-
公开(公告)号：US20240048617A1
公开(公告)日：2024-02-08
申请号：US18382196
申请日：2023-10-20
发明人： Tomohiro NARUI , Shuichi MURAYAMA , Kazuyuki NAGAHIRO , Fuyuki SATO , Toshihiro MEGA , Genta YOSHIMURA
摘要： A management device includes: an acquisition unit that acquires operating history data for an equipment device in a prescribed time period; and a classification processing unit that classifies, based on the operating history data acquired by the acquisition unit, an operating pattern of the equipment device in the prescribed time period. The classification processing unit includes: an operating pattern calculation unit that calculates a first operating pattern in a first time period and a second operating pattern in a remaining second time period when the prescribed time period is divided into unit time periods; a change calculation unit that calculates a degree of change in the operating pattern using the first operating pattern and the second operating pattern when the prescribed time period is divided into unit time periods; a split point calculation unit that calculates, as a split time point, a time point where the degree of change satisfies a prescribed condition for the prescribed time period; and a split processing unit that splits the prescribed time period at the calculated split time point.
-
2.发明公开公开(公告)号：US20240273367A1
公开(公告)日：2024-08-15
申请号：US18635549
申请日：2024-04-15
发明人： Takao ENDO , Genta YOSHIMURA
IPC分类号： G06N3/08 , G01V1/38 , G06N3/0464
CPC分类号： G06N3/08 , G01V1/3808 , G06N3/0464
摘要： A tsunami learning device includes: an input unit to acquire a training data set including observation data of a marine radar; and a CNN unit including CNN, to perform CNN processing on the training data set. The CNN includes a distance dimension feature extracting unit, a temporal dimension feature extracting unit, and a time-series prediction unit. The distance dimension feature extracting unit has a distance dimension convolution layer, and the distance dimension convolution layer has a filter having a size of 1 in a temporal dimension and a size of a natural number in a distance dimension. The temporal dimension feature extracting unit has a temporal dimension convolution layer, and the temporal dimension convolution layers has a convolutional filter having a size of a natural number in the temporal dimension and a size of a natural number in a distance dimension.
-
公开(公告)号：US20230305043A1
公开(公告)日：2023-09-28
申请号：US18200106
申请日：2023-05-22
摘要： An energy conservation assistance apparatus includes an event occurrence time extraction unit, a degree of change calculation unit, and a display control unit. The event occurrence time extraction unit refers to facility operation history information included in a reference period and a designated period to extract occurrence times at which a predetermined event has occurred in each of the reference period and the period of interest. The degree of change calculation unit calculates a degree of change in an operation pattern of a facility obtained from a distribution of the occurrence times at which the predetermined event has occurred in the period of interest, relative to an operation pattern of the facility obtained from a distribution of the occurrence times at which the predetermined event has occurred in the reference period. The display control unit presents information regarding a degree of change to a user.
-
公开(公告)号：US20220315011A1
公开(公告)日：2022-10-06
申请号：US17615749
申请日：2019-06-18
发明人： Kimika IKEGAMI , Takuji MORIMOTO , Genta YOSHIMURA , Shan GAO
摘要： An information collection unit collects information indicating a driving operation of a vehicle by a driver and a state of the vehicle changed by the driving operation, and outputs, among the collected information, information in a period from a start point at which a driving operation contributing to stop of the vehicle is performed to a stop start point in a stop state where a stop time of the vehicle continues for a predetermined time or more, as driving operation information. A state estimation unit acquires driver state information indicating a state of the driver from a learned learner on which machine learning has been performed so as to output the driver state information when the driving operation information is input, by inputting the driving operation information output from the information collection unit to the learner and performing arithmetic processing of the learner.
-
公开(公告)号：US20220147851A1
公开(公告)日：2022-05-12
申请号：US17581043
申请日：2022-01-21
发明人： Genta YOSHIMURA
IPC分类号： G06N5/04
摘要： A learning device includes: a learning data acquiring unit to acquire a plurality of pieces of learning data in which one piece of learning data is a combination of first information based on one of one or a plurality of pieces of time-series data including observation values in time series, second information based on one of a plurality of prediction periods including at least two prediction periods different from each other, and third information based on observation values after a lapse of the prediction period; and a learning unit to perform learning using the plurality of pieces of learning data acquired using information obtained by combining the first information and the second information in the learning data as an explanatory variable and using the third information as a response variable, and generate a learned model capable of inferring inference observation values after a lapse of a designated prediction period.
-
6.发明申请公开(公告)号：US20210311706A1
公开(公告)日：2021-10-07
申请号：US17347817
申请日：2021-06-15
发明人： Takashi MATSUMOTO , Genta YOSHIMURA
摘要： A development assistance device includes: multiple conversion units each for converting either an inputted signal value or inputted meta information into either a signal value or meta information, and for outputting either the signal value after conversion or the meta information after conversion as output information; a pipeline unit for causing, on the basis of pipeline information showing a relationship of mutual connections between the multiple conversion units, the multiple conversion units to sequentially perform the corresponding converting processes; an inference unit for making an inference by using the output information outputted by a final conversion unit which the pipeline unit causes, on the basis of the pipeline information, to finally perform the converting process, out of the multiple conversion units; and an image generation unit for generating image information for visualizing the connection relationship shown by the pipeline information, and a relationship of a connection between the final conversion unit and the inference unit.
-
公开(公告)号：US20240219873A1
公开(公告)日：2024-07-04
申请号：US18610055
申请日：2024-03-19
发明人： Toshisada MARIYAMA , Hiroaki HOKARI , Nobuyuki YOSHIKAWA , Genta YOSHIMURA , Yoshikuni MIYATA , Yusuke YOKOSUKA
CPC分类号： G05B13/048 , G05B13/0265
摘要： An apparatus control device includes an observed value acquiring unit that acquires, from a sensor that observes an environment in which a control target apparatus is installed, an observed value of the environment, an observation predicted value acquiring unit that gives an observed value acquired to a first learning model and acquires an observation predicted value that is a future observed value from the sensor from the first learning model, and an unobservable value acquiring unit that gives an observed value acquired to a second learning model and acquires an unobservable value that is a value not directly observed by the sensor from the second learning model. In addition, the apparatus control device includes a control value calculating unit that calculates a control value of the control target apparatus using the observed value acquired, the observation predicted value acquired, and the unobservable value acquired.
-
公开(公告)号：US20220350987A1
公开(公告)日：2022-11-03
申请号：US17866334
申请日：2022-07-15
发明人： Jun MARUTA , Genta YOSHIMURA
摘要： The feature amount extraction device includes: a data acquisition unit to acquire time-sequential data as input time-sequential data; a multiple-filter application unit, including multiple digital filters, to apply each of the digital filters to the input time-sequential data acquired by the data acquisition unit, and output, for each of the digital filters, filter response time-sequential data that is time-sequential data including a time-sequential feature or a frequency feature after having undergone the application; and a feature amount extracting unit to extract feature amounts for a plurality of pieces of the filter response time-sequential data output from the multiple-filter application unit for each of the plurality of pieces of the filter response time-sequential data, and output the extracted feature amounts as feature amount data.
-
公开(公告)号：US20210041487A1
公开(公告)日：2021-02-11
申请号：US17083572
申请日：2020-10-29
发明人： Fuyuki SATO , Shinichiro OTANI , Genta YOSHIMURA , Hiroki KAWANO , Toshihiro MEGA , Yoshinori NAKAJIMA
IPC分类号： G01R21/133 , G06Q50/06
摘要： A power consumption estimation device (10) which estimates power consumption of each of one object facility (100) or more whose operation statuses can be monitored includes: a total power vector generation unit (32) to acquire time-series data of total power consumption; a status matrix generation unit (34) to acquire time-series data of an operation parameter of the one object facility (100) or more; a reference signal generation unit (36) to generate one reference signal or more; a contribution degree estimation unit (38) to perform multiple regression analysis by taking the total power consumption as an objective variable, and the operation parameter of the one object facility (100) or more and a component value of the one reference signal or more, as explanatory variables, to thereby calculate a contribution degree of each of the one object facility (100) or more; and a breakdown calculation unit (42) to multiply the contribution degree of the object facility (100) and the operation parameter of the object facility (100), to thereby calculate power consumption of the object facility (100).
-
公开(公告)号：US20180053085A1
公开(公告)日：2018-02-22
申请号：US15554985
申请日：2015-08-31
发明人： Wataru MATSUMOTO , Genta YOSHIMURA , Xiongxin ZHAO
CPC分类号： G06N3/04 , G06N3/0445 , G06N3/0454 , G06N3/0481 , G06N3/084 , G06N3/088
摘要： A first intermediate layer activity level calculator refers to an index stored in a first intermediate layer storage, acquires, from among activity levels of respective nodes in an input layer calculated by an input layer activity level calculator and weight for respective edges and bias values stored in the first intermediate layer storage, an activity level of each node in the input layer that is connected with each node in the first intermediate layer and weight for each of edges and a bias value thereof, and calculates an activity level of each node in the first intermediate layer using the activity level of each node in the first input layer and the weight for each of the edges and the bias value having been acquired. This is capable of reducing the calculation amount and the memory amount upon performing inference, and also obtaining higher inference accuracy.
-
-
-
-
-
-
-
-
-
搜索结果
14 条记录 (耗时 0.022 秒)
