System and Method for Leveraging Human Physiological Traits to Control Microprocessor Frequency

• US 20100313048A1
• Filed: 06/09/2010
• Published: 12/09/2010
• Est. Priority Date: 06/09/2009
• Status: Active Grant

• Current Assignee: Northwestern University
• Original Assignee: Northwestern University
• Inventors: Pan, Yan, Miller, J. Scott, Scholbrock, Benjamin, Dinda, Peter A., Memik, Gokhan, Dick, Robert P., Shye, Alex
• Granted Patent: US 8,683,242 B2
• Time in Patent Office: Days
• US Class Current: 713/320
• CPC Class Codes: G06F 1/3231 Monitoring the presence, absence or movement of users
• CPC Class Codes: G06F 1/324 by lowering clock frequency
• CPC Class Codes: G06F 1/3296 by lowering the supply or operating voltage
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A system and method for leveraging physiological traits to control microprocessor frequency are disclosed. In some embodiments, the system and method may optimize, for example, a particular processor-based architecture based on, for example, end user satisfaction. In some embodiments, the system and method may determine, for example, whether their users are satisfied to provide higher efficiency, improved reliability, reduced power consumption, increased security, and a better user experience. The system and method may use, for example, biometric input devices to provide information about a user'"'"'s physiological traits to a computer system. Biometric input devices may include, for example, one or more of the following: an eye tracker, a galvanic skin response sensor, and/or a force sensor.

Claims

1. A system for controlling a computer, comprising:

a central processor that runs user-centric applications;

one or more biometric input devices that are operatively coupled to the central processor, the one or more biometric input devices providing information relating to physiological traits of a user of the computer,

wherein the central processor uses the information relating to the physiological traits of the user to provide a physiological traits-based power-management system,

wherein the physiological traits-based power-management system is user-aware due to the information received from the one or more biometric input devices, and

wherein the physiological traits-based power-management system drives the dynamic voltage and frequency scaling scheme based on user satisfaction levels that strongly correlate with changes in physiological traits of the user.

2. The system according to claim 1, wherein the one or biometric input devices comprises an eye tracker, a galvanic skin response sensor and a force sensor.

3. The system according to claim 1, wherein the one or biometric input devices comprises a galvanic skin response sensor that measures skin resistance or skin conductance.

4. The system according to claim 3, wherein low skin conductance indicates that user is in a state of relaxation, and wherein high skin conductance indicates that user is in a state of mental, emotional and/or physical arousal.

5. The system according to claim 3, wherein the galvanic skin response sensor comprises a first probe attached to a first strip and a second probe attached to a second strip, the first strip and the second strip being wrapped around respective fingers of the user, and wherein the first probe and the second probe are wired in a voltage divider circuit.

6. The system according to claim 3, wherein a delta galvanic skin response is computed by taking a difference between consecutive samples from the galvanic skin response sensor and filtering out negative values.

7. The system according to claim 6, wherein the delta galvanic skin response is characterized by being a measure of short-term changes in user arousal and by filtering out long-term trends in user arousal.

8. The system according to claim 6, wherein, when summed over a period of time, the delta galvanic skin response serves as a metric for total user arousal for the time period.

9. The system according to claim 1, wherein the one or biometric input devices comprises a force sensor that measures behavior.

10. The system according to claim 9, wherein the force sensor measures a force used to press down a key on a keyboard of the computer.

11. The system according to claim 10, wherein the force sensors are measured using a voltage divider circuit.

12. The system according to claim 1, wherein the one or biometric input devices comprises an eye tracker that measures pupil dilation and eye movement.

13. The system according to claim 12, wherein the eye tracker uses video-based combined pupil and corneal reflection to track a focus of a user eye.

14. The system according to claim 1, wherein the physiological traits-based power-management system tunes performance of the dynamic voltage and frequency scaling scheme to, but not above, a level necessary to meet user needs and expectations.

15. The system according to claim 1, wherein the physiological traits-based power-management system provides user-aware optimizations to the dynamic voltage and frequency scaling scheme based on at least implicit user feedback.

16. The system according to claim 1, wherein the physiological traits-based power-management system tunes performance of the dynamic voltage and frequency scaling scheme such that power consumption by the computer is reduced without substantial impact on user satisfaction.

17. A method for managing power consumption of a processor, comprising:

receiving dynamic physiological trait user information generated by biometric input devices;

adjusting power consumption of the processor based on the received dynamic physiological trait user information;

measuring impact of computer performance on the dynamic physiological trait user information measured by biometric input devices after the power consumption of the processor is adjusted; and

reducing the power consumption of the processor with little or no impact on user satisfaction.

18. The method according to claim 17, comprising:

making architecture-level decisions based on the received dynamic physiological trait user information generated by the biometric input devices.

19. The method according to claim 17, comprising:

detecting changes in the received dynamic physiological trait user information as the power consumption of the processor is adjusted.

20. The method according to claim 17, comprising:

determining a pupil dilation, a pupil movement, and an arrow-key force.

21. The method according to claim 17, comprising:

determining a delta GSR which is computed by taking a difference between consecutive samples and filtering out negative values.