Improved Twin Support Vector Machine Algorithm and Applications in Classification Problems

The distribution of data has a significant impact on the results of classification.When the distribution of one class is insignificant compared to the distribution of another class,data imbalance occurs.This will result in rising outlier values and noise.Therefore,the speed and performance of classification could be greatly affected.Given the above problems,this paper starts with the motivation and mathematical representing of classification,puts forward a new classification method based on the relationship between different classification formulations.Combined with the vector characteristics of the actual problem and the choice of matrix characteristics,we firstly analyze the orderly regression to introduce slack variables to solve the constraint problem of the lone point.Then we introduce the fuzzy factors to solve the problem of the gap between the isolated points on the basis of the support vector machine.We introduce the cost control to solve the problem of sample skew.Finally,based on the bi-boundary support vector machine,a twostep weight setting twin classifier is constructed.This can help to identify multitasks with feature-selected patterns without the need for additional optimizers,which solves the problem of large-scale classification that can’t deal effectively with the very low category distribution gap.

A Novel Resource Allocation Method in Ultra-Dense Network Based on Noncooperation Game Theory

In ultra-dense networks(UDNs), large-scale deployment of femto base stations is an important technique for improving the network throughput and quality of service(QoS). In this paper, a multidimensional resource allocation algorithm based on noncooperation game theory is proposed to manage the resource allocation in UDNs, including transmission point association, user channels, and power. The algorithm derives a multidimensional resource optimization model and converts into a noncooperation game model according to the analysis of transmission point association user channel and power allocation. The algorithm includes two phases: transmission point association, and channel and power allocation. Then, feasible domain and discrete variables relaxation approaches are introduced to derive an approximate optimal multidimensional resource allocation solution with low complexity. Simulation results show that this method has some advantages in suppressing interference and improves the overall system throughput, while ensuring the QoS of femtocell users.

THE OPTIMAL VARIABLE SUCCESSIVE OVER RELAXATION (OVSOR) METHOD FOR THREE-DIMENSIONAL RESERVOIR SIMULATIONS

This present paper has proved the theorem of the Point Optimal Variable Successive Over Relaxation (OVSOR) method of the three-dimensional unsteady flow in the reservoir, and has put forward a formu- la for calculating optimal parameters for OVSOR which vary with space points and time points. Using this method, internal memory of computer is the smallest, calculating work is the smallest, and calculating funds are the smallest. It is very easy to operate on microcomputers for three-dimensional res- ervoir simulation. The method is stable and convergent even if the time steps are taken to be large (for example, one year). The same applies for space steps. It is applicable both for homogeneous, isotropic porous mediums and for heterogeneous, anisotropic porous medium. On IBM microcomputers with internal memory of 512 thousand bytes, 8000 grid points may be cal- culated for three-dimensional simulation. It takes only two minutes to get convergence for one time step. It may be extended to three-dimensional heat conduction equation and three-dimensional simulation of the ground water flow. It looks much more advantageous for two-dimensional simulation.