公开(公告)号：US08788440B2

公开(公告)日：2014-07-22

申请号：US13373129

申请日：2011-11-04

Applicant: Mark Williams ,  Alan Williams

Inventor： Mark Williams ,  Alan Williams

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

CPC classification number: G06N3/12 ,  G06N3/126

Abstract: A method is disclosed that generates design profiles and a surface therefrom that promote water drainage from soil in an area of interest. Topographical data describing an initial surface of the area of interest are used to form initial profiles. The method generates the design profiles using the initial profiles and desired design parameters such as minimum slope, maximum slope, optimal slope, maximum depth, optimal depth, starting elevation, ending elevation, rules of curvature, and rules of earth balancing. The method generates design surface profiles so that the cut volumes and fill volumes of the soil are at or near balance as much as possible from the available soil in the area of interest.

Abstract translation: 公开了一种从感兴趣区域的土壤产生排水的设计简档和表面的方法。 描述描述感兴趣区域的初始表面的地形数据用于形成初始轮廓。 该方法使用初始轮廓和期望的设计参数（如最小坡度，最大坡度，最优坡度，最大深度，最佳深度，起始仰角，结束高程，曲率规则和土方平衡规则）生成设计轮廓。 该方法产生设计表面轮廓，使得土壤的切割体积和填充体积尽可能距离感兴趣区域中的可用土壤处于或接近平衡。

公开(公告)号：US08756179B2

公开(公告)日：2014-06-17

申请号：US13866379

申请日：2013-04-19

Applicant: International Business Machines Corporation

Inventor： Jason F. Cantin

IPC: G06N3/00 ,  G06N3/12

CPC classification number: G06N99/005 ,  G06N3/126

Abstract: An example system and process with some operations that include determining a plurality of values, wherein assignment of any of the plurality of values to one or more constrained variables of a candidate solution causes the candidate solution to comply with a constraint condition of an optimization problem, wherein the candidate solution complies with the constraint condition prior to being mutated via a computer-based simulation that tests fitness of the candidate solution. The operations further include after the candidate solution is mutated, determining that the candidate solution fails to comply with the constraint condition. The operations further include assigning at least one value, which is randomly selected from the plurality of values, to the one or more constrained variables of the candidate solution.

Abstract translation: 具有一些操作的示例系统和过程包括确定多个值，其中将多个值中的任何值分配给候选解决方案的一个或多个约束变量导致候选解符合优化问题的约束条件， 其中候选解决方案在通过测试候选解决方案的适应性的基于计算机的模拟被突变之前符合约束条件。 操作进一步包括在候选解决方案被突变之后，确定候选解决方案不符合约束条件。 操作还包括将从多个值中随机选择的至少一个值分配给候选解的一个或多个约束变量。

公开(公告)号：US20140143134A1

公开(公告)日：2014-05-22

申请号：US14162079

申请日：2014-01-23

Applicant: CoreLogic Solutions, LLC

Inventor： Rui Yan ,  Hoi-Ming Chi ,  Seongjoon Koo ,  James Baker

IPC: G06Q40/02

CPC classification number: G06Q40/025 ,  G06N3/084 ,  G06N3/088 ,  G06N3/126 ,  G06N5/003 ,  G06N5/048 ,  G06N20/10 ,  G06N20/20 ,  G06Q10/067 ,  G06Q30/0185 ,  G06Q40/02

Abstract: Embodiments include systems and methods of detecting and assessing multiple types of risks related to mortgage lending. One embodiment includes a system and method of detecting and assessing risks including fraud risks, early payment default risks, and risks related to fraudulently stated income on loan applications. One embodiment includes a computerized method that includes creating a combined risk detection model based on a plurality of risk detection models and using the combined risk detection model to evaluate loan application data and generate a combined risk score that takes into account interaction of different types of risks individually and collectively detected by the plurality of risk detection models.

Abstract translation: 实施例包括检测和评估与抵押贷款相关的多种风险的系统和方法。 一个实施例包括检测和评估风险的系统和方法，包括欺诈风险，早期支付违约风险以及与贷款申请中的欺诈性收入相关的风险。 一个实施例包括计算机化方法，其包括基于多个风险检测模型创建组合风险检测模型，并使用组合风险检测模型来评估贷款应用数据并生成考虑到不同类型风险的相互作用的组合风险评分 由多个风险检测模型单独和共同地检测。

公开(公告)号：US08700548B2

公开(公告)日：2014-04-15

申请号：US13265480

申请日：2010-10-15

Applicant: Dinabandhu Bhandari ,  C. A. Murthy ,  Sankar Kumar Pal

Inventor： Dinabandhu Bhandari ,  C. A. Murthy ,  Sankar Kumar Pal

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

CPC classification number: G06N3/126

Abstract: Provided embodiments include a method, a system, a device, and an article of manufacture. A system for terminating a genetic algorithm (GA), where the GA uses an iterator and generates one best solution per iteration, includes a memory, an iterative processor, and a terminating processor. The memory is provided for storing a plurality of best solutions generated in a plurality of iterations of the GA. One of the best solutions generated in one of the iterations is stored in the memory if the one of the best solutions is better than a previous one of the best solutions generated in a previous one of the iterations. The iterative processor computes a variance of the plurality of the best solutions stored in the memory. The terminating processor terminates the iterator when the variance is less than or equal to a predetermined threshold.

Abstract translation: 所提供的实施例包括方法，系统，设备和制品。 用于终止遗传算法（GA）的系统，其中GA使用迭代器并且每次迭代生成一个最佳解决方案，包括存储器，迭代处理器和终止处理器。 存储器被提供用于存储在GA的多次迭代中生成的多个最佳解。 在其中一个迭代中生成的最佳解决方案之一是存储在内存中，如果最好的解决方案之一比先前的一个迭代中生成的最佳解决方案更好。 迭代处理器计算存储在存储器中的多个最佳解的方差。 当方差小于或等于预定阈值时，终止处理器终止迭代器。

公开(公告)号：US20140032454A1

公开(公告)日：2014-01-30

申请号：US13561230

申请日：2012-07-30

Applicant: Fan Zhang ,  Jun Xiao ,  Ming Jin ,  Haitao Xia

Inventor： Fan Zhang ,  Jun Xiao ,  Ming Jin ,  Haitao Xia

IPC: G06N3/12

CPC classification number: G06N3/126 ,  G06N3/12

Abstract: The present inventions are related to systems and methods for data processing, and more particularly to systems and methods for manipulating soft data in a data processing system.

Abstract translation: 本发明涉及用于数据处理的系统和方法，更具体地涉及用于在数据处理系统中操纵软数据的系统和方法。

公开(公告)号：US20130304395A1

公开(公告)日：2013-11-14

申请号：US13997123

申请日：2011-12-22

Applicant: Ravendra Naidu ,  Liang Wang ,  Zuliang Chen ,  Megharaj Mallavarapu

Inventor： Ravendra Naidu ,  Liang Wang ,  Zuliang Chen ,  Megharaj Mallavarapu

IPC: G01N27/00

CPC classification number: G01N27/00 ,  G01N27/333 ,  G06N3/084 ,  G06N3/126

Abstract: The present invention relates to a method of assessing concentration of at least one analyte ion in a liquid, the method including contacting the liquid with a plurality of electrodes, each of which is configured to generate a signal in response to sensing a selected ion in the liquid; receiving the signal from each of the electrodes; processing the signal from each of the electrodes using a neural network algorithm residing on a processor that has been trained to calculate ion interference between the selected ion and other ions in the liquid sensed at one of the electrodes and/or electrode interference between ones of the electrodes sensing a same selected ion based on a result of a comparison of training data indicative of a known ionic concentration applied to the neural network algorithm and the known ionic concentration; compensating for said ion interference and/or said electrode interference; and assessing the concentration of the at least analyte ion in the liquid on the basis of a compensated output from the neural network algorithm.

Abstract translation: 本发明涉及一种评估液体中至少一种分析物离子的浓度的方法，该方法包括使液体与多个电极接触，每个电极被配置为响应于感测所选择的离子而产生信号 液体; 从每个电极接收信号; 使用驻留在处理器上的神经网络算法来处理来自每个电极的信号，所述神经网络算法已被训练以计算在所选择的离子与在其中一个电极中检测到的液体中检测到的液体中的所选离子和其它离子之间的离子干扰 基于指示应用于神经网络算法的已知离子浓度的训练数据与已知离子浓度的比较的结果，检测相同选定离子的电极; 补偿所述离子干扰和/或所述电极干扰; 并且基于来自神经网络算法的补偿输出来评估液体中至少分析物离子的浓度。

公开(公告)号：US08583572B1

公开(公告)日：2013-11-12

申请号：US13051835

申请日：2011-03-18

Applicant: Joseph J. Engler

Inventor： Joseph J. Engler

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

CPC classification number: G06N3/126

Abstract: A method of analyzing an environment is provided. The method comprises evaluating, using a fitness evaluation module, the fitness of the plurality of individuals in a population. Each of the plurality of individuals comprises a dominant genotype and a recessive genotype. The fitness is evaluated by applying a fitness function to the dominant genotype of each individual. The method further comprises recombining and mutating, using the fitness evaluation module, the dominant genotype of one or more selected individuals based on the fitness evaluation. The method further comprises storing, using a change detection module, previously encountered genotypes in the recessive genotypes of the individuals. The fitness evaluation module and change detection module comprise instructions stored on a non-transitory computer-readable medium that are executable by a processor.

Abstract translation: 提供了一种分析环境的方法。 该方法包括使用健身评估模块来评估群体中的多个个体的适应度。 多个个体中的每一个包括显性基因型和隐性基因型。 通过将适应度函数应用于每个个体的优势基因型来评估适应度。 该方法还包括基于适合度评估，使用健身评估模块重新组合和突变一个或多个选定个体的优势基因型。 该方法还包括使用变化检测模块存储先前在个体的隐性基因型中遇到的基因型。 健身评估模块和变化检测模块包括存储在可由处理器执行的非暂时计算机可读介质上的指令。

公开(公告)号：US20130263091A1

公开(公告)日：2013-10-03

申请号：US13443875

申请日：2012-04-10

Applicant: Atanu Neogi

Inventor： Atanu Neogi

IPC: G06F9/44

CPC classification number: G06F11/3612 ,  G06F8/35 ,  G06F9/44589 ,  G06F9/5061 ,  G06F11/3604 ,  G06F11/3608 ,  G06F11/3668 ,  G06F11/3688 ,  G06N3/126

Abstract: Methods and apparatus for automatically generating translation programs for translating computing services templates to service blueprints are disclosed. An example method includes generating a population of translation logic elements from a plurality of verified computing services template translation programs, where each of the verified programs is configured to correctly translate at least one computing services template of a plurality of known templates to a respective service blueprint. The example method further includes identifying a new computing services template and programmatically augmenting the population of translation logic elements. The example method also includes generating one or more additional translation programs based on the augmented population of translation logic elements and validating each of the one or more additional computing services template translation programs. Based on the validating, each of the one or more additional computing services template translation programs is added to the verified translation programs or is discarded.

Abstract translation: 公开了用于自动生成用于将计算服务模板翻译成服务蓝图的翻译程序的方法和装置。 示例性方法包括从多个经过验证的计算服务模板翻译程序生成翻译逻辑单元的总体，其中每个被验证的程序被配置为将多个已知模板的至少一个计算服务模板正确地翻译成相应的服务蓝图 。 示例性方法还包括识别新的计算服务模板并且以编程方式增加翻译逻辑元素的总体。 示例性方法还包括基于翻译逻辑元素的增加的群体生成一个或多个附加的翻译程序，并验证一个或多个附加的计算服务模板翻译程序中的每一个。 基于验证，将一个或多个附加计算服务模板翻译程序中的每一个添加到经过验证的翻译程序中或被丢弃。

公开(公告)号：US20130204901A1

公开(公告)日：2013-08-08

申请号：US13821207

申请日：2011-09-09

Applicant: Akshay Pottathil

Inventor： Akshay Pottathil

IPC: G06F17/30

CPC classification number: G06F16/28 ,  G06N3/126

Abstract: In alternative embodiments, the invention provides computer-implemented methods comprising: (a) representing a plurality of Data Node Archive (DNA) data elements, or a plurality of non-deoxyribonucleic acid (non-DNA) data elements, in a model having a format or organization in accordance with (or equivalent to, or analogous to) a biological deoxyribonucleic acid (DNA) model format or equivalent thereof; or, (b) a computer-implemented method comprising a subset of, substantially all, or all of the steps as set forth in the flow chart of FIG. 7.

Abstract translation: 在替代实施例中，本发明提供了计算机实现的方法，其包括：（a）在模型中表示多个数据节点归档（DNA）数据元素或多个非脱氧核糖核酸（非DNA）数据元素） 根据（或等同于或类似的）生物脱氧核糖核酸（DNA）模型格式或其等同物的形式或组织; 或者，（b）计算机实现的方法，其包括图3的流程图中所阐述的子集，基本上全部或全部步骤。 7。

公开(公告)号：US08504498B2

公开(公告)日：2013-08-06

申请号：US12867429

申请日：2009-02-12

Applicant: Richard Fox

Inventor： Richard Fox

IPC: G06F15/18

CPC classification number: C40B50/02 ,  G06F19/24 ,  G06N3/126

Abstract: The present disclosure relates to methods of rapidly and efficiently searching biologically-related data space to identify a population set maximally diverse and optimized for sets of desired properties. More specifically, the disclosure provides methods of identifying a diverse, evolutionary separated bio-molecules with desired properties from complex bio-molecule libraries. The disclosure additionally provides digital systems and software for performing these methods.

Abstract translation: 本公开涉及快速有效地搜索生物相关数据空间的方法，以识别针对所需属性的集合最大程度地多样化和优化的群体集合。 更具体地，本公开提供了鉴定来自复杂生物分子文库的具有所需性质的多种，进化分离的生物分子的方法。 本公开另外提供用于执行这些方法的数字系统和软件。