Fisher线性判别式FLDs(Fisher linear discriminates)的常用阈值对不平衡数据集分类效果较差。以不平衡数据集为应用背景,主要研究各种阈值对FLDs分类性能的影响。认为影响FLDs性能的主要是类间分布区域不平衡而不是样本数不平衡,因此...Fisher线性判别式FLDs(Fisher linear discriminates)的常用阈值对不平衡数据集分类效果较差。以不平衡数据集为应用背景,主要研究各种阈值对FLDs分类性能的影响。认为影响FLDs性能的主要是类间分布区域不平衡而不是样本数不平衡,因此提出多个经验阈值,并依据分类精度从中选择优化阈值。大量实验结果表明,所提出的阈值优化选择方法能有效提高FLDs对不平衡数据集的分类性能。展开更多
A new on-line batch process monitoring and diagnosing approach based on Fisher discriminant analysis （FDA） was proposed. This method does not need to predict the future observations of variables, so it is more sensi...A new on-line batch process monitoring and diagnosing approach based on Fisher discriminant analysis （FDA） was proposed. This method does not need to predict the future observations of variables, so it is more sensitive to fault detection and stronger implement for monitoring. In order to improve the monitoring performance, the variables trajectories of batch process are separated into several blocks. The key to the proposed approach for on-line monitoring is to calculate the distance of block data that project to low-dimension Fisher space between new batch and reference batch. Comparing the distance with the predefine threshold, it can be considered whether the batch process is normal or abnormal. Fault diagnosis is performed based on the weights in fault direction calculated by FDA. The proposed method was applied to the simulation model of fed-batch penicillin fermentation and the resuits were compared with those obtained using MPCA. The simulation results clearly show that the on-line monitoring method based on FDA is more efficient than the MPCA.展开更多
This paper presents a novel bootstrap based method for Receiver Operating Characteristic (ROC) analysis of Fisher classifier. By defining Fisher classifier’s output as a statistic, the bootstrap technique is used to ...This paper presents a novel bootstrap based method for Receiver Operating Characteristic (ROC) analysis of Fisher classifier. By defining Fisher classifier’s output as a statistic, the bootstrap technique is used to obtain the sampling distributions of the outputs for the positive class and the negative class respectively. As a result, the ROC curve is a plot of all the (False Positive Rate (FPR), True Positive Rate (TPR)) pairs by varying the decision threshold over the whole range of the boot- strap sampling distributions. The advantage of this method is, the bootstrap based ROC curves are much stable than those of the holdout or cross-validation, indicating a more stable ROC analysis of Fisher classifier. Experiments on five data sets publicly available demonstrate the effectiveness of the proposed method.展开更多
文摘Fisher线性判别式FLDs(Fisher linear discriminates)的常用阈值对不平衡数据集分类效果较差。以不平衡数据集为应用背景,主要研究各种阈值对FLDs分类性能的影响。认为影响FLDs性能的主要是类间分布区域不平衡而不是样本数不平衡,因此提出多个经验阈值,并依据分类精度从中选择优化阈值。大量实验结果表明,所提出的阈值优化选择方法能有效提高FLDs对不平衡数据集的分类性能。
文摘A new on-line batch process monitoring and diagnosing approach based on Fisher discriminant analysis （FDA） was proposed. This method does not need to predict the future observations of variables, so it is more sensitive to fault detection and stronger implement for monitoring. In order to improve the monitoring performance, the variables trajectories of batch process are separated into several blocks. The key to the proposed approach for on-line monitoring is to calculate the distance of block data that project to low-dimension Fisher space between new batch and reference batch. Comparing the distance with the predefine threshold, it can be considered whether the batch process is normal or abnormal. Fault diagnosis is performed based on the weights in fault direction calculated by FDA. The proposed method was applied to the simulation model of fed-batch penicillin fermentation and the resuits were compared with those obtained using MPCA. The simulation results clearly show that the on-line monitoring method based on FDA is more efficient than the MPCA.
基金the Natural Science Foundation of Zhejiang Province of China (No. Y104540)the Foundation of the Key Laboratory of Advanced Information Science and Network Technology of Beijing, China (No.TDXX0509).
文摘This paper presents a novel bootstrap based method for Receiver Operating Characteristic (ROC) analysis of Fisher classifier. By defining Fisher classifier’s output as a statistic, the bootstrap technique is used to obtain the sampling distributions of the outputs for the positive class and the negative class respectively. As a result, the ROC curve is a plot of all the (False Positive Rate (FPR), True Positive Rate (TPR)) pairs by varying the decision threshold over the whole range of the boot- strap sampling distributions. The advantage of this method is, the bootstrap based ROC curves are much stable than those of the holdout or cross-validation, indicating a more stable ROC analysis of Fisher classifier. Experiments on five data sets publicly available demonstrate the effectiveness of the proposed method.
