Applied Mechanics and Materials Vols. 278-280

Abstract: This paper presents a new personal identification approach with fusion of hand shape geometry and palmprint features based on Gabor wavelet transformation. Two kinds personal features can be extracted form the low-resolution hand images. Hand shape geometry features include length of four fingers and width of palm. The palmprint features are composed of principal lines, wrinkles, minutiae, delta points. In pattern matching, the normalization method of matching degree is proposed. At the same time square difference distance is used to calculate feature matching degree of the hand shape geometry and palmprint. The result of experiment show that this approach is the most suitable, acceptable and the higher recognition rate, respectively, using different feature extraction methods.

Abstract: Image, due to the impact of such as blurring, distortion, noise, etc., will cause a reduction in image quality and the formation of the degradation of the digital image. The using of some kind of a priori knowledge use the least squares method to be filtered, so that the original image and its recovery minimum mean square error between the two images. This can get a better recovery image.

Abstract: A novel technique of vision-aided navigation for autonomous aircraft is presented in this paper. The aircraft’s position and pose are estimated with several control points. The saliency descriptor of corner is defined and the control points are selected according their saliency. Control points are tracked in sequential images based on Fourier-Melline transform. The unscented Kalman filter is used to fuse the aircraft state information provided by the vision system and the inertial navigation system. Experiments show that the accuracy, efficiency and robustness of aircraft navigation system are improved with the proposed method.

Abstract: The problem of disturbance attenuating controller design for delayed cellular neural networks (DCNNs) is considered. Via combining four different states cases in DCNNs and applying Razumikhin function analysis, a feedback control law in the form of linear matrix inequality (LMI) is derived for guaranteeing disturbance attenuation of the closed systems. Finally, a numerical example of DCNNs is given to indicate the effectiveness of the proposed disturbance attenuating control.

Abstract: In this paper, we consider the problem of mu-stability of unbounded time-varying delays neural systems with nonlinear perturbations. Some mu-stability criterias are derived by using Lyapunov- Krasovski functional method . Those criteria are expressed in the form of linear matrix inequalities (LMIs).

Abstract: In competitive sporting events, the scores confirm replied on manual timing can’t satisfy the requirements, according to the provisions of the IAAF, the major sports event will require the use of electric timing system. At present, the development level of the photo finish collecting still stay in the black-and-white image level, high-speed color linear CCD array technology used in track events final electrical-timing system, carried out in-depth analysis of the various factors that affect image quality of the post-processing, described in digital image processing with gray technology , color balance, histogram equalization and digital image processing techniques so as to get clear, high quality color image data.

Abstract: Aimed at the difficulty of the route selection of urban public transport line, a new method was proposed for the improved genetic algorithm BP neural fuzzy system model and algorithm. For the problem of route selection, it is required to acquire evolution rule of system status from the changes of multiple environment variable factors. The BP neural fuzzy system model based on Mamdani inference was given, in order to overcome the existing limitations of BP neural network, it puts forward the thought of algorithm improved by GA. The algorithm as the foundation is applied in route selection of urban road public transport line, and the method’s usability is proven through simulation, calculation and analytical investigation of practical problems on the main lines of bus rapid transit the route selection.

Abstract: Welch method is a direct evolution from the periodogram method. Periodogram method is also commonly used in the power spectrum estimation, there are some inherent shortcomings in periodogram method, such as the variance and resolution of the spectrum estimation is not good, it does not satisfy the consistency estimation conditions and so on, so this paper uses improved periodogram method (welch method) to estimate the motor imagery EEG power spectrum, with Matlab for tools, through the simulation on the experimental data, comparativing and analysising the welch method’s different spectrum estimation properties with different window functions, which provides the theoretical guidance for selecting a suitable window function and makes the welch method play a good role in the EEG feature extraction.

Abstract: Aimed at the problem of real-time and accurate Geometry Dilution of Precision (GDOP) approximation, a new method using general regression neural network (GRNN) was proposed firstly, and the training samples selection and normalization method was studied by using spectrum analysis. The computation results show that the symmetrical constellation needs 24 hours continuous samples while the hybrid one needs 72 hours to train the neural network sufficiently. Finally, the performance analysis shows that this new method has excellent performance on temporal and spatial generalization approximation accuracy, when trained GRNN are used, the GDOP computational error is less than 0.25 within 30 days, and the error is less than 0.3 within 10 degrees latitude/longitude area.

Abstract: Differential evolution is a simple and powerful globally optimization new algorithm. It is a population-based, direct search algorithm, and has been successfully applied in various fields. Optimal allocation of water resources is an important part of the planning of water resources. Traditional planning methods prove insufficient for the multi-objective system of water resources. In this paper, multi-objective differential evolution(MODE) algorithm applied to the regional water resources optimal allocation, through definition of economic, social, Eco-environmental three objective function and the constraints, the regional water resources optimal allocation model has been established, and then multi-objective genetic algorithm is used to solve the model .The model gets different results for optimal allocation water resources of Ningxia in 2030(Guarantee rate of water supply 50% and 75%). The result of example proves that the method is reasonable and feasible in the application of region water resources optimal allocation.