Designation of a Characteristic of a Physical Capability by Motion Analysis, Systems and Methods

• US 20110052005A1
• Filed: 06/02/2010
• Published: 03/03/2011
• Est. Priority Date: 08/28/2009
• Status: Active Grant

• Current Assignee: Allen Joseph Selner
• Original Assignee: Allen Joseph Selner
• Inventors: Selner, Allen Joseph
• Granted Patent: US 8,139,822 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/1124 Determining motor skills
• CPC Class Codes: A61B 5/1127 using markers
• 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: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06F 18/2115 by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
• CPC Class Codes: G06V 10/771 Feature selection, e.g. selecting representative features from a multi-dimensional feature space
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G16H 20/30 relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

Motion Analysis is used to classify or rate human capability in a physical domain via a minimized movement and data collection protocol producing a discreet, overall figure of merit of the selected physical capability. The minimal protocol is determined by data mining of a more extensive movement and data collection. Protocols are relevant in medical, sports and occupational applications. Kinematic, kinetic, body type, Electromyography (EMG), Ground Reactive Force (GRF), demographic, and psychological data are encompassed. Resulting protocols are capable of transforming raw data representing specific human motions into an objective rating of a skill or capability related to those motions.

Claims

1. A method of producing a protocol comprising:

(a) accepting a time-series of values representative of parameters of a plurality of body locations on a plurality of individuals while those individuals perform a plurality of motion tasks;

(b) analyzing those values with a data mining computer program running on a computer system to effectively assign at least a portion of the plurality of individuals into one of at least two groups based upon that analyzing of the time-series values, each group being composed of individuals having a common physical attribute;

(c) identifying one or more subsets of the parameters, and of the associated body locations, and of the associated motion tasks, respectively, that collectively possess effective statistical power to assign an individual to their proper group;

further;

(d) identifying rules, that when applied to the subset of the parameters, and of the associated body locations, and of the associated motion tasks properly assigns an individual to their proper group;

(e) enumerating the subsets and rules for application to an unknown subject for effectively assigning the unknown subject to their proper group.

2. The method of claim 1 further comprising the step of measuring a time-series of values related to the position of a plurality of body regions on at least one individual.

3. The method of claim 1 where the physical capability is related to a sport skill.

4. The method of claim 2 where the physical capability is related to a medical condition.

5. The method of claim 2 wherein the step of measuring comprises tracking a plurality of body positions by three-dimensional image video recording.

6. The method of claim 2 wherein the step of measuring comprises measurements representative of joint angles.

7. The method of claim 1 wherein the at least two groups comprise a group of individuals with back pain and a group of individuals feigning back pain.

8. The method of claim 1 further comprising:

(i.) accepting a time-series of values representative of at least a portion of the enumerated parameters taken from a subject performing at least a portion of the enumerated motion tasks;

(j) analyzing the accepted values according to at least a portion of the enumerated rules;

(k.) assigning the subject to a group based upon the analyzing of that subjects'"'"' accepted values.

9. A method of producing a protocol for assessing a given aspect of a human'"'"'s physical performance comprising the steps of:

a. measuring, and recording in non-transient computer readable memory, human movement parameters from a series of performed movements for a set of human subjects, each subject respectively having a known capability in the given aspect of physical performance;

b. data mining, using an electronic computer executing a data mining application program, to identify correlations between the subjects'"'"' recorded movement parameters and their respective known capability in the given domain;

c. identifying a sensitive subset of the movement parameters, such that the sensitive subset collectively has adequate statistical correlative power to predict the known capabilities at a predetermined confidence level;

d. determining, from the data mining results, criteria for ascribing one or more distinct capability designations in the given aspect of physical performance to an unknown subject based upon that unknown subject'"'"'s performance on the identified subset of movements;

e. enumerating the identified subset of movements and their respective parameters, and enumerating the determined criteria and their respective designations of degree of physical performance, thereby producing an assessment protocol.

10. The method of claim 9 wherein the given aspect of physical performance relates to a game.

11. The method of claim 9 in which said data mining comprises a non-linear data clustering technique.

12. The method of claim 9 in which said data mining comprises a linear statistical hypothesis testing technique.

13. The method of claim 9 in which said data mining comprises an artificial neural net technique.

14. The method of claim 9 further comprising:

determining relevant human movement parameters to be measured and the associated specific movements to be performed while measuring, for a given aspect of human physical performance.

15. The method of claim 9 wherein the at least one of the one or more distinct capability designations is an ordinal value.

16. The method of claim 9 wherein at least one of the one or more distinct capability designations is a scalar value.

17. The method of claim 9 wherein measuring and recording parameters comprise real-time position measurements of at least two predetermined body locations.

18. A method of rating a given physical capability of a human, comprising:

ascribing a rating to a given motion-related physical capability of a subject by analyzing a time-series of information representing the relative motion between at least two predetermined points, each respectively related to the subject'"'"'s body position, while that subject performs a predetermined motion task;

wherein a point related to the subject'"'"'s body position is either a specific location on the body, or optionally, a location on an article in contact with the body;

further, the ascribed rating is determined by detecting a similarity between the time-series of information and time-series information from corresponding measurements made on one or more individuals performing the predetermined motion task;

the similarity criteria for ascribing a rating being based upon predetermined rules.

19. The method of claim 18 further comprising the steps of measuring and storing real-time data from which the time-series of information representing the relative motion between at least two points while that subject performs a predetermined motion task is derived.

20. The method of claim 19 wherein the measuring and storing are performed at a distinct geographic location from that where at least one of the analyzing, detecting and ascribing steps are preformed.

21. The method of claim 18 wherein at least one predetermined rule comprises at least one factor of substantial weight that is representative of rate of acceleration.

22. The method of claim 18 wherein at least one predetermined rule comprises at least one factor of substantial predetermined weight that is representative of comparison of a dynamic angular relationship of one body portion to another body portion.

23. The method of claim 18 wherein the predetermined motion tasks do not substantially consist of a sequence of motions normally performed in demonstrating the given physical capability.

24. The method of claim 18 wherein at least one rating signifies a high probability of back pain and another rating signifies a high probability of feigning back pain.

25. A protocol for assessing a degree of human capability in a given physical activity domain comprising the steps of:

a. instrumenting the human to allow measuring a predetermined set of movement parameters;

b. performing, by the instrumented human, a predetermined set of movements;

c. measuring and storing on a computer readable media, movement information derived from the instrumenting during the performing;

d. pre-processing the stored information into a form suitable for comparing;

e. comparing pre-processed information to predetermined criteria;

the predetermined criteria previously derived from tests conducted on a variety of humans with known capabilities in the domain;

f. assigning to the human, a designation of capability in the physical activity domain based on the results of the comparing to predetermined criteria.

26. The method of claim 25 wherein the designation of capability represents an overall figure of merit of the capability of the subject in the given domain.

27. The method of claim 25 wherein the steps of instrumenting and performing occur at a location distinct from that of the steps of comparing and assigning.

28. The method of claim 25 wherein the instrumenting comprises placing accelerometers in proximity to the subject'"'"'s body.

29. The method of claim 25 wherein the instrumenting comprises configuring video imaging to track portions of the subject'"'"'s body.

30. The method of claim 29 wherein portions of the subject'"'"'s body are marked to facilitate their identification and tracking by video imaging.

31. A method of associating a discrete designation to a given physical capability of a subject, comprising:

a) a step for accepting data that effectively characterize the movement of two or more of a subject'"'"'s body portions in relation to each other, while the subject performs a series of motions indicated by predetermined rules;

b) a step for assessing a degree of similarity of the subject'"'"'s characterized movement with respect to comparable characterizations of comparable movements made by a plurality of individuals;

the individuals each having respective designations in the given physical capability;

c) a step for associating a discrete designation to a given physical capability of a subject based upon said step for assessing.

32. The method of claim 31 wherein said step for accepting data comprises recording a force measurement between the body and an object.

33. The method of claim 31 wherein said step for accepting data comprises recording electrical activity readings of at least two related muscles.

34. The method of claim 31 wherein said step for acquiring data comprises position tracking of at least two body portions.

35. A system for transforming human motion data into an objective rating comprising:

a. at least one of;

one or more motion sensors, one or more angle sensors, and one or more pressure sensors for instrumenting a human performing one or more motions;

b. a first computer communicatively coupled to said sensors, said computer adapted to receive data representative of motion from said sensors;

the first computer is programmed to capture, store and pre-process the data received from sensors;

c. a second computer communicatively couplable to said first computer;

said second computer programmed for analyzing the pre-processed motion data in light of a plurality of pre-collected data motion from known subjects, said analysis to produce a discrete result indicative of a level of performance.

36. The system of claim 35 such that said second computer is operationally locatable other than proximate to the location of the subject'"'"'s performance.

37. The system of claim 35 wherein said first computer further comprises programming to store video images of the human performing the one or more motions;

and said second computer accepts and stores image information regarding the performance of the one or more motions.

38. A non-transient computer-readable medium containing instructions executable by a computer, said instructions directing the steps of:

a) accepting movement and force information representative of a human performing a series of movement tasks;

b) processing the movement and force information to extract biomechanical information;

c) comparing the biomechanical information for an effective match with data representative of biomechanical information related to a plurality of comparable movement tasks performed by a plurality of subjects, the subjects each respectively, having a known rating of a common physical capability;

d) assigning a designation of capability to the human according to detecting an effective match between the human'"'"'s biomechanical information and that of one or more of the subjects, an effective match being determined by predetermined criteria.

39. The non-transient computer-readable medium of claim 38 wherein the instructions executable on a computer further comprise:

the comparing step includes effective match criteria based on cluster analysis.