利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

39 条记录 (耗时 0.057 秒)

    SYSTEM AND METHOD FOR ADVANCED CONDITION MONITORING OF AN ASSET SYSTEM
    5.
    发明申请
    SYSTEM AND METHOD FOR ADVANCED CONDITION MONITORING OF AN ASSET SYSTEM 有权
    资产系统高级状态监测系统与方法

    公开(公告)号：US20090295561A1

    公开(公告)日：2009-12-03

    申请号：US12129611

    申请日：2008-05-29

    申请人： Xiao Hu ,  John Erik Hershey ,  Robert James Mitchell, JR. ,  Rajesh Venkat Subbu ,  Avinash Vinayak Taware ,  Piero Patrone Bonissone

    发明人： Xiao Hu ,  John Erik Hershey ,  Robert James Mitchell, JR. ,  Rajesh Venkat Subbu ,  Avinash Vinayak Taware ,  Piero Patrone Bonissone

    IPC分类号： G08B23/00

    CPC分类号： G05B19/41875 ,  G05B2219/31455 ,  G05B2219/32201 ,  G05B2219/33027 ,  Y02P90/18 ,  Y02P90/22

    摘要： A method for advanced condition monitoring of an asset system includes sensing actual values of an operating condition for an operating regime of the asset system using at least one sensor; estimating sensed values of the operating condition by using an auto-associative neural network; determining a residual vector between the estimated sensed values and the actual values; and performing a fault diagnostic on the residual vector. In another method, an operating space of the asset system is segmented into operating regimes; the auto-associative neural network determines estimates of actual measured values; a residual vector is determined from the auto-associative neural network; a fault diagnostic is performed on the residual vector; and a change of the operation of the asset system is determined by analysis of the residual vector. An alert is provided if necessary. A smart sensor system includes an on-board processing unit for performing the method of the invention.

    摘要翻译： 一种用于资产系统的高级状态监测的方法包括使用至少一个传感器来感测资产系统的操作状态的操作条件的实际值; 通过使用自动关联神经网络来估计操作条件的感测值; 确定估计的感测值和实际值之间的残差矢量; 并对残差向量进行故障诊断。 在另一种方法中，资产系统的运营空间被划分为运行状态; 自相关神经网络确定实际测量值的估计值; 从自相关神经网络确定残差向量; 对残差矢量执行故障诊断; 通过分析残差向量来确定资产系统的运作变化。 必要时提供警报。 智能传感器系统包括用于执行本发明的方法的车载处理单元。

    System and process for a fusion classification for insurance underwriting suitable for use by an automated system
    6.
    发明授权
    System and process for a fusion classification for insurance underwriting suitable for use by an automated system 有权
    用于融合分类的系统和过程，适用于自动化系统使用的保险承保

    公开(公告)号：US07383239B2

    公开(公告)日：2008-06-03

    申请号：US10425721

    申请日：2003-04-30

    申请人： Piero Patrone Bonissone ,  Kareem Sherif Aggour ,  Rajesh Venkat Subbu ,  Weizhong Yan ,  Naresh Sundaram Iyer ,  Anindya Chakraborty

    发明人： Piero Patrone Bonissone ,  Kareem Sherif Aggour ,  Rajesh Venkat Subbu ,  Weizhong Yan ,  Naresh Sundaram Iyer ,  Anindya Chakraborty

    IPC分类号： G06F17/00 ,  G06N5/02

    CPC分类号： G06Q40/08 ,  G06Q40/00

    摘要： A method and system for fusing a collection of classifiers used for an automated insurance underwriting system and/or its quality assurance is described. Specifically, the outputs of a collection of classifiers are fused. The fusion of the data will typically result in some amount of consensus and some amount of conflict among the classifiers. The consensus will be measured and used to estimate a degree of confidence in the fused decisions. Based on the decision and degree of confidence of the fusion and the decision and degree of confidence of the production decision engine, a comparison module may then be used to identify cases for audit, cases for augmenting the training/test sets for re-tuning production decision engine, cases for review, or may simply trigger a record of its occurrence for tracking purposes. The fusion can compensate for the potential correlation among the classifiers. The reliability of each classifier can be represented by a static or dynamic discounting factor, which will reflect the expected accuracy of the classifier. A static discounting factor is used to represent a prior expectation about the classifier's reliability, e.g., it might be based on the average past accuracy of the model, while a dynamic discounting is used to represent a conditional assessment of the classifier's reliability, e.g., whenever a classifier bases its output on an insufficient number of points it is not reliable.

    摘要翻译： 描述用于融合用于自动保险承保系统的分类器集合和/或其质量保证的方法和系统。 具体来说，分类器的集合的输出被融合。 数据的融合通常会导致一些共识和分类器之间的一些冲突。 共识将被测量并用于估计融合决策的信心程度。 根据融合的决定和信心程度以及生产​​决策引擎的决策和决策程度，然后可以使用比较模块来识别审计案例，增加用于重新调整生产的培训/测试集的案例 决策引擎，审查案例，或者可以简单地触发其发生记录以进行跟踪。 融合可以补偿分类器之间的潜在相关性。 每个分类器的可靠性可以由静态或动态折扣因子表示，这将反映分类器的预期准确性。 静态折扣因子用于表示对分类器的可靠性的先前期望，例如，可以基于模型的平均过去精度，而使用动态贴现来表示分类器的可靠性的条件评估，例如，每当 分类器的输出基于不可靠的点数不足。

    METHODS AND SYSTEMS FOR MANAGING AIR TRAFFIC
    7.
    发明申请
    METHODS AND SYSTEMS FOR MANAGING AIR TRAFFIC 审中-公开
    管理空中交通的方法和系统

    公开(公告)号：US20120215434A1

    公开(公告)日：2012-08-23

    申请号：US13032151

    申请日：2011-02-22

    申请人： Rajesh Venkat Subbu ,  Jon David Petersen ,  Weiwei Chen

    发明人： Rajesh Venkat Subbu ,  Jon David Petersen ,  Weiwei Chen

    IPC分类号： G08G5/00

    CPC分类号： G08G5/0013

    摘要： Methods and systems suitable for processing multiple trajectory modification requests received from multiple aircraft within an airspace. The methods include receiving multiple trajectory modification requests that are transmitted from multiple aircraft and request alterations of the altitudes, speeds and/or lateral routes thereof, sequentially performing conflict assessments on the multiple trajectory modification requests to determine if any of the multiple trajectory modification requests pose conflicts with the altitudes, speeds and lateral routes of any other of the multiple aircraft, placing in a computer memory data queue n trajectory modification requests of the multiple trajectory modification requests that are identified by the conflict assessments as posing conflicts, and periodically processing the queue to perform subsequent conflict assessments on the n trajectory modification requests to determine if any of the n trajectory modification requests still pose conflicts with the altitudes, speeds and lateral routes of any other of the multiple aircraft.

    摘要翻译： 适用于处理从空域内的多架飞机接收的多轨迹修改请求的方法和系统。 所述方法包括接收从多个飞行器发送的多个轨迹修改请求，并请求对其高度，速度和/或横向路线的改变，对多个轨迹修改请求顺序执行冲突评估，以确定多个轨迹修改请求中是否存在任何姿势 与多个飞机中的任何其他飞机的高度，速度和横向路线冲突，将由冲突评估识别的多个轨迹修改请求的轨迹修改请求放置在计算机存储器数据队列中，构成冲突，并周期性地处理队列 对n个轨迹修改请求执行随后的冲突评估，以确定n个轨迹修改请求中的任何一个是否仍然与多个飞行器中的任何另一个的高度，速度和横向路线相冲突。

    METHODS AND SYSTEMS FOR MANAGING AIR TRAFFIC
    8.
    发明申请
    METHODS AND SYSTEMS FOR MANAGING AIR TRAFFIC 有权
    管理空中交通的方法和系统

    公开(公告)号：US20120215433A1

    公开(公告)日：2012-08-23

    申请号：US13032101

    申请日：2011-02-22

    申请人： Rajesh Venkat Subbu ,  Feng Xue ,  Mauricio Castillo-Effen ,  Joel Kenneth Klooster ,  Joachim Karl Ulf Hochwarth ,  Sergio Torres ,  Weiwei Chen

    发明人： Rajesh Venkat Subbu ,  Feng Xue ,  Mauricio Castillo-Effen ,  Joel Kenneth Klooster ,  Joachim Karl Ulf Hochwarth ,  Sergio Torres ,  Weiwei Chen

    IPC分类号： G08G5/00

    CPC分类号： G08G5/0043 ,  G06Q10/047 ,  G06Q10/06 ,  G06Q50/30

    摘要： Methods and systems suitable for negotiating air traffic trajectory modification requests received from multiple aircraft that each has trajectory parameters. The methods include transmitting from at least a first aircraft a first trajectory modification request to alter the altitude, speed and/or lateral route thereof. A first conflict assessment is then performed to determine if the first trajectory modification request poses a conflict with the altitudes, speeds and lateral routes of other aircraft. If a conflict is not identified, the first trajectory modification request is granted and the first aircraft is notified of the first trajectory modification request being granted. Alternatively, if a conflict is identified, the first trajectory modification request is not granted and the first aircraft is notified thereof. If the first trajectory modification request was not granted, the first trajectory modification request is placed in a queue, which is periodically processed to perform subsequent conflict assessments.

    摘要翻译： 适用于协商从多台飞机接收的空中交通轨迹修改请求的方法和系统，每个航空器具有轨迹参数。 所述方法包括从至少第一飞行器发送第一轨迹修改请求以改变其高度，速度和/或横向路线。 然后执行第一冲突评估以确定第一轨迹修改请求是否与其他飞行器的高度，速度和侧向路线形成冲突。 如果没有识别到​​冲突，则授予第一轨迹修改请求，并且向第一飞机通知被授予的第一轨迹修改请求。 或者，如果确定了冲突，则未授予第一轨迹修改请求，并且通知第一飞行器。 如果未授予第一轨迹修改请求，则将第一轨迹修改请求放置在队列中，该队列被周期性地处理以执行随后的冲突评估。

    Systems and methods for initial sampling in multi-objective portfolio analysis
    9.
    发明授权
    Systems and methods for initial sampling in multi-objective portfolio analysis 有权
    多目标投资组合分析初始抽样的系统和方法

    公开(公告)号：US08126795B2

    公开(公告)日：2012-02-28

    申请号：US10781898

    申请日：2004-02-20

    申请人： Srinivas Bollapragada ,  Piero Patrone Bonissone ,  Kete Charles Chalermkraivuth ,  Neil Holger White Eklund ,  Naresh Sundaram Iyer ,  Rajesh Venkat Subbu

    发明人： Srinivas Bollapragada ,  Piero Patrone Bonissone ,  Kete Charles Chalermkraivuth ,  Neil Holger White Eklund ,  Naresh Sundaram Iyer ,  Rajesh Venkat Subbu

    IPC分类号： G06Q40/00

    CPC分类号： G06Q40/06

    摘要： The systems and methods of the invention are directed to portfolio optimization and related techniques. For example, the invention provides a method for multi-objective portfolio optimization for use in investment decisions based on competing objectives and a plurality of constraints constituting a portfolio problem, the method comprising: generating an initial population of solutions of portfolio allocations, the generating the initial population of solutions of portfolio allocations including systematically generating the initial population of solutions to substantially cover the space defined by the competing objectives and the plurality of constraints; and generating an efficient frontier in the space based on the initial population, the efficient frontier for use in investment decisioning.

    摘要翻译： 本发明的系统和方法针对组合优化和相关技术。 例如，本发明提供了一种用于基于竞争目标和构成组合问题的多个约束的投资决策中的多目标投资组合优化的方法，所述方法包括：生成投资组合分配的初始解决方案群体， 包括投资组合分配的最初解决方案，其中包括系统地产生解决方案的初始群体，以充分覆盖竞争目标和多个约束所界定的空间; 并根据初始人口，投资决策中使用的有效前沿，在空间中产生有效的前沿。

    System and process for multivariate adaptive regression splines classification for insurance underwriting suitable for use by an automated system
    10.
    发明授权
    System and process for multivariate adaptive regression splines classification for insurance underwriting suitable for use by an automated system 有权
    适用于自动化系统使用的保险承保的多变量自适应回归样条分类系统和过程

    公开(公告)号：US07813945B2

    公开(公告)日：2010-10-12

    申请号：US10425733

    申请日：2003-04-30

    申请人： Piero Patrone Bonissone ,  Richard Paul Messmer ,  Rajesh Venkat Subbu ,  Weizhong Yan ,  Anindya Chakraborty

    发明人： Piero Patrone Bonissone ,  Richard Paul Messmer ,  Rajesh Venkat Subbu ,  Weizhong Yan ,  Anindya Chakraborty

    IPC分类号： G06Q40/00

    CPC分类号： G06Q40/02 ,  G06Q40/08

    摘要： A method and system for automating the decision-making process used in underwriting of insurance applications is described. While this approach is demonstrated for insurance underwriting, it is broadly applicable to diverse decision-making applications in business, commercial, and manufacturing processes. A structured methodology is used based on a multi-model parallel network of multivariate adaptive regression splines (“MARS”) models to identify the relevant set of variables and their parameters, and build a framework capable of providing automated decisions. The parameters of the MARS-based decision system are estimated from a database consisting of a set of applications with reference decisions against each. Cross-validation and development/hold-out combined with re-sampling techniques are used to build a robust set of models that minimize the error between the automated system's decision and the expert human underwriter. Furthermore, this model building methodology can be used periodically to update and maintain the family of models if required to assure currency.

    摘要翻译： 描述了一种自动化用于承保保险应用程序的决策过程的方法和系统。 虽然这种方法在保险承保方面得到证明，但它广泛适用于商业，商业和制造过程中的各种决策应用。 基于多变量自适应回归样条（“MARS”）模型的多模式并行网络，使用一种结构化方法来识别相关的变量及其参数集，并构建能够提供自动化决策的框架。 基于MARS的决策系统的参数是由一组数据库估算出来的，该数据库由一组应用程序组成，具有相应的参考决定。 交叉验证和开发/保留与重新采样技术相结合，用于构建一套强大的模型，以最大限度地减少自动系统决策与专家人类承保人之间的错误。 此外，如果需要确保货币，则可以定期使用此模型构建方法来更新和维护模型系列。