专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO03005934A3 COGNITIVE STATE MACHINE FOR PROSTHETIC SYSTEMS 审中-公开
标题翻译：用于假体系统的认知状态机
公开(公告)号：WO03005934A3
公开(公告)日：2003-04-10
申请号：PCT/US0222337
申请日：2002-07-10
申请人： CALIFORNIA INST OF TECHN , ANDERSEN RICHARD A , PESARAN BIJAN , MITRA PARTHA , MEEKER DANIELLA , SHENOY KRISHNA V , CAO SHIYAN , BURDICK JOEL W
发明人： ANDERSEN RICHARD A , PESARAN BIJAN , MITRA PARTHA , MEEKER DANIELLA , SHENOY KRISHNA V , CAO SHIYAN , BURDICK JOEL W
IPC分类号： A61F2/70 , A61F2/72 , G06F3/00 , G06F3/01 , A61F2/48
CPC分类号： G06F3/015 , A61F2/68 , A61F2/72 , A61F2002/704 , A61F2002/705
摘要： A prosthetic system (100) may use a decoder to predict an intended action, such as a reach, from processed signals generated from measured neural activity. The decoder may included a cognitive state machine, which transitions between cognitive states based on transition rules.
摘要翻译：假体系统（100）可以使用解码器来根据从测量的神经活动产生的经处理的信号来预测预期的动作，诸如到达范围。解码器可以包括认知状态机，其基于转换规则在认知状态之间转换。

2. 发明申请

WO2012129574A3 NEUROSTIMULATOR 审中-公开
标题翻译：神经刺激器
公开(公告)号：WO2012129574A3
公开(公告)日：2012-12-27
申请号：PCT/US2012030624
申请日：2012-03-26
申请人： CALIFORNIA INST OF TECHN , UNIV LOUISVILLE RES FOUND , BURDICK JOEL W , TAI YU-CHONG , NABER JOHN F , KEYNTON ROBERT S
发明人： BURDICK JOEL W , TAI YU-CHONG , NABER JOHN F , KEYNTON ROBERT S
IPC分类号： A61N1/36 , A61N1/05 , A61N1/08
CPC分类号： A61N1/36103 , A61B5/0492 , A61B5/1106 , A61B5/407 , A61B5/4076 , A61B5/4836 , A61B2505/09 , A61N1/0551 , A61N1/0553 , A61N1/36003 , A61N1/36007 , A61N1/36067 , A61N1/36082 , A61N1/36107 , A61N1/3611 , A61N1/36114 , A61N1/36125 , A61N1/36139
摘要： A neurostimulator device for use with groups (e.g., more than four groups) of electrodes. The neurostimulator may include a stimulation assembly configured to deliver different stimulation to each of the groups. The neurostimulator may also include at least one processor configured to direct the stimulation assembly to deliver stimulation to the groups. The stimulation delivered to at least one of the groups may include one or more waveform shapes other than a square or rectangular wave shape. The processor may receive data from one or more sensors and use that data to modify the stimulation delivered. The neurostimulator may be configured to communicate with an external computing device. The neurostimulator may send data to and/or receive data and/or instructions from the computing device. The computing device may use information collected by one or more sensors to at least partially determine stimulation parameters to communicate to the neurostimulator.
摘要翻译：一种用于与组（例如多于四组）电极组合的神经刺激器装置。神经刺激器可以包括被配置为向每个组递送不同刺激的刺激组件。神经刺激器还可以包括至少一个处理器，该处理器被配置为引导刺激组件将刺激传递给组。输送到至少一个组的刺激可以包括除了正方形或矩形波形之外的一个或多个波形。处理器可以从一个或多个传感器接收数据，并使用该数据来修改递送的刺激。神经刺激器可以被配置为与外部计算设备进行通信。神经刺激器可以向计算设备发送数据和/或从计算设备接收数据和/或指令。计算设备可以使用由一个或多个传感器收集的信息来至少部分地确定刺激参数以与神经刺激器通信。

3. 发明申请

WO2013188886A2 METHOD AND SYSTEM FOR PARALLEL BATCH PROCESSING OF DATA SETS USING GAUSSIAN PROCESS WITH BATCH UPPER CONFIDENCE BOUND 审中-公开
标题翻译：使用高斯过程的数据集并行处理的方法和系统
公开(公告)号：WO2013188886A2
公开(公告)日：2013-12-19
申请号：PCT/US2013046196
申请日：2013-06-17
申请人： CALIFORNIA INST OF TECHN
发明人： KRAUSE ANDREAS , DESAUTELS THOMAS , BURDICK JOEL W
CPC分类号： G06N5/025 , G06N5/04
摘要： A method and system for selecting a batch of input data from available input data for parallel evaluation by a function is disclosed. The function is modeled as drawn from a Gaussian process. Observations are used to determine a mean and a variance of the modeled function. An upper confidence bound is determined from the determined mean and variance. A decision rule is applied to select input data from the available input data to add to the batch of input data. The selection of the input data is based on a domain-specific time varying parameter. Intermediate observations are hallucinated within the batch. The hallucinated observations are used with the decision rule to select subsequent input data from the available input data for the batch of input data. The input data of the batch is evaluated in parallel with the function. The resulting determined data outputs are stored.
摘要翻译：公开了一种用于从可用输入数据中选择一批输入数据以便通过功能进行并行评估的方法和系统。该函数被建模为从高斯过程绘制的。观察用于确定建模函数的平均值和方差。从确定的平均值和方差确定上限置信区间。应用决策规则从可用输入数据中选择输入数据以添加到批量的输入数据。输入数据的选择是基于域特定的时变参数。中间观察在批次中幻觉。幻灯片观察结果与决策规则一起使用，从批输入数据的可用输入数据中选择后续输入数据。批次的输入数据与功能并行进行评估。得到的确定的数据输出被存储。

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