公开(公告)号：US20230289406A1

公开(公告)日：2023-09-14

申请号：US18177189

申请日：2023-03-02

Applicant: Fujitsu Limited

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI

IPC: G06F18/2415 ,  G06F18/2431

CPC classification number: G06F18/2415 ,  G06F18/2431

Abstract: A non-transitory computer-readable recording medium stores a determination program for causing a computer to execute processing including: re-training a classification model that has been trained by using a first data set and that classifies input data into any one of a plurality of classes by using a loss calculatable based on a second data set that is different from the first data set; and determining, in a case where a change in a classification standard of the classification model based on the loss is a predetermined standard or more before and after re-training, that unknown data that is not classified into any one of the plurality of classes is included in the second data set.

公开(公告)号：US20140195144A1

公开(公告)日：2014-07-10

申请号：US14077866

申请日：2013-11-12

Applicant: FUJITSU LIMITED

Inventor： Hiroaki MORIKAWA ,  Tatsuya ASAI ,  Takashi KATOH ,  Shinichiro TAGO ,  Hiroya INAKOSHI

IPC: G01C21/36

CPC classification number: G01C21/3679 ,  G01C21/343 ,  G06F11/3656 ,  H04L67/306 ,  H04M1/72572

Abstract: An analysis method executed by a computer, the analysis method includes: detecting a plurality of staying points where one or more mobile bodies stayed in accordance with a plurality of trace data associated with trajectories of the one or more mobile bodies; comparing, in accordance with the plurality of trace data, a first ending time of stay in a first staying point selected from among the plurality of staying points with second ending times of stay in one or more second staying points which are similar to the first staying point; and determining feature of the first staying point in accordance with a result of the comparison.

Abstract translation: 一种由计算机执行的分析方法，所述分析方法包括：根据与所述一个或多个移动体的轨迹相关联的多个跟踪数据来检测一个或多个移动体停留的多个停留点; 比较根据所述多个跟踪数据，从所述多个停留点中选择的第一停留点的停留的第一结束停留时间，其中所述第一停留时间与所述第一停留时间相似的一个或多个第二停留点中的停留的第二结束时间 点; 以及根据比较的结果确定第一停留点的特征。

公开(公告)号：US20240147030A1

公开(公告)日：2024-05-02

申请号：US18364089

申请日：2023-08-02

Applicant: Fujitsu Limited

Inventor： Takashi KATOH ,  Kanata SUZUKI

IPC: H04N23/11 ,  H04N5/262 ,  H04N23/69 ,  H04N23/80

CPC classification number: H04N23/11 ,  H04N5/2624 ,  H04N23/69 ,  H04N23/80 ,  H04N23/698

Abstract: A control method including: obtaining an image of a given range captured by an image capturing device and a first invisible light image of the range captured by an invisible light image capturing device having a resolution lower than a resolution of the image capturing device; generating a second invisible light image at a resolution higher than a resolution of the first invisible light image by a machine learning model using the image and the first invisible light image as an input; identifying a target area from the range, based on an indicator indicating an uncertainty of each pixel in the second invisible light image; and obtaining, by an optical magnification control of the invisible light image capturing device, a third invisible light image of the target area at a resolution higher than a resolution of the target area in the first invisible light image.

公开(公告)号：US20230259827A1

公开(公告)日：2023-08-17

申请号：US18301582

申请日：2023-04-17

Applicant: FUJITSU LIMITED

Inventor： Takashi KATOH ,  Kento UEMURA ,  Suguru YASUTOMI ,  Tomohiro HAYASE

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A non-transitory computer-readable recording medium stores a generation program for causing a computer to execute a process including: with data included in each of a plurality of data sets, training a feature space in which a distance between pieces of the data included in a same domain is shorter and the distance of the data between different domains is longer; and generating labeled data sets by integrating labeled data included within a predetermined range in the trained feature space, among a plurality of pieces of the labeled data.

公开(公告)号：US20190303766A1

公开(公告)日：2019-10-03

申请号：US16358801

申请日：2019-03-20

Applicant: FUJITSU LIMITED

Inventor： Toshio ENDOH ,  Takashi KATOH

IPC: G06N3/08 ,  G06N3/04

Abstract: An adaptability calculation device inputs input data to a learning model and an encoder of an autoencoder that have performed learning with learning data, inputs an output from the learning model and an output from the encoder of the autoencoder to a decoder of the autoencoder, and calculates adaptability of the output from the learning model to the input data based on an output from the decoder and the input data.

公开(公告)号：US20240193924A1

公开(公告)日：2024-06-13

申请号：US18581044

申请日：2024-02-19

Applicant: FUJITSU LIMITED

Inventor： Takashi KATOH ,  Kanata SUZUKI ,  Taro SUNAGAWA ,  Tomotake SASAKI

IPC: G06V10/778 ,  B25J9/16 ,  G06N3/04 ,  G06N3/094 ,  G06V10/764 ,  G06V10/774 ,  G06V10/776 ,  H04N23/61 ,  H04N23/695

CPC classification number: G06V10/778 ,  B25J9/1664 ,  G06N3/04 ,  G06N3/094 ,  G06V10/774 ,  G06V10/776 ,  H04N23/61 ,  H04N23/695 ,  G06V10/764

Abstract: A computer-readable storage medium storing a data collection program for causing a computer, which is configured to collect training data used for training a machine learning model, to perform processing. In an example, the processing includes: selecting a target data having a confidence level lower than a predetermined value, the confidence level corresponding to a confidence for an output from the machine learning model when collected data is input into the machine learning model; and collecting, for a target object related to the selected target data, the training data such that the confidence is high.

公开(公告)号：US20240176844A1

公开(公告)日：2024-05-30

申请号：US18370992

申请日：2023-09-21

Applicant: Fujitsu Limited

Inventor： Takashi KATOH

IPC: G06F17/16

CPC classification number: G06F17/16

Abstract: A computer stores first matrix data that holds data of components of an array in a row direction, stores second matrix data that holds a flag that indicates whether the data is in an initialized state, and stores third matrix data that includes an area that holds an initial value common to a plurality of pieces of data in the column which is regarded as an initial value of each piece of data in the column in a case where a plurality of pieces of data in the column is collectively initialized in a column direction. Responding to a first initialization request for collectively initializing a plurality of pieces of data in a first column of the first matrix data in a column direction, a value that indicates an initialized state is set to a plurality of flags of the second matrix data.

公开(公告)号：US20200090076A1

公开(公告)日：2020-03-19

申请号：US16555395

申请日：2019-08-29

Applicant: FUJITSU LIMITED

Inventor： Takashi KATOH ,  Hiroaki Iwashita ,  Kotaro Ohori ,  Tatsuya Asai ,  Hikaru Yokono

IPC: G06N20/00 ,  G06N5/00 ,  G06N5/04

Abstract: A learning device creates a plurality of decision trees, using pieces of training data respectively including an explanatory variable and an objective variable, which are configured by a combination of the explanatory variables and respectively estimate the objective variable based on true or false of the explanatory variables. The learning device creates a linear model that is equivalent to the plurality of decision trees, and lists all terms configured by a combination of the explanatory variables without omission. The learning device outputs a prediction result by using the linear model from input data.

公开(公告)号：US20150026180A1

公开(公告)日：2015-01-22

申请号：US14315521

申请日：2014-06-26

Applicant: FUJITSU LIMITED

Inventor： Shinichiro TAGO ,  Takashi KATOH ,  Hiroya INAKOSHI

IPC: G06F17/30 ,  G06Q10/06

CPC classification number: G06F16/24565 ,  G06F16/2477 ,  G06Q10/063

Abstract: A collation device specifies a combination of event conditions in parallel with each other based on a query. The collation device sets the combination of event conditions in a parallel relation to the same window, connects a plurality of windows in series, and generates a similar query that sets a window interval condition between the windows in a connected relation. The collation device compares a similar query with collation data, and detects a combination of events that satisfies a condition of the similar query from among events included in the collation data.

Abstract translation: 归类装置基于查询来彼此并行地指定事件条件的组合。 排序规则装置将与相同窗口的并行关系的事件条件的组合设置为串联连接多个窗口，并生成在连接关系中的窗口之间设置窗口间隔条件的类似查询。 归类装置将类似的查询与对照数据进行比较，并且检测满足来自包括在对照数据中的事件中的类似查询的条件的事件的组合。

公开(公告)号：US20240256929A1

公开(公告)日：2024-08-01

申请号：US18415947

申请日：2024-01-18

Applicant: Fujitsu Limited ,  RIKEN

Inventor： Kimihiro YAMAZAKI ,  Yuichiro WADA ,  Mutsuyo WADA ,  Takashi KATOH ,  Atsushi TOKUHISA

IPC: G06N7/00

CPC classification number: G06N7/00

Abstract: A non-transitory computer-readable recording medium stores therein an information output program that causes a computer to execute a process including acquiring a first point and a second point in a presence probability distribution of a state of an object, specifying a plurality of points serving as candidates for a transition destination from the first point, selecting a third point from the points based on a distance from the first point to each of the points and probability during transition, and outputting a transition path from the first point to the second point including the third point as state transition information on the object.