Sequential feature computation for power efficient classification

• US 10,133,329 B2
• Filed: 03/15/2013
• Issued: 11/20/2018
• Est. Priority Date: 11/19/2012
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Grokop, Leonard Henry, Ahuja, Disha, Kulkarni, Rashmi, Sadasivam, Shankar, Teague, Edward Harrison, Nanda, Sanjiv
• Primary Examiner(s): Cassity, Robert A
• Application Number:
  US13/841,960
• Publication Number:
  US 20140143579A1
• Time in Patent Office: 2,076 Days
• CPC Class Codes: G06F 1/28 Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
• CPC Class Codes: G06F 9/4893 taking into account power or heat criteria power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Disclosed is an apparatus and method for power efficient processor scheduling of features. In one embodiment, features may be scheduled for sequential computing, and each scheduled feature may receive a sensor data sample as input. In one embodiment, scheduling may be based at least in part on each respective feature'"'"'s estimated power usage. In one embodiment, a first feature in the sequential schedule of features may be computed and before computing a second feature in the sequential schedule of features, a termination condition may be evaluated.

Claims

1. A method comprising:

receiving, by a processor, a sensor data sample from one or more sensors;

determining, by a processor, a classification associated with the sensor data sample based in part on the data sample and a type of each of the one or more sensors;

determining, by a processor, an estimated amount of power required by the processor to compute each of a plurality of features associated with the sensor data sample based in part on one or more prior feature calculations associated with the classification;

determining, by the processor, a sequential schedule for computing the plurality of features associated with the sensor data sample, wherein each of the plurality of features is computed based in part on data received by the processor from the one or more sensors, and wherein the schedule is determined based at least in part on the type of each of the one or more sensors and the estimated amount of power required to compute each of the plurality of features;

computing, by the processor, a first feature according to the sequential schedule; and

determining, by the processor, whether a termination condition is satisfied before computing a second feature in the sequential schedule.

2. The method of claim 1, further comprising:

determining, by the processor, the computing of the first feature satisfies the termination condition; and

classifying, by the processor, the sensor data sample based on a result of the computing of the first feature.

3. The method of claim 1, further comprising:

determining, by the processor, the computing of the first feature fails to satisfy the termination condition;

computing, by the processor, upon a failure of the first feature to satisfy the termination condition, the second feature in the sequential schedule for computing the plurality of features for computing;

determining, by the processor, the computing of the second feature satisfies the termination condition; and

classifying, by the processor, the sensor data sample according to results of computing the first and second features.

4. The method of claim 1, wherein the sequential schedule for computing a plurality of features is further determined based on one or more of:

a likelihood of each feature resulting in an unambiguous classification, or a relative frequency of occurrences of classes being classified from the sensor data sample.

5. The method of claim 1, wherein determining the termination condition is satisfied comprises determining that a classification confidence meets a threshold value, wherein the classification confidence is based on one or more of:

a similarity between a feature of the sensor data sample with a feature of a training data sample, or a difference in likelihood between a plurality of possible classifications.

6. The method of claim 1, wherein the first feature is a mean or standard deviation of an accelerometer, wherein computing the mean or standard deviation results in a stationary classification, and wherein the method further comprises cancelling computation of subsequent motion related feature computation.

7. The method of claim 1, wherein the first feature is a Mel-Frequency Cepstral Coefficient corresponding to audio energy from a microphone, wherein computing the Mel-Frequency Cepstral Coefficient results in a quiet classification, and wherein the method further comprises cancelling computation of subsequent audio related feature computation.

8. The method of claim 1, wherein the sensor data sample is from one or more of:

an accelerometer, a gyroscope, a magnetometer, a barometric pressure sensor, a temperature sensor, a global positioning sensor, a WiFi sensor, a Bluetooth sensor, an ambient light sensor, a camera, or a microphone.

9. A machine readable non-transitory storage medium containing executable instructions which cause a data processing device to perform a method comprising:

receiving, by a processor, a sensor data sample from one or more sensors;

determining, by a processor, a classification associated with the sensor data sample based in part on the data sample and a type of each of the one or more sensors;

determining, by a processor, an estimated amount of power required by the processor to compute each of a plurality of features associated with the sensor data sample based in part on one or more prior feature calculations associated with the classification;

determining, by the processor, a sequential schedule for computing the plurality of features associated with the sensor data sample, wherein each of the plurality of features is computed based in part on data received by the processor from the one or more sensors, and wherein the schedule is determined based at least in part on the type of each of the one or more sensors and the estimated amount of power required to compute each of the plurality of features;

computing, by the processor, a first feature according to the sequential schedule; and

determining, by the processor, whether a termination condition is satisfied before computing a second feature in the sequential schedule.

10. The machine readable non-transitory storage medium of claim 9, wherein the method further comprises:

determining, by the processor, the computing of the first feature satisfies the termination condition; and

classifying, by the processor, the sensor data sample based on a result of the computing of the first feature.

11. The machine readable non-transitory storage medium of claim 9, wherein the method further comprises:

determining, by the processor, the computing of the first feature fails to satisfy the termination condition;

computing, by the processor, upon a failure of the first feature to satisfy the termination condition, the second feature in the sequential schedule for computing the plurality of features for computing;

determining, by the processor, the computing of the second feature satisfies the termination condition; and

classifying, by the processor, the sensor data sample according to results of computing the first and second features.

12. The machine readable non-transitory storage medium of claim 9, wherein the sequential schedule for computing a plurality of features is further determined based on one or more of:

a likelihood of each feature resulting in an unambiguous classification, or a relative frequency of occurrences of classes being classified from the sensor data sample.

13. The machine readable non-transitory storage medium of claim 9, wherein determining the termination condition is satisfied comprises determining that a classification confidence meets a threshold value, wherein the classification confidence is based on one or more of:

a similarity between a feature of the sensor data sample with a feature of a training data sample, or a difference in likelihood between a plurality of possible classifications.

14. The machine readable non-transitory storage medium of claim 9, wherein the first feature is a mean or standard deviation of an accelerometer, wherein computing the mean or standard deviation results in a stationary classification, and wherein the method further comprises cancelling computation of subsequent motion related feature computation.

15. The machine readable non-transitory storage medium of claim 9, wherein the first feature is a Mel-Frequency Cepstral Coefficient corresponding to audio energy from a microphone, wherein computing the Mel-Frequency Cepstral Coefficient results in a quiet classification, and wherein the method further comprises cancelling computation of subsequent audio related feature computation.

16. The machine readable non-transitory storage medium of claim 9, wherein the sensor data sample is from one or more of:

an accelerometer, a gyroscope, a magnetometer, a barometric pressure sensor, a temperature sensor, a global positioning sensor, a WiFi sensor, a Bluetooth sensor, an ambient light sensor, a camera, or a microphone.

17. A data processing device comprising:

a classification module configured to receive a sensor data sample from one or more sensors and determine a classification associated with the sensor data sample based in part on the data sample and a type of each of the one or more sensors;

a power profile module configured to determine an estimated amount of power required by a processor to compute each of a plurality of features based in part on one or more prior feature calculations associated with the classification;

a scheduling module configured to receive sensor data from the one or more sensors, determine a sequential schedule for computing, the plurality of features for computing, wherein each of the plurality of features is computed by a processor based in part on data received from the one or more sensors, and wherein the schedule is determined based at least in part on the type of each of the one or more sensors and the estimated amount of power required by the processor to compute each of the plurality of features; and

a classifier module to compute a first feature in the sequential schedule and determine whether a termination condition is satisfied before computing a second feature in the sequential schedule.

18. The data processing device of claim 17, wherein the classifier module is further configured to:

determine the computing of the first feature satisfies the termination condition;

and

classify the sensor data sample based on a result of the computing of the first feature.

19. The data processing device of claim 17, wherein the classifier module is further configured to:

determine the computing the first feature fails to satisfy the termination condition;

compute, upon a failure of the first feature to satisfy the termination condition, the second feature in the sequential schedule for computing the plurality of features for computing;

determine the computing the second feature satisfies the termination condition; and

classify the sensor data sample according to results of computing the first and second features.

20. The data processing device of claim 17, wherein the sequential schedule for computing a plurality of features is further determined based on one or more of:

a likelihood of each feature resulting in an unambiguous classification, or a relative frequency of occurrences of classes being classified from the sensor data sample.

21. The data processing device of claim 17, wherein the classifier module is configured to determine the termination condition is satisfied based on a classification confidence meeting a threshold value, wherein the classification confidence is based on one or more of:

a similarity between a feature of the sensor data sample with a feature of a training data sample, or a difference in likelihood between a plurality of possible classifications.

22. The data processing device of claim 17, wherein the scheduling module is further configured to:

cancel computation of subsequent motion related feature computation upon determining the first feature is a mean or standard deviation of an accelerometer resulting in a stationary classification.

23. The data processing device of claim 17, wherein the scheduling module is further configured to:

cancel computation of subsequent audio related feature computation upon determining the first feature is Mel-Frequency Cepstral Coefficient corresponding to audio energy from a microphone resulting in a quiet classification.

24. The data processing device of claim 17, wherein the sensor data sample is from one or more of:

an accelerometer, a gyroscope, a magnetometer, a barometric pressure sensor, a temperature sensor, a global positioning sensor, a WiFi sensor, a Bluetooth sensor, an ambient light sensor, a camera, or a microphone.

25. An apparatus comprising:

means for receiving sensor data sample from one or more sensors;

means for determining a classification associated with the sensor data sample based in part on the data sample and a type of each of the one or more sensors;

means for determining, an estimated amount of power required by a processor to compute each of a plurality of features associated with the sensor data sample based in part on one or more prior feature calculations associated with the classification;

means for determining a sequential schedule for computing the plurality of features associated with the sensor data sample, wherein each of the plurality of features is computed based in part on data received from the one or more sensors, and wherein the schedule is determined based at least in part on the type of each of the one or more sensors and the estimated amount of power required to compute each of the plurality of features;

means for computing a first feature according to the sequential schedule; and

means for determining whether a termination condition is satisfied before computing a second feature in the sequential schedule.

26. The apparatus of claim 25, further comprising:

means for determining the computing of the first feature satisfies the termination condition; and

means for classifying the sensor data sample based on a result of the computing of the first feature.

27. The apparatus of claim 25, further comprising:

means for determining the computing of the first feature fails to satisfy the termination condition;

means for computing, upon a failure of the first feature to satisfy the termination condition, the second feature in the sequential schedule for computing the plurality of features for computing;

means for determining the computing of the second feature satisfies the termination condition; and

means for classifying the sensor data sample according to results of computing the first and second features.

28. The apparatus of claim 25, wherein the means for determining a sequential schedule for computing the plurality of features is configured to further determine the sequential schedule for computing the plurality of features based on one or more of:

a likelihood of each feature resulting in an unambiguous classification, or a relative frequency of occurrences of classes being classified from the sensor data sample.

29. The apparatus of claim 25, wherein determining the termination condition is satisfied comprises determining that a classification confidence meets a threshold value, wherein the classification confidence is based on one or more of:

a similarity between a feature of the sensor data sample with a feature of a training data sample, or a difference in likelihood between a plurality of possible classifications.

30. The apparatus of claim 25, wherein the first feature is a mean or standard deviation of an accelerometer resulting in a stationary classification, and wherein the apparatus further comprises means for cancelling computation of subsequent motion related feature computation.

31. The apparatus of claim 25, wherein the first feature is Mel-Frequency Cepstral Coefficient corresponding to audio energy from a microphone resulting in a quiet classification, and wherein the apparatus comprises means for cancelling computation of subsequent audio related feature computation.

32. The apparatus of claim 25, wherein the sensor data sample is from one or more of:

an accelerometer, a gyroscope, a magnetometer, a barometric pressure sensor, a temperature sensor, a global positioning sensor, a WiFi sensor, a Bluetooth sensor, an ambient light sensor, a camera, or a microphone.