Under the framework of support vector machines,this paper proposes a new kernel method based on neighbor bands mutual information for hyperspectral datum *** algorithm assigns weights to different bands in the kernel ...
详细信息
Under the framework of support vector machines,this paper proposes a new kernel method based on neighbor bands mutual information for hyperspectral datum *** algorithm assigns weights to different bands in the kernel function according to the amount of useful information that they contain,which makes the band with more useful informa-tion play more important role in the *** research has shown that the band with greater mutual information between neighbor bands contains more useful information,and hence we use the mutual information of each band and its neighbor bands as the weights of the proposed kernel *** experimental results show that for the support vector machines based on polynomial and radial basis function,after introducing the proposed kernel function,the average accuracy is increased more than 1.2% without using any reference map or increasing much more computational time.
Driving of sheet metal is one of the oldest manufacturing methods and does not require highly expensive single-purpose forming tools. The current working process is carried out manually using inexpensive kraftformer m...
详细信息
ISBN:
(纸本)9788957081525
Driving of sheet metal is one of the oldest manufacturing methods and does not require highly expensive single-purpose forming tools. The current working process is carried out manually using inexpensive kraftformer machines and universal tool sets. Driving allows the creation of almost any 2D or 3D geometry and is therefore very powerful, but a highly interactive process that is difficult to be automated just by traditional approaches. For this purpose, the incremental forming method driving is chosen as a perfect test bed to demonstrate challenging, novel cognitive forming methods in the future. To handle the complexity of this incremental and work piece dependent process, powerful sensors, flexible actors and sophisticated cognitive capabilities must be involved. At the institute for metal forming and casting an optical online measurement system is installed to detect any geometry deformation of the current work piece and to visualize the deviation between the actual and the stored reference geometry during the whole production process. This variance comparison is the first step for planning any following incremental forming actions based on acquired and/or learned knowledge. This paper provides general information about the application of cognitive methods for forming and with it the qualification of driving as a manufacturing concept for the production of individualized sheet metal products.
This paper adopts an ant colony system (ACS) algorithm to develop the current urban traffic vehicles path routing methods. Aiming at a goal path that both the distance and the time cost are involved into the goal func...
详细信息
ISBN:
(纸本)9781424415304;1424415306
This paper adopts an ant colony system (ACS) algorithm to develop the current urban traffic vehicles path routing methods. Aiming at a goal path that both the distance and the time cost are involved into the goal function, the algorithm developed a path routing process based on an inspired heuristics searching that the next times path searching are inducted by the effective paths last times found. Through some times search, the search would be converged at the best path that deposited most pheromone. This paper analyzed the characters of the urban traffic path routing, described the searching process based on the ACS method, and presented the results that using this algorithm in a simplified urban traffic model. And based on the analysis of the computational results, this paper got a series of algorithm parameters that make the search accurate and converged quickly.
In cutting tool temperature experiment, a large number of related data could be available. In order to define the relationship among the experiment data, the nonlinear regressive curve of cutting tool temperature must...
详细信息
In cutting tool temperature experiment, a large number of related data could be available. In order to define the relationship among the experiment data, the nonlinear regressive curve of cutting tool temperature must be constructed based on the data. This paper proposes the Particle Swarm Optimization (PSO) algorithm for estimating the parameters such a curve. The PSO algorithm is an evolutional method based on a very simple concept. Comparison of PSO results with those of GA and LS methods showed that the PSO algorithm is more effective for estimating the parameters of the above curve.
暂无评论