Influenza viruses originate from birds, and transmit to pigs and humans with the development of history. Previously, we took more attention on the study of human influenza epidemic, and neglected the roles played by t...
详细信息
ISBN:
(纸本)9781509037117
Influenza viruses originate from birds, and transmit to pigs and humans with the development of history. Previously, we took more attention on the study of human influenza epidemic, and neglected the roles played by the birds and pigs in influenza transmission. In this paper, we constructed a multi-SIR model to reflect the influenza transmission from birds, to pigs, to humans. We got the condition to guarantee the existence of epidemic equilibrium point and analyzed the stability of the epidemic equilibrium point and disease-free equilibrium point. From the results of numerical simulation, we got the significant role of pigs as intermedia hosts in the transmission of influenza viruses.
Closed-loop stimulation (CLS), based on intracardiac impedance, is a method of rate-responsive pacing. There are many CLS algorithms propounded in previous researches, such as stroke volume (SV), ejection fraction (EF...
详细信息
ISBN:
(纸本)9781509037117
Closed-loop stimulation (CLS), based on intracardiac impedance, is a method of rate-responsive pacing. There are many CLS algorithms propounded in previous researches, such as stroke volume (SV), ejection fraction (EF), half cycle activity (HCA) and ventricular inotropic parameter (VIP). To compare these algorithms' performance this study measured 3 male beagles' intracardiac impedance waveform during different exercise levels, and then impedance data were processed with different algorithms. It demonstrated that all algorithms have good linear correlation with exercise levels (r 2 in complete atrioventricular block, SV: 0.75310, EF: 0.74056, HCA: 0.75014, and VIP: 0.81278; r 2 in normal heart, SV: 0.70748, EF: 0.72637, HCA: 0.80509, VIP: 0.83660. in all case, p
Vehicle recognition has been an important topic in intelligent transportation. However, to recognize different vehicle models from a same make is difficult as there are many near-identical cars under different brand n...
详细信息
ISBN:
(纸本)9781509037117
Vehicle recognition has been an important topic in intelligent transportation. However, to recognize different vehicle models from a same make is difficult as there are many near-identical cars under different brand names. In this paper, we investigated fine-grained vehicle recognition via deep Convolutional Neural Network (CNN). Vehicle and the corresponding parts are localized with the help of Region-based Convolutional Neural Networks (RCNN) and their features from a set of pre-trained CNNs are aggregated to train a SVM classifier. We created a fine-grained vehicle dataset and performed subsequent experiments, with preliminary results showing the potentials of the method.
Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object b...
详细信息
ISBN:
(纸本)9781509037117
Vehicle detection and vehicle type/make classification have been attracting more research in recent years. Previous methods for vehicle detection typically rely on large number of annotated training images by object bounding boxes, which is expensive and often subjective. In this paper, we propose a vehicle detection and recognition system by applying weakly-supervised convolutional neural network (CNN), with training relying only on image-level labels. Experiments were conducted on a datasets acquired from field-captured traffic surveillance cameras, with vehicle classification performance mAP 98.79% and accuracy 98.28%, and vehicle detection performance mAP 85.26%.
High Definition video color information research and analysis, mainly considering compression process brought about a decline in the quality of visual perception. Four subjective evaluation is designed and experiments...
详细信息
ISBN:
(纸本)9781509037117
High Definition video color information research and analysis, mainly considering compression process brought about a decline in the quality of visual perception. Four subjective evaluation is designed and experiments has been done: The diversity of the human eye perception of time; rate selection; and two subjective evaluation experiments of the video with DSCQS as the standard. The High Definition video main characteristics of the human eye perception between color and compression rate injury. Before the experiment, statistical methods were used to calculate the actual sample size; according to R-REC-BT series of standards for subjective evaluation results of the statistical data after the experiment. Finally, analyzed the data results combined with color visual characteristics of the human eye.
Automatic segmentation and early diagnosis of brain tumor is a challenging problem in computer vision and it can provide possibility for pre-operative planning, and solve the problem such as low accurateness and time-...
详细信息
ISBN:
(纸本)9781509037117
Automatic segmentation and early diagnosis of brain tumor is a challenging problem in computer vision and it can provide possibility for pre-operative planning, and solve the problem such as low accurateness and time-consuming in traditional manual segmentation. Under the mentioned problems above, this paper put forward a new method: Based on traditional convolutional neural networks (CNNs), a new architecture model is proposed for automatic brain tumor segmentation, which combines multi-modality images. The newly designed CNNs model automatically learns useful features from multi-modality images to combine multi-modality information. Experiment results show that the proposed model is more accurate than traditional methods and can provide reliable information for clinic treatments.
In the past video restoration algorithms using exemplar-based method, the exhaustive strategy of searching for the best matching patch is always used, which makes the computation very heavy. Moreover the accumulated m...
详细信息
ISBN:
(纸本)9781509037117
In the past video restoration algorithms using exemplar-based method, the exhaustive strategy of searching for the best matching patch is always used, which makes the computation very heavy. Moreover the accumulated matching error easily leads the wrong information spread. So a novel fast video inpainting algorithm is proposed in this paper. When restoring the damaged background, the information is directly replicated to fill in the damaged region from the constructed panoramic background image. When restoring the damaged foreground, it seeks a best state matching frame by comparing the adjacent running foreground state of the damaged frame, and searches the best matching patch in this frame. Meanwhile, the algorithm also improves the way of searching exemplar patch, principle of matching cost and way of confidence term updating. Experimental results show that the proposed algorithm is suitable for video with stationary background and periodical running foreground, having better efficiency and restoration effects.
In this paper, we investigate the problem of learning multiple overlapped manifolds from data samples with noise. Learning low dimensional nonlinear manifolds embedded in high dimensional Euclidean space has been an i...
详细信息
ISBN:
(纸本)9781509037117
In this paper, we investigate the problem of learning multiple overlapped manifolds from data samples with noise. Learning low dimensional nonlinear manifolds embedded in high dimensional Euclidean space has been an important issue in many data driven pattern analysis applications. The work in this paper extends manifold learning into the complex situations where an unknown number of manifolds may overlap. The approach proposed introduces the notion of flow consisting of multi-agents in a formation exploring a smooth curve on a manifold and thus separating different manifolds. A flow generates an ordered sequence of neighborhoods visited by the agents and can be used to simplify elastic mapping to discover the principal manifold structures. Simulations in various settings demonstrate the effectiveness of the proposed approach.
We mainly research the method of designing the D-admissible controller for singular delta operator systems. In order to ensure that the generalized Delta operator system is D-admissible, we design a state feedback con...
详细信息
ISBN:
(纸本)9781509037117
We mainly research the method of designing the D-admissible controller for singular delta operator systems. In order to ensure that the generalized Delta operator system is D-admissible, we design a state feedback controller. According to the definition of the generalized discrete system and the generalized Delta operator system, the relationship between them is analyzed. And the necessary and sufficient conditions for the D-admissibility of the singular Delta operator system are derived. Secondly, on account of the condition, the method of solving this D-admissible controller is to use linear matrix inequalities (LMI). Finally, in order to verify the effectiveness of the method, we give some numerical examples. Thus, the design method of this paper is feasible, and the D-admissible controller is reasonable and effective.
In order to reduce the staircasing effect of total variation (TV) denoising results, the high order difference is regarded as the regularization item in the high order total variation model (HOTV). The degradation rat...
详细信息
ISBN:
(纸本)9781509037117
In order to reduce the staircasing effect of total variation (TV) denoising results, the high order difference is regarded as the regularization item in the high order total variation model (HOTV). The degradation rate of HOTV is faster than the degradation rate of TV in the edge area of the image, so the edge details are lost in the HOTV model while the noise are removed. For reducing the staircasing effect and preserving the edge details effectively, spatially adaptive HOTV model is introduced which difference eigenvalue is as improved adaptive coefficient. The experiment results have demonstrated that the new spatially adaptive HOTV model can preserve detail information and reduce the staircasing effect, at the same time, the de-noising rate and visual effect are superior to both of them.
暂无评论