Panicle swarm optimization （PSO） is an optimization algorithm based on the swarm intelligent principle. In this paper the modified PSO is applied to a kernel principal component analysis （ KPCA ） for an optimal ke...Panicle swarm optimization （PSO） is an optimization algorithm based on the swarm intelligent principle. In this paper the modified PSO is applied to a kernel principal component analysis （ KPCA ） for an optimal kernel function parameter. We first comprehensively considered within-class scatter and between-class scatter of the sample features. Then, the fitness function of an optimized kernel function parameter is constructed, and the particle swarm optimization algorithm with adaptive acceleration （CPSO） is applied to optimizing it. It is used for gearbox condi- tion recognition, and the result is compared with the recognized results based on principal component analysis （PCA）. The results show that KPCA optimized by CPSO can effectively recognize fault conditions of the gearbox by reducing bind set-up of the kernel function parameter, and its results of fault recognition outperform those of PCA. We draw the conclusion that KPCA based on CPSO has an advantage in nonlinear feature extraction of mechanical failure, and is helpful for fault condition recognition of complicated machines.展开更多
We assessed chemical composition and variation in oil content and seed weight of 40 wild-growing almonds（Prunus L. spp.） accessions collected from different parts of Iran. There were significant differences in kerne...We assessed chemical composition and variation in oil content and seed weight of 40 wild-growing almonds（Prunus L. spp.） accessions collected from different parts of Iran. There were significant differences in kernel weight and oil parameters. Accessions ranged from0.20 to 1.5 g in kernel weight, 0.2–3.0 mm in shell thickness, and 16–55 % in oil content. The predominant vegetable oil components of kernels were 4.6–9.5 % palmitic acid, 0.4–0.8 % palmitoleic acid, 1.0–3.4 % stearic acid,48.8–88.4 % oleic acid and 11.3–33.2 % linoleic acid.Linolenic acid was detected in 15 accessions. High heritability was recorded for all studied traits and was maximum for shell thickness（98.5 %） and minimum for oil content（97.1 %）. Maximum and minimum ‘Euclidean＇pair wise dissimilarities were 17.9 and 0.5, respectively.All 40 accessions were grouped into two major clusters.展开更多
The support vector machine （SVM） is a novel machine learning tool in data mining. In this paper, the geometric approach based on the compressed convex hull （CCH） with a mathematical framework is introduced to solv...The support vector machine （SVM） is a novel machine learning tool in data mining. In this paper, the geometric approach based on the compressed convex hull （CCH） with a mathematical framework is introduced to solve SVM classification problems. Compared with the reduced convex hull （RCH）, CCH preserves the shape of geometric solids for data sets; meanwhile, it is easy to give the necessary and sufficient condition for determining its extreme points. As practical applications of CCH, spare and probabilistic speed-up geometric algorithms are developed. Results of numerical experiments show that the proposed algorithms can reduce kernel calculations and display nice performances.展开更多
This paper deals with the FEEDBACK VERTEX SET problem on undirected graphs, which asks for the existence of a vertex set of bounded size that intersects all cycles. Due it is theoretical and practical importance,the p...This paper deals with the FEEDBACK VERTEX SET problem on undirected graphs, which asks for the existence of a vertex set of bounded size that intersects all cycles. Due it is theoretical and practical importance,the problem has been the subject of intensive study. Motivated by the parameter ecology program we attempt to classify the parameterized and kernelization complexity of FEEDBACK VERTEX SET for a wide range of parameters.We survey known results and present several new complexity classifications. For example, we prove that FEEDBACK VERTEX SET is fixed-parameter tractable parameterized by the vertex-deletion distance to a chordal graph. We also prove that the problem admits a polynomial kernel when parameterized by the vertex-deletion distance to a pseudo forest, a graph in which every connected component has at most one cycle. In contrast, we prove that a slightly smaller parameterization does not allow for a polynomial kernel unless NP coNP=poly and the polynomial-time hierarchy collapses.展开更多
基金supported by National Natural Science Foundation under Grant No.50875247Shanxi Province Natural Science Foundation under Grant No.2009011026-1
文摘Panicle swarm optimization （PSO） is an optimization algorithm based on the swarm intelligent principle. In this paper the modified PSO is applied to a kernel principal component analysis （ KPCA ） for an optimal kernel function parameter. We first comprehensively considered within-class scatter and between-class scatter of the sample features. Then, the fitness function of an optimized kernel function parameter is constructed, and the particle swarm optimization algorithm with adaptive acceleration （CPSO） is applied to optimizing it. It is used for gearbox condi- tion recognition, and the result is compared with the recognized results based on principal component analysis （PCA）. The results show that KPCA optimized by CPSO can effectively recognize fault conditions of the gearbox by reducing bind set-up of the kernel function parameter, and its results of fault recognition outperform those of PCA. We draw the conclusion that KPCA based on CPSO has an advantage in nonlinear feature extraction of mechanical failure, and is helpful for fault condition recognition of complicated machines.
基金financially supported by Payam-e-Noor University
文摘We assessed chemical composition and variation in oil content and seed weight of 40 wild-growing almonds（Prunus L. spp.） accessions collected from different parts of Iran. There were significant differences in kernel weight and oil parameters. Accessions ranged from0.20 to 1.5 g in kernel weight, 0.2–3.0 mm in shell thickness, and 16–55 % in oil content. The predominant vegetable oil components of kernels were 4.6–9.5 % palmitic acid, 0.4–0.8 % palmitoleic acid, 1.0–3.4 % stearic acid,48.8–88.4 % oleic acid and 11.3–33.2 % linoleic acid.Linolenic acid was detected in 15 accessions. High heritability was recorded for all studied traits and was maximum for shell thickness（98.5 %） and minimum for oil content（97.1 %）. Maximum and minimum ‘Euclidean＇pair wise dissimilarities were 17.9 and 0.5, respectively.All 40 accessions were grouped into two major clusters.
基金Supported by the National Natural Science Foundation of China (No. 30571059)the National High-Tech Research and Development Program of China (No. 2006AA02Z190)Shanghai Leading Academic Discipline Project (No. 530405)
文摘The support vector machine （SVM） is a novel machine learning tool in data mining. In this paper, the geometric approach based on the compressed convex hull （CCH） with a mathematical framework is introduced to solve SVM classification problems. Compared with the reduced convex hull （RCH）, CCH preserves the shape of geometric solids for data sets; meanwhile, it is easy to give the necessary and sufficient condition for determining its extreme points. As practical applications of CCH, spare and probabilistic speed-up geometric algorithms are developed. Results of numerical experiments show that the proposed algorithms can reduce kernel calculations and display nice performances.
基金supported by the European Research Council through Starting Grant 306992 "Parameterized Approximation"
文摘This paper deals with the FEEDBACK VERTEX SET problem on undirected graphs, which asks for the existence of a vertex set of bounded size that intersects all cycles. Due it is theoretical and practical importance,the problem has been the subject of intensive study. Motivated by the parameter ecology program we attempt to classify the parameterized and kernelization complexity of FEEDBACK VERTEX SET for a wide range of parameters.We survey known results and present several new complexity classifications. For example, we prove that FEEDBACK VERTEX SET is fixed-parameter tractable parameterized by the vertex-deletion distance to a chordal graph. We also prove that the problem admits a polynomial kernel when parameterized by the vertex-deletion distance to a pseudo forest, a graph in which every connected component has at most one cycle. In contrast, we prove that a slightly smaller parameterization does not allow for a polynomial kernel unless NP coNP=poly and the polynomial-time hierarchy collapses.
