In the paper, the fractal property of rotating machinery vibration signals and the principle of fractal data compression are summarized reviewed. Based on the fractal property, an approach for vibration signal data co...
详细信息
ISBN:
(纸本)9781424410651
In the paper, the fractal property of rotating machinery vibration signals and the principle of fractal data compression are summarized reviewed. Based on the fractal property, an approach for vibration signal data compression and reconstruction is proposed. In this method, a signal is represented by parameters of affine maps and is reconstructed according to self-similarity represented by the IFS parameters. the total data size of such a representation is far less than the original time domain data size. To demonstrate the effectiveness of this method to resolving the bottleneck in remote transmission of large amount signals and improving the capability of remote equipment fault diagnosis system, the presented method has been applied to some actual vibration signals as well as simulation signals.
this paper proposes an effective data hiding scheme for a binary host image for the purpose of access control, authentication and copyright protection of digital media. the binary image is divided into blocks of size ...
详细信息
ISBN:
(纸本)9781424410651
this paper proposes an effective data hiding scheme for a binary host image for the purpose of access control, authentication and copyright protection of digital media. the binary image is divided into blocks of size 2x2. these blocks are classified as embeddable or non-embeddable blocks according to their characteristic values, and a binary data sequence is embedded in those embeddable blocks by changing their characteristic values. the advantages of the method are low calculation, high embedding capacity, good security and maintaining high qualify of the host image.
In this paper, a novel view-based 3D object recognition method is proposed, which consists of three steps. First, employing wavelet transform to decompose view images of the object into different frequency sub-images....
详细信息
ISBN:
(纸本)9781424410651
In this paper, a novel view-based 3D object recognition method is proposed, which consists of three steps. First, employing wavelet transform to decompose view images of the object into different frequency sub-images. Second, for each sub-image, the features are extracted using singular-value decomposition (SVD) approach, and the features extracted from sub-images are combined to construct the feature vector of the original image. third, the feature vector is fed into the support vector machine (SVM) to classify the objects. Experimental results show that the proposed method is effective.
Lumber moisture content is a key parameter for regulating and controlling wood drying process. Its precision directly affects the drying quality, cost and drying time. In this paper a fusion model capable of on-line m...
详细信息
ISBN:
(纸本)9781424410651
Lumber moisture content is a key parameter for regulating and controlling wood drying process. Its precision directly affects the drying quality, cost and drying time. In this paper a fusion model capable of on-line measuring lumber moisture content is presented. Models for predicting lumber moisture content are established using both back-propagation neural networks (BPNN) and dynamical recurrent Mural networks (DRNN). Furthermore, the two models are integrated by arithmetic average and recursive estimation algorithm. the simulation result, which is worked out by experimental data, shows that fusion model have a higher predictive precision than any one of BP Mural network's and DRNN's, therefore, this method is proved to be feasible.
A new, distance estimation method for robot autonomous localization from high-dimensional camera images is proposed based on 4 popular manifold learning algorithms. the camera images are supposed to embed in a high-di...
详细信息
ISBN:
(纸本)9781424410651
A new, distance estimation method for robot autonomous localization from high-dimensional camera images is proposed based on 4 popular manifold learning algorithms. the camera images are supposed to embed in a high-dimensional;manifold, and then the dimension is reduced to estimate the corresponding coordinate of the robot. Two experiments show, that the distance is estimated regardless of the illumination, motion noise and, environment geometric features. Experiment results with 3 image sets acquiring;from the real environment verify the feasibility. and effectiveness of the scheme and algorithms proposed in this paper.
A kind of trading off algorithm off target classification combined with double mode intelligent fusion is presented, Applying neuron-fuzzy technique to the synthesis of the complementary information between radar and ...
详细信息
ISBN:
(纸本)9781424410651
A kind of trading off algorithm off target classification combined with double mode intelligent fusion is presented, Applying neuron-fuzzy technique to the synthesis of the complementary information between radar and infrared, through combining neuron-fuzzy, technique with D-S evidence fusion theory, the ability, of target classification could be improved At the same time, according to the effective defection range of sensors, reasonably select the target features that can ensure the accurate target classification so that the computation load of the algorithm can be largely decreased compared to the infrared single model fusion. Simulalion results illustrate that the trading off algorithm is effective.
the hybridization of optimization techniques can exploit the strengths of different approaches and avoid their weaknesses. In this work we present a hybrid optimization algorithm based on the combination of Evolution ...
详细信息
ISBN:
(数字)9783540734994
ISBN:
(纸本)9783540734987
the hybridization of optimization techniques can exploit the strengths of different approaches and avoid their weaknesses. In this work we present a hybrid optimization algorithm based on the combination of Evolution Strategies (ES) and Locally Weighted Linear Regression (LWLR). In this hybrid a local algorithm (LWLR) proposes a new solution that is used by a global algorithm (ES) to produce new better solutions. this new hybrid is applied in solving an interesting and difficult problem in astronomy, the two-dimensional fitting of brightness profiles in galaxy images. the use of standardized fitting functions is arguably the most powerful method for measuring the large-scale features (e.g. brightness distribution) and structure of galaxies, specifying parameters that can provide insight into the formation and evolution of galaxies. Here we employ the hybrid algorithm ES+LWLR to find models that describe the bi-dimensional brightness profiles for a set of optical galactic images. Models are created using two functions: de Vaucoleurs and exponential, which produce models that are expressed as sets of concentric generalized ellipses that represent the brightness profiles of the images. the problem can be seen as an optimization problem because we need to minimize the difference between the flux from the model and the flux from the original optical image, following a normalized Euclidean distance. We solved this optimization problem using our hybrid algorithm ES+LWLR. We have obtained results for a set of 100 galaxies, showing that hybrid algorithm is very well suited to solve this problem.
In oil well data analysis, for the existence of noises and the effort of singularity points, indention distribution is appears and normal analysis work is affected. For the redundant characters of discrete stationary ...
详细信息
ISBN:
(纸本)9781424410651
In oil well data analysis, for the existence of noises and the effort of singularity points, indention distribution is appears and normal analysis work is affected. For the redundant characters of discrete stationary wavelet transform, mid-way threshold method is applied to remove noises disturbance and smooththe whole procedure data. that is 10 smoothdata by using de-noising method Further more, adjusted modulus can be elected h? different slates and requirement of engineering technology for measuring data is satisfied.
Most of the existing studies on myocardial infraction (MI) feature extraction are based on certain important components. the subjective significance based method was introduced into the feature extraction from an enti...
详细信息
ISBN:
(纸本)9781424410651
Most of the existing studies on myocardial infraction (MI) feature extraction are based on certain important components. the subjective significance based method was introduced into the feature extraction from an entire ECG segment for the classification in the paper. the method was employed to discriminate the assumed prior class from the other classes and separate each of the classes at the same time. the data in the analysis including healthy control (HC), myocardial infraction in early stage and acute myocardial infraction (AMI) was collected from PTB diagnostic ECG database which is the latest public database for various research purposes. the results show that the proposed method can obtain the effective features from the ECGs with 12-leads for the classification purpose.
In this paper, a new, multiscale wavelet support vector machines model (MWSVM) is proposed, according to the Mercer condition, the wavelet frame theory and kernel function nature. From the statistical learningtheory ...
详细信息
ISBN:
(纸本)9781424410651
In this paper, a new, multiscale wavelet support vector machines model (MWSVM) is proposed, according to the Mercer condition, the wavelet frame theory and kernel function nature. From the statistical learningtheory and the SVM model, pointed out the SVM essence is kernel method, the different kernel function has decided the different SVM. the choice of kernel parameters is simplified in MWSVM. By the experiment withthe single-variable two-variable function and real image, the new model can approach linear and the non-linear combination functions very well. the experimental result shows that MWSVM is the validity and the usability.
暂无评论