautical and Astronautical University | Guo Q.,Yantai Naval Aeronautical and Astronautical University | Zhao J.,Yantai Naval Aeronautical and Astronautical University | Zhang Z.C.,PLA Unit 63880
International Conference on Signal Processing Proceedings, ICSP | Year: 2010

For resolving attibute reduction of the NP-hard problems effectively, a new complete and efficient Attribute Reduction Algorithm of Rough Set Based on Information Entropy and Ant Colony Algorithm is proposed. After computiing a core of the database by the algorithm of Rough Set and Information Entropy, find the other attibutes in the least reduction of attributes set by the proposed method. Experiments show that the proposed method can get not only the least reduction of complete and incomplete attributes set efficiently and effectively but also more least reductions. The proposed method is of profoud theoretical and pratical significance. © 2010 IEEE. Source


Guo Q.,Yantai Naval Aeronautical and Astronautical University | Guan X.,Yantai Naval Aeronautical and Astronautical University | Guan X.,National University of Defense Technology | Zhang Z.-C.,Yantai Naval Aeronautical and Astronautical University | And 2 more authors.
International Conference on Signal Processing Proceedings, ICSP | Year: 2010

Recognition degree of unknown radar emitter signal can be describe by upper and lower approximation sets of Rough Sets. From the uncertain degree measure by multi-sensors, pessimistic and non-pessimistic distances of every object to sensors and grey association matrix can be calculated by grey association theory. According α,β and grey association matrix, grey association degree and fusion result can gain. The simulation results show the method of combining Rough Sets and Grey Association theory is effective, and it can be applied on radar emitter signal recognition, especially in decreasing the uncertain degree introduced by multi-sensors. © 2010 IEEE. Source


Guan X.,Yantai Naval Aeronautical and Astronautical University | Guan X.,National University of Defense Technology | Guo Q.,Yantai Naval Aeronautical and Astronautical University | Zhang Z.-C.,PLA Unit 63880 | And 2 more authors.
Dianzi Keji Daxue Xuebao/Journal of the University of Electronic Science and Technology of China | Year: 2012

To deal with the problem of radar emitter recognition caused by noise environment, this paper presents a new method for emitter recognition based on backward cloud model and attribute similarity. In this method, a radar emitter database including noise data according with the reality is first constructed, the cloud numerical characteristic is then calculated based on backward cloud model. After that, the method for determining recognition weight of coefficients and a new classification implement based on backward cloud model and attribute similarity are proposed. Simulation results show that the proposed method can deal with the randomness and vagueness caused by noise environment much better and can conduct emitter recognition effectively in the adverse noise environment. Source


Kang J.,Ordnance Engineering College | Tang L.-W.,Ordnance Engineering College | Zuo X.-Z.,Ordnance Engineering College | Li H.,PLA Unit 63880 | Zhang X.-H.,Ordnance Engineering College
Zhendong yu Chongji/Journal of Vibration and Shock | Year: 2011

In order to reduce the amount of data of non-stationary and nonlinear signals collected in a sensor network, a grey Morlet wavelet kernel partial least squares (GMWKPLS) model was proposed. In this model, grey prediction theory was firstly introduced into kernel partial least squares (KPLS). Then, the input-output data were mapped to a nonlinear higher dimensional feature space with Morelt kernel transformation. Finally, a prediction and fusion model was constructed with linear partial least squares. Moreover, the moving window method was utilized to update samples continuously in this dynamical prediction model. The model was validated using vibration signals of gear tooth breakage with rising speed. The results showed that the model can execute dynamic multi-step prediction, and has higher precision prediction; thus, it can obviously reduce the data amount in a sensor network and save energy; compared with grey RBF kernel partial least squares (GRBFKPLS) and RBF kernel partial least squares (RBFKPLS), GMWKPLS is best in prediction performance, and the prediction errors are with in ±0.15%. Source


Qu W.,Tsinghua University | Qu W.,PLA Unit 63880 | Du Z.,Ordnance Engineering College | Du Z.,PLA Unit 63880 | And 3 more authors.
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | Year: 2011

The relative measurement is commonly used in measurement of laser radar cross section (LRCS) of a field target. It is effected by some factors, such as light beam mode of laser in measuring system, stability of laser power, atmospheric absorption, scattering and turbulence, laser reflection of background, circuit noise, etc. Laser beam mode is most important in these factors, causing the accuracy of LRCS measurement hard to test objectively. In order to solve this problem, the relative measurement of LRCS and its test system were introduced firstly. Then the effect of laser beam mode on system accuracy was discussed. Finally, the test method of system accuracy that combined shadowing method by using extinction cloth and laser spot image analyzing method was introduced. In addition, how to reduce the effect of light beam mode on system accuracy was analyzed. Source

Discover hidden collaborations