Event condition detection

Patent metadata

Field	Value
Publication number	US-9679255-B1
Application number	US-201615099786-A
Country	US
Kind code	B1
Filing date	Apr 15, 2016
Priority date	Feb 20, 2009
Publication date	Jun 13, 2017
Grant date	Jun 13, 2017

Abstract

A method includes receiving data from a sensor over time. The data comprises a plurality of values that are each indicative of a sensed condition at a unique time. The method also includes determining a real-time value, a mid-term moving average, and a long-term moving average based on the data and determining a most-recent combined average by averaging the real-time value, the mid-term moving average, and the long-term moving average. The method further includes determining an upper setpoint by adding an offset value to the most-recent combined average and determining a lower setpoint by subtracting the offset value to the most-recent combined average. The method also includes transmitting an alert based on a determination that a most recent value of the data is either greater than the upper setpoint or lower than the lower setpoint.

First claim

What is claimed is:

1. A method comprising:
receiving data from a sensor over time at a remote computing device that is in communication with the sensor, wherein the data comprises a plurality of values that are each indicative of a sensed condition at a unique time, and wherein the sensed condition is one of a temperature, an amount of smoke obscuration, or an amount of a gas in the atmosphere;
determining, by the remote computing device, a real-time value, a mid-term moving average, and a long-term moving average based on the data;
determining, by the remote computing device, a most-recent combined average by averaging the real-time value, the mid-term moving average, and the long-term moving average;
determining, by the remote computing device, an upper setpoint by adding an offset value to the most-recent combined average;
determining, by the remote computing device, a lower setpoint by subtracting the offset value to the most-recent combined average;
transmitting, by the remote computing device, an instruction to the sensor to generate an alert based on a determination that a most recent value of the data is either greater than the upper setpoint or lower than the lower setpoint; and
generating, by the sensor and in response to the instruction, the alert to warn of a possible emergency condition in a structure in which the sensor is located.

2. The method of claim 1 , wherein the real-time value is an arithmetic mean of values of the data of the previous three minutes.

3. The method of claim 1 , wherein the mid-term moving average is an arithmetic mean of values of the data of the previous thirty minutes.

4. The method of claim 1 , wherein the long-term moving average is an arithmetic mean of values of the data of the previous three hours.

5. The method of claim 1 , further comprising:
determining a plurality of combined averages; and
determining a standard deviation of the plurality of the combined averages,
wherein the offset value is a multiple of the standard deviation of the plurality of the combined averages.

6. The method of claim 5 , further comprising:
determining a goodness-of-fit value of the plurality of combined averages to a model distribution; and
determining the offset value by multiplying the standard deviation by a multiple of the goodness-of-fit value.

7. The method of claim 6 , wherein the model distribution is a normal distribution.

8. The method of claim 6 , wherein said determining the goodness-of-fit value comprises using a Shapiro-Wilk goodness-of-fit test function or a Kolmogorov-Smirnov goodness of fit test function.

9. The method of claim 1 , wherein the sensor is located in a room, and wherein said transmitting the alert causes an alarm to sound and notify occupants of the room.

10. The method of claim 1 , wherein said transmitting the alert is further based on a determination that a current risk level is greater than a predetermined risk threshold, wherein determining the current risk includes using a Bayesian Network of a plurality of risk nodes, and wherein one of the plurality of risk nodes comprises the most-recent combined average.

11. A system comprising:
a sensor configured to sense data that can indicate in an emergency condition in a structure; and
a remote computing device in communication with the sensor, wherein the remote computing device comprises
a transceiver configured to receive the data received from the sensor over time;
a memory configured to store the data, wherein the data comprises a plurality of values that are each indicative of a sensed condition at a unique time, and wherein the sensed condition is one of a temperature, an amount of smoke obscuration, or an amount of a gas in the atmosphere; and
a processor operatively coupled to the memory and the transceiver, and configured to:
determine a real-time value, a mid-term moving average, and a long-term moving average based on the data;
determine a most-recent combined average by averaging the real-time value, the mid-term moving average, and the long-term moving average;
determine an upper setpoint by adding an offset value to the most-recent combined average;
determine a lower setpoint by subtracting the offset value to the most-recent combined average; and
transmit an instruction to the sensor to generate an alert based on a determination that a most recent value of the data is either greater than the upper setpoint or lower than the lower setpoint;

wherein the sensor is configured to generate, responsive to the instruction, the alert to warn of the emergency condition in the structure in which the sensor is located.

12. The device of claim 11 , wherein the real-time value is an arithmetic mean of values of the data of the previous three minutes, the mid-term moving average is an arithmetic mean of values of the data of the previous thirty minutes, and the long-term moving average is an arithmetic mean of values of the data of the previous three hours.

13. The device of claim 11 , wherein the processor is further configure to:
determine a plurality of combined averages; and
determine a standard deviation of the plurality of the combined averages,
wherein the offset value is a multiple of the standard deviation of the plurality of the combined averages.

14. The device of claim 13 , wherein the processor is further configured to:
determine a goodness-of-fit value of the plurality of combined averages to a model distribution; and
determine the offset value by multiplying the standard deviation by a multiple of the goodness-of-fit value.

15. The device of claim 14 , wherein the model distribution is a normal distribution.

16. The device of claim 14 , wherein to determine the goodness-of-fit value, the processor is configured to use a Shapiro-Wilk goodness-of-fit test function or a Kolmogorov-Smirnov goodness of fit test function.

17. The device of claim 11 , wherein the sensor is located in a room, and wherein to transmit the alert, the processor is configured to cause an alarm to sound and notify occupants of the room.

18. A non-transitory computer-readable medium having computer-readable instructions stored thereon that, upon execution by a processor, cause a remote computing device to perform operations, wherein the instructions comprise:
instructions to receive, by the remote computing device, data from a sensor over time, wherein the remote computing device and the sensor are in communication with one another, and wherein the data comprises a plurality of values that are each indicative of a sensed condition at a unique time, and wherein the sensed condition is one of a temperature, an amount of smoke obscuration, or an amount of a gas in the atmosphere;
instructions to determine, by the remote computing device, a real-time value, a mid-term moving average, and a long-term moving average based on the data;
instructions to determine, by the remote computing device, a most-recent combined average by averaging the real-time value, the mid-term moving average, and the long-term moving average;
instructions to determine, by the remote computing device, an upper setpoint by adding an offset value to the most-recent combined average;
instructions to determine, by the remote computing device, a lower setpoint by subtracting the offset value to the most-recent combined average; and
instructions to transmit, by the remote computing device, an instruction to the sensor to generate an alert to warn of a possible emergency condition in a structure in which the sensor is located, wherein the instruction is transmi

Assignees

• Oneevent Tech Inc

Inventors

• Mullaly Paul Robert
• Wedig Kurt Joseph
• Parent Daniel Ralph
• Sadowski Kevin
• Smith Scott Todd
• Gabriel Nathan
• Nagler Laura

Classifications

• G06N7/01 Primary

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G08B29/186 Primary

  Fuzzy logic; neural networks · CPC title

• G06N99/00

  Subject matter not provided for in other groups of this subclass · CPC title

• G08B29/26

  by updating and storing reference thresholds · CPC title

• G08B17/10

  Actuation by presence of smoke or gases {, e.g. automatic alarm devices for analysing flowing fluid materials by the use of optical means} · CPC title