公开(公告)号：US20150127262A1

公开(公告)日：2015-05-07

申请号：US14404328

申请日：2012-06-21

Applicant: Dingding Chen ,  Mark A. Proett ,  Li Gao ,  Christopher Michael Jones

Inventor： Dingding Chen ,  Mark A. Proett ,  Li Gao ,  Christopher Michael Jones

IPC: G01V99/00 ,  G06N3/12 ,  G06N99/00

CPC classification number: G01V99/005 ,  E21B49/087 ,  G06N3/126 ,  G06N20/00

Abstract: Improved systematic inversion methodology applied to formation testing data interpretation with spherical, radial and/or cylindrical flow models is disclosed. A method of determining a parameter of a formation of interest at a desired location comprises directing a formation tester to the desired location in the formation of interest and obtaining data from the desired location in the formation of interest. The obtained data relates to a first parameter at the desired location of the formation of interest. The obtained data is regressed to determine a second parameter at the desired location of the formation of interest. Regressing the obtained data comprises using a method selected from a group consisting of a deterministic approach, a probabilistic approach, and an evolutionary approach.

Abstract translation: 公开了用于球形，径向和/或圆柱形流动模型的地层测试数据解释的改进的系统反演方法。 在期望的位置确定感兴趣的形成的参数的方法包括将地层测试仪引导到感兴趣的形成中的期望的位置，并从感兴趣的形成中的期望的位置获得数据。 获得的数据涉及在感兴趣形成的期望位置处的第一参数。 所获得的数据被回归以确定感兴趣形成的期望位置处的第二参数。 回归所获得的数据包括使用从由确定性方法，概率方法和进化方法组成的组中选择的方法。

公开(公告)号：US20150120778A1

公开(公告)日：2015-04-30

申请号：US14500092

申请日：2014-09-29

Applicant: International Business Machines Corporation

Inventor： Renaud Dumeur

IPC: G06F17/30 ,  G06N3/12

CPC classification number: G06N3/126

Abstract: Embodiments relate to approximate assignment in a constraint based evolutionary search. An aspect includes providing a genome representing a collection of variable assignment preferences encoded as genes. Another aspect includes reducing the domain until a unit sized domain is reached, the unit sized domain being an approximation to a value V. Another aspect includes searching for a first assignment of the value V that is less than or equal to the unit sized domain and a second assignment of the value V that is greater than the unit sized domain. Another aspect includes responsive to a first assignment and a second assignment being found, assigning the value V of one of the first assignment and the second assignment having the least distance from the unit sized domain to a variable X.

Abstract translation: 实施例涉及基于约束的进化搜索中的近似分配。 一方面包括提供代表编码为基因的可变分配偏好的集合的基因组。 另一方面包括减小域，直到达到单位大小的域，单位大小的域是近似值V.另一方面包括搜索小于或等于单位大小域的值V的第一分配，以及 值V大于单位大小的域的第二个赋值。 另一方面包括响应于第一分配和第二分配被发现，将第一分配中的一个的值V和从该单元大小的域具有最小距离的第二分配分配给变量X.

公开(公告)号：US08984103B2

公开(公告)日：2015-03-17

申请号：US13125540

申请日：2009-10-23

Applicant: Hideaki Suzuki ,  Hidefumi Sawai ,  Hiroyuki Ohsaki

Inventor： Hideaki Suzuki ,  Hidefumi Sawai ,  Hiroyuki Ohsaki

IPC: G06N3/08 ,  G06N3/12

CPC classification number: G06N3/126 ,  G06N3/08

Abstract: A calculation processing apparatus includes a monitor, a CPU, a memory and a hard disk. The hard disk stores an initial program input from outside, a network creation program, a network modifying program, network information, node operation definition, and learning variables. The CPU executes the network creation program, and creates network information related to a network representing an algorithm structure of the initial program. Further, the CPU executes the network modifying program and modifies the network information based on the result of calculation by the network, using a learning algorithm.

Abstract translation: 计算处理装置包括监视器，CPU，存储器和硬盘。 硬盘存储来自外部的初始程序输入，网络创建程序，网络修改程序，网络信息，节点操作定义和学习变量。 CPU执行网络创建程序，并创建与表示初始程序的算法结构的网络相关的网络信息。 此外，CPU执行网络修改程序，并且使用学习算法基于网络的计算结果修改网络信息。

公开(公告)号：US20150046379A1

公开(公告)日：2015-02-12

申请号：US13964227

申请日：2013-08-12

Applicant: Jason F. Cantin ,  Michael A. Cracraft

Inventor： Jason F. Cantin ,  Michael A. Cracraft

IPC: G06N99/00

CPC classification number: G06N5/02 ,  G06F17/30424 ,  G06N3/126

Abstract: Figures of merit by actual design parameters are tracked over iterations for candidate solutions that include both actual design parameters and actual context parameters. Instead of returning a current iteration figure of merit, a worst observed figure of merit for a set of actual design parameters is returned as the figure of merit for a candidate solution. Since the candidate solution includes both actual design parameters and actual context parameters and the worst observed figures of merit are tracked by actual design parameters, the figure of merit for a set of design parameters wilt be the worst of the observed worst case scenarios as defined by the actual context parameters over a run of a metaheuristic optimizer.

Abstract translation: 根据实际设计参数的实际设计参数和实际上下文参数的候选解决方案的迭代跟踪实际设计参数的数据。 不是返回当前的迭代品质因数，而是返回一组实际设计参数中最差的品质因数作为候选解决方案的品质因数。 由于候选解决方案包括实际设计参数和实际上下文参数，并且通过实际设计参数跟踪最差的观察到的品质因数，一组设计参数的品质因数将是最差的观察到的最坏情况情景，如 在元启发优化器的运行中的实际上下文参数。

公开(公告)号：US08924341B2

公开(公告)日：2014-12-30

申请号：US11378575

申请日：2006-03-17

Applicant: Edward E. Rothberg

Inventor： Edward E. Rothberg

IPC: G06F15/00 ,  G06F15/18 ,  G06N3/12 ,  G06N5/00

CPC classification number: G06N3/126 ,  G06N5/003

Abstract: Systems and methods for generating improved solutions to MIP models are described. The present invention involves the use of a polishing algorithm that uses mutation and combination of solutions within a solution pool to generate improved solutions. The polishing algorithm first randomly selects one or more seed solutions from a solution pool for mutation. The selected seed solutions are mutated by fixing a subset of integer variables in the models to the value they take in the seed solution. The remaining variables are then formulated into a sub-MIP problem that is solved by the MIP solver. The solutions generated from this mutation process may then be added to the solution pool. After the one or more iterations of the mutation processes have taken place, the polishing algorithm then selects one or more pluralities of parent solutions from the solution pool to use in generating offspring solutions. The integer variables that agree between one plurality of parent solutions are fixed in the offspring solution. The remaining variables are then formulated into a sub-MIP problem that is solved by the MIP solver. The offspring solutions generated by the combination process may then also be added to the solution pool.

Abstract translation: 描述了用于生成改进的MIP模型解决方案的系统和方法。 本发明涉及使用在溶液池内使用突变和溶液组合的抛光算法来产生改进的解决方案。 抛光算法首先从溶液池中随机选择一种或多种种子溶液进行突变。 通过将模型中的整数变量的子集固定为其在种子解决方案中获取的值，所选择的种子解决方案被突变。 然后将剩余的变量形成为由MIP求解器求解的子MIP问题。 然后可以将从该突变过程产生的溶液加入到溶液池中。 在突变进程的一次或多次迭代发生之后，抛光算法然后从解决方案池中选择一个或多个多个父解，以用于生成后代解。 在多个母体解决方案中一致的整数变量在后代解决方案中是固定的。 然后将剩余的变量形成为由MIP求解器求解的子MIP问题。 然后可以将由组合过程生成的后代解决方案添加到解决方案池中。

公开(公告)号：US08880052B2

公开(公告)日：2014-11-04

申请号：US13256736

申请日：2010-03-12

Applicant: Imran Ashraf ,  Lester Tse Wee Ho ,  Holger Claussen ,  Louis Gwyn Samuel

Inventor： Imran Ashraf ,  Lester Tse Wee Ho ,  Holger Claussen ,  Louis Gwyn Samuel

IPC: H04M3/00 ,  G06N3/12

CPC classification number: G06N3/126

Abstract: A method is provided of evolving algorithms for network node control in a telecommunications network by genetic programming to (a) generate algorithms (b) determining fitness level of the algorithms based on a model of the telecommunications network and (c) select the algorithm that meet a predetermined fitness level or number of generations of evolution. The model is updated and the steps (a), (b) and (c) are repeated automatically to provide a series of algorithms over time adapted to the changing model of the network for possible implementation in the network.

Abstract translation: 提供了一种用于通过遗传编程在电信网络中进行网络节点控制的演进算法的方法，以（a）生成算法（b）基于电信网络的模型确定算法的适应度级别;（c）选择满足的算法 预定的健身水平或进化代数。 该模型被更新，并且自动重复步骤（a），（b）和（c），以提供随时间变化的一系列算法，以适应网络的变化模型，以便可能在网络中实现。

公开(公告)号：US20140279765A1

公开(公告)日：2014-09-18

申请号：US13795165

申请日：2013-03-12

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Jason F. Cantin

IPC: G06N3/12

CPC classification number: G06N3/126

Abstract: While at least one candidate solution of a first generation of candidate solutions remains to be evaluated in accordance with a fitness function for an optimization problem, a plurality of candidate solutions is selected from the first generation of candidate solutions to participate in a tournament. It is determined whether each of the plurality of candidate solutions selected to participate in the tournament have been evaluated in accordance with the fitness function. If all have been evaluated, then one or more winners of the tournament are selected from the plurality of candidate solutions of the first generation of candidate solutions. A candidate solution of a second generation of candidate solutions is created with the selected one or more winners of the tournament in accordance with a genetic operator.

Abstract translation: 虽然第一代候选解决方案的至少一个候选解决方案仍然根据用于优化问题的适应度函数来评估，但是从第一代候选解决方案中选择多个候选解决方案以参与比赛。 确定选择参加比赛的多个候选解决方案中的每一个是否已经根据适应度函数进行了评估。 如果所有人都被评估，则从第一代候选解决方案的多个候选解中挑选一个或多个比赛胜利者。 根据遗传算子，使用所选择的一个或多个获胜者创建第二代候选解决方案的候选解决方案。

公开(公告)号：US20140243913A1

公开(公告)日：2014-08-28

申请号：US13774377

申请日：2013-02-22

Applicant: Sean Lineaweaver

Inventor： Sean Lineaweaver

IPC: A61N1/372 ,  A61N1/36

CPC classification number: A61N1/36032 ,  A61B5/12 ,  A61B5/123 ,  A61N1/0541 ,  A61N1/36036 ,  A61N1/37241 ,  A61N1/37247 ,  G06F19/00 ,  G06F19/3481 ,  G06N3/126 ,  G16H40/63 ,  H04R25/70 ,  H04R2225/41 ,  H04R2225/43

Abstract: Embodiments of the present invention are generally directed to the use of a genetic algorithm for the purpose of providing progressive and adaptive auditory training (rehabilitation) to a recipient of a hearing prosthesis. In general, the genetic algorithm is used to adapt the training process to automatically increase the difficulty of the training based on recipient feedback and performance. That is, the genetic algorithm progressively removes perceivable sounds from the training process so as to generate groups of sounds that are difficult for a recipient to perceive.

Abstract translation: 本发明的实施例通常涉及遗传算法的用途，以向听觉假体的接收者提供渐进式和适应性听觉训练（康复）。 一般来说，遗传算法用于适应训练过程，根据接收者的反馈和性能自动提高训练的难度。 也就是说，遗传算法逐渐地从训练过程中去除可感知的声音，以便生成难以接收者察觉的声音组。

公开(公告)号：US20140222738A1

公开(公告)日：2014-08-07

申请号：US14124407

申请日：2012-06-08

Applicant: Karen E. Joyce ,  Paul J. Laurienti ,  Satoru Hayasaka

Inventor： Karen E. Joyce ,  Paul J. Laurienti ,  Satoru Hayasaka

IPC: G06N3/10 ,  G06F19/00

CPC classification number: G06N3/10 ,  G06N3/126 ,  G16H50/50 ,  Y02A90/26

Abstract: An agent-based modeling system for predicting and/or analyzing brain behavior is provided. The system includes a computer processor configured to define nodes and edges that interconnect the nodes. The edges are defined by physiological interactions and/or anatomical connections. The computer processor further defines rules and/or model parameters that define a functional behavior of the nodes and edges. The computer processor assigns the nodes to respective brain regions, and the rules and/or model parameters are defined by observed physiological interaction of the nodes that are functionally and/or structurally connected by said edges of brain regions to thereby provide an agent-based brain model (ABBM) for predicting and/or analyzing brain behavior.

Abstract translation: 提供了一种用于预测和/或分析大脑行为的基于代理的建模系统。 该系统包括被配置为定义互连节点的节点和边缘的计算机处理器。 边缘由生理相互作用和/或解剖连接限定。 计算机处理器还定义了定义节点和边缘的功能行为的规则和/或模型参数。 计算机处理器将节点分配给相应的大脑区域，并且规则和/或模型参数通过由脑区域的所述边缘在功能和/或结构上连接的节点的观察到的生理相互作用来定义，从而提供基于代理的大脑 模型（ABBM）用于预测和/或分析大脑行为。

公开(公告)号：US08793202B2

公开(公告)日：2014-07-29

申请号：US13510301

申请日：2010-12-03

Applicant: Zhenyuan Wang ,  Wenping Li

Inventor： Zhenyuan Wang ,  Wenping Li

IPC: G06F15/18 ,  G06N3/00 ,  G06N3/12

CPC classification number: G06N3/126 ,  H02J3/006 ,  H02J13/0006 ,  H02J2003/007 ,  Y02E60/76 ,  Y04S10/525 ,  Y04S40/22

Abstract: A method for generating switching plans to restore power to out-of-service areas after fault isolation through back feeding. A chromosome architecture is defined to create chromosomes representing candidate post-restoration systems. The chromosomes are evaluated are repeatedly genetically altered until an acceptable solution is identified. The solution identifies a plurality of switching operations that back feed power to the out-of-service areas in the most optimal manner.

Abstract translation: 一种用于在通过反馈进行故障隔离之后产生切换计划以恢复到不在服务区域的电力的方法。 染色体结构被定义为创建代表候选修复后系统的染色体。 评估的染色体被重复遗传改变，直到识别出可接受的溶液。 该解决方案识别多个切换操作，其以最优的方式将失去服务区域的功率返回。