Information processing apparatus, control method, and non-transitory storage medium

Patent metadata

Field	Value
Publication number	US-12044667-B2
Application number	US-201817262955-A
Country	US
Kind code	B2
Filing date	Jul 31, 2018
Priority date	Jul 31, 2018
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

An information processing apparatus (2000) acquires time-series data (14) output by a sensor (10) and computes a plurality of feature constants θi and a contribution value ξi representing contribution with respect to the time-series data (14) for each feature constant θi. Thereafter, the information processing apparatus (2000) outputs information in which a set Θ of the feature constants θi and a set Ξ of the contribution values ξi are associated with each other 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.

First claim

The invention claimed is:

1. An information processing apparatus comprising:
at least one non-transitory memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
acquiring time-series data of detected values output from a sensor according to attachment and detachment of a molecule contained in a target gas containing a plurality of molecules of different types, wherein the sensor outputs the detected values based on changes in physical quantities of a member of the sensor that occur in response to the attachment and detachment of the molecule with respect to a receptor;
computing a plurality of feature constants regarding the time-series data and a contribution value representing a magnitude of contribution for each feature constant with respect to the time-series data; and
outputting a combination of the plurality of feature constants and the contribution values as a feature value of the target gas sensed by the sensor, wherein
each feature constant is a time constant or a velocity constant related to a magnitude of a temporal change of a number of molecules attached to the sensor, such that a feature the target gas is extracted from the detected values output from the sensor even though the plurality of molecules are of different types,
computing the plurality of feature constants and the contribution value for each feature constant comprises:
computing time-series vector data having, as elements, the detected values at a respectively plurality of times and a temporal change rate of the detected values at the respective plurality of, by using the time-series data;
computing a velocity vector for the computed time-series vector data;
extracting a plurality of partial periods from a measurement period of the time-series data based on a direction of the velocity vector; and
computing the feature constant for each of the partial periods based on the direction of the velocity vector in the partial period, and

the partial period is a period in which the direction of the velocity vector throughout the partial period is substantially the same.

2. The information processing apparatus according to claim 1 , wherein
computing the plurality of feature constants and the contribution value for each feature constant comprises computing the contribution value for each feature constant by performing, for a prediction model of a respective detected value of the sensor with the contribution value as a parameter, a parameter estimation that uses the acquired time-series data.

3. The information processing apparatus according to claim 2 , wherein
computing the plurality of feature constants and the contribution value for each feature constant comprises computing the contribution value for each feature constant by performing, for time-series data obtained from the prediction model and the acquired time-series data, a maximum likelihood estimation that uses a least squares method.

4. The information processing apparatus according to claim 3 , wherein
in the maximum likelihood estimation in the least squares method, a regularization term is included in an objective function.

5. The information processing apparatus according to claim 2 , wherein
computing the plurality of feature constants and the contribution value for each feature constant comprises computing the contribution value for each feature constant by using a Maximum a Posteriori (MAP) estimation or a Bayesian estimation that uses a prior distribution of each of the contribution value and the acquired time-series data.

6. The information processing apparatus according to claim 5 , wherein
the prior distribution is a multivariate normal distribution or a Gaussian process.

7. The information processing apparatus according to claim 2 , wherein
computing the plurality of feature constants and the contribution value for each feature constant comprises minimizing a minimum value of an objective function with respect to the plurality of feature constants for the objective function that represents a square error between the time-series data obtained from the prediction model and the acquired time-series data.

8. The information processing apparatus according to claim 2 , wherein
the prediction model contains a parameter that represents a bias, and
computing the plurality of feature constants and the contribution value for each feature constant comprises estimating parameters that each represent the contribution value and the bias for the prediction model.

9. The information processing apparatus according to claim 1 , wherein
acquiring the time-series data comprises acquiring a plurality of time-series data,
computing the plurality of feature constants and the contribution value for each feature constant comprises computing a group of a set of the feature constants and a set of the contribution values for each of the plurality of time-series data, and
outputting the combination of the plurality of feature constants and the contribution values comprises outputting information obtained by combining the computed group for each of the plurality of time-series data, as the feature value of the target gas.

10. The information processing apparatus according to claim 9 , wherein
the plurality of time-series data include both
time-series data obtained when the sensor is exposed to the target gas, and
time-series data obtained when the target gas is removed from the sensor.

11. The information processing apparatus according to claim 9 , wherein
the plurality of time-series data include time-series data obtained from each of a plurality of the sensors having different characteristics.

12. The information processing apparatus according to claim 1 , wherein the sensor has a functional membrane to which the molecule is attached as the receptor, and stress generated in a supporting member of the functional membrane is changed due to the attachment and detachment of the molecule with respect to the functional membrane.

13. A control method executed by a computer, the method comprising:
acquiring time-series data of detected values output from a sensor according to attachment and detachment of a molecule contained in a target gas containing a plurality of molecules of different types, wherein the sensor outputs the detected values based on changes in physical quantities of a member of the sensor that occur in response to the attachment and detachment of the molecule with respect to a receptor;
computing a plurality of feature constants regarding the time-series data and a contribution value representing a magnitude of contribution for each feature constant with respect to the time-series data; and
outputting a combination of the plurality of feature constants and the contribution values as a feature value of the target gas sensed by the sensor, wherein
each feature constant is a time constant or a velocity constant related to a magnitude of a temporal change of a number of molecules attached to the sensor, such that a feature the target gas is extracted from the detected values output from the sensor even though the plurality of molecules are of different types,
computing the plurality of feature constants and the contribution value for each feature constant comprises:
computing time-series vector data having, as elements, the detected values at a respectively plurality of times and a temporal change rate of the detected values at the respective plurality of, by using the time-series data;
computing a velocity vector for the computed time-series vector data;
extracting a plurality of partial periods from a measurement period o

Assignees

• Nec Corp

Inventors

• Suzuki Ryota
• Eto Riki

Classifications

• G01N1/24

  Suction devices {(G01N1/22 - G01N1/2294 take precedence)} · CPC title

• G01N33/0031

  comprising two or more sensors, e.g. a sensor array · CPC title

• G01N33/0016

  by regulating a physical variable, e.g. pressure or temperature · CPC title

• G01N33/0009

  General constructional details of gas analysers, e.g. portable test equipment (devices for withdrawing samples in the gaseous state G01N1/22) · CPC title

• G01N33/0027

  concerning the detector · CPC title