公开(公告)号：US20250161753A1

公开(公告)日：2025-05-22

申请号：US18839477

申请日：2022-03-30

Applicant: NEC Corporation

Inventor： Riki ETO

IPC: A63B24/00 ,  A63B71/06 ,  G16H20/30

Abstract: In order to generate a workout schedule in consideration of a state regarding a workout, a workout support apparatus (2) includes: a data acquiring section (21) for acquiring state data which indicates a state regarding a workout done by a targeted person; and a generating section (22) for generating a workout schedule in accordance with the state indicated by the state data, by performing an optimization calculation with use of an objective function, the objective function being generated by inverse reinforcement learning with use of training data which indicates a workout schedule that is in accordance with a state regarding a workout and that is to be applied in the state.

公开(公告)号：US20220390909A1

公开(公告)日：2022-12-08

申请号：US17775395

申请日：2019-11-14

Applicant: NEC CORPORATION

Inventor： Dai KUBOTA ,  Riki ETO

IPC: G05B13/02

Abstract: A learning unit 80 includes an input unit 81, a reward function estimation unit 82, and a temporal logic structure estimation unit 83. The input unit 81 receives input of an action history of a worker who performs multiple tasks in time series. The reward function estimation unit 82 estimates a reward function for each task in time series based on the action history. The temporal logic structure estimation unit 83 estimates a temporal logic structure between tasks based on a transition condition candidate at a point in time when each estimated reward function switched.

公开(公告)号：US20210293681A1

公开(公告)日：2021-09-23

申请号：US17262022

申请日：2018-07-31

Applicant: NEC Corporation

Inventor： Ryota SUZUKI ,  Riki ETO

IPC: G01N5/02

Abstract: An information processing apparatus (2000) acquires time-series data (14) output by a sensor (10) and computes a contribution value ξi representing contribution with respect to the time-series data (14) for each of a plurality of feature constants θi. Thereafter, the information processing apparatus (2000) outputs a set Ξ of the contribution values ξi as a feature value of a target gas. As the feature constant θ, a velocity constant β or a time constant τ that is a reciprocal of the velocity constant can be adopted.

公开(公告)号：US20210018479A1

公开(公告)日：2021-01-21

申请号：US16969621

申请日：2019-02-22

Applicant: NEC CORPORATION

Inventor： Junko WATANABE ,  Riki ETO ,  Hidetaka HANE ,  Shigeo KIMURA ,  Shintarou TSUCHIYA

IPC: G01N33/00 ,  G01N27/02

Abstract: An odor detection apparatus 100 includes a first odor sensor 10 provided with a sensitive membrane, a second odor sensor 20 provided with an identical sensitive membrane, and a control device 30. The control device 30 includes a sensor data acquisition unit 31 that acquires first sensor data output by the first odor sensor 10 and second sensor data output by the second odor sensor, a calculation processing unit 32 that calculates a difference between the first sensor data and the second sensor data, and a determination unit 33 that determines, when the sensitive membrane of one of the odor sensors is in a steady state, whether the sensitive membrane of the other odor sensor is in a steady state, based on the difference.

公开(公告)号：US20200249637A1

公开(公告)日：2020-08-06

申请号：US16639821

申请日：2017-09-22

Applicant: NEC Corporation

Inventor： Wemer WEE ,  Riki ETO ,  Yoshio KAMEDA

IPC: G05B13/02 ,  G06N20/20

Abstract: An ensemble control system 80 combines different types of plant control. A plurality of subcontrollers 81 output actions for the plant control based on a prediction result by a predictor. A combiner or switch 82 combines or switches actions to maximize prediction or control performance as best control action based on the actions output by each subcontroller 81. Subcontrollers 81 include at least two types of subcontrollers. A first type subcontroller is an optimization-based subcontroller which optimizes an objective function that is a cost function to be minimized for calculating actions and outputs a control action. A second type subcontroller is a prediction-subcontroller which predicts based on machine learning models and outputs a predicted action.

公开(公告)号：US20190196419A1

公开(公告)日：2019-06-27

申请号：US16307531

申请日：2016-06-10

Applicant: NEC Corporation

Inventor： Wemer WEE ,  Yoshio KAMEDA ,  Riki ETO

IPC: G05B13/02 ,  G06N20/20

CPC classification number: G05B13/028 ,  G05B13/024 ,  G06N20/20

Abstract: An expert model unit 81 generates predicted expert control actions based on an expert model which is a machine learning model trained using data collected when an expert operated a plant which is a control target or a plant of the same or similar characteristics. A transformer 82 constructs metrics or error measures involving the predicted expert control actions from the expert model unit 81 as an objective term. A combiner 83 collects different objective terms from the transformer 82 and a learner which outputs machine-learning models as objective terms and computes an optimal set of weights or combinations of the objective terms to construct an aggregated cost function for use in an optimizer.

公开(公告)号：US20180136076A1

公开(公告)日：2018-05-17

申请号：US15573039

申请日：2016-03-10

Applicant: NEC CORPORATION

Inventor： Yukitaka KUSUMURA ,  Sergey TARASENKO ,  Riki ETO ,  Yusuke MURAOKA ,  Ryohei FUJIMAKI

IPC: G01M3/28

CPC classification number: G01M3/28

Abstract: This invention provides a water-leakage state estimation system configured to estimate a state of a water leakage in a specific area of a water distribution network. A learning unit is configured to: receive labeled data, which is labeled so as to separate past flow rate data into abnormal values and normal values, and past environment state condition data; build a prediction model for predicting the normal values in the labeled data through learning; and determine a score parameter defining a length of a period involving data to be verified through learning as well. A water-leakage estimation unit is configured to: compare predicted flow rate data obtained by supplying current environment condition data into the prediction model and current flow rate data to produce error values; and calculate an average value of the error values in the period of a window width defined by the score parameter to estimate a water-leakage score representing a state of the water-leakage in the specific area.

公开(公告)号：US20140222741A1

公开(公告)日：2014-08-07

申请号：US13758267

申请日：2013-02-04

Applicant: NEC CORPORATION

Inventor： Riki ETO ,  Ryohei FUJIMAKI ,  Satoshi MORINAGA

IPC: G06N5/02

CPC classification number: G06N7/005 ,  G06F17/18 ,  G06K9/00536 ,  G06N5/02 ,  G06N5/025

Abstract: A hierarchical latent structure setting unit 81 sets a hierarchical latent structure that is a structure in which latent variables are represented by a tree structure and components representing probability models are located at nodes of a lowest level of the tree structure. A variational probability computation unit 82 computes a variational probability of a path latent variable that is a latent variable included in a path linking a root node to a target node in the hierarchical latent structure. A component optimization unit 83 optimizes each of the components for the computed variational probability. A gating function optimization unit 84 optimizes a gating function model that is a model for determining a branch direction according to the multivariate data in a node of the hierarchical latent structure, on the basis of the variational probability of the latent variable in the node.

Abstract translation: 分层潜在结构设置单元81设置作为其中潜变量由树结构表示的结构的分层潜在结构，并且表示概率模型的分量位于树结构的最底层的节点处。 变分概率计算单元82计算作为潜在变量的路径潜变量的变分概率，所述潜变量包括在将根节点链接到分层潜在结构中的目标节点的路径中。 分量优化单元83针对所计算的变分概率优化每个分量。 门控功能优化单元84基于节点中的潜在变量的变分概率来优化门控功能模型，门控功能模型是根据层级潜在结构的节点中的多变量数据确定分支方向的模型。

公开(公告)号：US20240320216A1

公开(公告)日：2024-09-26

申请号：US18575386

申请日：2021-07-13

Applicant: NEC Corporation

Inventor： Riki ETO ,  Hanae SHIMOMURA ,  Dai KUBOTA

IPC: G06F16/2453

CPC classification number: G06F16/24542

Abstract: The search means 91 searches for an optimization problem matching a specified search condition from a database that stores search information that associates first data indicating an optimization problem including an objective function and a constraint with second data indicating a feature of the optimization problem. The input means 92 accepts input of the second data as search condition.

公开(公告)号：US20240037452A1

公开(公告)日：2024-02-01

申请号：US18268664

申请日：2020-12-25

Applicant: NEC Corporation

Inventor： Riki ETO

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A function input means 91 accepts input of a reward function whose features are set to satisfy a Lipschitz continuity condition. An estimation means 92 estimates a trajectory that minimizes Wasserstein distance, which represents distance between probability distribution of a trajectory of an expert and probability distribution of a trajectory determined based on parameters of the reward function. An update means 93 updates the parameters of the reward function to maximize the Wasserstein distance based on the estimated trajectory.