公开(公告)号：GB2612470A

公开(公告)日：2023-05-03

申请号：GB202300135

申请日：2021-05-14

Applicant: IBM

Inventor： NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

IPC: G06N3/04

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data (504, 514, 702, 802) having forward dependence to a target variable (108, 110, 112, 604, 708, 804), a second time series of downstream sensor data (508, 518, 704, 806) having backward dependence to the target variable (108, 110, 112, 604, 708, 804) and a time series of measured target variable (108, 110, 112, 604, 708, 804) data associated with the target variable (108, 110, 112, 604, 708, 804). The target variable (108, 110, 112, 604, 708, 804) has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data (504, 514, 70, 802) and the downstream sensor data (508, 518, 704, 806). The hybrid sensor can estimate a value of the target variable (108, 110, 112, 604, 708, 804) at a given time, for example, during which no actual measured target variable (108, 110, 112, 604, 708, 804) value is available.

公开(公告)号：BRPI0511882B1

公开(公告)日：2018-12-18

申请号：BRPI0511882

申请日：2005-06-07

Applicant: IBM

Inventor： DAVID MARTIN ,  DIKRAN MELIKSETIAN ,  IRWIN BOUTBOUL ,  NIANJUN ZHOU

IPC: H04L29/06 ,  H04L29/08

Abstract: download de dados concomitante otimizado dentro de um ambiente computacional de grade. em um sistema computadorizado de grade que tem uma pluralidade de servidores de download em uma comunicação da rede com os computadores do cliente e em um sistema de gerenciamento de download, um cliente solicita um plano de download do sistema de gerenciamento de download para baixar dados em paralelo a partir da pluralidade de servidores de download para um cliente. o cliente solicita partes dos dados dos servidores de download identificados pelo plano de download. o cliente monitora o desempenho dos servidores de download que baixa as partes e atribui novamente as parcelas das partes entre os servidores de download a fim de melhorar o desempenho de completar o download das partes. uma parte dos dados de download é uma pluralidade de arquivos, um arquivo ou uma parcela do arquivo de dados.

公开(公告)号：IL297447B2

公开(公告)日：2024-10-01

申请号：IL29744722

申请日：2022-10-19

Applicant: IBM CORP ,  NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

Inventor： NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

IPC: G05B13/02 ,  G05B19/418 ,  G05B23/02 ,  G06Q50/04

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data having forward dependence to a target variable, a second time series of downstream sensor data having backward dependence to the target variable and a time series of measured target variable data associated with the target variable. The target variable has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data and the downstream sensor data. The hybrid sensor can estimate a value of the target variable at a given time, for example, during which no actual measured target variable value is available.

公开(公告)号：IL297447B1

公开(公告)日：2024-06-01

申请号：IL29744722

申请日：2022-10-19

Applicant: IBM ,  NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

Inventor： NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

IPC: G05B13/02 ,  G05B19/418 ,  G05B23/02 ,  G06Q50/04

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data having forward dependence to a target variable, a second time series of downstream sensor data having backward dependence to the target variable and a time series of measured target variable data associated with the target variable. The target variable has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data and the downstream sensor data. The hybrid sensor can estimate a value of the target variable at a given time, for example, during which no actual measured target variable value is available.

公开(公告)号：IL297447A

公开(公告)日：2022-12-01

申请号：IL29744722

申请日：2022-10-19

Applicant: IBM ,  NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

Inventor： NIANJUN ZHOU ,  DHARMASHANKAR SUBRAMANIAN ,  WESLEY M GIFFORD

IPC: G05B13/02 ,  G05B23/02 ,  G06Q50/04

Abstract: A hybrid sensor can be generated by training a machine learning model, such as a neural network, based on a training data set. The training data set can include a first time series of upstream sensor data having forward dependence to a target variable, a second time series of downstream sensor data having backward dependence to the target variable and a time series of measured target variable data associated with the target variable. The target variable has measuring frequency which is lower than the measuring frequencies associated with the upstream sensor data and the downstream sensor data. The hybrid sensor can estimate a value of the target variable at a given time, for example, during which no actual measured target variable value is available.