-
公开(公告)号：AU2021286514B2
公开(公告)日：2023-04-27
申请号：AU2021286514
申请日：2021-05-14
Applicant: IBM
Inventor： ZHOU NIANJUN , SUBRAMANIAN DHARMASHANKAR , GIFFORD WESLEY M
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：AT476030T
公开(公告)日：2010-08-15
申请号：AT05803248
申请日：2005-10-11
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MELIKSETIAN DIKRAN , PROST JEAN-PIERRE , ZHOU NIANJUN
Abstract: Automated topology formation in a dynamic distributed environment. The automatic topology formation includes receiving by an application of a first entity having an initial topology role, topology information from a master node. The first entity has an initial topology role and the received topology information varies based the initial topology role. A local topology representation information is derived from the received topology information wherein the local topology representation information comprises any one of: a first entity topology role as any one of a not-a-node, root node, a prime node or a leaf node for the topology; a list of entities that are parents of the first entity in the topology, or a list of entities that are subordinates to the first entity in the topology; and setting the local topology representation information at the first entity.
-
公开(公告)号：AU2021286514A1
公开(公告)日：2022-10-27
申请号：AU2021286514
申请日：2021-05-14
Applicant: IBM
Inventor： ZHOU NIANJUN , SUBRAMANIAN DHARMASHANKAR , GIFFORD WESLEY M
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：DE602005022609D1
公开(公告)日：2010-09-09
申请号：DE602005022609
申请日：2005-10-11
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MELIKSETIAN DIKRAN , PROST JEAN-PIERRE , ZHOU NIANJUN
-
公开(公告)号：DE602005003948T2
公开(公告)日：2008-12-04
申请号：DE602005003948
申请日：2005-06-07
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MARTIN DAVID , MELIKSETIAN DIKRAN , ZHOU NIANJUN
Abstract: In a Grid computer system having a plurality of download servers in network communication with client computers and a download management system, a client requests a download plan from the download management system for downloading data in parallel from the plurality of download servers to a client. The client requests chunks of data from download servers identified by the download plan. The client monitors the performance of the download servers downloading the chunks and reassigns portions of chunks amongst the download servers in order to improve the performance of completing the download of the chunks. A chunk of download data is a plurality of files, a file or a portion of file of data.
-
Patent Agency Ranking
公开(公告)号：CA2569925C
公开(公告)日：2010-08-03
申请号：CA2569925
申请日：2005-06-07
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MARTIN DAVID , MELIKSETIAN DIKRAN , ZHOU NIANJUN
Abstract: In a Grid computer system having a plurality of download servers in network communication with client computers and a download management system, a client requests a download plan from the download management system for downloading data in parallel from the plurality of download servers to a client. The client requests chunks of data from download servers identified by the download plan. The client monitors the performance of the download servers downloading the chunks and reassigns portions of chunks amongst the download servers in order to improve the performance of completing the download of the chunks. A chunk of download data is a plurality of files, a file or a portion of file of data.
-
公开(公告)号：DE602005003948D1
公开(公告)日：2008-01-31
申请号：DE602005003948
申请日：2005-06-07
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MARTIN DAVID , MELIKSETIAN DIKRAN , ZHOU NIANJUN
Abstract: In a Grid computer system having a plurality of download servers in network communication with client computers and a download management system, a client requests a download plan from the download management system for downloading data in parallel from the plurality of download servers to a client. The client requests chunks of data from download servers identified by the download plan. The client monitors the performance of the download servers downloading the chunks and reassigns portions of chunks amongst the download servers in order to improve the performance of completing the download of the chunks. A chunk of download data is a plurality of files, a file or a portion of file of data.
-
公开(公告)号：CA2569925A1
公开(公告)日：2005-12-22
申请号：CA2569925
申请日：2005-06-07
Applicant: IBM
Inventor： BOUTBOUL IRWIN , MELIKSETIAN DIKRAN , MARTIN DAVID , ZHOU NIANJUN
Abstract: In a Grid computer system having a plurality of download servers in network communication with client computers and a download management system, a client requests a download plan from the download management system for downloading data in parallel from the plurality of download servers to a client. The client requests chunks of data from download servers identified by the download plan. The client monitors the performance of the download servers downloading the chunks and reassigns portions of chunks amongst the download servers in order to improve the performance of completing the download of the chunks. A chunk of download data is a plurality of files, a file or a portion of file of data.
-
公开(公告)号：DE112021001953T5
公开(公告)日：2023-03-16
申请号：DE112021001953
申请日：2021-05-14
Applicant: IBM
Inventor： ZHOU NIANJUN , SUBRAMANIAN DHARMASHANKAR , GIFFORD WESLEY M
Abstract: Ein Hybridsensor kann durch Schulen eines Maschinenlernmodells, wie beispielsweise ein neuronales Netzwerk, auf Grundlage eines Schulungsdatensatzes generiert werden. Der Schulungsdatensatz kann eine erste Zeitreihe von vorgelagerten Sensordaten (504, 514, 702, 802) mit Vorwärtsabhängigkeit zu einer Zielvariablen (108, 110, 112, 604, 708, 804), eine zweite Zeitreihe von nachgelagerten Sensordaten (508, 518, 704, 806) mit Rückwärtsabhängigkeit zu der Zielvariablen (108, 110, 112, 604, 708, 804), und eine Zeitreihe von gemessenen Zielvariablendaten (108, 110, 112, 604, 708, 804) umfassen, die der Zielvariablen zugehörig sind. Die Zielvariable (108, 110, 112, 604, 708, 804) hat eine Messfrequenz, die niedriger als die Messfrequenzen ist, die den vorgelagerten Sensordaten (504, 514, 702, 802)und den nachgelagerten Sensordaten (508, 518, 704, 806) zugehörig sind. Der Hybridsensor kann zum Beispiel einen Wert der Zielvariablen (108, 110, 112, 604, 708, 804) zu einem bestimmten Zeitpunkt schätzen, während dem kein aktueller Messwert der Zielvariablen (108, 110, 112, 604, 708, 804) verfügbar ist.
-
公开(公告)号：CA3178043A1
公开(公告)日：2021-12-16
申请号：CA3178043
申请日：2021-05-14
Applicant: IBM
Inventor： ZHOU NIANJUN , SUBRAMANIAN DHARMASHANKAR , GIFFORD WESLEY M
IPC: G01D21/00
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.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.017 seconds)
