利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

119 条记录 (耗时 0.027 秒)

    MODEL GUIDED DEEP LEARNING APPROACH TOWARDS PREDICTION OF PHYSICAL SYSTEM BEHAVIOR
    4.
    发明申请
    MODEL GUIDED DEEP LEARNING APPROACH TOWARDS PREDICTION OF PHYSICAL SYSTEM BEHAVIOR 审中-公开

    公开(公告)号：US20190188587A1

    公开(公告)日：2019-06-20

    申请号：US16226461

    申请日：2018-12-19

    申请人： Sandeep Gupta ,  Ayan Banerjee

    发明人： Sandeep Gupta ,  Ayan Banerjee

    IPC分类号： G06N7/00 ,  G06N3/08 ,  A61B5/00 ,  A61B5/145

    CPC分类号： G06N7/00 ,  A61B5/14532 ,  A61B5/7275 ,  G06N3/08

    摘要： Systems and methods are provided for controlling predictive medical monitoring. A non-linear-predictive-guide model estimates a patient parameter that is used as a guide in a deep neural network for improving accuracy of estimation by the deep neural network. The guide model generates a guiding first estimated patient parameter based on the guide model and patient input data. The deep neural network generates a second estimated patient parameter based on the deep neural network, the patient input data, and the guiding first estimated patient parameter. The deep neural network includes an input layer that receives the guiding first estimated patient parameter, and hidden layers including respective artificial neurons configured to perform a linear or nonlinear transformation on output of at least one artificial neuron from an adjacent layer in the deep neural network. An output layer receives at least one output from a hidden layer.

    POWER DELIVERY SYSTEM MANAGEMENT
    6.
    发明申请
    POWER DELIVERY SYSTEM MANAGEMENT 审中-公开
    电力输送系统管理

    公开(公告)号：US20150277410A1

    公开(公告)日：2015-10-01

    申请号：US14667771

    申请日：2015-03-25

    申请人： Sandeep Gupta ,  Ayan Banerjee

    发明人： Sandeep Gupta ,  Ayan Banerjee

    IPC分类号： G05B19/042

    CPC分类号： H02J3/383 ,  H02J3/008 ,  H02J3/32 ,  H02J13/0006 ,  Y02E10/563 ,  Y02E10/566 ,  Y02E40/72 ,  Y02E60/722 ,  Y02E70/30 ,  Y04S10/123 ,  Y04S10/14 ,  Y04S50/10

    摘要： An energy management system includes a number of power sources, a first set of energy storage devices (ESDs), a second set of ESDs, and a control system. The first set of ESDs is coupled between the power sources and a load and has a first set of operating characteristics. The second set of ESDs is also coupled between the power sources and the load and has a second set of operating characteristics that are different from the first set of operating characteristics. The control system is configured to selectively deliver power from one of the plurality of power sources to the first plurality of ESDs, the second plurality of ESDs, or both and selectively deliver power from the first plurality of ESDs, the second plurality of ESDs, or both to the load based on short and long term variations in a set of energy delivery system characteristics.

    摘要翻译： 能量管理系统包括多个电源，第一组能量存储装置（ESD），第二组ESD以及控制系统。 第一组ESD耦合在电源和负载之间，并具有第一组工作特性。 第二组ESD也耦合在电源和负载之间，并且具有与第一组操作特性不同的第二组操作特性。 所述控制系统被配置为选择性地将功率从所述多个电源中的一个供电到所述第一多个ESD，所述第二多个ESD或两者，并且选择性地从所述第一多个ESD，所述第二多个ESD或 基于一组能量传递系统特性中的短期和长期变化的负载。

    Systems and methods for managing statistical expressions
    7.
    发明授权
    Systems and methods for managing statistical expressions 有权
    用于管理统计表达式的系统和方法

    公开(公告)号：US08700597B2

    公开(公告)日：2014-04-15

    申请号：US12186682

    申请日：2008-08-06

    申请人： Sandeep Gupta ,  James R. Reid ,  Matthew P. Welsh ,  Shannon M. Cothran ,  Sharmistha Das

    发明人： Sandeep Gupta ,  James R. Reid ,  Matthew P. Welsh ,  Shannon M. Cothran ,  Sharmistha Das

    IPC分类号： G06F7/00 ,  G06F17/30

    CPC分类号： G06F17/30976 ,  G06F8/51 ,  G06N5/02

    摘要： Using natural language-like user inputs to provide statistics on a subset of data is described. In one embodiment, a user input that includes at least one word or phrase representing a rule is received. The rule includes an identification of a subset of data and a statistical expression to be performed on the subset of data. The subset of data includes at least part of the data elements of a data set. Each data element includes information on an individual or group. Instructions are provided for translating the rule into an executable format. The executable format includes a translated identification of the subset and a translated statistical expression. The subset of the data is accessed using the translated identification of the subset. The translated statistical expression is executed to obtain statistics on data elements of the subset of data. The statistics on the data elements are provided.

    摘要翻译： 描述了使用自然语言的用户输入来提供数据子集的统计数据。 在一个实施例中，接收包括表示规则的至少一个单词或短语的用户输入。 该规则包括要对数据子集执行的数据子集的标识和统计表达式。 数据子集包括数据集的数据元素的至少一部分。 每个数据元素包括关于个人或组的信息。 提供了将规则翻译成可执行格式的说明。 可执行格式包括该子集的翻译标识和翻译的统计表达式。 使用子集的翻译标识来访问数据的子集。 执行翻译的统计表达式以获得关于数据子集的数据元素的统计。 提供了有关数据元素的统计信息。

    AROMATICS-RECOVERY PROCESS
    9.
    发明申请
    AROMATICS-RECOVERY PROCESS 有权
    AROMATICS-RECOVERY过程

    公开(公告)号：US20130001065A1

    公开(公告)日：2013-01-03

    申请号：US13170691

    申请日：2011-06-28

    申请人： Deepak Bisht ,  Anup Dhaigude ,  Sandeep Gupta

    发明人： Deepak Bisht ,  Anup Dhaigude ,  Sandeep Gupta

    IPC分类号： B01D3/40

    CPC分类号： B01D3/105 ,  B01D5/009 ,  B01D11/00 ,  B01D17/0211 ,  B01D17/0214 ,  Y10S203/14

    摘要： The present invention comprises a process for recovery of sulfolane used in a solvent-extraction or extractive-distillation process. A recovery column for the sulfolane solvent comprises a liquid-jet ejector for maintaining the needed vacuum conditions, preferably using water as the liquid.

    摘要翻译： 本发明包括用于溶剂萃取或萃取 - 蒸馏过程中使用的环丁砜的回收方法。 用于环丁砜溶剂的回收塔包括用于保持所需真空条件的液体喷射喷射器，优选使用水作为液体。