-
公开(公告)号：US20130085715A1
公开(公告)日：2013-04-04
申请号：US13248887
申请日：2011-09-29
IPC分类号： G06F17/18
CPC分类号： G06K9/00536 , G06K9/00523
摘要： Systems and methods for anomaly detection in streaming data are disclosed. An example method includes applying statistical analysis to streaming data in a sliding window. The method also includes extracting a feature. The method also includes determining class assignment for the feature using class conditional probability densities and a threshold.
摘要翻译： 公开了流数据中异常检测的系统和方法。 示例性方法包括将统计分析应用于滑动窗口中的流数据。 该方法还包括提取特征。 该方法还包括使用类条件概率密度和阈值确定特征的类分配。
-
2.发明申请SYSTEM AND METHOD FOR BRAIN MACHINE INTERFACE (BMI) CONTROL USING REINFORCEMENT LEARNING 有权使用加强学习的脑机接口（BMI）控制系统和方法公开(公告)号：US20100137734A1
公开(公告)日：2010-06-03
申请号：US12598217
申请日：2008-04-25
申请人： John F. Digiovanna , Babak Mahmoudi , Jeremiah D. Mitzelfelt , Justin C. Sanchez , Jose C. Principe
发明人： John F. Digiovanna , Babak Mahmoudi , Jeremiah D. Mitzelfelt , Justin C. Sanchez , Jose C. Principe
IPC分类号： A61B5/0476
CPC分类号： A61F2/68 , A61B5/0482 , A61F2/72 , G05B13/0265 , G06F3/015 , G06N3/08
摘要： A Brain Machine Interface (BMI) agent (110) is provided, that when operatively coupled to a subject during a mental task by the subject to control a prosthetic device (130), monitors one or more states (125) of neural activity of the subject, receives feedback associated with a behavior of the prosthetic device responsive to the control, learns a functional mapping between the mental task and the behavior in view of the feedback, and applies at least one control action (115) to the prosthetic device in accordance with the learning to control the prosthetic device for a targeted behavior.
摘要翻译： 提供了一种脑机接口（BMI）代理（110），当在受试者的精神任务期间可操作地耦合到受试者以控制假体装置（130）时，监视一个或多个状态（125）的神经活动 受试者响应于控制而接收与假肢装置的行为相关联的反馈，根据反馈来学习心理任务和行为之间的功能映射，并且根据反馈将至少一个控制动作（115）应用于假体装置 通过学习来控制假肢装置的目标行为。
-
公开(公告)号：US07066173B2
公开(公告)日：2006-06-27
申请号：US10407160
申请日：2003-04-04
IPC分类号： A61M16/00
CPC分类号： G06F19/3481 , A61B5/0205 , A61B5/0836 , A61B5/087 , A61B5/7264 , A61B5/7267 , A61M16/0051 , A61M16/026 , A61M16/12 , A61M2016/0021 , A61M2016/0036 , A61M2205/3553 , A61M2230/06 , A61M2230/205 , A61M2230/30 , A61M2230/432 , A61M2230/435 , A61M2230/50 , G06F19/00 , G06F19/3456 , G16H40/63 , Y10S128/924 , Y10S128/925 , A61M2230/005
摘要： Embodiments of the present invention described and shown in the specification and drawings include a system and method for monitoring the ventilation support provided by a ventilator and automatically supplying a breathing gas to a patient via a breathing circuit that is in fluid communication with the lungs of the patient.
摘要翻译： 在说明书和附图中描述和示出的本发明的实施例包括用于监测由呼吸机提供的通气支架并通过呼吸回路自动地向患者提供呼吸气体的系统和方法，所述呼吸回路与肺的肺部流体连通 患者。
-
公开(公告)号：US06420927B1
公开(公告)日：2002-07-16
申请号：US09633335
申请日：2000-08-07
IPC分类号： H03K500
CPC分类号： H03K5/135 , H03H19/004
摘要： The subject invention pertains to a method and circuit design particularly useful for long time constant RC active or passive circuits in either continuous or discrete time domains. The subject invention also relates to a method and circuit design useful for long time constant RL active or passive circuits in either continuous or discrete time domains. The subject invention can find advantage in the mixed-signal, electronic circuit component market. The subject invention widens the application and the price/performance ratio of VLSI analog electronic circuits, and can be easily included in conventional circuit designs.
摘要翻译： 本发明涉及对连续或离散时域中的长时间常数RC有源或无源电路特别有用的方法和电路设计。 本发明还涉及对连续或离散时域中的长时间常数RL有源或无源电路有用的方法和电路设计。 本发明可以在混合信号，电子电路元件市场中找到优势。 本发明扩大了VLSI模拟电子电路的应用和价格/性能比，并且可以容易地包括在常规电路设计中。
-
公开(公告)号：US09218527B2
公开(公告)日：2015-12-22
申请号：US13248887
申请日：2011-09-29
CPC分类号： G06K9/00536 , G06K9/00523
摘要： An example method for anomaly detection in streaming data includes applying statistical analysis to streaming data in a sliding window. The method also includes extracting a feature. The method also includes determining class assignment for the feature using class conditional probability densities and a threshold.
摘要翻译： 流数据中异常检测的一个示例方法包括：在滑动窗口中对流数据应用统计分析。 该方法还包括提取特征。 该方法还包括使用类条件概率密度和阈值确定特征的类分配。
-
公开(公告)号：US08611839B2
公开(公告)日：2013-12-17
申请号：US12597561
申请日：2007-04-26
申请人： Jose C. Principe , Weifeng Liu
发明人： Jose C. Principe , Weifeng Liu
CPC分类号： H04L25/06 , G06K9/00523 , G06K9/6248
摘要： A method (200) for detecting a periodic signal (141) in a noisy signal (101) is provided. The method can include applying (210) correntropy to the noisy signal to generate a non-linear mapping, and applying (220) a sub-space projection to the non-linear mapping to produce principal components. A correntropy kernel can be applied to the noisy signal to generate a Gram matrix that is used in a Temporal Principal Component Analysis (TPCA). The correntropy kernel projects nonlinearly the input data to a reproducing kernel Hilbert Space (RKHS) preserving the input time structure and attenuating impulsive noise. The correntropy kernel is data dependent, and the RKHS correlation matrix has the same dimension as the input data correlation matrix. A principal component having a majority of signal energy can be chosen (230) to detect the periodic signal.
摘要翻译： 提供一种用于检测噪声信号（101）中的周期信号（141）的方法（200）。 该方法可以包括对噪声信号应用（210）精度以产生非线性映射，并且将（220）子空间投影应用于（220）非线性映射以产生主成分。 可以将熵核应用于噪声信号以产生在时间主成分分析（TPCA）中使用的Gram矩阵。 科学核心非线性地将输入数据投射到重现核心希尔伯特空间（RKHS），保留输入时间结构并衰减脉冲噪声。 熵核是数据相关的，RKHS相关矩阵与输入数据相关矩阵具有相同的维度。 可以选择具有多数信号能量的主成分（230）来检测周期信号。
-
公开(公告)号：US20120238894A1
公开(公告)日：2012-09-20
申请号：US13443161
申请日：2012-04-10
IPC分类号： A61B5/0488
CPC分类号： A61B5/4356 , A61B5/04882 , A61B5/1107 , A61B5/7264 , A61B2503/02 , A61B2562/046 , G06F19/00
摘要： Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.
摘要翻译： 监测子宫收缩活动和劳动进展的系统和方法。 本发明的系统可以包括（1）多个传感器; （2）放大/滤波装置; （3）计算装置; 和（4）图形用户界面。 可以使用本发明的系统实时提取和提供给用户的准确临床数据包括但不限于劳动进展，早产预测和监测以及子宫内压力预测。 在优选实施例中，本发明的系统包括智能手段，例如神经网络系统，用于分析和解释用于临床诊断的临床数据以及递送策略。
-
公开(公告)号：US08160692B2
公开(公告)日：2012-04-17
申请号：US12475911
申请日：2009-06-01
IPC分类号： A61B5/05
CPC分类号： A61B5/4356 , A61B5/04882 , A61B5/1107 , A61B5/7264 , A61B2503/02 , A61B2562/046 , G06F19/00
摘要： Systems and methods for monitoring uterus contraction activity and progress of labor. The system of the subject invention can comprises (1) a plurality of sensors; (2) an amplifying/filtering means; (3) a computing means; and (4) a graphical user interface. Accurate clinical data, which can be extracted and provided to the user in real-time using the system of the invention, include without limitation, progress of labor, prediction and monitoring of preterm labor, and intrauterine pressure prediction. In a preferred embodiment, the system of the invention includes an intelligence means, such as a neural network system, to analyze and interpret clinical data for use in clinical diagnosis as well as delivery strategy.
摘要翻译： 监测子宫收缩活动和劳动进展的系统和方法。 本发明的系统可以包括（1）多个传感器; （2）放大/滤波装置; （3）计算装置; 和（4）图形用户界面。 可以使用本发明的系统实时提取和提供给用户的准确临床数据包括但不限于劳动进展，早产预测和监测以及子宫内压力预测。 在优选实施例中，本发明的系统包括智能手段，例如神经网络系统，用于分析和解释用于临床诊断的临床数据以及递送策略。
-
公开(公告)号：US20110192398A1
公开(公告)日：2011-08-11
申请号：US12986520
申请日：2011-01-07
CPC分类号： A61B5/033 , A61B5/044 , A61B5/4356 , A61B5/7221 , A61N1/36021
摘要： The present invention relates to systems and methods for providing a short-acting analgesic agent in the management of pain during labor, wherein the system enables efficient, real-time prediction of contractions for the coordinated administration of analgesia such that the peak effectiveness of the analgesic coincides with the intermittent pain of labor.
摘要翻译： 本发明涉及用于在劳动过程中提供短效镇痛剂以治疗疼痛的系统和方法，其中所述系统能够有效，实时地预测镇痛协调施用的收缩，使得止痛剂的峰值效力 与劳动力的间歇性痛苦相吻合。
-
公开(公告)号：US20080293372A1
公开(公告)日：2008-11-27
申请号：US12092234
申请日：2006-10-31
IPC分类号： H04B1/16
CPC分类号： G10L21/02 , G10L21/0208
摘要： A signal processing method is provided. The method includes receiving a signal input, and filtering the signal input using a nonlinear correntropy filter. The method additionally includes generating an output based upon the filtering of the signal input. The nonlinear correntropy filter can be configured as a nonlinear Wiener filter. Alternatively, the nonlinear correntropy filter can be configured as a correntropy least mean square (LMS) filter, or a correntropy Newton/LMS filter.
摘要翻译： 提供信号处理方法。 该方法包括接收信号输入，并使用非线性correntropy滤波器对信号进行滤波。 该方法还包括基于对信号输入的滤波产生输出。 非线性Correntropy滤波器可以被配置为非线性维纳滤波器。 或者，非线性correntropy滤波器可以被配置为公理最小均方（LMS）滤波器或牛顿/ LMS滤波器。
-
-
-
-
-
-
-
-
-
搜索结果
39 条记录 (耗时 0.028 秒)
