METHOD AND SYSTEM FOR DETERMINING AN INDIVIDUAL'S STATE OF ATTENTION

• US 20110028857A1
• Filed: 08/03/2010
• Published: 02/03/2011
• Est. Priority Date: 08/03/2009
• Status: Active Grant

• Current Assignee: FICO Mirrors SA (Panasonic Holdings Corporation)
• Original Assignee: FICO Mirrors SA (Panasonic Holdings Corporation)
• Inventors: Fernandez Chimeno, Mireya, Ramos Castro, Juan Jose, Rodriguez Ibanez, Noelia, Montseny Masip, Eduard, Garcia Gonzalez, Miguel Angel, Bande Matinez, Daniel
• Granted Patent: US 8,734,359 B2
• Time in Patent Office: Days
• US Class Current: 600/529
• CPC Class Codes: A61B 5/08 Detecting, measuring or recording devices for evaluating the respiratory organs A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/16 Devices for psychotechnics using teaching or educational appliances G09B1/00 - G09B7/00; Testing reaction times ; Devices for evaluating the psychological state
• CPC Class Codes: A61B 5/165 Evaluating the state of mind, e.g. depression, anxiety
• CPC Class Codes: A61B 5/168 Evaluating attention deficit, hyperactivity
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/7239 using differentiation including higher order derivatives
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: G06F 2218/16 by matching signal segments

Abstract

The present invention relates to a method and a system designed to determine an individual'"'"'s state of attention from an individual'"'"'s respiratory signal. The method of the invention comprises a first learning step, wherein the characteristics of an individual'"'"'s normal state are determined by selecting a respiratory signal fragment that is considered to be normal according to a pre-established criterion, and a second analysis phase, wherein the individual'"'"'s state of attention is determined from parameters extracted from the respiratory signal on the basis of some pre-defined rules and the individual'"'"'s normal state previously characterised. The method of the invention is implemented in two embodiments. A first embodiment is based on the identification of pre-defined patterns in the respiratory signal and, in the second embodiment, an index indicative of the variability of the respiratory signal is defined.

Claims

1. Method for determining an individual'"'"'s state of attention, which comprises the following operational steps:

a) obtaining an individual'"'"'s respiratory signal,

b) segmenting said respiratory signal into a plurality of segments,

c) extracting at least one parameter from each segment of the respiratory signal,

d) characterising an individual'"'"'s normal state by selecting a respiratory signal fragment that is considered to be normal according to a pre-established criterion and, in the event that no respiratory signal fragment is found that meets said pre-established criterion, characterising the individual'"'"'s normal state on the basis of certain data stored in a memory device, and

e) determining the individual'"'"'s state from the at least one parameter extracted from each segment on the basis of pre-defined rules and the individual'"'"'s state characterised as normal.

2. Method for determining an individual'"'"'s state of attention, according to claim 1, characterised in that said data stored in a memory device are data pertaining to the subject him/herself and/or data for a set of subjects that statistically represent a population.

3. Method for determining an individual'"'"'s state of attention, according to claim 1 or 2, characterised in that step d) comprises:

determining the variability of the respiratory signal in the signal fragment considered, or

evaluating the degree of similarity of the respiratory signal fragment considered with respect to a model respiratory signal pattern, or

evaluating the homogeneity of certain given variables in the respiratory cycles within the respiratory signal fragment in question.

4. Method for determining an individual'"'"'s state of attention, according to any one of claims 1-3, characterised in that:

step c) comprises obtaining at least one fuzzy parameter from the at least one parameter extracted from each segment, and

step e) comprises;

evaluating the degree of similarity of each segment with respect to each one of a plurality of pre-determined phases, by comparing the at least one fuzzy parameter of each segment to characteristic parameters for said pre-determined phases, and

determining the individual'"'"'s state from the degree of similarity of the segments of the signal with respect to said pre-determined phases on the basis of certain pre-defined rules.

5. Method for determining an individual'"'"'s state of attention, according to claim 4, characterised in that the at least one parameter is selected from the group constituted by amplitude, frequency, minimum value, maximum value, amplitude symmetry and frequency symmetry.

6. Method for determining an individual'"'"'s state of attention, according to any one of claim 4 or 5, characterised in that step b), wherein the respiratory signal is segmented, comprises using a watershed relevant peak algorithm in order to reduce the amount of information to be processed.

7. Method for determining an individual'"'"'s state of attention, according to any one of claims 4-6, characterised in that at least one of the pre-determined phases is selected from the group constituted by normal respiration, low-amplitude relaxation respiration, low-frequency relaxation respiration, relaxation sigh, fatigue sigh, chaotic phase, yawning, talking, singing/humming and M pattern.

8. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

normal respiration”

phase corresponds to a normal, symmetric frequency, a normal, symmetric amplitude, a normal maximum value and a normal minimum value.

9. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

low-amplitude relaxation respiration”

phase corresponds to a normal, symmetric frequency, a low, symmetric amplitude, a normal or low maximum and a normal minimum, or a normal, symmetric frequency, a low, symmetric amplitude, a normal maximum, and a normal or high minimum.

10. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

low-frequency relaxation respiration”

phase corresponds to a low, symmetric frequency, a normal, symmetric amplitude, a normal or low maximum and a normal minimum, or a low, symmetric frequency, a normal, symmetric amplitude, a normal maximum, and a normal or high minimum.

11. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

relaxation sigh”

phase corresponds to a low frequency, a high or very high maximum, and a low or very low minimum.

12. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

fatigue sigh”

phase corresponds to a low or very low frequency, a very high, asymmetric or very asymmetric amplitude, a very high maximum, and a very low minimum.

13. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

chaotic respiration”

phase corresponds to a low or very low, asymmetric or very asymmetric frequency, a low or very low, asymmetric or very asymmetric amplitude, a normal or high maximum, and a normal or low minimum.

14. Method for determining an individual'"'"'s state of attention, according to claim 7, characterised in that the “

M pattern”

phase corresponds to a signal fragment with three consecutive minima that exhibit the following characteristics;

the left minimum is normal, the central minimum is high or very high, the right minimum is normal, the left maximum is low or normal, and the right maximum is low or normal.

15. Method for determining an individual'"'"'s state of attention, according to any of claims 1-3, characterised in that:

step e) comprises;

determining the time between successive crossings with the same slope sign of the respiratory signal with a threshold T_h obtained from the individual'"'"'s respiratory signal in a normal state,

normalising said time between successive crossings by a time T_resp corresponding to the average respiratory period of the individual'"'"'s respiratory signal in a normal state,

filtering to obtain a signal K_s, and

filtering the absolute value of the derivative of signal K_s, normalised by the value corresponding to the average absolute value of the derivative of signal K_s in the stable respiratory interval,

where threshold T_h and the average respiratory period of the individual'"'"'s respiratory signal in a normal state are obtained from the respiratory signal fragment selected to characterise the individual'"'"'s normal state, or from the data stored in the memory device, in the event that no respiratory signal fragment is found that meets said pre-established criterion.

16. Method for determining an individual'"'"'s state of attention, according to claim 15, characterised in that step e) comprises determining the individual'"'"'s state by comparing the normalised, filtered absolute value of the derivative of signal K_s to at least one threshold, and, optionally, taking into consideration the states of attention determined at previous times.

17. Method for determining an individual'"'"'s state of attention, according to claim 15 or 16, characterised in that level T_h of the stable respiratory interval is determined as a percentile of the individual'"'"'s respiratory signal in a normal state greater than 50%.

18. Method for determining an individual'"'"'s state of attention, according to any one of claims 15-17, characterised in that the determination of the individual'"'"'s respiratory signal in a normal state comprises:

calculating a statistical variable RCX_Wi for different respiratory signal fragments, and

selecting the fragment with the most stable variance, which minimises statistical variable RCX_Wi.

19. Method for determining an individual'"'"'s state of attention, according to claim 18, characterised in that statistical variable RCX_Wi is obtained from a heteroscedasticity test.

20. Method for determining an individual'"'"'s state of attention, according to claim 19, characterised in that statistical variable RCX_Wi is:

21. Method for determining an individual'"'"'s state of attention, according to any of claims 1-20, characterised in that the determination of the individual'"'"'s state of attention comprises supplementing the analysis of the respiratory signal with data obtained from a second source.

22. Method for determining an individual'"'"'s state of attention, according to any one of the preceding claims, characterised in that it comprises informing the individual of the state of attention determined.

23. Method for determining an individual'"'"'s state of attention, according to claim 22, characterised in that it comprises activating an alarm in response to the detection of a given state of attention.

24. System designed to determine an individual'"'"'s state of attention, which comprises processing means adapted to implement the steps of the method according to any one of claims 1-21.

25. System designed to determine an individual'"'"'s state of attention, according to claim 24, which comprises means for capturing a respiratory signal.

26. System designed to determine an individual'"'"'s state of attention, according to claim 24 or 25, which comprises means of interaction with the individual, in order to inform them of a given state of attention.

27. System designed to determine an individual'"'"'s state of attention, according to claim 26, wherein the means of interaction with the individual are adapted for activating an alarm in response to the detection of a state of attention.

28. Vehicle that comprises the system, according to any one of claims 24-27.

29. Computer programme that implements the steps of the method according to any one of claims 1-23.