KR101862218B1 - System for context awareness by identification of electronic apparatus and method therefor - Google Patents
System for context awareness by identification of electronic apparatus and method therefor Download PDFInfo
- Publication number
- KR101862218B1 KR101862218B1 KR1020170020539A KR20170020539A KR101862218B1 KR 101862218 B1 KR101862218 B1 KR 101862218B1 KR 1020170020539 A KR1020170020539 A KR 1020170020539A KR 20170020539 A KR20170020539 A KR 20170020539A KR 101862218 B1 KR101862218 B1 KR 101862218B1
- Authority
- KR
- South Korea
- Prior art keywords
- event
- situation
- information
- electronic device
- power
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/06—Measuring real component; Measuring reactive component
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/10—Measuring sum, difference or ratio
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
- G01R22/061—Details of electronic electricity meters
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R22/00—Arrangements for measuring time integral of electric power or current, e.g. electricity meters
- G01R22/06—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods
- G01R22/10—Arrangements for measuring time integral of electric power or current, e.g. electricity meters by electronic methods using digital techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C19/00—Electric signal transmission systems
- G08C19/02—Electric signal transmission systems in which the signal transmitted is magnitude of current or voltage
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J9/00—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting
- H02J9/005—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting using a power saving mode
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2823—Reporting information sensed by appliance or service execution status of appliance services in a home automation network
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Automation & Control Theory (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
Description
BACKGROUND OF THE
Korean Patent Laid-Open Publication No. 10-2013-0073788 discloses a method and system for identifying a power device using power consumption.
However, in the case of such a conventional method and system for identifying power devices, it seems somewhat difficult to identify the operation of a conventional legacy electronic device connected to one switchboard.
In addition, if a plurality of electronic apparatuses are identified and a state of the user is recognized by determining the on or off state and the electronic apparatuses whose state information is incorrect according to the recognized state can be controlled, waste of electric power can be prevented In addition, it will provide users with a better environment for using electronic devices.
An object of the present invention is to solve the technical problems as described above, and it is an object of the present invention to identify an electronic device by sensing a change in the on or off state of a plurality of legacy electronic devices operated using power from one switchboard And an object of the present invention is to provide a situation recognition system and a method thereof by electronic device identification that can recognize a user's situation by using information of the identified electronic device.
According to a preferred embodiment of the present invention, there is provided a situation recognition system comprising: a device identification unit for identifying a status of a plurality of electronic devices; And a status recognition unit for recognizing the status of the user using the identification information of the plurality of electronic devices identified by the device identification unit.
The device identification unit calculates power using the input voltage signal and the current signal, extracts the feature value of the calculated power, and identifies the electronic device associated with the extracted feature value using the extracted feature value. In addition, it is preferable that the device identification unit determines whether an event related to a plurality of electronic devices to be identified is generated using the calculated power, and extracts a feature value when it is determined that an event has occurred.
In addition, the device identification unit may determine that an event has occurred primarily if the change value of the amount of power for the first predetermined period of time is equal to or greater than a preset power value. In addition, when it is determined that the event is generated first, the device identification unit compares the pre-stored reference power waveform and determines that the event is finally generated. Preferably, the device identification unit calculates the Euclidean distance for a third time at a second predetermined time interval, which is a waveform of the calculated power, based on a time when the event is first determined to have been generated, When the difference between the sum of the distances and the sum of the Euclidian distances for the third time of the second predetermined time interval of the reference power waveform stored in advance is equal to or smaller than a predetermined value, it is determined that the event is finally generated.
In addition, the device identification unit may calculate a moving average for a fifth time interval at a fourth time interval, and compare the calculated plurality of moving average values with a previously stored reference moving average to determine that an event has occurred. Specifically, the device identification unit determines that an event has occurred by comparing each of the plurality of moving average values within a predetermined statistical range from a corresponding reference moving average of the stored reference moving averages.
Preferably, the device identification unit searches for a steady state after the time when the event is determined to be generated, and extracts a difference value from a point before the time when the event is determined to be generated as a feature value. In addition, the device identification unit extracts the difference value between the reactive power and the active power before and after the occurrence of the event as a feature value.
The device identification unit can identify the electronic device by comparing the feature value stored in advance for each electronic device with the extracted feature value.
Preferably, the context recognition unit learns and inferences the situation by learning and inferring a situation by a predetermined zone by a neural network, integrates the situation information by a neural network, and learns and recognizes the situation of the user.
In addition, the situation recognition unit learns the situation by using the identification information and the time information of the corresponding electronic device among the identification information of the plurality of electronic devices identified by the device identification unit as input variables, And based on the information, identification information and time information of the electronic device are used to infer the situation for each zone.
Also, the situation recognition unit learns the final situation of the user by using the situation information of each zone as the input variable, and uses the inferred situation information of the zone based on the learning information of the user's final situation, It is preferable to deduce.
According to another aspect of the present invention, there is provided a situation recognition system including a control signal generator for generating a control signal for controlling a state of an electronic device, wherein the control signal generator comprises: And generates a control signal for controlling the state of the corresponding electronic device using the information when the state information of each electronic device differs from the current state information of the electronic device according to the situation information.
According to a preferred embodiment of the present invention, a method for recognizing a situation includes: a device identification step of identifying a state of a plurality of electronic devices; And a situation recognition step of recognizing the user's situation using the identification information of the plurality of electronic devices identified in the device identification step.
Specifically, the device identification step may include: (a-1) calculating power using the input voltage signal and the current signal; (a-2) extracting a feature value of the power calculated in the step (a-1); (a-3) identifying an electronic device associated with the extracted feature value using the feature value extracted in the step (a-2); And (a-4) determining whether an event related to a plurality of electronic devices to be identified is generated using the power calculated in the step (a-1). If it is determined in step (a-4) that an event has occurred, it is preferable that the feature value is extracted in step (a-2).
In addition, the step (a-4) may include: (a-4-1-1) determining that an event has occurred primarily if the change in the amount of power for the first predetermined time period is equal to or greater than a preset power value; And (a-4-1-2) when it is determined in the step (a-4-1-1) that an event has been generated primarily, it is determined that an event is finally generated through comparison with a previously stored reference power waveform And a step of judging. In the step (a-4-1-2), the waveform of the power calculated in the step (a-1) is set at a predetermined second time interval based on the time when the event is firstly determined to have been generated If the difference between the sum of the calculated distances and the sum of the Euclidean distances during the third time of the second predetermined time interval of the previously stored reference power waveform is less than a predetermined value, It is preferable to determine that an event has occurred.
The step (a-4) may further include: (a-4-2-1) calculating a moving average for a fifth time period at a fourth time interval, comparing the calculated plurality of moving average values with a previously stored reference moving average And determining that an event has occurred by performing the following steps. Specifically, in the step (a-4-2-1), an event is generated by comparing each of the plurality of moving averages with a predetermined reference moving average of the stored reference moving averages, .
In the step (a-2), it is preferable to search for a steady state after the time when the event is determined to be generated, and to extract the difference value from the time before the time when the event is determined to be generated as the feature value. In addition, the step (a-2) extracts the difference value between the reactive power and the active power before and after the event as a feature value.
It is preferable that the step (a-3) identifies the electronic device by comparing the feature value previously stored for each electronic device with the feature value extracted by the step (a-2).
The context recognition step may include: (b-1) learning and inferring a situation by a predetermined zone by a neural network; And (b-2) integrating the situation information for each zone by the neural network, and learning and inferring to recognize the user's situation.
Further, the step (b-1) may further include the step of: (b-1-1) using the identification information and the time information of the corresponding electronic device among the identification information of the plurality of electronic devices identified in the device identification step, Learning the situation; And (b-1-2) inferring the situation for each zone by using the identification information and the time information of the electronic device based on the learning information of the zone situation in the (b-1-1) step do.
The step (b-2) may include: (b-2-1) learning the final state of the user using the zone-specific context information as an input variable; And (b-2-2) inferring the situation of the user based on the inferred situation information of each zone based on the learning information of the user's final situation in the (b-2-1) step .
The present invention further provides a situation recognition method comprising: a control signal generation step of generating a control signal for controlling a state of an electronic device. Specifically, when the state information of each electronic device is different from the state information of the current electronic device according to the user's situation information using the inference result of the context recognition step, the control signal generation step It is preferable to generate a control signal for controlling the state of the electronic apparatus.
According to the context aware system and method of the present invention, it is possible to identify an electronic device by detecting a change in on or off state of a plurality of legacy electronic devices operated using electric power from one switchboard, So that the user can recognize the situation.
1 is a configuration diagram of a situation recognition system according to a preferred embodiment of the present invention;
2 is a configuration diagram of a device identification unit according to a preferred embodiment of the present invention;
3 is an explanatory diagram of an event determination method by the first event determination unit;
4 is an explanatory diagram of a Euclidean distance calculation method;
Fig. 5 is an rms value waveform of power. Fig.
6 is a configuration diagram of a situation recognition unit according to a preferred embodiment of the present invention;
7 is a flow diagram of a method for recognizing a situation according to a preferred embodiment of the present invention.
DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a situation recognition system and method according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings.
It should be understood that the following embodiments of the present invention are only for embodying the present invention and do not limit or limit the scope of the present invention. It will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
First, FIG. 1 shows a configuration diagram of a
Each component of the context
1, the
The device identification unit (100) serves to identify the status of a plurality of electronic devices. The
The operation of the
2 is a block diagram of a
2, the
The
The event determiner 120 determines whether an event related to a plurality of electronic devices to be identified by the
The event determiner 120 may include a first event determination unit 121 for a large amount of power consumption electronic equipment and a second
FIG. 3 is an explanatory diagram of an event determination method by the first event determination unit 121. FIG.
Specifically, the first event determiner 121 determines whether an event has occurred in step 2.
In the first step, it is determined that an event occurs primarily, that is, a preliminary event, if the change value of the amount of power for the first predetermined time period is equal to or greater than a preset power value. However, there is also a case where the change value of the amount of power for the first predetermined time period is equal to or larger than a preset power value, even though there is no electronic apparatus that is switched from the on state to the off state or from the off state to the on state. Examples include momentary power outages and power supply instability.
If it is determined that an event has been generated primarily, the first event determination unit 121 may determine that an event has occurred, even though the actual event has not occurred, It is determined that the event is finally generated. The comparison with the pre-stored reference power waveform can be exemplified by comparison with stored power waveforms for events in various cases at the learning stage.
The first event determination unit 121 determines the waveform of the power output from the
4 is an explanatory diagram of the Euclidean distance calculating method.
As can be seen from Fig. 4, the Euclidean distance means a distance in a diagonal direction from a point at a second time interval from the first point, and the sum of the distances is finally calculated at a second time interval .
The second
The second
The
Specifically, the
Fig. 5 shows the rms value waveform of the power.
As can be seen from FIG. 5, if the steady state is not a steady state after a certain period of time has elapsed since the occurrence of the event, an error may occur in the feature value extraction.
Preferably, the
The
It is preferable that the
In the learning step, a set of feature values is generated and stored by matching the power waveforms and the operated electronic devices according to various event occurrences. In the classifying step, the operated electronic devices are identified through comparison with stored feature value set data .
Hereinafter, the
6 shows a configuration diagram of the
As can be seen from FIG. 6, the
The
The per-
The area-
The zone-
The
The
The final learning device 221 plays a role of learning the final situation of the user by using the situation information for each zone as an input variable. The
The control
FIG. 7 shows a flowchart of a method for recognizing a situation according to a preferred embodiment of the present invention.
The context awareness method according to a preferred embodiment of the present invention uses the context
7, the method for recognizing a situation according to an exemplary embodiment of the present invention includes a device identification step S100 for identifying the states of a plurality of electronic devices, a plurality of devices identified in the device identification step S100, A state recognition step (S200) of recognizing the user's situation using the identification information of the electronic device, and a control signal generation step (S300) of generating a control signal for controlling the state of the electronic device.
Specifically, the device identification step S100 includes calculating a power using the input voltage signal and the current signal in step S110, generating an event related to a plurality of electronic devices to be identified using the power calculated in step S110 (S140) of extracting a feature value of the power calculated in step S110, and identifying (S140) an electronic device associated with the feature value extracted using the extracted feature value in step S130. .
The step S120 includes a first event determination step (S121) for a large electric power consumption electronic device and a second event determination step (S122) for a small electric power consumption electronic device according to the electric power consumption amount of the electronic appliance.
If it is determined in step S1211 that a primary event has occurred, if it is determined in step S1211 that a primary event has occurred in step S1211, (S1212) that the event is finally generated through comparison with the reference power waveform stored in advance.
In step S1212, the Euclidean distance is calculated for a third time at a predetermined second time interval, based on the time when it is determined that the event has been primarily generated, and the waveform of the power calculated in step S110 is calculated based on the calculated distance And the sum of the Euclidian distances for the third time of the second predetermined time interval of the reference power waveform stored in advance is equal to or smaller than a predetermined value, it is determined that an event has finally occurred.
In operation S122, a moving average for a fifth time period is calculated at a fourth time interval, and the calculated plurality of moving average is compared with a previously stored reference moving average to determine that an event has occurred .
Specifically, in step S1221, it is determined that an event has occurred by comparing each of the plurality of moving average values within a predetermined statistical range from a corresponding reference moving average of the stored reference moving averages.
In step S130, a steady state after the time when the event is determined to be generated is searched, and a difference value with a time before the occurrence of the event is extracted as a feature value. Specifically, the step S130 extracts a difference value between the reactive power and the active power before and after the occurrence of the event as a feature value.
In step S140, the electronic device is identified by comparing the feature value previously stored for each electronic device with the feature value extracted in step S130.
In the context recognition step S200, the neural network learns the situation for each preset zone, integrates the situation information for each zone by the perception-per-zone recognition step S210 and the neural network, (Step S220). The output variable in step S220 is the user's context information.
More specifically, the step S210 includes steps S211 and S211 of using the identification information and the time information of the corresponding electronic device among the identification information of the plurality of electronic devices identified in the device identification step S100 as input variables, (S212), based on the learning information of the zone-by-zone situation, by using the identification information and time information of the electronic device.
In operation S220, based on the context information for each region, the user's final context is learned (S221). Using the context information for the inferred region on the basis of the learning information of the user's final context in operation S221 And inferring the situation of the user (S222).
If the state information of each electronic device is different from the state information of the current electronic device according to the user's situation information using the speculation result of the state recognition step (S200), the control signal generation step (S300) And generates a control signal for controlling the state of the electronic apparatus.
As described above, according to the context-
1000: Situational awareness system
100: device identification unit 200:
300: control signal generating unit
110: power calculator 120: event determiner
130: Feature value extractor 140: Device identifier
121: first event determination unit 122: second event determination unit
210: per-cognition part 220: final cognition part
211: Learning machine by section 212: Reasoning machine by section
221: Final Learning Machine 222: Final Reasoner
Claims (30)
A device identification unit for identifying a state of a plurality of electronic devices; And
And a status recognition unit for recognizing the status of the user using the identification information of the plurality of electronic devices identified by the device identification unit,
Wherein the device identification unit includes: a power calculator that calculates power consumed by a plurality of electronic devices using the input voltage signal and the current signal; An event determiner for determining whether an event related to a plurality of electronic devices to be identified is generated; A feature value extractor for extracting a feature value of the power calculated by the power calculator and extracting a feature value when the event determiner determines that an event has occurred; And a device identifier for identifying an electronic device associated with the extracted feature value using the feature value extracted by the feature value extractor,
Wherein the event determiner includes a first event determiner and a second event determiner,
Wherein the first event determination unit is used for an electronic device having a larger power consumption than the second event determination unit,
Wherein the first event determination unit determines that an event has occurred primarily if the change value of the amount of power for the first predetermined time period is equal to or greater than a preset power value,
Wherein the first event determination unit determines that an event is generated eventually through comparison with a reference power waveform stored in advance when it is determined that an event is generated first,
The feature value extractor searches for a steady state after a time when an event is determined to be generated, extracts a difference value from a point before the time when the event is determined to be generated as a feature value,
Wherein the feature value extractor extracts a difference value between the reactive power and the active power before and after the occurrence of the event as a feature value,
Wherein the situation recognition unit includes: a per-cognition unit for learning and inferring a situation by a predetermined zone by a neural network; And a final cognitive part for learning and inferring the situation of the user by recognizing the situation of the user by integrating the categorical situation information from the cognitive unit by the neural network,
The per-cognition unit may include a zone-specific learning unit for learning the zone-specific situation using the identification information and the time information of the corresponding electronic device among the identification information of the plurality of electronic devices identified by the device identification unit as input variables; And an inference unit for inferring the situation of each zone by using the identification information and time information of the electronic device based on the learning information of the situation of each zone of the zone learning unit,
Wherein the final recognition unit comprises: a final learning unit for learning the final state of the user using the situation information for each zone as an input variable; And a final inferencing unit for inferring the user's situation using the zone-specific situation information derived from the zone-specific reasoner based on the learning information of the user's final situation by the final learning unit.
Wherein the first event determination unit
The Euclidean distance is calculated for a third time at a second predetermined time interval based on a time point at which the event is firstly determined to have occurred, and the sum of the calculated distances and the previously stored reference power And determines that an event has finally occurred when the difference in the sum of the Euclidean distances for the third time of the predetermined second time interval of the waveform is less than or equal to a predetermined value.
The second event determination unit may determine,
And calculates a moving average for a fifth time in a fourth time interval, and determines that the event has occurred by comparing the calculated plurality of moving average with a previously stored reference moving average.
The second event determination unit may determine,
And determines that an event has occurred by comparing each of the plurality of moving average values with a predetermined statistically predetermined range from a corresponding reference moving average of a previously stored reference moving average.
The device identifier comprises:
And identifies the electronic device by comparing the feature value previously stored for each electronic device with the feature value extracted by the feature value extractor.
The situation recognition system comprises:
And a control signal generator for generating a control signal for controlling the state of the electronic device,
Wherein the control signal generator comprises:
When the status information of each electronic device differs from the status information of the current electronic device according to the user's context information using the inference result of the context awareness unit, a control signal for controlling the status of the corresponding electronic device Generate, context aware systems.
A device identification step of identifying a state of a plurality of electronic devices; And
And a context recognition step of recognizing a user's situation using identification information of a plurality of electronic devices identified in the device identification step,
(A-1) calculating power consumed by a plurality of electronic devices using the input voltage signal and the current signal; (a-2) extracting a feature value of the power calculated in the step (a-1); (a-3) identifying an electronic device associated with the extracted feature value using the feature value extracted in the step (a-2); And (a-4) determining whether an event related to a plurality of electronic devices to be identified is generated using the power calculated in the step (a-1)
If it is determined in step (a-4) that an event has occurred, the feature value is extracted in step (a-2)
The step (a-4) includes: (a-4-1) a first event determination step; And (a-4-2) a second event determination step,
The step (a-4-1) is used for an electronic device having a larger power consumption than the step (a-4-2)
Wherein the step (a-4-1) comprises: (a-4-1-1) determining that an event has occurred primarily if the change in the amount of power for the first predetermined period of time is equal to or greater than a preset power value; And (a-4-1-2) when it is determined in the step (a-4-1-1) that an event has been generated primarily, it is determined that an event is finally generated through comparison with a previously stored reference power waveform And determining,
The step (a-2) searches for a steady state after a time when an event is determined to be generated, extracts a difference value from a point before the time when the event is determined to be generated as a feature value,
In the step (a-2), the difference value between the reactive power and the active power before and after the occurrence of the event is extracted as a feature value,
The context recognition step may include: (b-1) learning and inferring a situation by a preset zone by a neural network; And (b-2) integrating the situation information for each zone by the neural network, and learning and inferring to recognize the situation of the user,
Wherein the step (b-1) comprises the steps of: (b-1-1) using the identification information and the time information of the corresponding electronic device among the identification information of the plurality of electronic devices identified in the device identification step, Learning step; And (b-1-2) inferring the situation for each zone by using the identification information and the time information of the electronic device based on the learning information of the zone situation in the (b-1-1) step and,
The step (b-2) comprises the steps of: (b-2-1) learning the final state of the user by using the situation information for each zone as an input variable; And (b-2-2) inferring the user's situation by using the inferred information of the area based on the learning information of the user's final situation in the step (b-2-1). How to recognize the situation.
The step (a-4-1-2)
The Euclidean distance is calculated for a third time at a second predetermined time interval based on the time when the event is firstly determined to have occurred, and the waveform of the power calculated in the step (a-1) When the difference between the sum of the distances and the sum of the Euclidian distances for the third time of the second predetermined time interval of the previously stored reference power waveform is less than a predetermined value, the event is finally determined to have occurred.
The step (a-4-2)
(a-4-2-1) determining that an event has occurred by calculating a moving average for a fifth time period at a fourth time interval, and comparing the calculated plurality of moving average values with a previously stored reference moving average; / RTI >
The step (a-4-2-1)
And determines that an event has occurred by comparing each of the plurality of moving average with a statistically predetermined range from a corresponding reference moving average of the previously stored reference moving average.
The step (a-3)
Wherein the electronic device is identified by comparing feature values previously stored for each electronic device with feature values extracted by the step (a-2).
The context recognition method includes:
And a control signal generating step of generating a control signal for controlling the state of the electronic apparatus,
The control signal generation step includes:
When the status information of each electronic device according to the user's situation information using the inference result of the context recognition step is different from the current electronic device status information, a control signal for controlling the status of the corresponding electronic device Gt; a < / RTI >
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170020539A KR101862218B1 (en) | 2017-02-15 | 2017-02-15 | System for context awareness by identification of electronic apparatus and method therefor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170020539A KR101862218B1 (en) | 2017-02-15 | 2017-02-15 | System for context awareness by identification of electronic apparatus and method therefor |
Publications (1)
Publication Number | Publication Date |
---|---|
KR101862218B1 true KR101862218B1 (en) | 2018-07-05 |
Family
ID=62920514
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020170020539A KR101862218B1 (en) | 2017-02-15 | 2017-02-15 | System for context awareness by identification of electronic apparatus and method therefor |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101862218B1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020009293A1 (en) * | 2018-07-06 | 2020-01-09 | 한국전력공사 | Schedule generation apparatus and method |
WO2021112577A1 (en) * | 2019-12-05 | 2021-06-10 | 주식회사 아이티공간 | Method for learning and detecting abnormal part of device through artificial intelligence |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005039548A (en) * | 2003-07-15 | 2005-02-10 | Sony Corp | Monitoring system and method, information processing apparatus, recording medium, and program |
JP2008160991A (en) * | 2006-12-25 | 2008-07-10 | Toshiba Corp | System for controlling use state of apparatus |
JP2008198213A (en) * | 1998-08-17 | 2008-08-28 | Aspen Technology Inc | Sensor validation apparatus and method |
JP2011065648A (en) * | 2009-09-15 | 2011-03-31 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Method and system for determining activity of person and recording medium for the same method |
-
2017
- 2017-02-15 KR KR1020170020539A patent/KR101862218B1/en active IP Right Grant
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2008198213A (en) * | 1998-08-17 | 2008-08-28 | Aspen Technology Inc | Sensor validation apparatus and method |
JP2005039548A (en) * | 2003-07-15 | 2005-02-10 | Sony Corp | Monitoring system and method, information processing apparatus, recording medium, and program |
JP2008160991A (en) * | 2006-12-25 | 2008-07-10 | Toshiba Corp | System for controlling use state of apparatus |
JP2011065648A (en) * | 2009-09-15 | 2011-03-31 | Commissariat A L'energie Atomique Et Aux Energies Alternatives | Method and system for determining activity of person and recording medium for the same method |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020009293A1 (en) * | 2018-07-06 | 2020-01-09 | 한국전력공사 | Schedule generation apparatus and method |
WO2021112577A1 (en) * | 2019-12-05 | 2021-06-10 | 주식회사 아이티공간 | Method for learning and detecting abnormal part of device through artificial intelligence |
KR20210070867A (en) * | 2019-12-05 | 2021-06-15 | (주)아이티공간 | Method of detecting abnormal part learning of device through artificial intelligence |
KR102344464B1 (en) * | 2019-12-05 | 2021-12-29 | (주)아이티공간 | Method of detecting abnormal part learning of device through artificial intelligence |
US11714403B2 (en) | 2019-12-05 | 2023-08-01 | Its Co., Ltd. | Method for learning and detecting abnormal part of device through artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alcalá et al. | Event-based energy disaggregation algorithm for activity monitoring from a single-point sensor | |
Zeifman | Disaggregation of home energy display data using probabilistic approach | |
Wild et al. | A new unsupervised event detector for non-intrusive load monitoring | |
EP2741437A1 (en) | Behavior estimation apparatus, threshold calculation apparatus, and behavior estimation method | |
KR101862218B1 (en) | System for context awareness by identification of electronic apparatus and method therefor | |
Barsim et al. | Toward a semi-supervised non-intrusive load monitoring system for event-based energy disaggregation | |
Quek et al. | Smart sensing of loads in an extra low voltage DC pico-grid using machine learning techniques | |
CN110574389B (en) | Identifying device state changes using power data and network data | |
Park et al. | Appliance identification algorithm for a non-intrusive home energy monitor using cogent confabulation | |
Yang et al. | A systematic approach in load disaggregation utilizing a multi-stage classification algorithm for consumer electrical appliances classification | |
Bilski et al. | Generalized algorithm for the non-intrusive identification of electrical appliances in the household | |
CN111968644A (en) | Intelligent device awakening method and device and electronic device | |
CN112784210A (en) | Load identification method based on multivariate Gaussian discrimination mode | |
Ghosh et al. | Extraction of statistical features for type-2 fuzzy NILM with IoT enabled control in a smart home | |
CN104991537A (en) | Control method of smart device | |
Makonin | Approaches to non-intrusive load monitoring (nilm) in the home | |
Yan et al. | Robust event detection for residential load disaggregation | |
Wu et al. | Non-intrusive load monitoring using identity library based on structured feature graph and group decision classifier | |
CN106707741B (en) | Electrical equipment control method and device | |
Abbas et al. | Non-intrusive load monitoring for residential customers using adaptive-neuro fuzzy interface system and fine tree classifier | |
Chávez et al. | Automatic laser pointer detection algorithm for environment control device systems based on template matching and genetic tuning of fuzzy rule-based systems | |
KR101815904B1 (en) | Identification system for electronic apparatus and identification method therefor | |
WO2022137255A1 (en) | Methods and systems for remotely controlling smart electrical switches and associated devices using analytics | |
CN113094931B (en) | Non-invasive load decomposition method, device and equipment | |
KR102210743B1 (en) | Apparatus and method for detecting event in a smart plug |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant |