Method and apparatus for analysis of variables

• US 7,242,808 B2
• Filed: 01/12/2004
• Issued: 07/10/2007
• Est. Priority Date: 08/04/2000
• Status: Expired due to Term

• Current Assignee: Alexei V. Nikitin, Ruslan L. Davidchack
• Original Assignee: Alexei V. Nikitin, Ruslan L. Davidchack
• Inventors: Nikitin, Alexei V., Davidchack, Ruslan L.
• Primary Examiner(s): Grant, II; Jerome
• Application Number:
  US10/755,956
• Publication Number:
  US 20040158592A1
• Time in Patent Office: 1,275 Days
• Field of Search: 382/265, 382/260, 382/210, 382/156, 382/157, 382/160, 382/261, 382/262, 382/263, 382/264
• US Class Current: 382/210
• CPC Class Codes: G01D 1/00 Measuring arrangements giving results other than momentary value of variable, of general application G01D3/00 takes precedence; in tariff metering apparatus G01D4/00; transducers not specially adapted for a specific variable G01D5/00
• CPC Class Codes: G06F 2218/02 Preprocessing
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G10L 25/48 specially adapted for particular use
• CPC Class Codes: H03H 11/0405 Non-linear filters

Abstract

Various components of the present invention are collectively designated as Analysis of Variables Through Analog Representation (AVATAR). It is a method, processes, and apparatus for measurement and analysis of variables of different type and origin. AVATAR offers an analog solution to those problems of the analysis of variables which are normally handled by digital means. The invention allows (a) the improved perception of the measurements through geometrical analogies, (b) effective solutions of the existing computational problems of the order statistic methods, and (c) extended applicability of these methods to analysis of variables.

The invention employs transformation of discrete or continuous variables into normalized continuous scalar fields, that is, into objects with mathematical properties of density and/or cumulative distribution functions. In addition to dependence on the displacement coordinates (thresholds), these objects can also depend on other parameters, including spatial coordinates (e.g., if the incoming variables are themselves scalar or vector fields), and/or time (if the variables depend on time). Moreover, this transformation of the measured variables may be implemented with respect to any reference variable. Thus, the values of the reference variable provide a common unit, or standard, for measuring and comparison of variables of different natures, for assessment of mutual dependence of these variables, and for evaluation of changes in the variables and their dependence with time.

The invention enables, on a consistent general basis, a variety of new techniques for analysis of variables, which can be implemented through various physical means in continuous action machines as well as through digital means or computer calculations. Several of the elements of these new techniques do have digital counterparts, such as some rank order techniques in digital signal and image processing. However, this invention significantly extends the scope and applicability of these techniques and enables their analog implementation. The invention also introduces a wide range of signal analysis tools which do not exist, and cannot be defined, in the digital domain. In addition, by the present invention, all existing techniques for statistical processing of data, and for studying probability fluxes, are made applicable to analysis of any variable.

Claims

1. A method for analysis of variables operable to transform an input variable into an output variable comprising the following steps:

(a) applying a Threshold Filter to a difference of a Displacement Variable and an input variable producing a first scalar field of said Displacement Variable; and

(b) filtering said first scalar field of step (a) with a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function to produce a second scalar field of said Displacement Variable.

2. A method for analysis of variables operable to transform an input variable into an output variable as recited in claim 1 further comprising the step:

modulating said first scalar field of step (a) by a Modulating Variable producing a modulated first scalar field of said Displacement Variable.

3. A method for analysis of variables as recited in claim 2 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input variable.

4. A method for analysis of variables as recited in claim 3 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

5. A method for analysis of variables as recited in claim 2 further comprising the step:

dividing said second scalar field of step (b) by said Modulating Variable where said Modulating Variable has been first filtered with a second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function.

6. A method for analysis of variables as recited in claim 5 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input variable.

7. A method for analysis of variables as recited in claim 6 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

8. A method for analysis of variables as recited in claim 5 wherein said Threshold Filter is a Discriminator and said Modulating Variable is a norm of a first time Derivative of the input variable.

9. A method for analysis of variables as recited in claim 8 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

10. A method for analysis of variables as recited in claim 5 wherein said Threshold Filter is a first Probe and where said second scalar field of step (b) is a Modulated Threshold Density.

11. A method for analysis of variables as recited in claim 10 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

12. A method for analysis of variables as recited in claim 10 further comprising the following steps:

(a) applying a second Probe to a difference between a feedback of a Quantile Density variable and said Modulated Threshold Density producing a first function of said Quantile Density variable;

(b) multiplying said first function of Quantile Density of step (a) by said Modulated Threshold Density producing a first modulated function of Quantile Density;

(c) filtering said first modulated function of Quantile Density of step (b) with a first Time Averaging Filter producing a first time averaged modulated function of Quantile Density;

(d) integrating said first time averaged modulated function of step (c) over the values of said Displacement Variable producing a first threshold integrated function of Quantile Density;

(e) applying a first Discriminator to the difference between the feedback of said Quantile Density variable and said Modulated Threshold Density variable wherein said first Discriminator is a respective discriminator of said second Probe producing a second function of said Quantile Density variable;

(f) subtracting a quantile value and said second function of Quantile Density of step (g) from a unity and multiplying the difference by said Modulated Threshold Density producing a second modulated function of Quantile Density;

(g) filtering said second modulated function of Quantile Density of step (f) with a second Time Averaging Filter wherein the impulse response of said second Time Averaging Filter is a first derivative of the impulse response of said first Time Averaging Filter producing a second time averaged modulated function of Quantile Density;

(h) integrating said second averaged modulated function of step (g) over the values of said Displacement Variable producing a second threshold integrated function of Quantile Density; and

(i) dividing said second threshold integrated function of step (h) by said first threshold integrated function of step (d) and time-integrating the quotient to output said Quantile Density variable.

13. A method for analysis of variables as recited in claim 12 further comprising the step:

applying a second Discriminator to the difference of said Modulated Threshold Density and said Quantile Density variable to output a Quantile Domain Factor variable.

14. A method for analysis of variables as recited in claim 13 further comprising the step:

integrating said Quantile Domain Factor variable over the values of said Displacement Variable to output a Quantile Volume variable.

15. A method for analysis of variables as recited in claim 5 wherein said Threshold Filter is a Discriminator.

16. A method for analysis of variables as recited in claim 15 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

17. A method for analysis of variables as recited in claim 1 wherein said Threshold Filter is a first Probe and where said second scalar field of step (b) is an Amplitude Density.

18. A method for analysis of variables as recited in claim 17 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

19. A method for analysis of variables as recited in claim 17 further comprising the following steps:

(a) applying a second Probe to a difference between a feedback of a Quantile Density variable and said Amplitude Density producing a first function of said Quantile Density variable;

(b) multiplying said first function of Quantile Density of step (a) by said Amplitude Density producing a first modulated function of Quantile Density;

(c) filtering said first modulated function of Quantile Density of step (b) with a first Time Averaging Filter producing a first time averaged modulated function of Quantile Density;

(d) integrating said first time averaged modulated function of step (c) over the values of said Displacement Variable producing a first threshold integrated function of Quantile Density;

(e) applying a first Discriminator to the difference between the feedback of said Quantile Density variable and said Amplitude Density wherein said first Discriminator is a respective discriminator of said second Probe producing a Second function of said Quantile Density variable;

(f) subtracting a quantile value and said second function of Quantile Density of step (e) from a unity and multiplying the difference by said Amplitude Density producing a second modulated function of Quantile Density;

(g) filtering said second modulated function of Quantile Density of step (f) with a second Time Averaging Filter wherein the impulse response of said second Time Averaging Filter is a first derivative of the impulse response of said first Time Averaging Filter producing a second time averaged modulated function of Quantile Density;

(h) integrating said second time averaged modulated function of step (g) over the values of said Displacement Variable producing a second threshold integrated function of Quantile Density; and

(i) dividing said second threshold integrated function of step (h) by said first threshold integrated function of step (d) and time-integrating the quotient to output said Quantile Density variable.

20. A method for analysis of variables as recited in claim 19 further comprising the step:

applying a second Discriminator to the difference of said Amplitude Density and said Quantile Density variable to output a Quantile Domain Factor variable.

21. A method for analysis of variables as recited in claim 20 further comprising the step:

integrating said Quantile Domain Factor variable over the values of said Displacement Variable to output a Quantile Volume variable.

22. A method for analysis of variables as recited in claim 1 wherein said Threshold Filter is a Discriminator.

23. A method for analysis of variables as recited in claim 22 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

24. A method for Rank Normalization of an input variable with respect to a reference variable comprising the following steps:

(a) applying a Discriminator to a difference of a Displacement Variable and a reference variable producing a first scalar field of said Displacement Variable;

(b) filtering said first scalar field of step (a) with a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function to produce a second scalar field of said Displacement Variable;

(c) applying a Probe to a difference of said Displacement Variable and an input variable producing a third scalar field of said Displacement Variable; and

(d) multiplying said third scalar field of step (c) by said second scalar field of step (b) and integrating the product over the values of said Displacement Variable to output a Rank Normalized variable.

25. A method for Rank Normalization of an input variable with respect to a reference variable as recited in claim 24 wherein the reference variable is analogous to the input variable.

26. A method for Rank Normalization of an input variable with respect to a reference variable as recited in claim 24 further comprising the following steps:

(a) modulating said first scalar field of step (a) by a Modulating Variable; and

(b) dividing said second scalar field variable of step (b) by said Modulating Variable where said Modulating Variable has been first filtered with a second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function.

27. A method for Rank Normalization of an input variable with respect to a reference variable as recited in claim 26 wherein the reference variable is analogous to the input variable.

28. A method for analysis of variables operable to transform an input variable into an output variable comprising the following steps:

(a) applying a Probe to a difference of a Displacement Variable and a reference variable producing a first scalar field of said Displacement Variable;

(b) modulating said first scalar field of step (a) by an input variable producing a modulated first scalar field of said Displacement Variable;

(c) filtering said modulated first scalar field of step (b) with a first Averaging Filter to produce a second scalar field of said Displacement Variable where said first Averaging Filter is operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function; and

(d) dividing said second scalar field of step (c) by said first scalar field of step (a) where said first scalar field has been first filtered with a second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function producing an output variable.

29. A method for analysis of variables operable to transform an input variable into an output variable comprising the following steps:

(a) applying a first Probe to a difference of a Displacement Variable and an input variable producing a first scalar function of said Displacement Variable;

(b) filtering said first scalar function of step (a) with a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function to produce a first averaged scalar function of said Displacement Variable;

(c) applying a Discriminator to the difference of said Displacement Variable and the input variable wherein said Discriminator is a respective discriminator of said first Probe producing a second scalar function of said Displacement Variable;

(d) filtering said second scalar function of step (c) with a second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function producing a second averaged scalar function of said Displacement Variable;

(e) applying a second Probe to a difference of a quantile value and said second averaged scalar function of step (d) wherein the width parameter of said second Probe is substantially smaller than unity producing an output of the second Probe; and

(f) multiplying said output of the second Probe of step (e) by said first averaged scalar function of step (b) and by said Displacement Variable and integrating the product over the values of said Displacement Variable to produce an output variable.

30. A method for analysis of variables operable to transform an input variable into an output variable as recited in claim 29 wherein said first scalar function of step (a) and said second scalar function of step (c) are modulated by a Modulating Variable further comprising the step:

dividing said first averaged scalar function of step (b) and said second averaged scalar function of step (d) by said Modulating Variable where said Modulating Variable has been first filtered with a third Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function.

31. A method for analysis of variables as recited in claim 30 wherein said Modulating Variable is an absolute value of a first time derivative of the input Variable.

32. A method for analysis of variables operable to transform an input scalar field variable into an output variable comprising the following steps:

(a) applying a Probe to a difference between a feedback of an output variable and an input variable producing a first scalar function of said output variable;

(b) filtering said first scalar function of step (a) with a first Averaging Filter operable to perform time and spatial averaging of said first scalar function producing a first averaged scalar function of said output variable;

(c) applying a Discriminator to the difference between the feedback of said output variable and the input variable wherein said Discriminator is a respective discriminator of said Probe producing a second scalar function of said output variable;

(d) subtracting said second scalar function of step (c) from a quantile value and filtering the difference with a second Averaging Filter wherein the impulse response of said second Averaging Filter is a first time derivative of the impulse response of said first Averaging Filter producing a second averaged scalar function of said output variable; and

(e) dividing said second averaged scalar function of step (d) by said first averaged scalar function of step (b) and time-integrating the quotient to output said output variable.

33. A method for analysis of variables as recited in claim 32 wherein the width parameter of said Discriminator and the respective Probe is indicative of variability of said Rank Filtered variable.

34. A method for analysis of variables operable to transform an input scalar field variable into an output variable comprising the following steps:

(a) applying a Probe to a difference between a feedback of an output variable and an input variable producing a first scalar function of said output variable where said first scalar function is modulated by a Modulating Variable;

(b) filtering said first scalar function of step (a) with a first Averaging Filter operable to perform time and spatial averaging of said first scalar function producing a first averaged scalar function of said output variable;

(c) applying a Discriminator to the difference between the feedback of said output variable and the input variable wherein said Discriminator is a respective discriminator of said Probe producing a second scalar function of said output variable;

(d) subtracting said second scalar function of step (c) from a quantile value and filtering the difference with a second Averaging Filter wherein said difference between said quantile value and said second scalar function is modulated by said Modulating Variable and wherein the impulse response of said second Averaging Filter is a first time derivative of the impulse response of said first Averaging Filter producing a second averaged scalar function of said output variable; and

(e) dividing said second averaged scalar function of step (d) by said first averaged scalar function of step (b) and time-integrating the quotient to output said output variable.

35. A method for analysis of variables as recited in claim 34 wherein said Modulating Variable is an absolute value of a first time derivative of the input variable.

36. A method for analysis of variables as recited in claim 35 wherein the width parameter of said Discriminator and the respective Probe is indicative of variability of said Rank Filtered variable.

37. A method for analysis of variables as recited in claim 34 wherein the width parameter of said Discriminator and the respective Probe is indicative of variability of said Rank Filtered variable.

38. A method for analysis of variables operable to transform an input variable into an output variable comprising the following steps:

(a) applying a Probe to a difference between a feedback of an output variable and an input variable producing a first scalar function of the output variable;

(b) filtering said first scalar function of step (a) with a Time Averaging Filter having an exponentially forgetting impulse response and a first Spatial Averaging Filter operable on the spatial coordinates of the input variable producing a first averaged scalar function of the output variable;

(c) applying a Discriminator to the difference between the feedback of the output variable and the input variable wherein said Discriminator is a respective discriminator of said Probe producing a second scalar function of the output variable;

(d) filtering the difference between a quantile value and said second scalar function of step (c) with a second Spatial Averaging Filter operable on the spatial coordinates of the input variable producing a second averaged scalar function of the output variable; and

(e) dividing said second averaged scalar function of step (d) by said first averaged scalar function of step (b) and by the time constant of the impulse response of said Time Averaging Filter and time-integrating the quotient to produce said output variable.

39. A method for image analysis operable to transform an input image signal into an output signal comprising the following steps:

(a) applying a Threshold Filter to a difference of a Displacement Variable and an input image signal producing a first scalar field of said Displacement Variable; and

(b) filtering said first scalar field of step (a) with a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function to produce a second scalar field of said Displacement Variable.

40. A method for image analysis operable to transform an input image signal into an output signal as recited in claim 39 further comprising the step:

modulating said first scalar field of step (a) by a Modulating Variable producing a modulated first scalar field of said Displacement Variable.

41. A method for image analysis as recited in claim 40 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input image signal.

42. A method for image analysis as recited in claim 41 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

43. A method for image analysis as recited in claim 40 further comprising the step:

dividing said second scalar field of step (b) by said Modulating Variable where said Modulating Variable has been first filtered with a second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function.

44. A method for image analysis as recited in claim 43 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input image signal.

45. A method for image analysis as recited in claim 44 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

46. A method for image analysis as recited in claim 43 wherein said Threshold Filter is a Discriminator and said Modulating Variable is a norm of a first time derivative of the input image signal.

47. A method for image analysis as recited in claim 46 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

48. A method for image analysis as recited in claim 43 wherein said Threshold Filter is a Probe.

49. A method for image analysis as recited in claim 48 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

50. A method for image analysis as recited in claim 43 wherein said Threshold Filter is a Discriminator.

51. A method for image analysis as recited in claim 50 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

52. A method for image analysis as recited in claim 39 wherein said Threshold Filter is a Probe.

53. A method for image analysis as recited in claim 52 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

54. A method for image analysis as recited in claim 39 wherein said Threshold Filter is a Discriminator.

55. A method for image analysis as recited in claim 54 wherein the input image signal further comprises a vector combining the components of the input image signal and first time derivatives of said components of the input image signal.

56. An apparatus for analysis of variables operable to transform an input variable into an output variable comprising:

a Threshold Filter operable to apply a Threshold Filter to a difference of a Displacement Variable and an input variable producing a first scalar field of said Displacement Variable; and

a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function so as to filter said first scalar field to produce a second scalar field of said Displacement Variable.

57. An apparatus for analysis of variables operable to transform an input variable into an output variable as recited in claim 56 further comprising:

a modulator operable to modulate said first scalar field by a Modulating Variable producing a modulated first scalar field of said Displacement Variable.

58. An apparatus for analysis of variables as recited in claim 57 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input variable.

59. An apparatus for analysis of variables as recited in claim 58 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

60. An apparatus for analysis of variables as recited in claim 57 further comprising:

a second Averaging Filter operable to alter said Modulating Variable with a second Averaging Filter to produce an averaged Modulating Variable where said second Averaging Filter is operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function; and

a divider operable to divide said second scalar field by said averaged Modulating Variable.

61. An apparatus for analysis of variables as recited in claim 60 wherein said Threshold Filter is a Probe and said Modulating Variable is a norm of a first time derivative of the input variable.

62. An apparatus for analysis of variables as recited in claim 61 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

63. An apparatus for analysis of variables as recited in claim 60 wherein said Threshold Filter is a Discriminator and said Modulating Variable is a norm of a first time derivative of the input variable.

64. An apparatus for analysis of variables as recited in claim 63 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

65. An apparatus for analysis of variables as recited in claim 60 wherein said Threshold Filter is a Probe.

66. An apparatus for analysis of variables as recited in claim 65 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

67. An apparatus for analysis of variables as recited in claim 60 wherein said Threshold Filter is a Discriminator.

68. An apparatus for analysis of variables as recited in claim 67 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

69. An apparatus for analysis of variables as recited in claim 56 wherein said Threshold Filter is a Probe.

70. An apparatus for analysis of variables as recited in claim 69 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

71. An apparatus for analysis of variables as recited in claim 56 wherein said Threshold Filter is a Discriminator.

72. An apparatus for analysis of variables as recited in claim 71 wherein the input variable further comprises a vector combining the components of the input variable and first time derivatives of said components of the input variable.

73. An apparatus for Rank Normalization of an input variable with respect to a reference variable comprising:

a Discriminator operable to apply a Discriminator to a difference of a Displacement Variable and a reference variable producing a first scalar field of said Displacement Variable;

a first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function so as to alter said first scalar field to produce a second scalar field of said Displacement Variable;

a Probe operable to apply a Probe to a difference of said Displacement Variable and an input variable producing a third scalar field of said Displacement Variable;

a multiplier operable to multiply said third scalar field by said second scalar field to produce a product; and

an integrator operable to integrate said product over the values of said Displacement Variable to output a Rank Normalized variable.

74. An apparatus for Rank Normalization of an input variable with respect to a reference variable as recited in claim 73 wherein the reference variable is analogous to the input variable.

75. An apparatus for Rank Normalization of an input variable with respect to a reference variable as recited in claim 73 further comprising:

a modulator operable to modulate said first scalar field by a Modulating Variable;

a second Averaging Filter operable to alter said Modulating Variable to produce an averaged Modulating Variable where said second Averaging Filter is operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function; and

a divider operable to divide said second scalar field by said averaged Modulating Variable.

76. An apparatus for Rank Normalization of an input variable with respect to a reference variable as recited in claim 75 wherein the reference variable is analogous to the input variable.

77. An apparatus for analysis of variables operable to transform an input variable into an output variable comprising:

a Probe operable to apply a Probe to a difference of a Displacement Variable and a reference variable producing a first scalar field of said Displacement Variable;

a modulator operable to modulate said first scalar field by an input variable producing a modulated first scalar field of said Displacement Variable;

a first Averaging Filter operable to alter said modulated first scalar field, said first Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function so as to produce a second scalar field of said Displacement Variable;

a second Averaging Filter operable to alter said first scalar field, said second Averaging Filter operable to perform a function selected from the group consisting of time averaging function, spatial averaging function, and time and spatial averaging function so as to produce an averaged first scalar field; and

a divider operable to divide said second scalar field by said averaged first scalar field.

78. An apparatus for Rank Normalization of an input variable with respect to a reference variable comprising:

(a) a component operable to determine a measure of central tendency of an Amplitude Density of a reference variable;

(b) a component operable to determine a measure of variability of said Amplitude Density of the reference variable; and

(c) a Discriminator operable to apply a Discriminator to a difference of said measure of central tendency and the input variable wherein the width parameter of said Discriminator is indicative of said measure of variability.

79. An apparatus for Rank Normalization of an input variable with respect to a reference variable as recited in claim 78 wherein the reference variable is analogous to the input variable.

80. An apparatus for Rank Normalization of an input variable with respect to a reference variable comprising:

(a) a component operable to determine a measure of central tendency of a Modulated Threshold Density of a reference variable;

(b) a component operable to determine a measure of variability of said Modulated Threshold Density of the reference variable; and

(c) a Discriminator operable to apply a Discriminator to a difference of said measure of central tendency and the input variable wherein the width parameter of said Discriminator is indicative of said measure of variability.

81. An apparatus for Rank Normalization of an input variable with respect to a reference variable as recited in claim 80 wherein the reference variable is analogous to the input variable.