Systems and methods for adaptive smart environment automation

• US 8,880,378 B2
• Filed: 04/08/2013
• Issued: 11/04/2014
• Est. Priority Date: 09/11/2008
• Status: Active Grant

• Current Assignee: Washington State University
• Original Assignee: Washington State University
• Inventors: Cook, Diane J., Rashidi, Parisa
• Primary Examiner(s): LE, TOAN M
• Application Number:
  US13/858,751
• Publication Number:
  US 20130238538A1
• Time in Patent Office: 575 Days
• Field of Search: 702/181, 702/1, 702/81, 702/84, 702/127, 702/179, 702182-183, 702188-189, 703/2, 703/4, 703 17- 22, 705/2, 705 711- 713, 705/7.15, 705/7.23, 705/7.38, 705 741- 742, 705/325, 706/16, 706 20- 21, 706/23, 706/25, 706 44- 45, 706/48, 706/59, 700/1, 700/9, 700 11- 12, 700 19- 20, 700 28- 34, 700/44, 700 47- 49, 700/52, 700/91, 700/93, 700108-109, 700110-111
• US Class Current: 702/181
• CPC Class Codes: G05B 15/02 electric
• CPC Class Codes: G05B 2219/2642 Domotique, domestic, home control, automation, smart house
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06Q 50/08 Construction
• CPC Class Codes: G06Q 50/12 Hotels or restaurants
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule
• CPC Class Codes: G08B 21/0484 Arrangements monitoring consumption of a utility or use of an appliance which consumes a utility to detect unsafe condition, e.g. metering of water, gas or electricity, use of taps, toilet flush, gas stove or electric kettle
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking

Abstract

Several embodiments of systems and methods for adaptive smart environment automation are described herein. In one embodiment, a computer implemented method includes determining a plurality of sequence patterns of data points in a set of input data corresponding to a plurality of sensors in a space. The input data include a plurality of data points corresponding to each of the sensors, and the sequence patterns are at least partially discontinuous. The method also includes generating a plurality of statistical models based on the plurality of sequence patterns, and the individual statistical models corresponding to an activity of a user. The method further includes recognizing the activity of the user based on the statistical models and additional input data from the sensors.

Claims

1. A computer system, comprising:

a plurality of sensors installed in a space, the sensors being configured to provide input data;

a control element installed in the space; and

a controller operatively coupled to the sensors and the control element, at least partially via a wireless communication link, the controller being programmed to;

recognize an activity of a resident based at least in part on the input data; and

automate an operation of the control element based at least in part on an average of user feedback values associated with a plurality of events comprising the recognized activity.

2. A system as recited in claim 1, wherein the plurality of sensors includes one or more of:

an ultraviolet light sensor;

a laser sensor;

an item sensor;

or

a capacitive sensor.

3. A system as recited in claim 1, wherein the control element is implemented as an electrical switch.

4. A system as recited in claim 1, wherein the controller is operatively coupled to one or more of the sensors via a wireless communication link.

5. A system as recited in claim 1, wherein the controller is operatively coupled to the control element via a wireless communication link.

6. A system as recited in claim 1, wherein the controller includes a discrete input module for receiving the input data from one or more of the sensors.

7. A system as recited in claim 1, wherein the controller includes an Ethernet driver for receiving the input data from one or more of the sensors.

8. A system as recited in claim 1, wherein the controller includes a discontinuous varied-order sequential mining module configured to analyze the input data from the plurality of sensors to determine periodic activity sequences that are at least partially discontinuous or exhibit a varied order.

9. A system as recited in claim 1, wherein the controller includes a dynamic adapter programmed to:

detect a change in a behavior of the resident while performing a particular activity; and

modify an automation policy associated with the particular activity based, at least in part, on the detected change in behavior.

10. A system as recited in claim 1, wherein the controller includes an activity model programmed to:

generate a model of activities of the resident; and

identify at least portions of activities that may be automated based at least in part on the model.

11. A system as recited in claim 10, wherein the activity model includes at least one of:

a dynamic Bayes network;

or

a naï

ve Bayes classifier.

12. A system as recited in claim 1, wherein the controller includes a user interface programmed to receive user-submitted automation changes.

13. A system as recited in claim 1, wherein the controller is further programmed to automate an operation of the control element based at least in part on the probability of transitioning to the recognized activity.

14. A computer system, comprising:

a plurality of sensors installed in a space, wherein;

the sensors are configured to provide input data; and

the sensors include one or more of;

an ultraviolet light sensor;

a laser sensor;

an item sensor;

or

a capacitive sensor;

a control element installed in the space; and

a controller operatively coupled to the sensors and the control element, the controller programmed to being configured to;

recognize activities of a plurality of residents based at least in part on the input data; and

generate respective models of activities for individual residents of the plurality of residents.

15. A computer system as recited in claim 14, wherein the controller is further programmed to identify at least portions of activities that may be automated based at least in part on the generated models.

16. A computer system as recited in claim 15, wherein the controller is further programmed to automate the activities based at least in part on an average of user feedback values associated with one or more events comprising the recognized activity.

17. A computer system as recited in claim 16, wherein the controller is further programmed to build models for the activities represented by the set of clusters.

18. A computer system as recited in claim 17, wherein input data includes activities performed by a plurality of residents.

19. A computer system as recited in claim 18, wherein the controller is further programmed to build a model for each of the one or more residents.

20. A computer system, comprising:

a plurality of sensors installed in a space, the sensors being configured to provide input data;

a control element installed in the space; and

a controller operatively coupled to the sensors and the control element, the controller being programmed configured to;

analyze the input data from the plurality of sensors to determine periodic activity sequences that are at least partially discontinuous or exhibit a varied order;

group the periodic activity sequences into a set of clusters based in part on at least the distance between the periodic activity sequences;

recognize an activity of a resident based at least in part on the set of clusters; and

automate an operation of the control element based at least in part on the recognized activity.