A forecasting system of patent application counts is studied in this paper. The optimization model proposed in the research is based on support vector machines （SVM）, in which cross-validation algorithm is used for ...A forecasting system of patent application counts is studied in this paper. The optimization model proposed in the research is based on support vector machines （SVM）, in which cross-validation algorithm is used for preferences selection. Results of data simulation show that the proposed method has higher forecasting precision power and stronger generalization ability than BP neural network and RBF neural network. In addi- tion, it is feasible and effective in forecasting patent application counts.展开更多
利用可见/近红外光谱技术对冷却肉菌落总数和颜色进行快速、无损检测。采用400~1 100 nm可见/近红外光谱成像系统,获取54个冷却肉样本表面的光谱图像,采用主成分分析结合马氏距离方法对异常光谱进行判别及剔除。通过Gompertz分布函数对...利用可见/近红外光谱技术对冷却肉菌落总数和颜色进行快速、无损检测。采用400~1 100 nm可见/近红外光谱成像系统,获取54个冷却肉样本表面的光谱图像,采用主成分分析结合马氏距离方法对异常光谱进行判别及剔除。通过Gompertz分布函数对散射特征曲线进行拟合,得到表征光谱信息的Gompertz参数,结合支持向量机算法建立冷却肉菌落总数和肉色L*的预测模型。α、β、θ、δ组合和α、β、δ组合建模对细菌总数预测效果最好,预测相关系数分别为0.937和0.935,预测标准差为0.600 lg CFU/g和0.702 lg CFU/g。β、δ组合建模对肉色L*预测效果较好,预测相关系数达到0.930,预测标准差为1.515。研究结果表明利用Vis/NIR光谱散射特征结合支持向量机可以实现冷却肉品质的快速、高效、无损伤检测。展开更多
A novel detection method of support vector machine （SVM） based on fractal dimension of signals is presented. And models of SVM are made based on nugget size defects of spot welding. Classification using these traine...A novel detection method of support vector machine （SVM） based on fractal dimension of signals is presented. And models of SVM are made based on nugget size defects of spot welding. Classification using these trained SVM models is done to signals of spot welding. It is shown from effect of different SVM models that these models with different inputs. In detection of defects, these models with inputs including sound signal have a high percentage of accuracy, the detection accuracy of these models with inputs including voltage signal will reduce. So the SVM models based on fractal dimensions of sound are some optimal nondestructive detection ones. At last a comparison between SVM detection model and ANNS detection model is researched which indicates that SVM is a more effective measure than Artificial neural networks in detection of nugget size defects during spot welding.展开更多
在利用WiFi信号实现人群计数中,基于信道状态信息幅度(Channel State Information,CSI)存在分类模型滤波不彻底和准确度差的问题,本文提出了一种基于多接收天线之间相位差扩展矩阵信息的支持向量机(Support Vector Machine,SVM)增量学...在利用WiFi信号实现人群计数中,基于信道状态信息幅度(Channel State Information,CSI)存在分类模型滤波不彻底和准确度差的问题,本文提出了一种基于多接收天线之间相位差扩展矩阵信息的支持向量机(Support Vector Machine,SVM)增量学习算法.首先对CSI原始相位数据执行三重处理,以便最大程度的消除环境干扰和相位误差;另外提出了一种建立相位差扩展矩阵的思想,加入了不同人数场景的动态特征,提高了人群计数准确性.考虑到新增场景后,原训练数据和新增数据需合并进行重新训练,因训练数据过多会造成计算复杂度过高,为此我们提出了一种基于SVM增量学习分类算法,设计了一个循环迭代过程,实现了对增量数据在线学习的功能,且在提升人群计数准确率和降低计算复杂度方面均取得了较好的效果.算法结果表明,本文方法可实现实时人群计数,在最大计数误差为1人时,平均计数精度可达95%以上,且随着场景增多在训练识别模型时节约的时间越显著.展开更多
基金Sponsored by "985" Philosophy and Social Science Innovation Base of the Ministry of Education of China (107008200400024)
文摘A forecasting system of patent application counts is studied in this paper. The optimization model proposed in the research is based on support vector machines （SVM）, in which cross-validation algorithm is used for preferences selection. Results of data simulation show that the proposed method has higher forecasting precision power and stronger generalization ability than BP neural network and RBF neural network. In addi- tion, it is feasible and effective in forecasting patent application counts.
文摘利用可见/近红外光谱技术对冷却肉菌落总数和颜色进行快速、无损检测。采用400~1 100 nm可见/近红外光谱成像系统,获取54个冷却肉样本表面的光谱图像,采用主成分分析结合马氏距离方法对异常光谱进行判别及剔除。通过Gompertz分布函数对散射特征曲线进行拟合,得到表征光谱信息的Gompertz参数,结合支持向量机算法建立冷却肉菌落总数和肉色L*的预测模型。α、β、θ、δ组合和α、β、δ组合建模对细菌总数预测效果最好,预测相关系数分别为0.937和0.935,预测标准差为0.600 lg CFU/g和0.702 lg CFU/g。β、δ组合建模对肉色L*预测效果较好,预测相关系数达到0.930,预测标准差为1.515。研究结果表明利用Vis/NIR光谱散射特征结合支持向量机可以实现冷却肉品质的快速、高效、无损伤检测。
基金Supported by the Key Scientific and Technological Project of Henan Province(142102210010)the Key Research Project in Science and Technology of the Education Department of Henan Province(14A520028,14A520052)the Ph.D.Programs Foundation of the Ministry of Education of China(YBXSZC20131031)
基金supported by National Natural Science Foundation of China (No.50575159)Science Foundation of Ministry of Education of China (No.106049)+1 种基金Doctoral Foundation of Ministry of Education of China (No.20060056058)and Tianjin Municipal Natural Science Foundation of China (No.06YFJMJC03400).
文摘A novel detection method of support vector machine （SVM） based on fractal dimension of signals is presented. And models of SVM are made based on nugget size defects of spot welding. Classification using these trained SVM models is done to signals of spot welding. It is shown from effect of different SVM models that these models with different inputs. In detection of defects, these models with inputs including sound signal have a high percentage of accuracy, the detection accuracy of these models with inputs including voltage signal will reduce. So the SVM models based on fractal dimensions of sound are some optimal nondestructive detection ones. At last a comparison between SVM detection model and ANNS detection model is researched which indicates that SVM is a more effective measure than Artificial neural networks in detection of nugget size defects during spot welding.
文摘在利用WiFi信号实现人群计数中,基于信道状态信息幅度(Channel State Information,CSI)存在分类模型滤波不彻底和准确度差的问题,本文提出了一种基于多接收天线之间相位差扩展矩阵信息的支持向量机(Support Vector Machine,SVM)增量学习算法.首先对CSI原始相位数据执行三重处理,以便最大程度的消除环境干扰和相位误差;另外提出了一种建立相位差扩展矩阵的思想,加入了不同人数场景的动态特征,提高了人群计数准确性.考虑到新增场景后,原训练数据和新增数据需合并进行重新训练,因训练数据过多会造成计算复杂度过高,为此我们提出了一种基于SVM增量学习分类算法,设计了一个循环迭代过程,实现了对增量数据在线学习的功能,且在提升人群计数准确率和降低计算复杂度方面均取得了较好的效果.算法结果表明,本文方法可实现实时人群计数,在最大计数误差为1人时,平均计数精度可达95%以上,且随着场景增多在训练识别模型时节约的时间越显著.
