-
公开(公告)号：US09702768B2
公开(公告)日：2017-07-11
申请号：US13961292
申请日：2013-08-07
CPC分类号： G01K11/24 , G01K13/02 , G01K2013/024
摘要： An acoustic signal traversing a hot gas is sampled at a source and a receiver and is represented in overlapping windows that maximize useable signal content. Samples in each window are processed to represented in different sparsified bins in the frequency domain. Determining a signal delay between the source and the receiver from a summation of maximum smoothed coherence transform cross-correlation values of different data windows wherein a sparseness of a mean smoothed coherence transform cross-correlation of windows is maximized. Determining a set of delay times wherein outliers are deleted to estimate a time of flight from which a temperature of the hot gas is calculated.
-
2.发明申请公开(公告)号：US20150063411A1
公开(公告)日：2015-03-05
申请号：US14017386
申请日：2013-09-04
CPC分类号： G01M15/14 , F02C7/32 , F05D2260/83 , G01H3/00 , G01K11/24 , G01K13/02 , G01K2013/024
摘要： A method and apparatus for operating a gas turbine engine including determining a temperature of a working gas at a predetermined axial location within the engine. An acoustic signal is encoded with a distinct signature defined by a set of predetermined frequencies transmitted as a non-broadband signal. Acoustic signals are transmitted from an acoustic transmitter located at a predetermined axial location along the flow path of the gas turbine engine. A received signal is compared to one or more transmitted signals to identify a similarity of the received signal to a transmitted signal to identify a transmission time for the received signal. A time-of-flight is determined for the signal and the time-of-flight for the signal is processed to determine a temperature in a region of the predetermined axial location.
摘要翻译： 一种用于操作燃气涡轮发动机的方法和装置，包括确定发动机内预定轴向位置处的工作气体的温度。 声信号用由作为非宽带信号发送的一组预定频率定义的不同签名编码。 声音信号从位于燃气涡轮发动机的流路的预定轴向位置处的声发射器发射。 将接收到的信号与一个或多个发射信号进行比较，以识别接收到的信号与发射信号的相似性，以识别接收信号的传输时间。 确定信号的飞行时间，并处理信号的飞行时间以确定预定轴向位置的区域中的温度。
-
公开(公告)号：US20140064326A1
公开(公告)日：2014-03-06
申请号：US13961292
申请日：2013-08-07
IPC分类号： G01K11/24
CPC分类号： G01K11/24 , G01K13/02 , G01K2013/024
摘要： An acoustic signal traversing a hot gas is sampled at a source and a receiver and is represented in overlapping windows that maximize useable signal content. Samples in each window are processed to represented in different sparsified bins in the frequency domain. Determining a signal delay between the source and the receiver from a summation of maximum smoothed coherence transform cross-correlation values of different data windows wherein a sparseness of a mean smoothed coherence transform cross-correlation of windows is maximized. Determining a set of delay times wherein outliers are deleted to estimate a time of flight from which a temperature of the hot gas is calculated.
摘要翻译： 在源和接收器处对穿过热气体的声信号进行采样，并且在可用信号内容最大化的重叠窗口中进行表示。 处理每个窗口中的样本以在频域中的不同的稀疏箱中表示。 从不同数据窗口的最大平滑相干变换相加值的总和确定源和接收器之间的信号延迟，其中窗口的平均平滑相干变换互相关的稀疏度最大化。 确定一组延迟时间，其中异常值被删除以估计计算出热气体的温度的飞行时间。
-
公开(公告)号：US20140036060A1
公开(公告)日：2014-02-06
申请号：US14112502
申请日：2012-03-21
申请人： Heiko Claussen , Ti-chiun Chang , Justinian Rosca
发明人： Heiko Claussen , Ti-chiun Chang , Justinian Rosca
IPC分类号： H04N7/18
摘要： A system and methods to deblend seismic data from a plurality of sources and received by a plurality of sensors as shot gathers are disclosed. The deblending is performed by a Mutual Interdependence Analysis Method to separate contributions of different shots. Deblending is also performed by applying a measure of coherence in parallel data domains such as Common Shot Gather and Common Midpoint. Deblending is also achieved by using the hyperbolic nature of seismic data in the common midpoint domain. Deblended signals are estimated and are applied to create a seismic image. Also, Bergman iteration based migration is applied directly on the blended seismic shot gathers without first deblending as an alternative method. The methods are applied in seismic imaging for exploration of natural resources.
摘要翻译： 公开了一种用于从多个源中去除地震数据并由多个传感器接收的射击集合的系统和方法。 通过相互依赖关系分析方法对不同镜头进行分类。 还可以通过在并行数据域（例如Common Shot Gather和Common Midpoint）中应用一致性测量来执行去混合。 通过使用共同中点域中的地震数据的双曲线性质也可以实现消除混合。 去除信号被估计并被应用以产生地震图像。 此外，基于Bergman迭代的迁移也直接应用于混合地震射击聚集中，而无需首先解除拆分作为替代方法。 该方法应用于地震成像勘探自然资源。
-
公开(公告)号：US20130245389A1
公开(公告)日：2013-09-19
申请号：US13718023
申请日：2012-12-18
申请人： Christian P. Schultz , Justinian Rosca , Heiko Claussen , Carolyn Joiner , Steven A. Russell , Nazif Tas
发明人： Christian P. Schultz , Justinian Rosca , Heiko Claussen , Carolyn Joiner , Steven A. Russell , Nazif Tas
IPC分类号： A61B5/00
CPC分类号： A61B5/0002 , A61B5/0077 , A61B5/02 , A61B5/0205 , A61B5/024 , A61B5/0402 , A61B5/0813 , A61B5/14542 , A61B5/68 , A61B5/6892 , G06F19/00 , G06F19/3418 , G08B21/0461 , G08B25/10 , G16H50/20 , G16H50/70
摘要： A patient monitoring and intervention system, comprises an interface for receiving data representing multiple different parameters from multiple different sensors, comprising sensors in a patient bed and attached to a patient including, a heart rate sensor, a respiration sensor and a pressure sensor indicating bed pressure points. A learning processor determines a normal range for a set of the different received patient parameters for the patient by recording the patient parameter values over a time period and analyzing the recorded parameter values to determine their range. A data processor determines if the set of different received patient parameters exceeds the determined normal range and in response to this determination and in response to the type of parameters in the set and medical record information of the patient, initiates adjustment of a patient bed and at least one of, (a) changes medication administered to a patient and (b) alerts a worker of the patient parameter change.
摘要翻译： 一种患者监测和干预系统，包括用于从多个不同传感器接收表示多个不同参数的数据的接口，包括患者床中的传感器并附接到患者，所述传感器包括心率传感器，呼吸传感器和指示床压的压力传感器 积分 学习处理器通过在一段时间内记录患者参数值来确定用于患者的一组不同接收的患者参数的正常范围，并分析记录的参数值以确定其范围。 数据处理器确定不同接收到的患者参数的集合是否超过确定的正常范围，并且响应于该确定，并且响应于患者的设置和医疗记录信息中的参数的类型，启动患者床的调整 至少一个，（a）改变向患者施用的药物，和（b）警告工作者患者参数变化。
-
6.发明申请SYSTEM AND METHOD FOR SIGNATURE EXTRACTION USING MUTUAL INTERDEPENDENCE ANALYSIS 审中-公开使用相互独立分析的签名提取的系统和方法公开(公告)号：US20100316293A1
公开(公告)日：2010-12-16
申请号：US12614625
申请日：2009-11-09
申请人： Heiko Claussen , Justinian Rosca
发明人： Heiko Claussen , Justinian Rosca
IPC分类号： G06T7/00
CPC分类号： G06K9/6242 , G06K9/00288 , G06K9/4661 , G06K9/6278 , G10L17/02 , G10L17/20
摘要： A method for determining a signature vector of a high dimensional dataset includes initializing a mutual interdependence vector wGMIA from a a set X of N input vectors of dimension D, where N≦D, randomly selecting a subset S of n vectors from set X, where n is such that n>>1 and n
摘要翻译： 一种用于确定高维数据集的签名向量的方法包括从维D的N个输入向量的集合X初始化相互依赖性向量wGMIA，其中N＆n; E; D，从集合X随机选择n个向量的子集S，其中n 使得n >> 1和n
-
公开(公告)号：US09263041B2
公开(公告)日：2016-02-16
申请号：US13804947
申请日：2013-03-14
申请人： Heiko Claussen , Justinian Rosca
发明人： Heiko Claussen , Justinian Rosca
摘要： Methods related to Generalized Mutual Interdependence Analysis (GMIA), a low complexity statistical method for projecting data in a subspace that captures invariant properties of the data, are implemented on a processor based system. GMIA methods are applied to the signal processing problem of voice activity detection and classification. Real-world conversational speech data are modeled to fit the GMIA assumptions. Low complexity GMIA computations extract reliable features for classification of sound under noisy conditions and operate with small amounts of data. A speaker is characterized by a slow varying or invariant channel that is learned and is tracked from single channel data by GMIA methods.
摘要翻译： 与广义相互依赖关系分析（GMIA）相关的方法是在基于处理器的系统上实现的一种低复杂度统计方法，用于在捕获数据不变属性的子空间中投影数据。 GMIA方法应用于语音活动检测和分类的信号处理问题。 现实世界对话语音数据被建模以适应GMIA假设。 低复杂度的GMIA计算提取了可靠的特征，用于在嘈杂条件下对声音进行分类，并使用少量数据进行操作。 扬声器的特征在于慢速变化或不变的通道，通过GMIA方法从单通道数据中学习并跟踪。
-
8.发明授权Systems and methods for own voice recognition with adaptations for noise robustness 有权用于自身语音识别的系统和方法，适应噪声鲁棒性公开(公告)号：US08462969B2
公开(公告)日：2013-06-11
申请号：US13089738
申请日：2011-04-19
CPC分类号： H04R25/505 , G10L17/02 , G10L17/06 , G10L17/20 , H04R25/407 , H04R2225/43
摘要： Own voice recognition (OVR) for hearing aids, detects time instances where the person wearing the device is speaking. Classification of the own voice is performed dependent on a fixed or adaptive detection threshold. Automatic tuning in a real-time system depends on general noise statistics in the input signals. The noise is removed from the received signal and is characterized by signal-to-noise ratio and noise color. An optimal detection threshold for own voice recognition is determined based on the noise characteristics. A noise detection model is created by smoothed Voronoi tessellation. Own voice detection is performed by a processor.
摘要翻译： 自己的语音识别（OVR）用于助听器，可以检测穿戴设备的人在说话的时间。 根据固定或自适应检测阈值执行自身语音的分类。 实时系统中的自动调谐取决于输入信号中的一般噪声统计。 噪声从接收信号中去除，其特征在于信噪比和噪声颜色。 基于噪声特性确定自身语音识别的最佳检测阈值。 噪声检测模型通过平滑的Voronoi镶嵌创建。 自己的语音检测由处理器执行。
-
公开(公告)号：US20110302114A1
公开(公告)日：2011-12-08
申请号：US13084692
申请日：2011-04-12
申请人： Heiko Claussen , Justinian Rosca
发明人： Heiko Claussen , Justinian Rosca
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： Methods for one-class learning using support vector machines from a plurality of data batches are provided. A first support vector machine is learned from the plurality of data batches by a processor. A new data batch is received by the processor and is classified by the first support vector machine. If a non-zero loss classification occurs a new support vector machine is trained using the first support vector machine and the new data batch only. Data batches can be discarded if they are represented by the current support vector machine or after being used for training an updated support vector machine. Weighing factors applied to update the first support vector machine depend upon a parameter which is optimized iteratively. Support vectors do not need to be recalculated. A classifier is learned in a number of stages equal to the number of data batches processed on-line.
摘要翻译： 提供了使用来自多个数据批次的支持向量机的一类学习的方法。 通过处理器从多个数据批中学习第一支持向量机。 处理器接收到新的数据批次，并由第一支持向量机分类。 如果发生非零损失分类，则仅使用第一支持向量机和新的数据批次训练新的支持向量机。 如果数据批次由当前的支持向量机表示，或者在用于训练更新的支持向量机之后，则可以丢弃它们。 应用于更新第一支持向量机的称重因子取决于迭代优化的参数。 支持向量不需要重新计算。 在与在线处理的数据批次数相等的多个阶段中学习分类器。
-
10.发明申请SYSTEMS AND METHODS FOR OWN VOICE RECOGNITION WITH ADAPTATIONS FOR NOISE ROBUSTNESS 有权用于噪声语音识别的噪声识别系统和方法公开(公告)号：US20110261983A1
公开(公告)日：2011-10-27
申请号：US13089738
申请日：2011-04-19
IPC分类号： H04R25/00
CPC分类号： H04R25/505 , G10L17/02 , G10L17/06 , G10L17/20 , H04R25/407 , H04R2225/43
摘要： Own voice recognition (OVR) for hearing aids, detects time instances where the person wearing the device is speaking. Classification of the own voice is performed dependent on a fixed or adaptive detection threshold. Automatic tuning in a real-time system depends on general noise statistics in the input signals. The noise is removed from the received signal and is characterized by signal-to-noise ratio and noise color. An optimal detection threshold for own voice recognition is determined based on the noise characteristics. A noise detection model is created by smoothed Voronoi tessellation. Own voice detection is performed by a processor.
摘要翻译： 自己的语音识别（OVR）用于助听器，可以检测穿戴设备的人在说话的时间。 根据固定或自适应检测阈值执行自身语音的分类。 实时系统中的自动调谐取决于输入信号中的一般噪声统计。 噪声从接收信号中去除，其特征在于信噪比和噪声颜色。 基于噪声特性确定自身语音识别的最佳检测阈值。 噪声检测模型通过平滑的Voronoi镶嵌创建。 自己的语音检测由处理器执行。
-
-
-
-
-
-
-
-
-
搜索结果
64 条记录 (耗时 0.027 秒)