In this work we introduce a new methodology to build a kernel matrix from a collection of kernels. the key idea is to build a unique kernel that eliminates spurious differences between kernels. We propose a method bas...
详细信息
In this work we introduce a new methodology to build a kernel matrix from a collection of kernels. the key idea is to build a unique kernel that eliminates spurious differences between kernels. We propose a method based on the Procrustes problems that uses the alternating projections method to minimize a certain error measure. the resulting kernel will be used for classification purposes using support vector machines (SVMs). the proposed method has been successfully evaluated against alternative kernel combination techniques
the quantization parameter (QP) has a very important impact on the compression rate in H.264. In this paper we show that in order to achieve efficient rate-control coding a good estimate for the initial QP parameter i...
详细信息
the quantization parameter (QP) has a very important impact on the compression rate in H.264. In this paper we show that in order to achieve efficient rate-control coding a good estimate for the initial QP parameter is necessary. An extensive altering of this value, to keep the required titrate, results in significant fluctuation of the image quality and decreases the average quality of the whole coded sequence. We propose a simple and fast method to decide the starting value for QP for each part of the video sequence. Experimental results show stabilized image quality and significant gain in PSNR
Disparity flow depicts the 3D motion of a scene in disparity space of a given view and can be considered as view-dependent scene flow. the disparity flow map of a given view is a 2D array of 3D vectors that depicts th...
详细信息
ISBN:
(纸本)0769525210
Disparity flow depicts the 3D motion of a scene in disparity space of a given view and can be considered as view-dependent scene flow. the disparity flow map of a given view is a 2D array of 3D vectors that depicts the 3D motion observed at different pixel locations. Estimating 3D motion in form of disparity flow map limits all computations in the 2D image space and converts the 3D motion estimation problem into a 2D labeling problem. A novel algorithm is presented in this paper for disparity flow estimation using the orthogonal reliability-based dynamic programming technique. Experimental results using captured stereo sequences show that the new algorithm can generate dense and smooth 3D motion for dynamic scenes
Software project control and software process improvement both depend on the ability to measure software development status. this paper introduces the software engineering expert system (SEES) tool where the software ...
详细信息
Software project control and software process improvement both depend on the ability to measure software development status. this paper introduces the software engineering expert system (SEES) tool where the software professional can gather metrics from CASE tool databases to reconstruct all activities in a software project from project initiation to project termination. SEES is Internet based and can be applied to help manage globally distributed projects
We present the design and implementation of ***, a prototype for managing, querying, and visualizing 3D CT (computed tomography) datasets. the system is motivated by scientific studies of fossil records. Our prototype...
详细信息
We present the design and implementation of ***, a prototype for managing, querying, and visualizing 3D CT (computed tomography) datasets. the system is motivated by scientific studies of fossil records. Our prototype is built on top of SQL server 2005 and uses both Web service and service broker technologies. the desktop client utilizes commodity graphics cards to interactively render 3D volumes. this paper presents the user requirements, discusses the design of the data model and desktop client, and reports on preliminary performance measurements. Our experiments show that by pushing the spatial logic as low as possible into the DBMS, we can filter the data early. We observe some significant performance benefits from the reduced message traffic to and from the remote client
Instruction scheduling is one of the most important steps for improving the performance of object code produced by a compiler. A fundamental problem that arises in instruction scheduling is to find a minimum length sc...
详细信息
Instruction scheduling is one of the most important steps for improving the performance of object code produced by a compiler. A fundamental problem that arises in instruction scheduling is to find a minimum length schedule for a basic block - a straight-line sequence of code with a single entry point and a single exit point - subject to precedence, latency, and resource constraints. Solving the problem exactly is NP-complete, and heuristic approaches are currently used in most compilers. In contrast, we present a scheduler that finds provably optimal schedules for basic blocks using techniques from constraint programming. In developing our optimal scheduler, the key to scaling up to large, real problems was in the development of preprocessing techniques for improving the constraint model. We experimentally evaluated our optimal scheduler on the SPEC 2000 integer and floating point benchmarks. On this benchmark suite, the optimal scheduler was very robust -all but a handful of the hundreds of thousands of basic blocks in our benchmark suite were solved optimally within a reasonable time limit - and scaled to the largest basic blocks, including basic blocks with up to 2600 instructions. this compares favorably to the best previous exact approaches
Most genetic programming paradigms are population-based and require huge amount of memory. In this paper, we review the instruction matrix based genetic programming which maintains all program components in a instruct...
详细信息
Most genetic programming paradigms are population-based and require huge amount of memory. In this paper, we review the instruction matrix based genetic programming which maintains all program components in a instruction matrix (IM) instead of manipulating a population of programs. A genetic program is extracted from the matrix just before it is being evaluated. After each evaluation, the fitness of the genetic program is propagated to its corresponding cells in the matrix. then, we extend the instruction matrix to the condition matrix (CM) for generating rule base from datasets. CM keeps some of characteristics of IM and incorporates the information about rule learning. In the evolving process, we adopt an elitist idea to keep the better rules alive to the end. We consider that genetic selection maybe lead to the huge size of rule set, so the reduct theory borrowed from rough sets is used to cut the volume of rules and keep the same fitness as the original rule set. In experiments, we compare the performance of condition matrix for rule learning (CMRL) with other traditional algorithms. Results are presented in detail and the competitive advantage and drawbacks of CMRL are discussed
According to the characteristics of the operational behavior and runtime state of application sever, the resource consumption time series are observed and modeled by fuzzy wavelet network (FWN) with fuzzy logic infere...
详细信息
According to the characteristics of the operational behavior and runtime state of application sever, the resource consumption time series are observed and modeled by fuzzy wavelet network (FWN) with fuzzy logic inference and learning capability. the objective is to model the extracted data series of systematic performance parameters to predict software aging in application server. the dimensionality of input variables of FWN is reduced by principal components analysis (PCA), and the structure and parameters of FWN are optimized with adaptive genetic algorithm (GA). Judging by the model, we can get the aging threshold before application server failed and preventively maintenance the application server before systematic parameter value reaches the threshold. the experiments are carried out to validate the efficiency of the proposed model and show that the aging prediction model based on FWN with adaptive genetic algorithm is superior to the neural network (NN) model and wavelet network (WN) model in the aspects of convergence rate and prediction precision
We proposed a new method for on-line handwritten Chinese word recognition based on lexicon. A pre-segment strategy is first applied to the input strokes and merges the strokes into candidate character boxes. Segmentat...
详细信息
ISBN:
(纸本)0769525210
We proposed a new method for on-line handwritten Chinese word recognition based on lexicon. A pre-segment strategy is first applied to the input strokes and merges the strokes into candidate character boxes. Segmentation path generation and filtering method is then invoked to generate segmentation paths from the boxes and filter out impossible paths by the recognition results of candidate character and lexicon-based technique. the optimal segmentation path along withthe best matching word in the lexicon is finally chosen by a voting strategy using both recognition and geometrical information. Superiority of the proposed approach has been proven by testing it with 8550 words collected by Tablet PC. the accuracy of segmentation and recognition is about 99%
Dynamic time warping (DTW) has been widely used to align and compare two sequences. DTW can efficiently deal with local warp or deformation between sequences. However, it can't take account of affine transformatio...
详细信息
ISBN:
(纸本)0769525210
Dynamic time warping (DTW) has been widely used to align and compare two sequences. DTW can efficiently deal with local warp or deformation between sequences. However, it can't take account of affine transformation of sequences, such as rotation, shift and scale. this paper introduces a novel affine invariant dynamic time warping (AI-DTW) method, which tries to deal withthe affine transformation and sequence alignment in a unified framework. We propose an iterative algorithm to estimate the optimal transformation matrix and warping path by mutually updating them. Recognition experiments on the online rotated handwritten data illustrated that the AI-DTW achieves a recognition rate of 95.54%, which is significantly higher than that (65.87%) of the classical DTW method
暂无评论