公开(公告)号：US20100179395A1

公开(公告)日：2010-07-15

申请号：US12687936

申请日：2010-01-15

申请人： David R. Bloem

发明人： David R. Bloem

IPC分类号： A61B5/00

CPC分类号： A61B5/0205 ,  A61B5/1455 ,  A61B5/7207 ,  A61N1/3718 ,  A61N1/3925 ,  G06K9/00503 ,  G06K9/6247 ,  G06K2009/00939

摘要： A medical device includes multiple sensors used to acquire sensor signals grouped into multiple sets to obtain multiple multi-dimensional signals. Principal component analysis of the multi-dimensional signals is performed to compute principal components of variation of the multi-dimensional signals. Features extracted from the principal components are used in detecting physiological events.

摘要翻译： 医疗设备包括多个传感器，用于获取分组为多组的传感器信号以获得多个多维信号。 执行多维信号的主成分分析以计算多维信号的变化的主分量。 从主要成分提取的特征用于检测生理事件。

公开(公告)号：US07725146B2

公开(公告)日：2010-05-25

申请号：US11240926

申请日：2005-09-29

申请人： Li Li ,  Scott Amundson ,  Michael Patrick O'Neil

发明人： Li Li ,  Scott Amundson ,  Michael Patrick O'Neil

IPC分类号： A61B5/1455 ,  A61B5/02

CPC分类号： G06K9/00503

摘要： A technique is provided for processing a physiological signal. The technique includes performing one or more multi-resolution decompositions on a physiological signal and one or more morphological operations on some or all of the respective decomposition components. In one embodiment, the technique is implemented as iteratively wavelet transformations where morphological operations, such as erosions and dilations, are applied to modify some or all of the respective wavelet coefficients. The modified wavelet coefficients may then be reconstructed to generate a clean version of the physiological signal from which some or all of the noise and/or artifacts have been removed.

摘要翻译： 提供了一种用于处理生理信号的技术。 该技术包括对生理信号执行一个或多个多分辨率分解，并对一些或所有相应的分解分量执行一个或多个形态学运算。 在一个实施例中，该技术被实现为迭代小波变换，其中应用形态学操作（例如侵蚀和扩张）来修改相应小波系数中的一些或全部。 修改后的小波系数可以被重建，以产生生理信号的干净版本，从该信号的一部分或全部已经去除了噪声和/或伪影。

公开(公告)号：US20090052796A1

公开(公告)日：2009-02-26

申请号：US12183282

申请日：2008-07-31

申请人： Yasutaka Furukawa ,  Jean Ponce

发明人： Yasutaka Furukawa ,  Jean Ponce

IPC分类号： G06K9/40

CPC分类号： G06K9/00503 ,  G06T7/596

摘要： In accordance with one or more aspects of a match, expand, and filter technique for multi-view stereopsis, features across multiple images of an object are matched to obtain a sparse set of patches for the object. The sparse set of patches is expanded to obtain a dense set of patches for the object, and the dense set of patches is filtered to remove erroneous patches. Optionally, reconstructed patches can be converted into 3D mesh models.

摘要翻译： 根据多视图立体视觉的匹配，扩展和过滤技术的一个或多个方面，匹配对象的多个图像的特征以获得对象的稀疏集合。 稀疏的补丁集被扩展以获得对象的一组密集的补丁，并且密集的补丁集被过滤以去除错误的补丁。 可选地，重建的补丁可以被转换成3D网格模型。

公开(公告)号：US07392181B2

公开(公告)日：2008-06-24

申请号：US11070612

申请日：2005-03-02

申请人： Radu Victor Balan ,  Justinian Rosca ,  Peter Casazza ,  Dan Edidin

发明人： Radu Victor Balan ,  Justinian Rosca ,  Peter Casazza ,  Dan Edidin

IPC分类号： G10L21/02

CPC分类号： G06K9/00503

摘要： A system and method for nonlinear signal enhancement is provided. The method comprises: performing a linear transformation on a measured signal comprising a source component and a noise component; determining a modulus of the linear transformed signal; estimating a noise-free part of the linear transformed signal; and reconstructing the source component of the measured signal using the noise-free part of the linear transformed signal.

摘要翻译： 提供了一种用于非线性信号增强的系统和方法。 该方法包括：对包括源分量和噪声分量的测量信号执行线性变换; 确定线性变换信号的模数; 估计线性变换信号的无噪声部分; 以及使用线性变换信号的无噪声部分来重构测量信号的源分量。

公开(公告)号：US20080033701A1

公开(公告)日：2008-02-07

申请号：US11458644

申请日：2006-07-19

申请人： Ronald T. Kurnik

发明人： Ronald T. Kurnik

IPC分类号： G06F17/10 ,  G06F7/38

CPC分类号： G06F17/17 ,  C12Q1/6851 ,  G06F17/10 ,  G06K9/00503 ,  C12Q2537/165

摘要： Systems and methods for improving Ct determination in PCR amplification curves by correcting PCR data for temperature shifts that may occur during the PCR process. A double sigmoid function with parameters determined by a Levenberg-Marquardt (LM) regression process is used to find an approximation to the portion of the curve in the region after the temperature shift, termed “CAC”, the cycle where the temperature shift occurred. A robust linear approximation is determined for the portion of the curve in the region before the temperature shift. Values of the fluorescent intensity for the cycle CAC or CAC+1 are determined using both the linear approximation and the LM process, and a difference in these values is subtracted off of the portion of the data set representing the portion of the curve before the temperature shift occurred to produce a shift-corrected data set. The shift-corrected data set may be displayed or otherwise used for further processing.

摘要翻译： 通过校正可能在PCR过程中可能发生的温度变化的PCR数据来改进PCR扩增曲线中的Ct测定的系统和方法。 使用由Levenberg-Marquardt（LM）回归过程确定的参数的双S形函数用于找到在温度偏移之后的区域中的曲线部分的近似值，称为“CAC”，即发生温度变化的周期。 对于温度偏移之前的区域中的曲线部分确定鲁棒的线性近似。 使用线性近似和LM过程来确定循环CAC或CAC + 1的荧光强度的值，并且将这些值的差值从表示温度之前的曲线部分的数据集的部分减去 发生偏移以产生移位校正数据集。 移位校正数据集可以被显示或以其他方式用于进一步处理。

公开(公告)号：US07133568B2

公开(公告)日：2006-11-07

申请号：US09921524

申请日：2001-08-03

申请人： Alexei V. Nikitin ,  Ruslan L. Davidchack

发明人： Alexei V. Nikitin ,  Ruslan L. Davidchack

IPC分类号： G06K9/40

CPC分类号： G06K9/00503 ,  G01D1/00 ,  G06T5/002 ,  G06T5/20 ,  G10L25/48 ,  H03H11/0405

摘要： Various components of the present invention are collectively designated as Analysis of Variables Through Analog Representation (AVATAR). AVATAR offers an analog solution to those problems of the analysis of variables which are normally handled by digital means. The invention allows (a) the improved perception of the measurements through geometrical analogies, (b) effective solutions of the existing computational problems of the order statistic methods, and (c) extended applicability of these methods to analysis of variables. The invention employs transformation of discrete or continuous variables into normalized continuous scalar fields, that is, into objects with mathematical properties of density and/or cumulative distribution functions. In addition to dependence on the displacement coordinates (thresholds), these objects can also depend on other parameters, including spatial coordinates. Moreover, this transformation of the measured variables may be implemented with respect to any reference variable. Thus, the values of the reference variable provide a common unit, or standard, for measuring and comparison of variables of different natures, for assessment of mutual dependence of these variables, and for evaluation of changes in the variables and their dependence with time.The invention enables, on a consistent general basis, a variety of new techniques for analysis of variables, which can be implemented through various physical means in continuous action machines as well as through digital means or computer calculations. Several of the elements of these new techniques do have digital counterparts, such as some rank order techniques in digital signal and image processing.

摘要翻译： 本发明的各种组件被统称为通过模拟表示的变量分析（AVATAR）。 AVATAR为通常以数字方式处理的变量分析提供了模拟解决方案。 本发明允许（a）通过几何类比改进对测量的感知，（b）有序的方案对现有的计算问题的秩序统计方法，以及（c）这些方法对变量分析的扩展适用性。 本发明将离散或连续变量转换成归一化的连续标量场，即将其转换为具有密度和/或累积分布函数的数学性质的对象。 除了依赖于位移坐标（阈值）之外，这些对象还可以依赖于其他参数，包括空间坐标。 此外，可以相对于任何参考变量实现测量变量的这种变换。 因此，参考变量的值为测量和比较不同性质的变量提供了一个共同的单位或标准，用于评估这些变量的相互依赖性，以及评估变量的变化及其随时间的依赖性。 本发明可以在一致的一般基础上实现用于分析变量的各种新技术，其可以通过连续动作机器中的各种物理手段以及通过数字方式或计算机计算来实现。 这些新技术的几个要素确实具有数字对应物，例如数字信号和图像处理中的一些排序技术。

公开(公告)号：US07075064B2

公开(公告)日：2006-07-11

申请号：US11134560

申请日：2005-05-20

申请人： James R. Oliphant ,  H. Dennis Tolley ,  Alan Rockwood ,  Edgar Lee ,  Milton Lee

发明人： James R. Oliphant ,  H. Dennis Tolley ,  Alan Rockwood ,  Edgar Lee ,  Milton Lee

IPC分类号： H01J49/26

CPC分类号： G06K9/00503 ,  G01N30/7206

摘要： A system and method are provided of extracting spectra from data produced by temporally indexed spectral scans from a spectrometer and spectrometer. The method includes the operation of receiving a data matrix from the spectrometer. The noise can then be removed from the data matrix. A further operation is identifying spectra of interest in the data matrix based on information content. In addition, a reduction transformation can be applied to the data matrix based upon the spectra of interest based upon the denizen transformation for the purpose of extracting the spectra of interest from the data matrix.

摘要翻译： 提供了一种系统和方法，从光谱仪和光谱仪的时间索引光谱扫描产生的数据中提取光谱。 该方法包括从光谱仪接收数据矩阵的操作。 然后可以从数据矩阵中去除噪声。 进一步的操作是基于信息内容来识别数据矩阵中的感兴趣的光谱。 此外，为了从数据矩阵中提取感兴趣的光谱，可以基于基于转换的感兴趣的光谱，将数据矩阵应用于数据矩阵。

公开(公告)号：US20060002634A1

公开(公告)日：2006-01-05

申请号：US11224200

申请日：2005-09-12

申请人： James Riley ,  Keith Frost

发明人： James Riley ,  Keith Frost

IPC分类号： G06K9/32

CPC分类号： G06K9/00503 ,  G01J3/28 ,  G01J3/2803 ,  G01J3/32 ,  G01J3/36 ,  G01N15/147 ,  G01N15/1475 ,  G06K9/00127 ,  G06T5/50 ,  G06T7/32 ,  G06T7/33 ,  G06T2207/10036

摘要： A multichannel imaging system generates an ensemble of images for each field of view of an object. Each image in the ensemble is intended to contain information from only one source among a plurality of sources for the object. However, due to crosstalk, at least a portion of the signal from a first source appears in a channel intended for a second source. Because the accuracy of the correction will be degraded if the images in an ensemble are spatially misaligned with respect to one another, the spatial offset between images is determined and a correction is applied to substantially eliminate the offset. Then, a correction to the signals is determined to substantially reduce the contributions to the signal in a channel from the signals in other channels. The signal processing can be employed to process the output signals for each of a plurality of different disclosed imaging systems.

公开(公告)号：US20050209821A1

公开(公告)日：2005-09-22

申请号：US11104645

申请日：2005-04-13

申请人： Phuc Nguyen ,  Denis Collin ,  Peter Matschek

发明人： Phuc Nguyen ,  Denis Collin ,  Peter Matschek

IPC分类号： G05B23/02 ,  G06F11/30 ,  G06F17/00 ,  G06F17/10 ,  G06F19/00 ,  G06K9/00

CPC分类号： G05B23/0221 ,  G06K9/00503 ,  G06K9/00536

摘要： A method and system are disclosed for removing very low frequency noise from a time-based data set for use in data analysis of the time-based data set having a plurality of data points, the method comprising providing the time-based data set to be analyzed, determining a baseline value from at least a portion of the data set, smoothing the data set to diminish an effect of extraneous data points and obtain smoothed data, wherein the smoothing includes using a Fast Fourier Transform (FFT) algorithm to transfer the time-based data set into a frequency based data set, attenuating low frequencies of the frequency-based data set and using an inverse Fourier Transform (FFT) algorithm to transfer the attenuated frequency based data set into an attenuated time-based data set.

摘要翻译： 公开了一种用于从具有多个数据点的基于时间的数据集的数据分析中使用的基于时间的数据集中去除非常低频噪声的方法和系统，所述方法包括提供基于时间的数据集 分析，从所述数据集的至少一部分确定基线值，平滑所述数据集以减少外部数据点的影响并获得平滑数据，其中所述平滑包括使用快速傅里叶变换（FFT）算法来传送时间 基于频率的数据集，衰减基于频率的数据集的低频，并且使用逆傅立叶变换（FFT）算法将衰减的基于频率的数据集传输到衰减的基于时间的数据集中。

公开(公告)号：US06941301B2

公开(公告)日：2005-09-06

申请号：US10051266

申请日：2002-01-18

申请人： Bruce Ferguson ,  Eric Hartman

发明人： Bruce Ferguson ,  Eric Hartman

IPC分类号： G06E1/00 ,  G06F7/00 ,  G06F15/18 ,  G06F17/30 ,  G06K9/00

CPC分类号： G06K9/00503 ,  Y10S707/99934 ,  Y10S707/99936 ,  Y10S707/99943

摘要： A system and method for preprocessing input data to a support vector machine (SVM). The SVM is a system model having parameters that define the representation of the system being modeled, and operates in two modes: run-time and training. A data preprocessor preprocesses received data in accordance with predetermined preprocessing parameters, and outputs preprocessed data. The data preprocessor includes an input buffer for receiving and storing the input data. The input data may include one or more outlier values. A data filter detects and removes any outlier values in the input data, generating corrected input data. The filter may optionally replace the outlier values in the input data. An output device outputs the corrected data from the data filter as preprocessed data. The corrected data may be input to the SVM in training mode to train the SVM, and/or in run-time mode to generate control parameters and/or predictive output information.

摘要翻译： 一种用于将输入数据预处理到支持向量机（SVM）的系统和方法。 SVM是具有定义正在建模的系统的表示的参数的系统模型，并且以运行时和训练两种模式运行。 数据预处理器根据预定的预处理参数对接收到的数据进行预处理，并输出预处理数据。 数据预处理器包括用于接收和存储输入数据的输入缓冲器。 输入数据可以包括一个或多个异常值。 数据滤波器检测和去除输入数据中的任何异常值，产生校正的输入数据。 滤波器可以可选地替换输入数据中的异常值。 输出装置将来自数据滤波器的校正数据作为预处理数据输出。 校正数据可以在训练模式下输入到SVM，以训练SVM，和/或以运行时模式生成控制参数和/或预测输出信息。