Signal interpretation engine

• US 6,546,378 B1
• Filed: 04/24/1997
• Issued: 04/08/2003
• Est. Priority Date: 04/24/1997
• Status: Expired due to Term

• Current Assignee: Bright Ideas L.L.C.
• Original Assignee: Bright Ideas Company Incorporated
• Inventors: Cook, Daniel Reed
• Primary Examiner(s): Downs, Robert W.
• Application Number:
  US08/840,052
• Time in Patent Office: 2,175 Days
• Field of Search: 706/52, 706/2, 706/20, 706/12, 382/159
• US Class Current: 706/12
• CPC Class Codes: A61B 5/245 specially adapted for magnetoencephalographic [MEG] signals
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/372 Analysis of electroencephalograms
• CPC Class Codes: A61B 5/407 Evaluating the spinal cord A61B5/4896 takes precedence
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G01V 1/282 Application of seismic models, synthetic seismograms
• CPC Class Codes: G01V 1/30 Analysis G01V1/50 takes precedence
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients
• CPC Class Codes: G16Z 99/00 Subject matter not provided for in other main groups of this subclass

Abstract

A signal interpretation engine apparatus and method are disclosed in certain presently preferred embodiment as including a computer programmed to run a plurality of modules comprising a feature expansion module, a weight table module, a consolidation module, and a map generation module. The feature expansion module contains feature operators for operating on a signal to expand the signal to form a feature map of feature segments Each feature segment corresponds to a unique representation of the signal created by a feature operator operating on the signal across an epoch. An epoch corresponds to an event occurring within a time segment. The weight table module provides a weight table having weight elements Each weight element has a weight corresponding to a feature segment of the feature map. The consolidation module provides a superposition segment by combining the feature segments of the feature map corresponding to the epoch by forming an inner product of the feature map and the weight table. The consolidation module also applies aggregators to consolidate the inner products or superposition segments into a distribution function representing an attribute over a domain reflecting a selected weight table, aggregator, and event type, corresponding to each value of the attribute. The map generation module produces an interpretation map that reflects a preferred weight table and aggregator to be applied to the signal data to characterize the event.

Claims

1. An apparatus for providing an interpretation corresponding to a signal, the apparatus comprising a computer programmed to run a plurality of modules comprising:

a feature expansion module containing feature operators operating on a signal, expanding the signal to form a plurality of feature segments, each feature segment corresponding to a unique representation of the signal across an epoch corresponding to an event occurring within a time segment, the event having a type;

a consolidation module for forming inner products between the plurality of feature segments and a weight table comprising weight elements, and for applying aggregators to consolidate the inner products into a distribution function representing an attribute over a domain, the domain having one or more values;

a map generation module for producing an interpretation map reflecting a preferred weight table and aggregator to be applied to the signal data to characterize the event.

2. The apparatus of claim 1, wherein the domain reflects a selected weight table, aggregator, and event type, corresponding to each value of the attribute.

3. The apparatus of claim 1, further comprising a data module for processing the signal data;

and a control module for controlling execution of the modules.

4. The apparatus of claim 3, wherein the control module is further programmed to provide selections to a user for controlling creation and use of the weight table, aggregators, and feature operators.

5. The apparatus of claim 3, wherein the data module is further programmed to process the signal data for creating signal segments, each signal segment corresponding to an epoch, and bound to an event type corresponding to the event.

6. The apparatus of claim 1, wherein the feature expansion module is further programmed to characterize the signal data in terms of a plurality of variables, creating a feature map relating each feature segment to a feature operator creating the feature segment, and selected values of the plurality of variables corresponding to the feature operator and the feature segment.

7. The apparatus of claim 1, further comprising a weight table module for providing a weight table comprising weight elements having a weight corresponding to at least one feature segment of the plurality of feature segments.

8. The apparatus of claim 7, wherein the weight table module is further programmed to receive an input for selecting the weight table.

9. The apparatus of claim 1, wherein the weight elements of the weight table are formed from the feature segments.

10. The apparatus of claim 1, wherein the weight elements of the weight table correspond to variables used by the feature operators to create the feature segments.

11. The apparatus of claim 10, wherein the weight table further comprises a number of elements corresponding to the number of feature segments.

12. The apparatus of claim 1, wherein the consolidation module further comprises a superposition module, an aggregation module, and an ordering module.

13. The apparatus of claim 12, wherein the superposition module is programmed to superimpose a plurality of feature segments into a single superposition segment.

14. The apparatus of claim 12, wherein the aggregation module is further programmed to aggregate a plurality of superposition segments provided by the superposition module into a plurality of attribute values, and wherein the ordering module is further programmed to order the attribute values into a plurality of distribution functions relating the attribute values to an event type, an instance of an event, a weight table selected, and an aggregator operator selected for use by the aggregator module of the consolidation module.

15. The apparatus of claim 12, wherein the aggregation module is further programmed to aggregate a plurality of superposition segments provided by the superposition module into a plurality of attribute values, and wherein the ordering module is further programmed to order the attribute values into a plurality of distribution functions relating the attribute values to an event type, an instance of an event, a weight table selected, and an aggregator operator selected for use by the aggregator module of the consolidation module.

16. The apparatus of claim 1, wherein the map generation module further comprises a typing confidence module for applying typing confidence operators to distribution functions to provide a typing confidence function.

17. The apparatus of claim 16, wherein the map generation module further comprises a classification module programmed to receive attribute threshold values from the typing confidence module, and to use the attribute threshold values to classify the epoch according to an event type corresponding to the event of the epoch.

18. The apparatus of claim 17, wherein the classification module is further programmed to provide a measure of classification reliability for the event type selected to correspond to the event.

19. The apparatus of claim 18, wherein the measure of classification reliability comprises a reliability table for indicating a degree to which a classified event type accords with a true event type.

20. The apparatus of claim 19, wherein the reliability table comprises a relationship between two or more event types.

21. The apparatus of claim 1, wherein the consolidation module further comprises an optimization module for providing the interpretation map.

22. The apparatus of claim 21, wherein the optimization module is further programmed to use a discrimination expression in association with discrimination criteria to determine a satisfaction value corresponding to a consolidator comprising a weight table and an aggregator in combination.

23. The apparatus of claim 22, wherein the optimization module is further programmed to provide in the interpretation map a plurality of parameters for identifying signal processing, feature expansion, consolidation, and classification of the event.

24. The apparatus of claim 23, wherein classification of the event comprises classification of epoch data into a pair of event types.

25. The apparatus of claim 23, wherein the interpretation map further comprises integration data for identifying methods of integrating at least two interpretation maps into an integrated interpretation map.

26. The apparatus of claim 1, wherein the signal data is selected from the group consisting of data from a medical context, a research context, and an industrial context.

27. The apparatus of claim 26, wherein the signal data is from a medical context, and the medical context is selected from the group consisting of a disease, a physical impairment, a mental impairment, a medical procedure, and a therapy or treatment.

28. The apparatus of claim 27, wherein the medical context is a disease and the disease is selected from the group consisting of cancer, autoimmunity, a disease related to a cardiovascular condition, a viral infection, a neurological disease, a degenerative disease, a disease correlated with aging, and a disease correlated with stress.

29. The apparatus of claim 26, wherein the signal data is from a research context and the research context is selected from the group consisting of single-trial analysis, cognitive study, psychology, neurology, cardiology, oncology, study of sleep, study of breathing, study of body conductance, study of body temperature, plant study, insect study, animal study, pharmaceutical drug-effect study, population study, flow study, physical environment study, geology, seismology, astronomy, medical clinical research, molecular biology, neuroscience, chemistry, and physics.

31. The apparatus of claim 1, wherein the interpretation map provides a control mechanism based on an event or series of events selected from the group consisting of rehabilitation, biofeedback, real-time and hands-free control of virtual and real objects, mind mouse and thinking cap for controlling objects, neural controlled devices and video games, muscle controlled devices and video games, conductivity controlled video games using skin conductance, hands-free voice-free computer assisted telepathy, communication for the deaf, mute, blind or severely disabled, and a mechanism aiding prosthetic use and control.

32. The apparatus of claim 1, wherein the interpretation map generates a prediction based on an event or series of events comprising an area of observation and monitoring selected from the group consisting of meteorology, a stock market, geology, astronomy, seismology, genetics, neurology, cardiology, and oncology.

33. The apparatus of claim 1, further comprising a computer display, the computer display comprising a display element selected from the group consisting of a raw epoch signal segment, a superposition segment, an event type activation, an event type probability, an event type membership, an event type confidence level, an even type classification, a visual icon corresponding to an event type classification, an epoch feature segment, a weight table, an aggregator, a distribution function, and a typing confidence function.

30. The apparatus of 26, wherein the signal data is from an industrial context and the industrial context is selected from the group consisting of individual identification for security purposes, drug evaluation and testing, lie detection, vehicle vibration analysis, temperature diagnostics, fluid diagnostics, mechanical system diagnostics, industrial plant diagnostics, radio communications, microwave technology, turbulent flow diagnostics, sonar imaging, radar imaging, audio mechanism, yield optimization, efficiency optimization, natural resource exploration, information exchange optimization, traffic monitoring, spatial interpretation, and toxicology.

34. A method for providing an interpretation map, the method comprising:

providing signal data corresponding to an event, the event having a type;

expanding the signal data by applying a feature operator to create feature segments;

consolidating the feature segments by forming inner products between the plurality of feature segments and a weight table;

generating an interpretation map reflecting parameters for optimizing the feature expansion, consolidation, and classification of signal data into event types.

35. The method of claim 34, wherein consolidating the feature segments further comprises applying aggregators to consolidate the inner products into a distribution function representing an attribute over a domain, the attribute having one or more values.

36. The method of claim 35, wherein the domain comprises a domain reflecting a selected weight table, aggregator, and event type corresponding to each value of the attribute.

37. The method of claim 35, wherein consolidating further comprises superimposing a plurality of feature segments to provide a superposition segment and operating on a plurality of superposition segments to provide a distribution function.

38. The method of claim 37, further comprising applying a plurality of aggregator operators to a plurality of superposition segments, each superposition segment corresponding to a weight table, to provide a plurality of attribute values, each attribute value corresponding to a weight table and an aggregator operator.

39. The method of claim 38, further comprising ordering the attribute values in a distribution function relating each attribute value to an event type, an event instance, a weight table, and an aggregator operator.

40. The method of claim 35, wherein generating a map further comprises providing a typing confidence function using the distribution function and a typing confidence operator to relate a confidence value to a pair of event types and the attribute value.

41. The method of claim 34 further comprising controlling the method by providing selections from a user to control providing weight tables and aggregators.

42. The method of claim 34, further comprising providing a data module for processing the signal data to create epochs corresponding to time segments and bound to event types corresponding to the events.

43. The method of claim 42, wherein the event is selected from the group consisting of a keyboard, a mouse movement, a mouse button press, a touch-pad activity, a light-pen activity, a pointer activity, a joystick movement, a joystick button press, a software event, condition or state, a game event, condition or state, a presence of elements on a computer screen, a movement of elements on a computer screen, a sound from a speaker, a microphone reception of sound, an eye focus location, an eye movement, and a body or body-part movement.

44. The method of claim 42, wherein the interpretation map that is generated comprises an ability to provide a control mechanism for an event or series of events comprising a function selected from the group consisting of controlling the position and movement of a cursor on the screen, moving a game paddle, influencing the outcome of a game, modifying the operation of computer software, tracking the movement of attention, and monitoring comprehension.

45. The method of claim 34, wherein expanding further comprises providing feature operators corresponding to one or more variables to create a feature map reflecting the feature segments corresponding to the one or more variables and the feature operators for the signal data within an epoch.

46. The method of claim 34, wherein the weight table comprises weight elements having weights that are generated by processing feature segments, wherein the processing comprises adjusting the relative influence of each of the feature segments with respect to one another.

47. The method of claim 46, wherein each weight element corresponds to a selected feature segment and feature operator, corresponding to an ordered set comprising the variables corresponding to the feature segment.

48. The method of claim 34, further comprising providing a computer display, the computer display comprising a display element selected from the group consisting of a raw epoch signal segment, a superposition segment, an event type activation, an event type probability, an event type membership, an event type confidence level, an even type classification, a visual icon corresponding to an event type classification, an epoch feature segment, a weight table, an aggregator, a distribution function, and a typing confidence function.

49. The method of claim 48, wherein the interpretation map that is generated comprises an ability to develop an interpretation of an event or series of events.

50. The method of claim 48, wherein the interpretation map that is generated comprises an ability to provide a control mechanism for an event or series of events.

51. The method of claim 50, wherein the control mechanism comprises a simulated device driver or a real-time device driver.

52. The method of claim 48, wherein the interpretation map that is generated comprises an ability to generate a prediction based on an event or series of events.

53. The method of claim 34, wherein the method is applied to a task selected from the group consisting of developing an interpretation of an event or series of events, providing a control mechanism for an event or series of events, and generating a prediction based on an event or series of events.

54. The method of claim 53, wherein the task comprises developing an interpretation of an event or series of events comprising information selected from the group consisting of a medical context, a research context, and an industrial context.

55. The method of claim 54, wherein the information is from a medical context and the medical context comprises a condition selected from the group consisting of a disease, a physical impairment, a mental impairment, a medical procedure, and a therapy or treatment.

56. The method of claim 55, wherein the condition comprises a disease and the disease is selected from the group consisting of cancer, autoimmunity, a disease related to a cardiovascular condition, a viral infection, a neurological disease, a degenerative disease, a disease correlated with aging, and a disease correlated with stress.

57. The method of claim 54, wherein the information is from a research context and the research context is selected from the group consisting of single-trial analysis, cognitive study, psychology, neurology, cardiology oncology, study of sleep, study of breathing, study of body conductance, study of body temperature, plant study, insect study, animal study, pharmaceutical drug-effect study, population study, flow study, physical environment study, geology, seismology, astronomy, medical clinical research, molecular biology, neuroscience, chemistry, and physics.

58. The method of claim 54, wherein information is from an industrial context and the industrial context is selected from the group consisting of individual identification for security purposes, drug evaluation and testing, lie detection, vehicle vibration analysis, temperature diagnostics, fluid diagnostics, mechanical system diagnostics, industrial plant diagnostics, radio communications, microwave technology, turbulent flow diagnostics, sonar imaging, radar imaging, audio mechanism, yield optimization, efficiency optimization, natural resource exploration, information exchange optimization, traffic monitoring, spatial interpretation, and toxicology.

59. The method of claim 53, wherein the task comprises providing a control mechanism for an event or series of events and the control mechanism is selected from the group consisting of rehabilitation, biofeedback, real-time and hands-free control of virtual and real objects, mind mouse and thinking cap for controlling objects, neural controlled devices and video games, muscle controlled devices and video games, conductivity controlled video games using skin conductance, hands-free voice-free computer assisted telepathy, communication for the deaf, mute, blind or severely disabled, and a mechanism aiding prosthetic use and control.

60. The method of claim 53 wherein the task comprises generating a prediction based on an event or series of events comprising an area of observation and monitoring selected from the group consisting of meteorology, a stock market, geology, astronomy, seismology, genetics, neurology, cardiology, and oncology.