DNA sequence homology is a critical and fundamental problem in bioinformatics. In this paper, we solve this problem by use of the second order Markov modal instead of traditional sequence alignment because DNA charact...
详细信息
A vertex separator in an undirected graph is a subset of the vertices, whose removal disconnects the graph in at least two nonempty connected components. Given a connected undirected graph G = (V ,E) with |V| = n, an ...
详细信息
This paper introduces the theory of ϕ-Jensen variance. Our main motivation is to extend the connotation of the analysis of variance and facilitate its applications in probability, statistics and higher education. To t...
详细信息
Kernel independent component analysis (KICA) has been widely used in the field of blind source separation. The selection of kernel function and its parameters plays an important role in KICA algorithm performance. An ...
详细信息
ISBN:
(纸本)9781479979684
Kernel independent component analysis (KICA) has been widely used in the field of blind source separation. The selection of kernel function and its parameters plays an important role in KICA algorithm performance. An optimal kernel model should be rich enough to well map the given samples. However, users usually use a singular kernel based model in their experiments, which leads to a suboptimal kernel model. In order to solve this problem, we propose the evolution based multiple kernel independent component analysis (EMKICA), in which a convex combination of multiple base kernels is used instead of single kernel of KICA. The combination weights are learned by particle swarm optimization algorithm. Firstly, we elaborate the basic theory of KICA and concept of EMKICA, also the combination form of the composition kernel used in EMKICA. Secondly, we describe the presentation of the individuals in the particle swarm optimization algorithm, the settings of the evaluation function and general algorithm. Finally, we evaluate the separation ability of EMKICA on three different data sets including one-dimensional mixed signals, composite images and images with reflection. The experimental results verify the effectiveness of EMKICA.
In view of the draw backs of apple grade identification in China,which still relies on photoelectric sorting and manual separation,this paper presents a processing method on the basis of the technology of computer vis...
详细信息
In view of the draw backs of apple grade identification in China,which still relies on photoelectric sorting and manual separation,this paper presents a processing method on the basis of the technology of computer vision and digital *** image processing technology,the researcher calculated the length of the long-short-axis,marked the location of it and calculated the 4 parameters,color,mean square,shape,size,as the key characteristics of the BP input of network to build a network and identify the level of apple through analysis of the external characteristics of *** optimum structure parameters of the BP neural network which had 9 hidden layer neurons were determined by RP training *** showed that average accuracy for fruit classification can reach 92.5% by using this model,and the executing time of microcomputer for grading of one apple is 9.3 *** method has the characteristics of high accuracy and good real-time performance.
Aluminum air fuel cell has several characters as a kind of new energy, such as large specific energy, rich fuel source, low environmental pollution and so on. The character of high specific energy could extend driving...
详细信息
ISBN:
(纸本)9781467381086
Aluminum air fuel cell has several characters as a kind of new energy, such as large specific energy, rich fuel source, low environmental pollution and so on. The character of high specific energy could extend driving range of electric vehicle, but a low specific power with aluminum air fuel cell demands it should cooperate with lithium ion battery and super capacitor, which export higher power to drive the electronic vehicle. As a rechargeable power supply, lithium ion battery and super capacitor can effectively recycle energy at braking mode, so that they can step to extend driving range.
Electric valve has been applied to various occasions and domains. In some adverse environments where such defects of traditional control system as low efficiency and poor safety have been exposed, optical encoder is a...
详细信息
For natural numbers n and k, where n > 2k, a generalized Petersen graph P(n,k) is obtained by letting its vertex set be {u1,u 2,..,un} ∪ {u1,v2..,u n} and its edge set be the union of vi v i+1,uivi,ViVi+k over 1 ...
详细信息
For natural numbers n and k, where n > 2k, a generalized Petersen graph P(n,k) is obtained by letting its vertex set be {u1,u 2,..,un} ∪ {u1,v2..,u n} and its edge set be the union of vi v i+1,uivi,ViVi+k over 1 ≤ i ≤ n, where subscripts are reduced modulo n. In this paper, an integer programming formulation for Roman domination is established, which is used to give upper bounds for the Roman domination numbers of the generalized Petersen graphs P(n,3) and P(n,4). Together with the dynamic algorithm, we determine the Roman domination number of the generalized Petersen graph P(n, 3) for n ≥ 5.
One key challenge of facial trait recognition is the large non-rigid appearance variations due to some irrelevant real world factors, such as viewpoint and expression changes. In this paper, we explore how the shape i...
详细信息
ISBN:
(纸本)9781467369657
One key challenge of facial trait recognition is the large non-rigid appearance variations due to some irrelevant real world factors, such as viewpoint and expression changes. In this paper, we explore how the shape information, i.e. facial landmark positions, can be explicitly deployed into the popular Convolutional Neural Network (CNN) architecture to disentangle such irrelevant non-rigid appearance variations. First, instead of using fixed kernels, we propose a kernel adaptation method to dynamically determine the convolutional kernels according to the spatial distribution of facial landmarks, which helps learning more robust features. Second, motivated by the intuition that different local facial regions may demand different adaptation functions, we further propose a tree-structured convolutional architecture to hierarchically fuse multiple local adaptive CNN subnetworks. Comprehensive experiments on WebFace, Morph II and MultiPIE databases well validate the effectiveness of the proposed kernel adaptation method and tree-structured convolutional architecture for facial trait recognition tasks, including identity, age and gender recognition. For all the tasks, the proposed architecture consistently achieves the state-of-the-art performances.
暂无评论