主要研究设备异常度的检测问题。在无故障样本的情况下,如何快速检测设备异常度已经成为状态检测的重要问题。为此,提出一种用于设备异常和异常度检测的信息匹配检测方法——可变阈值信息检测器(Variable threshold information detecto...主要研究设备异常度的检测问题。在无故障样本的情况下,如何快速检测设备异常度已经成为状态检测的重要问题。为此,提出一种用于设备异常和异常度检测的信息匹配检测方法——可变阈值信息检测器(Variable threshold information detector,VTI-detector),在分析分散增量理论并提出数据分布相亲有限信息密度概念的基础上,计算了每个正常训练样本对自己样本(正常样本)的匹配阈值,建立了带有匹配阈值信息的矩阵,即确立VTI-detector。最后利用确立的VTI-detector,结合相亲有限信息密度的概念,提出了设备异常度的计算公式。以UCI数据库中的Iris数据集为例,将所提出的异常检测方法与其他三种常用的异常检测方法进行对比,显示VTI-detector具有比其他方法更好的检测性能。利用异常度公式在线计算轴承正常和各种故障状态的异常度,并以异常度曲线的形式进行显示,结果表明故障异常度检测效果明显,具有较好的应用前景。展开更多
Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc.,...Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc., are studied in compressed domain. A skin detection method based on data-mining in compressed domain is proposed firstly and achieves the higher detection accuracy as well as higher speed. Then, a cascade scheme of pornographic image recognition based on selective decision tree ensemble is proposed in order to improve both the speed and accuracy of recognition. A pornographic video oriented key frame extraction solution in compressed domain and an approach of pornographic video recognition are discussed respectively in the end.展开更多
文摘主要研究设备异常度的检测问题。在无故障样本的情况下,如何快速检测设备异常度已经成为状态检测的重要问题。为此,提出一种用于设备异常和异常度检测的信息匹配检测方法——可变阈值信息检测器(Variable threshold information detector,VTI-detector),在分析分散增量理论并提出数据分布相亲有限信息密度概念的基础上,计算了每个正常训练样本对自己样本(正常样本)的匹配阈值,建立了带有匹配阈值信息的矩阵,即确立VTI-detector。最后利用确立的VTI-detector,结合相亲有限信息密度的概念,提出了设备异常度的计算公式。以UCI数据库中的Iris数据集为例,将所提出的异常检测方法与其他三种常用的异常检测方法进行对比,显示VTI-detector具有比其他方法更好的检测性能。利用异常度公式在线计算轴承正常和各种故障状态的异常度,并以异常度曲线的形式进行显示,结果表明故障异常度检测效果明显,具有较好的应用前景。
基金Supported by the National Natural Science Foundation of China (No.60772069)863 High-Tech Project (2008AA01A313)
文摘Pornographic image/video recognition plays a vital role in network information surveillance and management. In this paper, its key techniques, such as skin detection, key frame extraction, and classifier design, etc., are studied in compressed domain. A skin detection method based on data-mining in compressed domain is proposed firstly and achieves the higher detection accuracy as well as higher speed. Then, a cascade scheme of pornographic image recognition based on selective decision tree ensemble is proposed in order to improve both the speed and accuracy of recognition. A pornographic video oriented key frame extraction solution in compressed domain and an approach of pornographic video recognition are discussed respectively in the end.
