CALIBRATION CURVE GENERATION METHOD, CALIBRATION CURVE GENERATION DEVICE, TARGET COMPONENT CALIBRATION METHOD, TARGET COMPONENT CALIBRATION DEVICE, ELECTRONIC DEVICE, GLUCOSE CONCENTRATION CALIBRATION METHOD, AND GLUCOSE CONCENTRATION CALIBRATION DEVICE

• US 20160103018A1
• Filed: 10/07/2015
• Published: 04/14/2016
• Est. Priority Date: 10/08/2014
• Status: Abandoned Application

• Current Assignee: Seiko Epson Corporation (Seiko Group)
• Original Assignee: Seiko Epson Corporation (Seiko Group)
• Inventors: KURASAWA, Hikaru, ARAI, Yoshifumi
• Application Number:
  US14/877,827
• Publication Number:
  US 20160103018A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G01J 3/0297 Constructional arrangements for removing other types of optical noise or for performing calibration
• CPC Class Codes: G01J 3/28 Investigating the spectrum using colour filters G01J3/51
• CPC Class Codes: G01N 21/359 using near infrared light
• CPC Class Codes: G01N 2201/1293 resolving multicomponent spectra
• CPC Class Codes: G06F 17/18 for evaluating statistical data , e.g. average values, frequency distributions, probability functions, regression analysis forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04
• CPC Class Codes: G06F 18/21342 using statistical independence, i.e. minimising mutual information or maximising non-gaussianity
• CPC Class Codes: G06V 10/143 Sensing or illuminating at different wavelengths

Abstract

A calibration curve generation method includes acquiring an independent component matrix including independent components of each sample the independent component matrix by performing first pre-processing that includes normalizing observation data, second pre-processing that includes whitening, and independent component analysis processing in order. Further, the same noise is added to the observation data related to a plurality of samples in the first pre-processing.

Claims

1. A calibration curve generation method of generating a calibration curve used for deriving a content of a target component of a subject from observation data of the subject, the method comprising:

estimating a plurality of independent components when the observation data for each sample of the subject is divided into the plurality of independent components and acquiring a mixing coefficient corresponding to the target component for each of the samples based on the plurality of independent components,

wherein the estimating of the plurality of independent components includes;

(i) acquiring an independent component matrix that includes the independent components of each of the samples;

(ii) acquiring an estimated mixed matrix indicating a set of vectors that define a ratio of independent component elements for each of the independent components in each of the samples from the independent component matrix; and

(iii) acquiring a correlation with respect to the content of the target component of the plurality of samples for each of the vectors included in the estimated mixed matrix and selecting the vector determined that the correlation is the maximum as a mixing coefficient corresponding to the target component,

Wherein the independent component matrix is acquired by performing first pre-processing that includes normalizing the observation data, second pre-processing that includes whitening, and independent component analysis processing in order, and

Wherein the same noise is added to the observation data related to the plurality of samples in the first pre-processing.

2. The calibration curve generation method according to claim 1,

wherein processing using project on null space and the normalizing are performed in order after the noise is added in the first pre-processing.

3. The calibration curve generation method according to claim 1,

wherein the adding of the noise and the normalizing are performed in order after processing using project on null space is performed in the first pre-processing.

4. A calibration curve generation device which generates a calibration curve used for deriving a content of a target component of a subject from observation data of the subject, the device comprising:

a sample observation data acquisition unit that acquires the observation data related to a plurality of samples of the subject;

a sample target component amount acquisition unit that acquires the content of the target component related to each of the samples;

a mixing coefficient estimation unit that estimates a plurality of independent components when the observation data for each of the samples is divided into the plurality of independent components and acquires a mixing coefficient corresponding to the target component for each of the samples based on the plurality of independent components; and

a regression formula calculation unit that acquires a regression formula of the calibration curve based on the content of the target component of the plurality of samples and the mixing coefficient for each of the samples,

wherein the mixing coefficient estimation unit includes;

(i) an independent component matrix calculation unit that acquires an independent component matrix including each of the independent components of each of the samples;

(ii) an estimated mixed matrix calculation unit that acquires an estimated mixed matrix indicating a set of vectors that define a ratio of independent component elements for each of the independent components in each of the samples from the independent component matrix; and

(iii) a mixing coefficient selection unit that acquires a correlation with respect to the content of the target component of the plurality of samples for each of the vectors included in the estimated mixed matrix and selecting the vector determined that the correlation is the maximum as a mixing coefficient corresponding to the target component,

Wherein the independent component matrix calculation unit acquires the independent component matrix by performing first pre-processing that includes normalizing the observation data, second pre-processing that includes whitening, and independent component analysis processing in order, and

Wherein the independent component matrix calculation unit adds the same noise to the observation data related to the plurality of samples in the first pre-processing.

5. The calibration curve generation device according to claim 4,

wherein processing using project on null space and the normalizing are performed in order after the noise is added in the first pre-processing.

6. The calibration curve generation device according to claim 4,

wherein the adding of the noise and the normalizing are performed in order after processing using project on null space is performed in the first pre-processing.

7. A target component calibration method of acquiring a content of a target component related to a subject, the method comprising:

(a) acquiring observation data related to the subject;

(b) acquiring calibration data including at least an independent component corresponding to the target component;

(c) acquiring a mixing coefficient corresponding to the target component related to the subject based on the observation data and the calibration data related to the subject; and

(d) calculating the content of the target component based on a constant of a regression formula indicating a relationship between the mixing coefficient and the content corresponding to the target component, prepared in advance, and the mixing coefficient acquired in (c) the acquiring of the mixing coefficient,

wherein first pre-processing that includes normalizing the observation data and second pre-processing that includes whitening are performed in this order in (c) the acquiring of the mixing coefficient, and

wherein noise is added to the observation data related to the subject in the first pre-processing.

8. The target component calibration method according to claim 7,

wherein processing using project on null space and the normalizing are performed in order after the noise is added in the first pre-processing.

9. The target component calibration method according to claim 7,

wherein the adding of the noise and the normalizing are performed in order after processing using project on null space is performed in the first pre-processing.

10. A target component calibration device which acquires a content of a target component related to a subject, the device comprising:

a subject observation data acquisition unit that acquires observation data related to the subject;

a calibration data acquisition unit that acquires calibration data including at least an independent component corresponding to the target component;

a mixing coefficient calculation unit that acquires a mixing coefficient corresponding to the target component related to the subject based on the observation data and the calibration data related to the subject; and

a target component amount calculation unit that calculates the content of the target component based on a constant of a regression formula indicating a relationship between the mixing coefficient and the content corresponding to the target component, prepared in advance, and the mixing coefficient acquired by the mixing coefficient calculation unit,

wherein the mixing coefficient calculation unit performs first pre-processing including normalizing the observation data and second pre-processing including whitening in this order and adds noise to the observation data related to the subject in the first pre-processing.

11. The target component calibration device according to claim 10,

wherein processing using project on null space and the normalizing are performed in order after the noise is added in the first pre-processing.

12. The target component calibration device according to claim 10,

wherein the adding of the noise and the normalizing are performed in order after processing using project on null space is performed in the first pre-processing.

13. An electronic device comprising the target component calibration device according to claim 10.

14. An electronic device comprising the target component calibration device according to claim 11.

15. An electronic device comprising the target component calibration device according to claim 12.