该文提出一种多标签排位小波支持向量机(rank wavelet support vector machine,Rank-WSVM),并将其应用于电能质量复合扰动分类中。Rank-WSVM将小波技术与多标签排位支持向量机(Rank-SVM)结合,利用小波的优良特性提高分类器的整体性能。...该文提出一种多标签排位小波支持向量机(rank wavelet support vector machine,Rank-WSVM),并将其应用于电能质量复合扰动分类中。Rank-WSVM将小波技术与多标签排位支持向量机(Rank-SVM)结合,利用小波的优良特性提高分类器的整体性能。首先,对电能质量扰动信号进行离散小波分解,计算Tsallis小波熵作为特征向量;然后利用所提出的Rank-WSVM多标签分类器进行分类。仿真结果表明,在不同噪声条件下,该方法有效改善了Rank-SVM的分类性能,可有效识别电压暂降、电压暂升、电压短时中断、脉冲暂态、振荡暂态、谐波和闪变等电能质量扰动及其组合而成的复合扰动。展开更多
Adjacent high-rise building with CFG pile composite foundation was studied using model test method to investigate stress and displacement of the foundation pile retaining structure, the subsidence and transmogrificati...Adjacent high-rise building with CFG pile composite foundation was studied using model test method to investigate stress and displacement of the foundation pile retaining structure, the subsidence and transmogrification law of the composite foundation. Two different project cases with and without high-rise building adjacent to pile foundation were compared. The relationships of slope pile bending moment, earth pressure, pile top displacement and complex settlement with respect to time were obtained. 1) When there is no adjacent building, the displacement of supporting system caused by excavation is mainly in the horizontal direction; while when the adjacent building exists, the displacement of supporting system will be vertical. 2) When the excavation depth is less than or equal to the adjacent building's composite foundation depth, the force of supporting structure is uniform and has small value, at the same time, the pile strength is in fully use and the foundation is stable; while when the excavation depth is greater than the depth of adjacent building's composite foundation, the results will be opposite. 3) During the excavation process, the adjustment of the composite ground loads on the supporting structure is carried out downward and the force of the supporting structure is reduced through the deformation of the bearing layer.展开更多
A model of correcting the nonlinear error of photoelectric displacement sensor was established based on the least square support vector machine.The parameters of the correcting nonlinear model,such as penalty factor a...A model of correcting the nonlinear error of photoelectric displacement sensor was established based on the least square support vector machine.The parameters of the correcting nonlinear model,such as penalty factor and kernel parameter,were optimized by chaos genetic algorithm.And the nonlinear correction of photoelectric displacement sensor based on least square support vector machine was applied.The application results reveal that error of photoelectric displacement sensor is less than 1.5%,which is rather satisfactory for nonlinear correction of photoelectric displacement sensor.展开更多
In view of the difficulty in supporting the surrounding rocks of roadway 3-411 ofFucun Coal Mine of Zaozhuang Mining Group, a deformation forecasting model was putforward based on particle swarm optimization.The kerne...In view of the difficulty in supporting the surrounding rocks of roadway 3-411 ofFucun Coal Mine of Zaozhuang Mining Group, a deformation forecasting model was putforward based on particle swarm optimization.The kernel function and model parameterswere optimized using particle swarm optimization.It is shown that the forecast result isvery close to the real monitoring data.Furthermore, the PSO-SVM (Particle Swarm Optimization-Support Vector Machine) model is compared with the GM(1,1) model and L-M BPnetwork model.The results show that PSO-SVM method is better in the aspect of predictionaccuracy and the PSO-SVM roadway deformation pre-diction model is feasible for thelarge deformation prediction of coal mine roadway.展开更多
Motivation: It was found that high accuracy splicing-site recognitio n of rice (Oryza sativa L.) DNA sequence is especially difficult. We describe d a new method for the splicing-site recognition of rice DNA sequences...Motivation: It was found that high accuracy splicing-site recognitio n of rice (Oryza sativa L.) DNA sequence is especially difficult. We describe d a new method for the splicing-site recognition of rice DNA sequences. Method: Bas e d on the intron in eukaryotic organisms conforming to the principle of GT-AG,w e used support vector machines (SVM) to predict the splicing sites. By machine l earning,we built a model and used it to test the effect of the test data set of true and pseudo splicing sites. Results: The prediction accuracy we obtained wa s 87.53% at the true 5' end splicing site and 87.37% at the true 3' end splicing sites. The results suggested that the SVM approach could achieve higher accuracy than the previous approaches.展开更多
Support Vector Machine (SVM) is a powerful methodology for solving problems in non-linear classification, function estimation and density estimation, which has also led to many other recent developments in kernel base...Support Vector Machine (SVM) is a powerful methodology for solving problems in non-linear classification, function estimation and density estimation, which has also led to many other recent developments in kernel based methods in general. This paper presents a highaccuracy and fault-tolerant SVM for the mobile geo-location problem, which is an important component of pervasive computing. Simulation results show its basic location performance, and illustrate impacts of the number of training samples and training area on test location error.展开更多
The goal in reinforcement learning is to learn the value of state-action pair in order to maximize the total reward. For continuous states and actions in the real world, the representation of value functions is critic...The goal in reinforcement learning is to learn the value of state-action pair in order to maximize the total reward. For continuous states and actions in the real world, the representation of value functions is critical. Furthermore, the samples in value functions are sequentially obtained. Therefore, an online sup-port vector regression （OSVR） is set up, which is a function approximator to estimate value functions in reinforcement learning. OSVR updates the regression function by analyzing the possible variation of sup-port vector sets after new samples are inserted to the training set. To evaluate the OSVR learning ability, it is applied to the mountain-car task. The simulation results indicate that the OSVR has a preferable con- vergence speed and can solve continuous problems that are infeasible using lookup table.展开更多
文摘该文提出一种多标签排位小波支持向量机(rank wavelet support vector machine,Rank-WSVM),并将其应用于电能质量复合扰动分类中。Rank-WSVM将小波技术与多标签排位支持向量机(Rank-SVM)结合,利用小波的优良特性提高分类器的整体性能。首先,对电能质量扰动信号进行离散小波分解,计算Tsallis小波熵作为特征向量;然后利用所提出的Rank-WSVM多标签分类器进行分类。仿真结果表明,在不同噪声条件下,该方法有效改善了Rank-SVM的分类性能,可有效识别电压暂降、电压暂升、电压短时中断、脉冲暂态、振荡暂态、谐波和闪变等电能质量扰动及其组合而成的复合扰动。
基金Project(41202220) supported by the National Natural Science Foundation of ChinaProject(20120022120003) supported by the Research Fund for the Doctoral Program of Higher Education,ChinaProject(2-9-2012-65) supported by the Fundamental Research Funds for the Central Universities,China
文摘Adjacent high-rise building with CFG pile composite foundation was studied using model test method to investigate stress and displacement of the foundation pile retaining structure, the subsidence and transmogrification law of the composite foundation. Two different project cases with and without high-rise building adjacent to pile foundation were compared. The relationships of slope pile bending moment, earth pressure, pile top displacement and complex settlement with respect to time were obtained. 1) When there is no adjacent building, the displacement of supporting system caused by excavation is mainly in the horizontal direction; while when the adjacent building exists, the displacement of supporting system will be vertical. 2) When the excavation depth is less than or equal to the adjacent building's composite foundation depth, the force of supporting structure is uniform and has small value, at the same time, the pile strength is in fully use and the foundation is stable; while when the excavation depth is greater than the depth of adjacent building's composite foundation, the results will be opposite. 3) During the excavation process, the adjustment of the composite ground loads on the supporting structure is carried out downward and the force of the supporting structure is reduced through the deformation of the bearing layer.
基金Project(50925727) supported by the National Fund for Distinguish Young Scholars of ChinaProject(60876022) supported by the National Natural Science Foundation of China+1 种基金Project(2010FJ4141) supported by Hunan Provincial Science and Technology Foundation,ChinaProject supported by the Fund of the Key Construction Academic Subject (Optics) of Hunan Province,China
文摘A model of correcting the nonlinear error of photoelectric displacement sensor was established based on the least square support vector machine.The parameters of the correcting nonlinear model,such as penalty factor and kernel parameter,were optimized by chaos genetic algorithm.And the nonlinear correction of photoelectric displacement sensor based on least square support vector machine was applied.The application results reveal that error of photoelectric displacement sensor is less than 1.5%,which is rather satisfactory for nonlinear correction of photoelectric displacement sensor.
基金Supported by the National Natural Science Foundation of Zhejiang Province(2009C33049)the National Natural Science Foundation of China(50674040)
文摘In view of the difficulty in supporting the surrounding rocks of roadway 3-411 ofFucun Coal Mine of Zaozhuang Mining Group, a deformation forecasting model was putforward based on particle swarm optimization.The kernel function and model parameterswere optimized using particle swarm optimization.It is shown that the forecast result isvery close to the real monitoring data.Furthermore, the PSO-SVM (Particle Swarm Optimization-Support Vector Machine) model is compared with the GM(1,1) model and L-M BPnetwork model.The results show that PSO-SVM method is better in the aspect of predictionaccuracy and the PSO-SVM roadway deformation pre-diction model is feasible for thelarge deformation prediction of coal mine roadway.
文摘Motivation: It was found that high accuracy splicing-site recognitio n of rice (Oryza sativa L.) DNA sequence is especially difficult. We describe d a new method for the splicing-site recognition of rice DNA sequences. Method: Bas e d on the intron in eukaryotic organisms conforming to the principle of GT-AG,w e used support vector machines (SVM) to predict the splicing sites. By machine l earning,we built a model and used it to test the effect of the test data set of true and pseudo splicing sites. Results: The prediction accuracy we obtained wa s 87.53% at the true 5' end splicing site and 87.37% at the true 3' end splicing sites. The results suggested that the SVM approach could achieve higher accuracy than the previous approaches.
文摘Support Vector Machine (SVM) is a powerful methodology for solving problems in non-linear classification, function estimation and density estimation, which has also led to many other recent developments in kernel based methods in general. This paper presents a highaccuracy and fault-tolerant SVM for the mobile geo-location problem, which is an important component of pervasive computing. Simulation results show its basic location performance, and illustrate impacts of the number of training samples and training area on test location error.
文摘The goal in reinforcement learning is to learn the value of state-action pair in order to maximize the total reward. For continuous states and actions in the real world, the representation of value functions is critical. Furthermore, the samples in value functions are sequentially obtained. Therefore, an online sup-port vector regression （OSVR） is set up, which is a function approximator to estimate value functions in reinforcement learning. OSVR updates the regression function by analyzing the possible variation of sup-port vector sets after new samples are inserted to the training set. To evaluate the OSVR learning ability, it is applied to the mountain-car task. The simulation results indicate that the OSVR has a preferable con- vergence speed and can solve continuous problems that are infeasible using lookup table.
