公开(公告)号：US06317732B1

公开(公告)日：2001-11-13

申请号：US08925186

申请日：1997-09-08

申请人： Haruki Inoue ,  Mayumi Mizutani ,  Masami Shiozawa ,  Satoru Yoshikawa

发明人： Haruki Inoue ,  Mayumi Mizutani ,  Masami Shiozawa ,  Satoru Yoshikawa

IPC分类号： G06N312

CPC分类号： G06Q10/06 ,  Y10S707/99933

摘要： A planning system includes an input device which accepts at least a given planning problem and values of variables required to solve the given planning problem; a display device which provides a visual display of an optimum plan obtained for the given planning problem; and a planner device which prepares an objective function representing items to be averaged and designs a plan to minimize a value of the objective function. The planner device includes an initial plan reader which reads an initial plan; an objective function value operation unit which calculates an objective function value of the initial plan; a reproduction unit which generates random numbers to a set composed by elements contacting to boundary planes of divided subsets, wherein the random numbers include a range of number of contacting elements and an equally-opportunity-selectable distribution, select at least one element based on the random numbers, equal-opportunity-selecting one of the subsets to which element contacts, and schedule the plan such that the selected element is rendered to belong to the selected subset; a plan renewal unit which compares the objective function value of the current plan with the objective function value of the previous plan to determine the plan having a smaller objective function value as an optimum plan; and a control unit which provides a visual display of an optimum plan on the display device.

摘要翻译： 规划系统包括至少接受给定规划问题的输入设备和解决给定规划问题所需的变量值; 显示装置，其提供针对给定规划问题获得的最佳计划的视觉显示; 以及计划器装置，其准备表示要平均的项目的目标函数，并设计使目标函数的值最小化的计划。 计划器装置包括初始计划读取器，其读取初始计划; 目标函数值运算单元，计算初始计划的目标函数值; 生成随机数的再现单元，其生成由与分割子集的边界面接触的元素组成的集合，其中，所述随机数包括接触元素的数量范围和同等机会选择分布，基于 随机数，等于机会选择元素联系的子集之一，并且调度该计划，使得所选择的元素被归属于所选择的子集; 计划更新单元，其将当前计划的目标函数值与先前计划的目标函数值进行比较，以将具有较小目标函数值的计划确定为最优计划; 以及控制单元，其在所述显示装置上提供最佳计划的视觉显示。

公开(公告)号：US06714874B1

公开(公告)日：2004-03-30

申请号：US09526131

申请日：2000-03-15

申请人： Gene W. Myers ,  Arthur L. Delcher ,  Ian M. Dew ,  Michael J. Flanigan ,  Saul A. Kravitz ,  Clark M. Mobarry ,  Knut Reinert ,  Karin A. Remington ,  Granger G. Sutton

发明人： Gene W. Myers ,  Arthur L. Delcher ,  Ian M. Dew ,  Michael J. Flanigan ,  Saul A. Kravitz ,  Clark M. Mobarry ,  Knut Reinert ,  Karin A. Remington ,  Granger G. Sutton

IPC分类号： G06N312

CPC分类号： G06F19/22 ,  G06F19/24 ,  Y10S707/99943

摘要： The present invention provides methods and systems for assembling a genome from a shot-gun set of end sequenced DNA fragments. Specifically, the present invention provides a method of determining the genomic sequence (base sequence and orientation) of a complex genome using DNA sequence information generated from a collection of DNA fragments obtained from the genome. The present method is particularly useful in assembling genomes of at least 10 MB (up to 5 GB) and which are made up of at least 5% repetitive DNA sequences (up to 25% repetitive), but can be used also for smaller genomes with a lower percentage of repetitive DNA.

摘要翻译： 本发明提供了用于组合来自枪枪组的终止测序的DNA片段的基因组的方法和系统。 具体地，本发明提供了使用从基因组获得的DNA片段的集合产生的DNA序列信息来确定复合基因组的基因组序列（碱基序列和取向）的方法。 本方法在组装至少10MB（至多5GB）的基因组中是特别有用的，它们由至少5％重复的DNA序列组成（高达25％重复），但也可用于较小的基因组， 重复DNA的百分比较低。

公开(公告)号：US06480832B2

公开(公告)日：2002-11-12

申请号：US09231498

申请日：1999-01-14

申请人： Ramin C. Nakisa

发明人： Ramin C. Nakisa

IPC分类号： G06N312

CPC分类号： G06Q30/02

摘要： The present invention relates to modeling the variables of a data set by means of a robabilistic network including data nodes and causal links. The term ‘probabilistic networks’ includes Bayesian networks, belief networks, causal networks and knowledge maps. The variables of an input data set are registered and a population of genomes is generated each of which individually models the input data set. Each genome has a chromosome to represent the data nodes in a probabilistic network and a chromosome to represent the causal links between the data nodes. A crossover operation is performed between the chromosome data of parent genomes in the population to generate offspring genomes. The offspring genomes are then added to the genome population. A scoring operation is performed on genomes in the said population to derive scores representing the correspondence between the genomes and the input data. Genomes are selected from the population according to their scores and the crossover, scoring, addition and selecting operations for a plurality of generations of the genomes. Finally a genome is selected from the last generation according to the best score. A mutation operation may be performed on the genomes. The mutation may consist of the addition or deletion of a data node and the addition or deletion of a causal link.

摘要翻译： 本发明涉及通过包括数据节点和因果链接的可靠性网络对数据集的变量进行建模。 术语“概率网络”包括贝叶斯网络，信念网络，因果网络和知识图，输入数据集的变量被注册，并且生成基因组群，每个基因组都单独地模拟输入数据集，每个基因组都有染色体 代表概率网络中的数据节点和染色体，以表示数据节点之间的因果关系，在群体中的亲代基因组的染色体数据之间进行交叉操作以产生后代基因组，然后将后代基因组添加到 基因组群体，对所述群体中的基因组进行评分操作，以得出表示基因组与输入数据之间的对应关系的分数。根据他们的分数，从群体中选择基因组，以及对于基因组的交叉，评分，添加和选择操作 多代的基因组，最后一个基因组选自上一代协议 达到最佳分数。 可以对基因组进行突变操作。 该突变可能包括数据节点的添加或删除以及因果链接的添加或删除。

公开(公告)号：US06499022B1

公开(公告)日：2002-12-24

申请号：US09413299

申请日：1999-10-06

申请人： Mark Dittmar ,  James Alexander

发明人： Mark Dittmar ,  James Alexander

IPC分类号： G06N312

CPC分类号： G06F3/0607 ,  G06F3/0634 ,  G06F3/0674 ,  G06N3/126 ,  G11B5/012 ,  G11B20/10009 ,  G11B20/10055 ,  G11B20/10481 ,  G11B27/36 ,  G11B2005/001 ,  G11B2220/20

摘要： A genetic process is used to tune servo parameter values in a disk drive. An initial population of individuals is generated each including a value for each of a plurality of servo parameters. Fitness values are then calculated for each of the individuals in the initial population. Individuals from the initial population are then chosen for mating based on the calculated fitness values. The chosen individuals are manipulated using genetic operators to produce a new population of individuals. Fitness values are then calculated for the new population and the cycle is repeated. The process is continued until a predetermined criterion has been met. After the process has ended, an individual is chosen based on fitness values and the servo parameters of the disk drive are set accordingly.

摘要翻译： 遗传过程用于调整磁盘驱动器中的伺服参数值。 产生个体的初始种群，其包括多个伺服参数中的每一个的值。 然后针对初始人口中的每个个人计算健身价值。 然后根据计算的适合度值选择初始种群的个体进行交配。 所选择的个人使用遗传算子进行操纵以产生新的个体群体。 然后计算新人群的健身值，并重复循环。 该过程一直持续到达到预定标准。 过程结束后，根据适合度值选择个体，相应地设置磁盘驱动器的伺服参数。

公开(公告)号：US06490570B1

公开(公告)日：2002-12-03

申请号：US09141453

申请日：1998-08-27

申请人： Chisato Numaoka

发明人： Chisato Numaoka

IPC分类号： G06N312

CPC分类号： G06N5/043 ,  G06N3/004

摘要： An architecture, which may be embodied in hardware, software or a combination of the two, is adapted to develop reflexes conditioned based on influences external to the architecture (such as user activity) in order to optimize the fulfillment of operational requirements of application modules in the architecture. The architecture includes, in addition to one or more application modules, modulation modules involved in the regulation of the functions performed by the application modules, a central regulator for registering the existence of an unsatisfied operational requirement in an application module and for controlling the modulation modules to seek a solution by a strategy including the external indication of a “need” condition via output modules. This manifestation is detected by the architecture itself via input modules, which also detect external phenomena indicating the activity of a user or external agent. An external event or input leads to satisfaction of the operational requirement. A conditioning system receiving inputs from the application modules, modulation modules, central regulator and input and output modules generates, on the basis of conditioning received through past experience, a signal indicating the expectation of satisfaction of the operational requirement. The operation of the architecture responds to the value of this expectation signal.

摘要翻译： 可以以硬件，软件或两者的组合体现的架构适于开发基于架构外部影响（例如用户活动）进行调节的反射，以便优化对应用模块的操作需求的满足 架构。 除了一个或多个应用模块之外，该架构还包括参与由应用模块执行的功能的调节的调制模块，用于在应用模块中登记不满足的操作需求的存在并用于控制调制模块的中央调节器 通过包括通过输出模块的“需要”条件的外部指示的策略寻求解决方案。 这种体现是由体系结构本身通过输入模块检测到的，该模块还检测指示用户或外部代理的活动的外部现象。 外部事件或输入可以满足操作要求。 接收来自应用模块，调制模块，中央调节器和输入和输出模块的输入的调节系统基于通过过去经验接收到的调节产生一个表示期望满足操作要求的信号。 架构的操作响应该期望信号的值。

公开(公告)号：US06226603B1

公开(公告)日：2001-05-01

申请号：US09089097

申请日：1998-06-02

申请人： Ernesto Freire ,  Irene Luque

发明人： Ernesto Freire ,  Irene Luque

IPC分类号： G06N312

CPC分类号： G06F19/16 ,  C07K1/00 ,  C07K2299/00 ,  G06F19/18

摘要： A computer-based method for the identification of binding targets in proteins and other macromolecules. More particularly, the invention includes an algorithm aimed at predicting binding targets in proteins. This algorithm, named Woolford, requires knowledge of the high resolution structure of the protein but no knowledge of the location or identity of natural binding sites or ligands. Binding targets in the protein are identified and classified according to their expected optimal affinities. Binding targets can be located at the protein surface or at internal surfaces that become exposed as a result of partial unfolding, conformational changes, subunit dissociation, or other events. The entire protein is mapped according to the binding potential of its constituent atoms. Once binding targets are identified, optimal ligands are designed and progressively built by the addition of individual atoms that complement structurally and energetically the selected target.

摘要翻译： 一种基于计算机的方法，用于鉴定蛋白质和其他大分子中的结合目标。 更具体地，本发明包括旨在预测蛋白质中的结合靶的算法。 该名称为Woolford的算法需要知道蛋白质的高分辨率结构，但不知道天然结合位点或配体的位置或身份。 根据其预期的最佳亲和力来鉴定和分类蛋白质中的结合目标。 结合靶可以位于蛋白质表面或由于部分展开，构象变化，亚基解离或其他事件而变得暴露的内表面。 根据其组成原子的结合电位对整个蛋白进行定位。 一旦确定了结合目标，则通过添加在结构上和能量上补充所选靶的各个原子来设计和逐步构建最佳配体。

公开(公告)号：US06816846B1

公开(公告)日：2004-11-09

申请号：US09439808

申请日：1999-11-12

申请人： Maribeth J. Back ,  Maureen C. Stone

发明人： Maribeth J. Back ,  Maureen C. Stone

IPC分类号： G06N312

CPC分类号： G06N3/126

摘要： Small, high-quality soundfiles are algorithmically recombined and their behavior altered to create rich, non-looping sound environments. These environments consist of sound effects as well as musical tones; for example, the sound of a single water drop or a single ocean wave can be replicated and regenerated according to algorithmic rules to create a long-running non-looping sound effect. Sonic parameters such as pitch, start time, intensity, and apparent spatial location are given initial values which are then changed in realtime via genetic algorithms to generate new values. When applied in Web-based 3D environments (e.g., VRML, Java3D, etc.), the present invention dramatically reduces the necessity for downloading large soundfiles. The present invention may also be used in real-world systems to produce long-running, interactive, non-looping sound environments. Applications of the present invention include awareness systems, entertainment systems, real/virtual interplay, and long-term auditory monitoring and display.

摘要翻译： 小型，高质量的声音文件在算法上重新组合，并且改变其行为以创建丰富的非循环声音环境。 这些环境包括声音效果和音乐音调; 例如，可以根据算法规则复制和再生单个水滴或单个海浪的声音，以创建长时间运行的非循环声音效果。 给出了音调，起始时间，强度和表观空间位置等声学参数的初始值，然后通过遗传算法实时改变生成新的值。 当应用于基于Web的3D环境（例如，VRML，Java3D等）时，本发明显着地减少了下载大型声音文件的必要性。 本发明还可以用于实际系统中以产生长时间运行的，交互式的，非循环的声音环境。 本发明的应用包括提醒系统，娱乐系统，实际/虚拟相互作用以及长期听觉监视和显示。

公开(公告)号：US06807491B2

公开(公告)日：2004-10-19

申请号：US09943579

申请日：2001-08-30

申请人： Vladimir Pavlovic ,  Simon Kasif ,  Ashutosh Garg

发明人： Vladimir Pavlovic ,  Simon Kasif ,  Ashutosh Garg

IPC分类号： G06N312

CPC分类号： G06F19/18 ,  C12Q2600/158

摘要： Computer based apparatus and method automates gene prediction in a subject genomic sequence. A plurality of expert systems provide preliminary or intermediate gene predictions. A Bayesian network combiner combines the intermediate gene predictions and forms a final gene prediction. The final gene prediction accounts for dependencies between individual expert systems and dependencies between adjacent parts of the subject genomic sequence.

摘要翻译： 基于计算机的设备和方法使得基因组序列中的基因预测自动化。 多个专家系统提供初步或中间基因预测。 贝叶斯网络组合器结合了中间基因预测并形成最终的基因预测。 最终的基因预测考虑了个体专家系统之间的依赖关系以及受试者基因组序列的相邻部分之间的依赖关系。

公开(公告)号：US06564194B1

公开(公告)日：2003-05-13

申请号：US09393863

申请日：1999-09-10

申请人： John R. Koza ,  Martin A. Keane ,  Jessen Yu ,  Forrest H Bennett, III ,  William Mydlowec

发明人： John R. Koza ,  Martin A. Keane ,  Jessen Yu ,  Forrest H Bennett, III ,  William Mydlowec

IPC分类号： G06N312

CPC分类号： G05B11/42 ,  G05B13/027 ,  G05B13/042

摘要： A general automated method for synthesizing the design of both the topology and parameter values for controllers is described. The automated method automatically makes decisions concerning the total number of signal processing blocks to be employed in the controller, the type of each signal processing block, the topological interconnections between the signal processing blocks, the values of all parameters for the signal processing blocks, and the existence, if any, of internal feedback between the signal processing blocks within the controller. The general automated method can simultaneously optimize prespecified performance metrics (such as minimizing the time required to bring the plant outputs to the desired values as measured by the integral of the time-weighted absolute error or the integral of the squared error), satisfy time-domain constraints (such as overshoot, disturbance rejection, limits on control variables, and limits on state variables), and satisfy frequency domain constraints (bandwidth).

摘要翻译： 描述了用于合成控制器的拓扑和参数值的设计的一般自动化方法。 自动化方法自动地做出关于控制器中使用的信号处理块的总数的决定，每个信号处理块的类型，信号处理块之间的拓扑互连，信号处理块的所有参数的值以及 在控制器内的信号处理块之间存在内部反馈（如果有的话）。 一般的自动化方法可以同时优化预先指定的性能指标（例如，最小化将工厂输出转换为按时间加权绝对误差的积分或平方误差的积分所测量的所需值所需的时间） 域约束（如过冲，干扰抑制，控制变量限制和状态变量限制），并满足频域约束（带宽）。

公开(公告)号：US06446055B1

公开(公告)日：2002-09-03

申请号：US09284079

申请日：1999-04-07

申请人： Stephen L. Grand

发明人： Stephen L. Grand

IPC分类号： G06N312

CPC分类号： G06N3/006 ,  A63F2300/408 ,  A63F2300/6027 ,  A63F2300/8058 ,  G06F9/465

摘要： A process control system is described using a plurality of autonomous process cells. Each process cell has data inputs, data outputs, processing logic, state variable, and link data specifying the other cells that provides its inputs. A scheduler triggers the plurality of cells as a whole to update their state. Cell may be recursive and contain child cells, at least some of which are linked to the parent cell. The cells can be subject to mutation and a non-brittle program language is provided for the logic within the cells in order to stop mutation causing a cell to cease to function. Cells within a neural network are provided with both fast and slow feedback mechanisms to improve their responsiveness to action reinforcement cycles. A mediated peer-to-peer network is described for use to simulate a tessellated virtual environment.

摘要翻译： 使用多个自主过程单元描述过程控制系统。 每个进程单元都具有数据输入，数据输出，处理逻辑，状态变量和指定提供其输入的其他单元的链接数据。 调度器触发多个小区作为整体更新其状态。 单元可以是递归的并且包含子单元，其中至少一些与父单元相连。 细胞可以经历突变，并为细胞内的逻辑​​提供非脆性程序语言，以便停止导致细胞停止运作的突变。 提供神经网络中的细胞具有快速和慢速反馈机制，以提高其对动作强化循环的响应性。 介绍的对等网络被描述为用于模拟镶嵌虚拟环境。