WO2006000166B1

WO2006000166B1 - Method and device for detecting operator fatigue or quality

Info

Publication number: WO2006000166B1
Application number: PCT/CZ2005/000051
Authority: WO
Inventors: Miloslav Pavelka; Tamer Keshi
Original assignee: Miloslav Pavelka; Tamer Keshi
Priority date: 2004-06-29
Filing date: 2005-06-29
Publication date: 2006-05-11
Also published as: CZ2004770A3; WO2006000166A1

Abstract

The method of operator fatigue detection from operator muscular activity is performed by detecting at least one parameter affected by operator muscular activity, which parameter is assessed using fatigue assessment rules obtained using a data mining method from a corresponding parameter of at least one operator for whom the extent of fatigue is known. The device to perform the fatigue detection method comprises a programmable unit with a preprogrammed fatigue detection model - that is to say fatigue assessment rules obtained by measuring a signal of at least one of parameters generated by operator muscular activity for at least one fatigued operator and at least one alert operator -, a detector or detectors to measure or measure and process the signal of the parameter or parameters used by the model, connected to the input of the programmable unit to assess operator fatigue, while the programmable unit output is connected to a fatigue signaling device.

Claims

59AMENDED CLAIMS received by the International Bureau on 27 December 2005 (27.12.05)NEW CLAIMS

1. A method of operator fatigue detection or operator quality evaluation from an activity performed by the operator, said activity comprising operator's muscular activity, wherein a fatigue detection model or a quality evaluation model being capable of generalization is created, said model being based upon measuring parameters derived from the activity of different operators performing said activity, whereas the extent of their fatigue or quality is known beforehand, the fatigue or the quality evaluation model is created as a set of decision rules for evaluating operator fatigue or quality or for making a decision if the operator is capable of performing his activity or not.

2. A method according to claim 1, characterized by detecting at least one parameter affected by operator's muscular activity, which parameter is evaluated based on fatigue detection or quality evaluation model or rules obtained using a data mining method from a corresponding parameter of different operators for whom the extent of fatigue or quality is known beforehand.

3. A method according to claim 2 characterized in that the data mining method uses one of the following techniques: neural networks, decision trees, regression, random forests, genetic algorithms, splines, SVM₃ CHAID, CART, non-parametric system identification models, non parametric regression, clustering, and any combination of those techniques.

4. A method according to any of claims 1 to 3, characterized by creating variables derived from parameters affected by the operator muscular activity, said variables express the fatigue difference between a fatigued operator and alert operator or the quality difference between a high-quality-operator and low-quality-operator.

5 A method according to claim 4, characterized by creating a table or structure comprising sets of input variables and a corresponding output variable set, the input variable values are derived from the parameter or parameters of individual operators in individual time intervals, the output variable value describes the corresponding extent of operator fatigue in each time interval for each individual operator. 60

6. A method according to any of Claims 1 to 5, characterized in that one parameter obtained by the activity of operators performing said activity is generated from a motor vehicle steering-wheel movement being detected from any suitable part of the vehicle including the steering-wheel itself, the parts between the steering-wheel and the axle, or the axle itself.

7. A method according to Claim 6, characterized in that further parameters derived from the activity of operators performing said activity are generated from at least one of the following components: speed control related to an accelerator pedal movement, speed control related to a brake pedal movement, vehicle speed, vehicle lateral acceleration, vehicle longitudinal acceleration, windscreen wiper switched on as a rain indicator, vehicle loading, outside temperature values measured, and vehicle's position on the street.

8. A method according to any of Claims 1 to 7, characterized in that the parameters are generated from the vehicle longitudinal and/or transverse acceleration.

9. A method of operator fatigue or quality evaluation from operator muscular activity, wherein: a) at least one parameter influenced by the operator muscular activity is detected to ensure generalization for at least two alert operators and at least two fatigued operators or at least two high-quality operators and at least two low-quality operators b) a set of data or preferably variables is obtained and stored in a suitable form, c) based on the stored data or variables a fatigue detection model or a quality evaluation model is created using a data mining method, d) at least one parameter measured in step a) is measured for the evaluated operator, e) values measured in step d) are used to create data or preferably variables in the same or similar way as in step b) f) data or variables are used as input data for the model created in step c), whilst the model output provides the fatigue detection or quality estimation of the evaluated operator. 61

10. A device for fatigue detection or quality evaluation capable of generalization, comprising a programmable unit, wherein the programmable unit includes fatigue or quality evaluation model for operator fatigue evaluation or for operator quality evaluation, the model being obtained by a data mining method using signal derived from at least one of parameters generated by operator muscular activity, the parameters being detected for different fatigued operators and for different alert operators or for different high-quality operators and for different low-quality operators, the device further comprising at least one detector to measure or to measure-and-process the signal derived from the parameter or parameters used by the model, the detector or detectors are connected to the input of the programmable unit to evaluate operator fatigue or quality, the programmable unit output being connected to a fatigue or quality signaling equipment, while the device advantageously also comprises at least one unit for signal or data processing to generate suitable inputs for the fatigue or quality evaluation model.

11. A device according to claim 10, characterized by performing signal measuring, signal processing into the form of input data or variables of the detection or evaluation model, and fatigue detection or quality estimation in real time, i.e. simultaneously with operator's routine activity.

12. A device for performing a method according to any of claims 1 to 9 for a real-time fatigue detection or quality evaluation, capable of generalization, comprising a programmable unit, wherein the programmable unit includes fatigue or quality evaluation model for operator fatigue evaluation or for operator quality evaluation, the model being obtained by a data mining method using a signal obtained from at least one of parameters generated by operator muscular activity for more than 5 fatigued operators and for more than 5 alert operators or for more than 5 high-quality operators and for more than 5 low-quality operators, the device further comprising at least one detector to measure or to measure-and-process the signal used by the model, the detector or detectors are connected to the input of the programmable unit to evaluate operator fatigue or quality, the programmable unit output being connected to a fatigue or quality signaling equipment, while the device preferably also comprises at least one unit for signal or data processing to generate suitable inputs for the fatigue or quality evaluation model, the device further performing signal measuring, signal processing into the 62

form of input data or variables of the detection or evaluation model, and fatigue or quality estimation m real time, i.e. simultaneously with operator's routine activity.