Mobility normalizer, normalizing method, normalizing program, self-organized map, substance detecting method, detecting program, detection rule creating method, and data structure

• US 7,991,569 B2
• Filed: 07/11/2006
• Issued: 08/02/2011
• Est. Priority Date: 11/17/2005
• Status: Expired due to Fees

• Current Assignee: Kochi University
• Original Assignee: Kochi University
• Inventors: Kataoka, Hiromi
• Primary Examiner(s): Nghiem; Michael P
• Assistant Examiner(s): Suarez; Felix E
• Application Number:
  US12/084,370
• Publication Number:
  US 20090136139A1
• Time in Patent Office: 1,848 Days
• Field of Search: 702/30, 702/35, 702/63, 702/66, 702/73, 702/150, 702/176, 702/179, 250/282, 382/124, 382/129, 600/509
• US Class Current: 702/66
• CPC Class Codes: G01N 27/44717 Arrangements for investigating the separated zones, e.g. localising zones
• CPC Class Codes: G01N 30/8644 Data segmentation, e.g. time windows
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06F 2218/02 Preprocessing

Abstract

The object of the present invention is to provide an apparatus, a method, a program, and a self-organizing map which are capable of normalizing mobility without using a marker, as well as a substance detection method, a program, a detection rule creating method, and a data structure which use normalized mobility. The mobility normalizing method comprises the steps of determining a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility, to the respective plurality of reference waveform data sets, and a DTW distance associated with each warping function; evaluating a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance; determining a slope and an intercept of a straight line approximating the determined warping function; and correcting the data to be corrected using a linear function specified by the slope and the intercept.

Claims

1. A mobility normalizing apparatus comprising:

a recording unit containing a plurality of reference waveform data sets; and

a processing unit;

wherein the processing unit

defines the measurement data as data to be corrected, when externally acquired mobility measurement data is unit time sequence data;

interpolates a plurality of two-dimensional data sets to create the data to be corrected, the data to be corrected being unit time sequence data, when externally acquired mobility measurement data is the plurality of two-dimensional data sets associated with time information and measured values;

reads the plurality of reference waveform data sets from the recording unit, and determines a plurality of warping functions converting the data to be corrected to the respective plurality of reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

evaluates a minimum value of the plurality of DTW distances, and determines the warping function associated with the determined minimum DTW distance;

determines a slope and an intercept of a straight line approximating the determined warping function; and

corrects the data to be corrected using a linear function specified by the slope and the intercept and obtains a normalized data; and

wherein

the mobility measurement data is obtained from mobility measurement of an analytical target without mixing a marker substance into a sample.

2. The mobility normalizing apparatus according to claim 1, wherein the processing unit calculates a slope between given vertices for each determined warping function, excludes slopes included in predetermined areas at both ends when the plurality of slopes between vertices are arranged in order of increasing size, and determines the slope of the straight line approximating the warping function based on the slopes between vertices which are not excluded.

3. The mobility normalizing apparatus according to claim 2, wherein the processing unit determines a median of the plurality of slopes between vertices as the slope of the straight line approximating the warping function.

4. The mobility normalizing apparatus according to claim 1, wherein the plurality of reference waveform data sets are data obtained by correcting mobility measurement data for an analyte containing a marker substance, using the mobility of the marker substance.

5. The mobility normalizing apparatus according to claim 1, wherein the plurality of reference waveform data sets are data forming a self-organizing map created using a plurality of mobility measurement data sets.

6. A mobility normalizing method comprising:

a first step of determining, in a processor device, a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample, to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

a second step of evaluating, in the processor device, a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

a third step of determining, in the processor device, a slope and an intercept of a straight line approximating the determined warping function; and

a fourth step of correcting, in the processor device, the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data.

7. The mobility normalizing method according to claim 6, wherein the data obtained by measuring mobility is a plurality of two-dimensional data sets associated with time information and measured values;

and wherein

the data to be corrected is unit time sequence data created by interpolating the plurality of two-dimensional data sets.

8. The mobility normalizing method according to claim 6, wherein the third step comprises:

a fifth step of calculating, in the processor device, a slope between given vertices for each warping function determined in the second step; and

a sixth step of excluding, in the processor device, slopes included in predetermined areas at both ends when the plurality of slopes between vertices are arranged in order of increasing size, and determining the slope of the straight line approximating the warping function based on the slopes between vertices which are not excluded.

9. The mobility normalizing method according to claim 8, wherein the sixth step is a step of determining, in the processor device, a median of the plurality of slopes between vertices as the slope of the straight line approximating the warping function.

10. The mobility normalizing method according to claim 6, wherein the plurality of given reference waveform data sets are data obtained by correcting mobility measurement data for an analyte containing a marker substance, using the mobility of the marker substance.

11. The mobility normalizing method according to claim 6, wherein the plurality of given reference waveform data sets are data forming a self-organizing map created using a plurality of mobility measurement data sets.

12. A non-transitory computer-readable recording medium containing instructions for a mobility normalizing program stored therein, wherein a processor device comprises a recording unit containing a plurality of reference waveform data sets, and a processing unit;

the instructions for causing the processing unit to perform the steps of;

determining a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample, to the respective plurality of reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

evaluating a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

determining a slope and an intercept of a straight line approximating the determined warping function; and

correcting the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data.

13. A non-transitory computer-readable recording medium containing instructions for a self-organizing map stored therein, the instructions for performing, on a processor device:

using the self-organizing map as the reference waveform data in

a first step of determining, in a processor device, a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample, to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

a second step of evaluating, in the processor device, a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

a third step of determining, in the processor device, a slope and an intercept of a straight line approximating the determined warping function; and

a fourth step of correcting, in the processor device, the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data,

wherein the self-organizing map comprises typical waveform data sets; and

creating the self-organizing map by a learning process executed by the processor device till the typical waveform data sets are extracted by performing self-organizing map clustering of waveform data obtained by visually correcting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analyte not containing a marker substance, or by performing self-organizing map clustering of waveform data obtained by correcting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analyte containing the marker substance, based on the mobility of the marker substance.

14. A processor-implemented substance detection method comprising:

using, in a processor device, a decision tree determined as a detection rule by learning that uses supervised data;

determining, in the processor device, the decision tree by learning that performs;

obtaining normalized data by correcting a plurality of mobility measurement data sets for a plurality of analytes not containing a marker substance, using

a first step of determining the processor device, a plurality of functions converting data to be corrected, which time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample, to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

a second step of evaluating, in the processor device, a minimum vale of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

a third step of determining, in the processor device, a slope and an intercept of a straight e approximating the determined warping function; and

a fourth step of correcting, in the processor device, the data to be corrected using a linear function specified b the slope and the intercept and obtaining a normalized data;

wherein the supervised data includes information representing the presence or absence of a given substance, which is associated with each measurement data set.

15. A non-transitory computer-readable recording medium containing instructions of a substance detection program stored therein for causing a processor device to perform a function of detecting a substance, the instructions for implementing the steps of:

using a decision tree determined as a detection rule by learning that uses supervised data;

determining the decision tree by learning that performs;

obtaining normalized data by correcting a plurality of mobility measurement data sets for a plurality of analytes not containing a marker substance, using

a first step of determining a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DIV) distance associated with each warping function;

a second step of evaluating a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

a third step of determining a slope and an intercept of a straight line approximating the determined warping function; and

a fourth step of correcting the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data;

wherein the supervised data includes information representing the presence or absence of a given substance, which is associated with each measurement data set.

16. A processor device-implemented method for creating a detection rule for use in detecting a substance, the method comprising:

a first step of using a processor device to correct a plurality of mobility measurement data sets for a plurality of analytes not containing a marker substance, using the following steps to create normalized data;

a step of determining, in the processor device, a plurality of warping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DTW) distance associated with each warping function;

a step of evaluating, in the processor device, a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTW distance;

a step of determining, in the processor device, a slope and an intercept of a straight tine approximating the determined warping function; and

a step of correcting, in the processor device the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data; and

a second step of determining, in the processor device, a decision tree as a detection rule by learning, using supervised data including information representing the presence or absence of a given substance, which is associated with each measurement data set, and the normalized data.

17. A non-transitory computer-readable recording medium containing instructions of a data structure for being used as a substance detection rule, the instructions when executed on a processor device implement the steps of:

representing the data structure as a decision tree determined by learning that performs;

obtaining normalized data by correcting a plurality of mobility measurement data sets for a plurality of analytes not containing a marker substance, using

a first step of determining a plurality of Tarping functions converting data to be corrected, which is unit time sequence data obtained by measuring mobility of an analytical target without mixing a marker substance into a sample, to respective plurality of given reference waveform data sets, and a Dynamic Time Warping (DTW distance associated with each warping function;

a second step of evaluating a minimum value of the plurality of DTW distances, and determining the warping function associated with the determined minimum DTNAT distance;

a third step of determining a slope and an intercept of a straight line approximating the determined warping function; and

a fourth step of correcting the data to be corrected using a linear function specified by the slope and the intercept and obtaining a normalized data;

detecting a presence or absence of a given substance based on supervised data, the supervised data including information representing the presence or absence of a given substance, which is associated with each measurement data set.