为提升谱聚类的聚类精度和适用性,提出了一种基于Fréchet距离的谱聚类算法(A Spectral Clustering Algorithm Based on Fréchet Distance,FSC),通过Fréchet距离构建相似度矩阵,并将重构的相似矩阵应用于谱聚类中。利用Fr...为提升谱聚类的聚类精度和适用性,提出了一种基于Fréchet距离的谱聚类算法(A Spectral Clustering Algorithm Based on Fréchet Distance,FSC),通过Fréchet距离构建相似度矩阵,并将重构的相似矩阵应用于谱聚类中。利用Fréchet距离度量数据特征维度的相似性对样本的多个特征进行分析,进而扩展典型谱聚类算法的适用性。FSC不仅适用于低维流形结构清晰的数据,也适用于高维或稀疏数据,如高光谱图像数据。在3个经典的高光谱图像上的实验结果表明,FSC算法有效提高了高光谱图像聚类的精度。展开更多
In this paper, a new distribution called Marshall-Olkin Exponentiated Fréchet distribution (MOEFr) is proposed. The goal is to increase the flexibility of the existing Exponentiated Fréchet distribution by i...In this paper, a new distribution called Marshall-Olkin Exponentiated Fréchet distribution (MOEFr) is proposed. The goal is to increase the flexibility of the existing Exponentiated Fréchet distribution by including an extra shape parameter, resulting into a more flexible distribution that can provide a better fit to various data sets than the baseline distribution. A generator method introduced by Marshall and Olkin is used to develop the new distribution. Some properties of the new distribution such as hazard rate function, survival function, reversed hazard rate function, cumulative hazard function, odds function, quantile function, moments and order statistics are derived. The maximum likelihood estimation is used to estimate the model parameters. Monte Carlo simulation is used to evaluate the behavior of the estimators through the average bias and root mean squared error. The new distribution is fitted and compared with some existing distributions such as the Exponentiated Fréchet (EFr), Marshall-Olkin Fréchet (MOFr), Beta Exponential Fréchet (BEFr), Beta Fréchet (BFr) and Fréchet (Fr) distributions, on three data sets, namely Bladder cancer, Carbone and Wheaton River data sets. Based on the goodness-of-fit statistics and information criteria values, it is demonstrated that the new distribution provides a better fit for the three data sets than the other distributions considered in the study.展开更多
针对动力电池在电动汽车运行过程中的安全性和动力性问题,将离散Fréchet距离法与电池充放电曲线辨识相结合,提出了基于在线检测平台的电池健康度(State of Health,SOH)诊断方法。通过CAN通信模块,系统直接控制车载电池完成在线满...针对动力电池在电动汽车运行过程中的安全性和动力性问题,将离散Fréchet距离法与电池充放电曲线辨识相结合,提出了基于在线检测平台的电池健康度(State of Health,SOH)诊断方法。通过CAN通信模块,系统直接控制车载电池完成在线满充放试验,获取实际运行状态数据。并建立电动汽车服役全周期信息数据库,进行健康度诊断预测,来指导动力电池的安全评估和均衡维护。通过算例试验分析,将诊断结果与退运后的检测数据做比较,验证了该方法的正确性和准确性。展开更多
文摘为提升谱聚类的聚类精度和适用性,提出了一种基于Fréchet距离的谱聚类算法(A Spectral Clustering Algorithm Based on Fréchet Distance,FSC),通过Fréchet距离构建相似度矩阵,并将重构的相似矩阵应用于谱聚类中。利用Fréchet距离度量数据特征维度的相似性对样本的多个特征进行分析,进而扩展典型谱聚类算法的适用性。FSC不仅适用于低维流形结构清晰的数据,也适用于高维或稀疏数据,如高光谱图像数据。在3个经典的高光谱图像上的实验结果表明,FSC算法有效提高了高光谱图像聚类的精度。
文摘In this paper, a new distribution called Marshall-Olkin Exponentiated Fréchet distribution (MOEFr) is proposed. The goal is to increase the flexibility of the existing Exponentiated Fréchet distribution by including an extra shape parameter, resulting into a more flexible distribution that can provide a better fit to various data sets than the baseline distribution. A generator method introduced by Marshall and Olkin is used to develop the new distribution. Some properties of the new distribution such as hazard rate function, survival function, reversed hazard rate function, cumulative hazard function, odds function, quantile function, moments and order statistics are derived. The maximum likelihood estimation is used to estimate the model parameters. Monte Carlo simulation is used to evaluate the behavior of the estimators through the average bias and root mean squared error. The new distribution is fitted and compared with some existing distributions such as the Exponentiated Fréchet (EFr), Marshall-Olkin Fréchet (MOFr), Beta Exponential Fréchet (BEFr), Beta Fréchet (BFr) and Fréchet (Fr) distributions, on three data sets, namely Bladder cancer, Carbone and Wheaton River data sets. Based on the goodness-of-fit statistics and information criteria values, it is demonstrated that the new distribution provides a better fit for the three data sets than the other distributions considered in the study.
文摘针对动力电池在电动汽车运行过程中的安全性和动力性问题,将离散Fréchet距离法与电池充放电曲线辨识相结合,提出了基于在线检测平台的电池健康度(State of Health,SOH)诊断方法。通过CAN通信模块,系统直接控制车载电池完成在线满充放试验,获取实际运行状态数据。并建立电动汽车服役全周期信息数据库,进行健康度诊断预测,来指导动力电池的安全评估和均衡维护。通过算例试验分析,将诊断结果与退运后的检测数据做比较,验证了该方法的正确性和准确性。
