公开(公告)号：US20230154098A1

公开(公告)日：2023-05-18

申请号：US17455371

申请日：2021-11-17

Applicant: International Business Machines Corporation

Inventor： Hendrik F. Hamann ,  Carlo Siebenschuh ,  Siyuan Lu ,  Conrad M. Albrecht

IPC: G06T15/00 ,  G06F16/51 ,  G06F16/55 ,  G06F16/583

CPC classification number: G06T15/00 ,  G06F16/51 ,  G06F16/55 ,  G06F16/583

Abstract: A computer implemented method rasterizes point cloud data. A number of processor units rasterizes the point cloud data into rasterized layers based on classes in which each rasterized layer in the rasterized layers corresponds to a class in the classes. The number of processor units creates key value pairs from the rasterized layers. The number of processor units store the key value pairs in a key value store. According to other illustrative embodiments, a computer system and a computer program product for rasterizing point cloud data are provided.

公开(公告)号：US11580387B2

公开(公告)日：2023-02-14

申请号：US16729406

申请日：2019-12-29

Applicant: International Business Machines Corporation ,  IHI Corporation

Inventor： Johannes W. Schmude ,  Siyuan Lu ,  Hendrik F. Hamann ,  Akihisa Sakurai ,  Taku Izumiyama ,  Masao Hasegawa

IPC: G06N3/08 ,  G06N3/063 ,  G06N3/04

Abstract: A computer produces predictions throughout a raster field in response to point data, by obtaining a partially empty matrix of point data, filling a matrix of extrapolated raster data by dilating the point data in a first convolutional neural network, and generating a matrix of aggregate raster data by combining the extrapolated raster data with organic raster data in a second convolutional neural network.

公开(公告)号：US11436712B2

公开(公告)日：2022-09-06

申请号：US16658533

申请日：2019-10-21

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Conrad M. Albrecht ,  Hendrik F. Hamann ,  Levente Klein ,  Siyuan Lu ,  Sharathchandra Pankanti ,  Wang Zhou

IPC: G06T7/00 ,  G06N5/04 ,  G06N3/08 ,  G06K9/62 ,  G06N20/00 ,  G06V20/10

Abstract: Methods and systems for managing vegetation include training a machine learning model based on an image of a training data region before a weather event, an image of the training data region after the weather event, and information regarding the weather event. A risk score is generated for a second region using the trained machine learning model based on an image of the second region and predicted weather information for the second region. The risk score is determined to indicate high-risk vegetation in the second region. A corrective action is performed to reduce the risk of vegetation in the second region.

公开(公告)号：US20220196860A1

公开(公告)日：2022-06-23

申请号：US17131452

申请日：2020-12-22

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Carlo Siebenschuh ,  Conrad M. Albrecht ,  Johannes Walter Schmude ,  Hendrik F. Hamann ,  Siyuan Lu ,  Oki Gunawan

IPC: G01V1/00 ,  G06T7/246 ,  G06N3/08 ,  G06N3/04

Abstract: From each of a plurality of cameras, a visual input of a location is received over a network. For each visual input from the plurality of cameras, a coupling correction is performed between a shaking of the camera with respect to the visual input by subtracting velocity vectors of the plurality of cameras from velocity vectors of pixels defining the visual input to provide a processed input. It is determined whether a shaking identified in the processed input is above a predetermined threshold based on the processed input, thereby detecting one or more anomalies. From the one or more anomalies, at least one of a location, magnitude, or depth of an earthquake are inferred based on the shaking identified in the processed input of each of the plurality of cameras.

公开(公告)号：US11360970B2

公开(公告)日：2022-06-14

申请号：US16188964

申请日：2018-11-13

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Marcus Oliver Freitag ,  Conrad M. Albrecht ,  Fernando Jimenez Marianno ,  Siyuan Lu ,  Hendrik F. Hamann ,  Johannes Walter Schmude

IPC: G06F16/24 ,  G06F16/242 ,  G06T17/00 ,  G06F16/2457 ,  G06F16/29 ,  G06T17/05 ,  G06F16/31

Abstract: A computer-implemented method includes accessing, by a processing unit, an existing layer representing geospatial-temporal data at a selected timestamp. A first overview layer of the existing layer is generated by iteratively aggregating each cluster of cells of the existing layer into a corresponding lower-resolution cell of the first overview layer. The first overview layer therefore has a lower resolution than the existing layer. A query is received related to the geospatial-temporal data in the existing layer, and the query is processed with reference to the first overview layer.

公开(公告)号：US20210201129A1

公开(公告)日：2021-07-01

申请号：US16729406

申请日：2019-12-29

Applicant: International Business Machines Corporation ,  IHI Corporation

Inventor： Johannes W. Schmude ,  Siyuan Lu ,  Hendrik F. Hamann ,  Akihisa Sakurai ,  Taku Izumiyama ,  Masao Hasegawa

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: A computer produces predictions throughout a raster field in response to point data, by obtaining a partially empty matrix of point data, filling a matrix of extrapolated raster data by dilating the point data in a first convolutional neural network, and generating a matrix of aggregate raster data by combining the extrapolated raster data with organic raster data in a second convolutional neural network.

公开(公告)号：US10697928B2

公开(公告)日：2020-06-30

申请号：US15287654

申请日：2016-10-06

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： S. J. Chey ,  Hendrik F. Hamann ,  Levente Klein ,  Siyuan Lu ,  Roland Nagy

IPC: G01N7/00 ,  G01N21/00 ,  G01N27/00 ,  G01N31/00 ,  G01N33/00 ,  H01S4/00 ,  G01N27/414 ,  G01N27/12 ,  C23C14/08 ,  C23C14/14 ,  C23C14/30 ,  C23C14/34 ,  G08B21/16 ,  G08B29/18 ,  G08B29/22

Abstract: A gas sensing device includes a dielectric substrate, a heater integrated into a first side of the substrate and an insulating dielectric formed over the heater. A gas sensing layer is formed on a second side of the substrate opposite the first side. Contacts are formed on the gas sensing substrate. A noble material is formed on a portion of the gas sensing layer between the contacts to act as an ionizing catalyst such that, upon heating to a temperature, adsorption of a specific gas changes electronic properties of the gas sensing layer to permit detection of the gas.

公开(公告)号：US20200151272A1

公开(公告)日：2020-05-14

申请号：US16188964

申请日：2018-11-13

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Marcus Oliver Freitag ,  Conrad M. Albrecht ,  Fernando Jimenez Marianno ,  Siyuan Lu ,  Hendrik F. Hamann ,  Johannes Walter Schmude

IPC: G06F17/30 ,  G06T17/00

Abstract: A computer-implemented method includes accessing, by a processing unit, an existing layer representing geospatial-temporal data at a selected timestamp. A first overview layer of the existing layer is generated by iteratively aggregating each cluster of cells of the existing layer into a corresponding lower-resolution cell of the first overview layer. The first overview layer therefore has a lower resolution than the existing layer. A query is received related to the geospatial-temporal data in the existing layer, and the query is processed with reference to the first overview layer.

公开(公告)号：US20190285504A1

公开(公告)日：2019-09-19

申请号：US15919405

申请日：2018-03-13

Applicant: International Business Machines Corporation

Inventor： Ramachandran Muralidhar ,  Josephine B. Chang ,  Siyuan Lu ,  Theodore van Kessel ,  Hendrik F. Hamann

IPC: G01M3/04 ,  G01P13/02 ,  G01P5/00

Abstract: Heuristic-based techniques for gas leak source identification are provided. In one aspect, a method for identifying a location of a gas leak source includes: obtaining gas sensor data and wind data synchronously from a gas leak detection system having a network of interconnected motes comprising gas sensors and wind sensors, with the gas sensors arranged around possible gas leak sources in a given area of interest; identifying the location of the gas leak source using the gas sensor data and wind data; and determining a magnitude of gas leak from the gas leak source using the location of the gas leak source and a distance d between the location of the gas leak source and a select one of the gas sensors from which the gas sensor data was obtained. A gas leak detection system is also provided.

公开(公告)号：US10408973B2

公开(公告)日：2019-09-10

申请号：US15463412

申请日：2017-03-20

Applicant: International Business Machines Corporation

Inventor： Levente Klein ,  Siyuan Lu ,  Fernando J. Marianno ,  Theodore G. van Kessel

IPC: G01W1/14 ,  G01W1/10

Abstract: Embodiments for controlling precipitation collection vessels to accurately and efficiently collect, measure, and aggregate precipitation accumulation data are disclosed. In one embodiment according to aspects of the present invention, a computer-implemented method includes collecting snow in a plurality of collection vessels by orienting an open end of each of the plurality of collection vessels perpendicularly to a direction of the wind based at least in part on a wind model. The computer-implemented method further includes measuring a snow level of the snow in each of the plurality of collection vessels to generate snow level data for each of the plurality of collection vessels. The computer-implemented method further includes aggregating the snow level data for each of the plurality of snow collection by assembling the snow accumulation data from each of the plurality of collection vessels.