专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US08352400B2 Adaptive pattern recognition based controller apparatus and method and human-factored interface therefore 失效
标题翻译：因此，基于自适应模式识别的控制器装置和方法以及人为因素的界面
公开(公告)号：US08352400B2
公开(公告)日：2013-01-08
申请号：US13244152
申请日：2011-09-23
申请人： Steven M. Hoffberg , Linda I. Hoffberg-Borghesani
发明人： Steven M. Hoffberg , Linda I. Hoffberg-Borghesani
IPC分类号： G06F17/00 , G06F15/00 , G06F15/18 , H04N7/10 , H04N7/025 , G06Q30/00 , G06G7/00 , G06N5/02 , G06E1/00 , G06E3/00
CPC分类号： F24F11/006 , F24F11/0034 , F24F11/30 , F24F11/62 , F24F2120/10 , G05B2219/2642 , G06F7/023 , G06N5/048 , G06N7/06 , G06N99/005
摘要： A system and method of predicting items likely to appeal to a user, based on data received from a remote site. One or more local systems are provided, along with a remote system, said local systems communicating with said remote system over a network connection. Each local system maintains a set of characterized items. A local processor predicts an appeal of an item to a user based on the comparison with the set of characterized items with, e.g., user preferences. The user may interact through graphical user interface. At least one user-preference predictive algorithm may be employed to present items predicted to appeal to the user.
摘要翻译：基于从远程站点接收的数据来预测可能吸引用户的项目的系统和方法。提供一个或多个本地系统以及远程系统，所述本地系统通过网络连接与所述远程系统通信。每个本地系统维护一组特征项目。本地处理器基于与特定项目的集合的比较（例如，用户偏好）来预测项目对用户的吸引力。用户可以通过图形用户界面进行交互。可以使用至少一个用户偏好预测算法来呈现预测以吸引用户的项目。

52. 发明授权

US08351688B2 Categorization quality through the combination of multiple categorizers 有权
标题翻译：分类质量通过多个分类器的组合
公开(公告)号：US08351688B2
公开(公告)日：2013-01-08
申请号：US12640030
申请日：2009-12-17
申请人： Scott Robert Hancock , Francois Ragnet , Damien Cramet
发明人： Scott Robert Hancock , Francois Ragnet , Damien Cramet
IPC分类号： G06K9/62 , G06E1/00
CPC分类号： G06K9/6292
摘要： A system categorizes one or more objects based at least in part upon one or more characteristics associated therewith. A first classifier includes a rule set to determine if each of the one or more objects meets or exceeds a quality threshold. A second classifier, orthogonal to the first classifier, includes a rule set to determine if each of the one or more objects meets or exceeds a quality threshold. In one embodiment, the quality threshold associated with the first classifier and the quality threshold associated with the second classifier are less than a predetermined target threshold. The result for each object of the first classifier is compared to the result of the second classifier. The object is categorized if the result of the first classifier and the result of the second classifier match. The object is uncategorized if the result of the first classifier does not match the result of the second classifier.
摘要翻译：系统至少部分地基于与其相关联的一个或多个特征来对一个或多个对象进行分类。第一分类器包括用于确定一个或多个对象中的每一个是否满足或超过质量阈值的规则集。与第一分类器正交的第二分类器包括用于确定一个或多个对象中的每一个是否满足或超过质量阈值的规则集。在一个实施例中，与第一分类器相关联的质量阈值和与第二分类器相关联的质量阈值小于预定目标阈值。将第一分类器的每个对象的结果与第二分类器的结果进行比较。如果第一个分类器的结果和第二个分类器的结果匹配，则对象进行分类。如果第一个分类器的结果与第二个分类器的结果不匹配，则对象是未分类的。

53. 发明授权

US08343053B2 Detection of structure in ultrasound M-mode imaging 有权
标题翻译：超声M模式成像检测结构
公开(公告)号：US08343053B2
公开(公告)日：2013-01-01
申请号：US12839547
申请日：2010-07-20
申请人： Shaolei Feng , Wei Zhang , Shaohua Kevin Zhou , Jin-hyeong Park
发明人： Shaolei Feng , Wei Zhang , Shaohua Kevin Zhou , Jin-hyeong Park
IPC分类号： A61B8/00 , G06K9/00 , G06E1/00
CPC分类号： A61B8/08 , A61B5/107 , A61B5/7267 , A61B8/0883 , A61B8/461 , A61B8/463 , A61B8/465 , A61B8/486 , G06T7/73 , G06T2207/10132 , G06T2207/30048
摘要： Automated detection of structure is provided in ultrasound M-mode imaging. A coarse and fine search for structure is used. For example, a less noise susceptible initial position or range of positions for a given structure is determined. This position is then refined. The coarse positioning and/or the refined position may use machine-trained classifiers. The positions of other structure may be used in either coarse or fine positioning, such as using a Markov Random Field. The structure or structures may be identified in the M-mode image without user input of a location in the M-mode image or along the line.
摘要翻译：在超声M模式成像中提供了结构的自动检测。使用粗略和精细的结构搜索。例如，确定给定结构的较小噪声敏感的初始位置或位置范围。然后改善这一立场。粗略定位和/或精细位置可以使用机器训练的分类器。其他结构的位置可以用于粗略或精细定位，例如使用马尔可夫随机场。可以在M模式图像中识别结构或结构，而无需用户输入M模式图像中的位置或沿着线。

54. 发明授权

US08321360B2 Method and system for weighting transactions in a fraud detection system 有权
标题翻译：用于在欺诈检测系统中加权交易的方法和系统
公开(公告)号：US08321360B2
公开(公告)日：2012-11-27
申请号：US12604208
申请日：2009-10-22
申请人： Eyal S. Lanxner , Shay Raz , Oren Gross
发明人： Eyal S. Lanxner , Shay Raz , Oren Gross
IPC分类号： G06F15/18 , G06E1/00 , G06E3/00 , G06G7/00
CPC分类号： G06Q40/00 , G06Q20/4016
摘要： A method of computing a similarity between a first transaction having a set of properties and a second transaction having the set of properties includes computing an initial weight for each of the properties of the set of properties and computing a similarity between each of the properties of the first transaction and the properties of the second transaction. The method also includes adjusting the initial weight for each of the properties based on a measure of the commonness of each of the properties of the set of properties, normalizing the adjusted weights, and computing the similarity by summing the products of the normalized adjusted weights and the computed similarities.
摘要翻译：计算具有一组属性的第一事务和具有该属性集合的第二事务之间的相似度的方法包括：计算该属性集合的每个属性的初始权重，并计算该属性集合的每个属性之间的相似度第一个交易和第二个交易的属性。该方法还包括基于属性集合的每个属性的共同性的度量来调整每个属性的初始权重，归一化调整的权重，以及通过将归一化的调整权重的乘积和计算出的相似之处。

55. 发明授权

US08315962B1 System and method for multiclass discrimination of neural response data 有权
标题翻译：用于神经反应数据的多类别辨别的系统和方法
公开(公告)号：US08315962B1
公开(公告)日：2012-11-20
申请号：US12625985
申请日：2009-11-25
申请人： James Herbert Horne
发明人： James Herbert Horne
IPC分类号： G06E1/00 , G06E3/00 , G06F15/18 , G06G7/00
CPC分类号： A61B5/04 , A61B5/0476 , A61B5/055 , A61B5/16 , A61B2576/026 , G01R33/4806 , G06F19/00 , G16H50/20
摘要： Systems and methods are described herein for analyzing neural response data that can be assigned to multiple classes. The systems and methods begin with a set of training data from which optimal weight factors are derived. The derived weight factors are used in a classifier which is then applied to test data from test subjects. The classifier filters out the effects of less relevant data in the test data and provides a result in the form of probabilities associated with classes for the test data.
摘要翻译：本文描述了用于分析可分配给多个类别的神经反应数据的系统和方法。系统和方法从一组训练数据开始，从中得出最佳权重因子。派生的权重因子用于分类器，然后将其应用于测试受试者的数据。分类器滤除测试数据中较少相关数据的影响，并以与测试数据类别相关的概率的形式提供结果。

56. 发明授权

US08290882B2 Evaluating decision trees on a GPU 有权
标题翻译：评估GPU上的决策树
公开(公告)号：US08290882B2
公开(公告)日：2012-10-16
申请号：US12248536
申请日：2008-10-09
申请人： Toby Sharp
发明人： Toby Sharp
IPC分类号： G06E1/00
CPC分类号： G06N99/005
摘要： Methods and apparatus for evaluating decision trees on a GPU are described. In an embodiment, the structure of a decision tree is converted into a 2D “tree” array with each row representing a node in the tree. Each row comprises details of any child nodes and the parameters which are required to perform the binary test at the node. A pixel shader can then be used to evaluate the decision tree in parallel for each input data point in an input array by navigating through rows in the 2D tree array. For each row, data is read from the input array dependent upon the parameters in the row and the shader moves to another row dependent upon the result of the binary test. On reaching a row which represents a leaf node, the pixel shader outputs evaluation results, such as a leaf node index or a probability distribution over classes.
摘要翻译：描述了用于评估GPU上的决策树的方法和装置。在一个实施例中，将决策树的结构转换为2D树数组，每行表示树中的节点。每行包括任何子节点的细节和在节点执行二进制测试所需的参数。然后可以使用像素着色器通过在2D树数组中的行进行导航来并行计算输入数组中每个输入数据点的决策树。对于每一行，取决于行中的参数，从输入数组读取数据，并且着色器根据二进制测试的结果移动到另一行。在到达表示叶节点的行时，像素着色器输出评估结果，例如叶节点索引或类上的概率分布。

57. 发明授权

US08223989B2 Signal processing system and method for calibrating channel signals supplied from an array of sensors having different operating characteristics 有权
标题翻译：用于校准从具有不同操作特性的传感器阵列提供的信道信号的信号处理系统和方法
公开(公告)号：US08223989B2
公开(公告)日：2012-07-17
申请号：US13276815
申请日：2011-10-19
申请人： Akihiko Sugiyama
发明人： Akihiko Sugiyama
IPC分类号： H04R3/00 , H04B1/38 , G01R1/02 , G06E1/00
CPC分类号： H04R1/406 , H04B17/21 , H04R3/005 , H04R2201/401 , H04R2201/403 , H04R2430/25
摘要： In a signal processing system, a set of channel signals from an array of sensors of different operating characteristics are processed in calibration circuitry that calculates individual average values of the channel signals and calculates an average of the individual average values of channel signals as a reference value. Reciprocal calculators calculate reciprocal values of the individual average values of the channel signals. Scaling circuitry scales the reciprocal values by the reference value to produce a set of amplitude calibration signals and scales the channel signals by the calibration signals respectively. As a result, the channel signals are normalized by their own average values and scaled by the reference value to produce a set of calibrated channel signals.
摘要翻译：在信号处理系统中，来自不同操作特性的传感器阵列的一组通道信号在校准电路中被处理，该校准电路计算通道信号的各个平均值，并且计算通道信号的各个平均值的平均值作为参考值。互惠计算器计算通道信号的各个平均值的互逆值。缩放电路将互逆值缩放参考值，以产生一组幅度校准信号，并分别用校准信号对信道信号进行缩放。结果，信道信号通过它们自己的平均值被归一化并且被参考值缩放以产生一组校准的信道信号。

58. 发明授权

US08214313B1 Turn rate calculation 有权
标题翻译：转速计算
公开(公告)号：US08214313B1
公开(公告)日：2012-07-03
申请号：US12554686
申请日：2009-09-04
申请人： Gintaras V. Puskorius , Bryan R. Goodman , Martin Lenardon , He Li , Barbara Nance
发明人： Gintaras V. Puskorius , Bryan R. Goodman , Martin Lenardon , He Li , Barbara Nance
IPC分类号： G06F15/18 , G06E1/00 , G06E3/00 , G06G7/00
CPC分类号： G06Q10/087
摘要： A data store includes item configuration data for a plurality of configurations of an item and inventory mix rate data. A computing device is configured to generate a matrix that combines the item configuration data with the inventory mix rate data such that cells in the matrix include an indication of an inventory mix rate related to an item feature; use the matrix to develop a plurality of neural network inventory turn rate models; and use the turn rate models to associate a value with each configuration in the plurality of configurations.
摘要翻译：数据存储包括项目的多个配置和库存混合速率数据的项目配置数据。计算设备被配置为生成将项目配置数据与库存混合速率数据组合的矩阵，使得矩阵中的单元包括与项目特征相关的库存混合速率的指示; 使用矩阵开发多个神经网络库存转换率模型; 并且使用转弯模型将值与多个配置中的每个配置相关联。

59. 发明授权

US08190542B2 Neural network, a device for processing information, a method of operating a neural network, a program element and a computer-readable medium 有权
标题翻译：神经网络，用于处理信息的设备，操作神经网络的方法，程序元件和计算机可读介质
公开(公告)号：US08190542B2
公开(公告)日：2012-05-29
申请号：US12089535
申请日：2006-09-27
申请人： Eugen Oetringer
发明人： Eugen Oetringer
IPC分类号： G06E1/00 , G06F15/18
CPC分类号： G06N3/063 , G06N3/04
摘要： A neural network includes neurons and wires adapted for connecting the neurons. Some of the wires comprise input connections and exactly one output connection and/or a part of the wires comprise exactly one input connection and output connections. Neurons are hierarchically arranged in groups. A lower group of neurons recognizes a pattern of information input to the neurons of this lower group. A higher group of neurons recognizes higher level patterns. A strength value is associated with a connection between different neurons. The strength value of a particular connection is indicative of a likelihood that information which is input to the neurons propagates via the particular connection. The strength value of each connection is modifiable based on an amount of traffic of information which is input to the neurons and which propagates via the particular connection and/or is modifiable based on a strength modification impulse.
摘要翻译：神经网络包括适于连接神经元的神经元和线。一些电线包括输入连接和正好一个输出连接和/或一部分导线包括恰好一个输入连接和输出连接。神经元分层次排列。下一组神经元识别输入到该下位组神经元的信息模式。较高的神经元组识别更高级别的模式。强度值与不同神经元之间的连接有关。特定连接的强度值表示输入到神经元的信息经由特定连接传播的可能性。每个连接的强度值可以基于输入到神经元并且经由特定连接传播并且/或可以基于强度修改脉冲进行修改的信息量的量来修改。

60. 发明授权

US08185955B2 Intrusion detection method and system, related network and computer program product therefor 有权
标题翻译：入侵检测方法及系统，相关网络及计算机程序产品
公开(公告)号：US08185955B2
公开(公告)日：2012-05-22
申请号：US11791609
申请日：2004-11-26
申请人： Gianluca Cangini , Francesco Coda Zabetta , Gerardo Lamastra
发明人： Gianluca Cangini , Francesco Coda Zabetta , Gerardo Lamastra
IPC分类号： G06F11/00 , G06F12/14 , G06F12/16 , G08B23/00 , G06E1/00 , G06E3/00 , G06F15/18 , G06F17/00 , G06G7/00 , G06N3/08 , G06N7/00 , G06N7/08
CPC分类号： H04L63/1408 , G06F21/552 , G06F21/554 , G06F2221/2135 , G06F2221/2151
摘要： Intrusions in a system under surveillance are detected by matching the events occurring during operation of the system against a knowledge base including information on events which occurred during a learning phase. The detection technique includes the steps of: recording, during the learning phase, temporal data related to the events during the learning phase; identifying, as a function of the temporal data recorded, a dynamic part of the knowledge base; discovering patterns that cover the dynamic part of the knowledge base; and using, during the analysis phase, a regular expression match at least with respect to the dynamic part of the knowledge base.
摘要翻译：通过将系统运行期间发生的事件与包括在学习阶段发生的事件的信息相关的知识库相匹配来检测被监视的系统中的入侵。检测技术包括以下步骤：在学习阶段记录与学习阶段期间的事件有关的时间数据; 根据记录的时间数据识别知识库的动态部分; 发现涵盖知识库动态部分的模式; 并且在分析阶段期间使用至少相对于知识库的动态部分的正则表达式匹配。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式