Advanced Materials Research Vols. 765-767

Abstract: According to the question that BP Neural Network has slow velocity of convergence and is apt to fall into the minimum value, chaos thought is adopted in the particle swarm optimization (PSO). For this, chaos particle swarm optimization algorithm, which improve the ability of getting rid of fractional extreme point in the PSO, is presented and applied to the BP network exercise so that the calculation accuracy and velocity of convergence of BP network are increased. The method of training the BP network for speaker recognition, the recognition rate and speed of training have been greatly improved, making the speaker recognition based on BP neural network to get better results.

Abstract: The article has carried on the optimization to the HMM algorithms Viterbi algorithm and LBG algorithm, It can be proofed that the optimized algorithm improved the text dependent recognition efficiency throgh experiment.

Abstract: Recently, automatic face recognition method has become one of the key issues in the field of pattern recognition and artificial intelligence. Typically, the face recognition process can be divided into three parts: the detection and recognition of human face, facial feature extraction and face recognition, and among which the facial feature extraction is the key to face recognition technology. In this paper, an extraction algorithm of face recognition feature, which is based on face recognition feature, is proposed. The experimental results based on the ORL face database demonstrate that this algorithm works well.

Abstract: Helicopter rotor system (HRS), which is a key component without redundancy design, is of significant importance for flight safety. Working under demanding environment, HRS faults are hard to detect. This paper proposes a new approach based on Hilbert-Huang Transform (HHT) and envelope demodulation to realize HRS fault feature extraction under strong interference. Empirical mode decomposition (EMD) was used to decompose the vibration signal into several intrinsic mode functions (IMFs) first, then, Hilbert transformation was applied to the IMFs to get the envelopes. And at last, fast Fourier transform (FFT) was adopted with the IMF which was closely related to the fault features. This method can avoid the selection of center frequency and filter band in resonance demodulation method, therefore, it has good adaptivity. Two commonly occurring faults in HRS are simulated on a test rig to validate the performance and effectiveness of the proposed method. The experimental results demonstrate that the proposed method based on HHT envelope demodulation is effective for the HRS fault feature extraction.

Abstract: In this paper, we propose a depth image based real-time 3D hand tracking method. Our method is based on the fact that human hand is an end point of human body. Therefore, we locate human hand by finding the end point from a predicted position of hand based on the hand position of the previous frame. We iteratively grow a region around the predicted position. The end point on the major axis of the region which stops moving with region growing is selected as the final position of human hand. Experiments on Microsoft Kinect for Xbox captured sequences show the effectiveness and efficiency of our proposed method.

Abstract: In this paper, we propose a novel real-time 3D hand gesture recognition algorithm based on depth information. We segment out the hand region from depth image and convert it to a point cloud. Then, 3D moment invariant features are computed at the point cloud. Finally, support vector machine (SVM) is employed to classify the shape of hand into different categories. We collect a benchmark dataset using Microsoft Kinect for Xbox and test the propose algorithm on it. Experimental results prove the robustness of our proposed algorithm.

Abstract: The forecast of precipitations is important in meteorology and atmospheric sciences. A new model is proposed based on empirical mode decomposition and the RBF neural network. Firstly, GPS PWV time series is broken down into series of different scales intrinsic mode function. Secondly, the phase space reconstruction is done. Thirdly, each component is predicted by RBF. Finally, the final prediction value is reconstructed. Next, the model is tested on annual precipitation sequence from 2001 to 2010 in northeast China. The result shows that predictive value is close to the actual precipitation, which can better reflect the actual precipitation change. From 2001 to 2010, the maximum deviation of the predicted values never exceeds 4%. The testing results show that the proposed model can increase precipitation forecasting accuracies not only in GPS PWV but also in annual precipitation.

Abstract: The examination of the Computer Graphics is basically the computer examination to investigate the drawing ability in universities in recent years. Based on many years of teaching practice and according to the transformation trend of the computer intelligent paper marking, the image processing technology is adopted, and the key information of the image is extracted, and the image similarity calculation program is compiled, and the CAD automatic paper marking function is implemented by the contrast of the students plots with the standard answer. Through the calculation examples, the grading results are consistent with the artificial results ideally. The calculation speed is faster than the manual speed, thus the teachers working efficiency is improved.

Abstract: The Scintillation effect of turbulence on laser measurement in high temperature environment will cause light moves, bend, or shake according to the ideal path. The object will have fuzzy dispersion and abnormal image on focal plane. By measuring the thickness of the high-environment glass, using characteristics of the distribution of the linear array CCD image spot inner-pixel grayscale in high-temperature environment and high relevance between each image spot, to create a mathematic model which can report the relationship between grayscale of the target area and the location of the center of mass of the target image spot as accurately as possible. By using this model, the accurate estimation of the location of the target point will be achieved.

Abstract: The authors improve the performance of an image cipher algorithm based chaos theory. The authors do Preprocessing for the algorithm firstly, makes spatial scrambling based on image blocking in order to interrupt pixel position, then furthering this interruption through Arnold mapping, and transforms pixel RGB color space through optimized Arnold Mapping. At last, we get the final encrypted image through a series of iteration. With some theoretical analysis of security, this algorithm has a lot of advantages such as, good diffusion properties, its key space is safe enough to resist exhaustive-key-research attack, high effectiveness and resisting common attack successfully, but it needs improvements on some aspects, such as the key sensitivity.