利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

682 条记录 (耗时 0.034 秒)

    Low power, wavelet-based spike detector
    82.
    发明授权
    Low power, wavelet-based spike detector 失效
    低功率，基于小波的尖峰检测器

    公开(公告)号：US07965779B2

    公开(公告)日：2011-06-21

    申请号：US11909060

    申请日：2006-03-17

    申请人： Christy L. She ,  John G. Harris ,  Jose C. Principe

    发明人： Christy L. She ,  John G. Harris ,  Jose C. Principe

    IPC分类号： H04B14/04

    CPC分类号： A61B5/04001 ,  A61B5/7225 ,  A61B5/726 ,  G06K9/00523

    摘要： A multi-scale spike detector for performing multi-resolution spike detections of a signal is provided. The spike detector includes a gamma filter having cascaded low-pass filters. The cascaded filters collectively provide different cutoff frequencies, each of the filters having a respective output. One of the filters has an input, at which the signal is received. The spike detector further includes combining circuitry that combines at least some of the respective outputs of the cascaded filters. The differences formed from this combining provide a waveform representation of the input signal. The waveform representation consists essentially of spikes that occur in the signal.

    摘要翻译： 提供了用于执行信号的多分辨率尖峰检测的多尺度尖峰检测器。 尖峰检测器包括具有级联低通滤波器的伽马滤波器。 级联滤波器共同提供不同的截止频率，每个滤波器具有相应的输出。 滤波器中的一个具有接收信号的输入端。 尖峰检测器还包括组合电路，其组合级联滤波器的相应输出的至少一些。 由该组合形成的差异提供了输入信号的波形表示。 波形表示基本上由信号中出现的尖峰组成。

    Use of Machine Learning for Classification of Magneto Cardiograms
    83.
    发明申请
    Use of Machine Learning for Classification of Magneto Cardiograms 有权
    使用机器学习分类磁心图

    公开(公告)号：US20110047105A1

    公开(公告)日：2011-02-24

    申请号：US12819095

    申请日：2010-06-18

    申请人： Karsten Sternickel ,  Mark J. Embrechts ,  Boleslaw Szymanski

    发明人： Karsten Sternickel ,  Mark J. Embrechts ,  Boleslaw Szymanski

    IPC分类号： G06F15/18

    CPC分类号： A61B5/7267 ,  A61B5/04007 ,  A61B5/7203 ,  A61B5/7253 ,  A61B5/726 ,  A61B2560/0475 ,  G06K9/00496 ,  G06K9/00523 ,  G06N3/086 ,  G16H50/20

    摘要： The use of machine learning for pattern recognition in magnetocardiography (MCG) that measures magnetic fields emitted by the electrophysiological activity of the heart is disclosed herein. Direct kernel methods are used to separate abnormal MCG heart patterns from normal ones. For unsupervised learning, Direct Kernel based Self-Organizing Maps are introduced. For supervised learning Direct Kernel Partial Least Squares and (Direct) Kernel Ridge Regression are used. These results are then compared with classical Support Vector Machines and Kernel Partial Least Squares. The hyper-parameters for these methods are tuned on a validation subset of the training data before testing. Also investigated is the most effective pre-processing, using local, vertical, horizontal and two-dimensional (global) Mahanalobis scaling, wavelet transforms, and variable selection by filtering.

    摘要翻译： 本文公开了在测量由心脏的电生理活性发出的磁场的磁心动图（MCG）中使用机器学习用于模式识别。 直接内核方法用于将异常MCG心脏模式与正常心脏模式分离。 对于无监督学习，引入了基于直接内核的自组织映射。 对于监督学习，使用直接内核部分最小二乘法和（直接）内核岭回归。 然后将这些结果与经典支持向量机和内核部分最小二乘法进行比较。 这些方法的超参数在测试前对训练数据的验证子集进行调整。 还进行了调查，最有效的预处理，使用局部，垂直，水平和二维（全局）Mahanalobis缩放，小波变换和通过过滤的变量选择。

    Systems for structural clustering of time sequences
    84.
    发明授权
    Systems for structural clustering of time sequences 有权
    时间序列结构聚类系统

    公开(公告)号：US07890294B2

    公开(公告)日：2011-02-15

    申请号：US12115166

    申请日：2008-05-05

    申请人： Vittorio Castelli ,  Michail Vlachos ,  Philip S. Yu

    发明人： Vittorio Castelli ,  Michail Vlachos ,  Philip S. Yu

    IPC分类号： G06F15/00

    CPC分类号： G06K9/00523 ,  Y10S706/90 ,  Y10S707/99936 ,  Y10S707/99937 ,  Y10S707/99945 ,  Y10S707/99953

    摘要： Arrangements are provided for performing structural clustering between different time series. Time series data relating to a plurality of time series is accepted, structural features relating to the time series data are ascertained, and at least one distance between different time series via employing the structural features is determined. The different time series may be partitioned into clusters based on the at least one distance, and/or the k closest matches to a given time series query based on the at least one distance may be returned.

    摘要翻译： 提供了在不同时间序列之间进行结构聚类的安排。 接收与多个时间序列相关的时间序列数据，确定与时间序列数据相关的结构特征，并且确定通过采用结构特征的不同时间序列之间的至少一个距离。 可以基于至少一个距离将不同的时间序列划分成簇，并且可以返回基于至少一个距离的/或与给定时间序列查询的k个最接近的匹配。

    Biometric information measuring apparatus
    85.
    发明授权
    Biometric information measuring apparatus 有权
    生物特征信息测量仪器

    公开(公告)号：US07885432B2

    公开(公告)日：2011-02-08

    申请号：US11600559

    申请日：2006-11-16

    申请人： Keisuke Tsubata

    发明人： Keisuke Tsubata

    IPC分类号： G06K9/00

    CPC分类号： A61B5/02438 ,  A61B5/7257 ,  G06K9/00523

    摘要： A biometric information measuring apparatus has a biometric signal detecting portion that detects a biometric signal. A control section calculates biometric information based on the detected biometric signal by nullifying an amplitude of the detected biometric signal corresponding to a noise portion of the detected biometric signal when the nullified amplitude does not satisfy a predetermined threshold value.

    摘要翻译： 生物体信息测量装置具有检测生物体信号的生物体信号检测部。 当无效振幅不满足预定阈值时，控制部分通过使与检测到的生物信号的噪声部分相对应的检测到的生物信号的幅度无效，基于检测到的生物体信号来计算生物信息。

    Method of extracting and evaluating paced heart beats using max-min transform analysis
    89.
    发明授权
    Method of extracting and evaluating paced heart beats using max-min transform analysis 失效
    使用max-min变换分析提取和评估节奏心跳的方法

    公开(公告)号：US07542794B1

    公开(公告)日：2009-06-02

    申请号：US11439900

    申请日：2006-05-24

    申请人： Hongxuan Zhang ,  Ananth Natarajan ,  Nitish V. Thakor

    发明人： Hongxuan Zhang ,  Ananth Natarajan ,  Nitish V. Thakor

    IPC分类号： A61B5/04

    CPC分类号： A61B5/0472 ,  A61B5/7207 ,  A61N1/37 ,  G06K9/00523

    摘要： Methods for identifying and extracting heart depolarization and repolarization in a paced heart. Certain methods also include identifying and analyzing particular features of at least one pacing spike and QRS waveform for heart beat characterization. These features may include signal changing speed and signal time interval (distance) of pacing spikes and QRS depolarization when pacing excitation is initialized.

    摘要翻译： 识别和提取心脏去极化和复极化的方法。 某些方法还包括识别和分析用于心跳表征的至少一个起搏尖峰和QRS波形的特征。 这些特征可以包括起搏激发初始化时的起搏尖峰和QRS去极化的信号变化速度和信号时间间隔（距离）。

    Method and apparatus for cardiac arrhythmia classification using sample entropy
    90.
    发明授权
    Method and apparatus for cardiac arrhythmia classification using sample entropy 有权
    使用样本熵进行心律失常分类的方法和装置

    公开(公告)号：US07480529B2

    公开(公告)日：2009-01-20

    申请号：US11151102

    申请日：2005-06-13

    申请人： Dan Li

    发明人： Dan Li

    IPC分类号： A61B5/0402 ,  A61B5/0472

    CPC分类号： G06K9/00523 ,  A61B5/04525 ,  A61B5/0464 ,  A61B5/7264

    摘要： An implantable medical device includes an arrhythmia detection and classification system that classifies an arrhythmia episode based on an irregularity parameter and/or a complexity parameter. The arrhythmia episode is detected from a cardiac signal. The irregularity parameter is indicative of the degree of cycle length irregularity of the cardiac signal and the complexity parameter is indicative of the degree of morphological complexity of the cardiac signal. One example of the irregularity parameter is an irregularity sample entropy, or a parameter related to the irregularity sample entropy, computed to indicate the cycle length irregularity. One example of the complexity parameter is a complexity sample entropy, or a parameter related to the complexity sample entropy, computed to indicate the morphological complexity. In one embodiment, the detected arrhythmia episode is classified using both the irregularity parameter and the complexity parameter.

    摘要翻译： 可植入医疗装置包括基于不规则参数和/或复杂度参数对心律失常发作进行分类的心律失常检测和分类系统。 从心脏信号检测心律失常发作。 不规则参数表示心脏信号的周期长度不规则度，复杂度参数表示心脏信号的形态复杂程度。 不规则参数的一个示例是不规则样本熵或与不规则样本熵相关的参数，计算以指示周期长度不规则性。 复杂度参数的一个例子是复杂度样本熵或与复杂度样本熵有关的参数，用于指示形态复杂度。 在一个实施例中，使用不规则参数和复杂度参数来分类检测到的心律失常发作。