In this paper, we provided an algorithm to reconstruct images with Least Squares Support Vector Machines(LS-SVM) and Simulated Annealing Particle Swarm Optimization(APSO), named SAP. This algorithm introduces simulate...
详细信息
In this paper, we provided an algorithm to reconstruct images with Least Squares Support Vector Machines(LS-SVM) and Simulated Annealing Particle Swarm Optimization(APSO), named SAP. This algorithm introduces simulated annealing ideas into PSO, adopts cooling process functions to replace the inertia weight function and construct the time variant inertia weight function featured in annealing mechanism;takes use of the APSO algorithm to search for the optimized resolution of Electrical Capacitance Tomography(ECT) reconstruction image. In order to overcome the soft field characteristics of ECT sensitivity field, we exercised some image samples of typical flow pattern with LSSVM so as to predict the capacitance error caused by the soft field characteristics and then construct the fitness function of the particle swarm optimization on basis of the capacitance error. The simulation results show that SAP algorithm is featured in quick convergence rate and higher imaging precision. Compared with Landweber algorithm, the quality of reconstruction image with SAP is significantly improved.
Hierarchy task network (HTN) planning, as one of AI planning approaches, has been widely used in the emergency decision making for action planning in recent years, in which domain knowledge plays an important role. Th...
详细信息
Hierarchy task network (HTN) planning, as one of AI planning approaches, has been widely used in the emergency decision making for action planning in recent years, in which domain knowledge plays an important role. The special and complicated characteristics of emergency domain knowledge make it difficult to model, hindering the application of HTN planning to emergency action plan development. Though ontology modeling can get over the difficulty, existing ontology models for the emergency domain knowledge are either incomplete or not applicable for HTN planning. This paper aims at constructing emergency domain knowledge ontology applicable for HTN planner SHOP2 which can effectively support the emergency action plan development. An approach of translating an emergency domain knowledge model into a SHOP2 domain is also discussed in the paper. Finally an implementation of our work is roughly introduced.
This paper is to present a defect detecting and locating method of tubular cylindrical conductor based on alternating current impedance measurement theory. A defect estimation can be made through the impedance measure...
详细信息
This paper presents an investigation on the dynamics of a supply chain system under stock-dependent demand. Considering the feature of piecewise linearity, a switched linear model composed of three subsystems is devel...
详细信息
This paper presents an investigation on the dynamics of a supply chain system under stock-dependent demand. Considering the feature of piecewise linearity, a switched linear model composed of three subsystems is developed. Based on the switched model, some analytical stability results are derived. Simulation experiments are designed to verify the stability results and observe nonlinear dynamics. We show that stock-dependent demand not only leads to different stability results but also makes nonlinear dynamics more complicated. We also reveal that the nonlinear dynamics of the switched model, such as chaotic and periodic fluctuations of inventory and order, are essentially caused by switching frequently among subsystems due to uncertainties of inventory status. The results obtained in this paper help us understand the dynamic complexities of supply chain system and provide guidelines for selecting decision parameters to improve overall performance.
The transient electromagnetic exploration in borehole is a full space geophysical problem. The Gaver-Stehfeest inverse Laplace transform is used to theoretically calculate the transient electromagnetic response in the...
详细信息
The transient electromagnetic exploration in borehole is a full space geophysical problem. The Gaver-Stehfeest inverse Laplace transform is used to theoretically calculate the transient electromagnetic response in the receiver loop. And the effects of the parameters of the borehole mud, metal casing, the cement sheath and the formation on electromagnetic logging responses are analyzed. The response curves of different electrical conductivity of the borehole mud indicate that the borehole mud has little effect on the electromagnetic responses. The numerical results of different geometry of the casing pipe show that the inner radius and the thickness of casing have an obvious effect on the logging responses, moreover the abnormality of transient response appears where the casing thickness suddenly increases or decreases. The simulation results of different magnetic permeability of the casing pipe show that it has an important effect on transient response in borehole and the higher the magnetic permeability, the more difficult the electromagnetic signals transmitting through the casing. Results of different parameters of the cement sheath reflect that the high conductive cement sheath can generate large measurement error for low conductive formation. It is also found that the effect of the thickness of the cement sheath can be ignored for high conductive formation.
Synchronization and pinning control of complex networks is to regulate the agents' behavior and improve network performance. In this article, we review some recent developments in pinning control. Stability algori...
详细信息
As the Harris detector can produce false and unstable corners, and obtained matching points have different accuracies in aerial video registration, an aerial video registration algorithm using optimal gradient filters...
详细信息
As the Harris detector can produce false and unstable corners, and obtained matching points have different accuracies in aerial video registration, an aerial video registration algorithm using optimal gradient filters and projective invariant was proposed. Firstly, a Harris detector based on optimal gradient filters was presented to determine the location of corners, and the locally most stable points were selected to be matching points. Then, the Delaunay triangulation was used to perform the initial matching. Finally, the most "useful" matching points that best satisfied the cross-ratio invariant were presented to estimate the geometry transformation and finish the image registration. Experiment results show that the proposed method by the optimal gradient filters and cross-ratio invariant can realize the registration between the frames, and the average geometric fidelity error is 0.869 for 8 sets of the unmanned video sequences with a resolution of 320 pixel×240 pixel. The method can capture moving objects effectively.
This paper proposed a H∞ based controller design method for MIMO system. We use the bound real lemma to design the controller when the reference model is given. The BMI (Bi-linear Matrix Inequality) problem is turned...
详细信息
This paper proposes a novel method for content-based image retrieval based on interest points. Interest points are detected from the scale and rotation normalized image. Then the normalized image is divided into a ser...
详细信息
This paper proposes a novel method for content-based image retrieval based on interest points. Interest points are detected from the scale and rotation normalized image. Then the normalized image is divided into a series of sector sub-regions with different area according to the distribution of interest points. With robustness to the image's rotation, scale and translation, local features of every sector sub-region are extracted to describe the image and make the similarity measure. In the relevant feedback phase, images are regarded as multi-instance (MI) bags, and the MI learning algorithm is employed to compute the target image feature. Finally, the similarity is recalculated. Experimental results show that our method can effectively describe the image, and obviously improve the average retrieval precision.
The overview presents the development and application of Hierarchical Temporal Memory (HTM). HTM is a new machine learning method which was proposed by Jeff Hawkins in 2005. It is a biologically inspired cognitive met...
详细信息
暂无评论