公开(公告)号：US20220343184A1

公开(公告)日：2022-10-27

申请号：US17640474

申请日：2019-09-18

Applicant: NEC Corporation

Inventor： So YAMADA ,  Riki ETO ,  Junko WATANABE ,  Ryota SUZUKI ,  Hiromi SHIMIZU

IPC: G06N5/02 ,  G06N5/04

Abstract: A learning apparatus acquires learning data in which odor data of each object and a label representing the object in a label space expressing features of odors are associated with each other, and learns, based on odor data, a model for predicting a label of the odor data in the label space, by using the learning data. In a data processing apparatus for processing odor data, an acquisition unit acquires odor data from an outside. A prediction unit predicts a label of the acquired odor data in the label space by using the model in which a relationship between sets of odor data and labels in the label space expressing the features of the odors is learned.

公开(公告)号：US20230110600A1

公开(公告)日：2023-04-13

申请号：US17908968

申请日：2020-03-17

Applicant: NEC Corporation

Inventor： So YAMADA ,  Junko WATANABE ,  Riki ETO ,  Hiromi SHIMIZU ,  Noriyuki TONOUCHI

IPC: G01N33/00

Abstract: In a noise removing apparatus, a data acquisition unit acquires sets of odor data measured using a sensor with respect to a plurality of objects, each set of odor data representing features of an odor of an object by respective rates of a plurality of odor molecules. A noise component extraction unit extract a noise component using a set of odor data. A noise removing unit removes the noise component from each set of odor data to be processed.

公开(公告)号：US20220018823A1

公开(公告)日：2022-01-20

申请号：US17294146

申请日：2018-11-16

Applicant: NEC Corporation

Inventor： Riki ETO ,  Hiromi SHIMIZU

IPC: G01N33/00

Abstract: An information processing apparatus (2000) acquires a feature vector (20) obtained based on signal data (14) of a detected value of a sensor (10) that senses gas to be measured. The information processing apparatus (2000) decomposes the feature vector (20) into a product of a coefficient vector and a feature matrix by using a non-negative matrix factorization (NMF). The detected value of the sensor (10) changes according to an attachment and a detachment of a molecule contained in a sensed gas. A value of each element of the feature vector (20) is equal to or greater than zero.

公开(公告)号：US20220309397A1

公开(公告)日：2022-09-29

申请号：US17618045

申请日：2019-06-19

Applicant: NEC Corporation

Inventor： So YAMADA ,  Riki ETO ,  Junko WATANABE ,  Hiromi SHIMIZU ,  Hidetaka HANE ,  Shigeo KIMURA ,  Wataru FUJII ,  Tomoyuki KAWABE

IPC: G06N20/00 ,  G01N33/02

Abstract: To mitigate degradation in the accuracy of a prediction model by re-learning the prediction model with consideration given to the characteristics of a detection value of a sensor.
This prediction model re-learning device comprises: a calculation unit that, on the basis of data related to smell detection by a sensor, calculates an index for determining whether or not to re-learn a prediction model for smell; and a re-learning unit that re-learns the prediction model in cases where the calculated index satisfies a predetermined condition.

公开(公告)号：US20220133079A1

公开(公告)日：2022-05-05

申请号：US17431848

申请日：2019-02-25

Applicant: NEC Corporation

Inventor： Yuko OHTA ,  Hiromi SHIMIZU

IPC: A47J31/52 ,  G01N33/00

Abstract: A control apparatus (10) includes a signal detection unit (110) and a data acquisition unit (120). The signal detection unit (110) acquires operation signals relating to an operation of a processing apparatus (20) that processes food and drink, and detects a specific operation signal relating to a specific operation from among the operation signals. The data acquisition unit (120) determines, based on a detection timing of the specific operation signal, a data acquisition period of an odor sensor (30) provided in the processing apparatus (20), and acquires output data being output from the odor sensor (20) during the data acquisition period.