KR20220108418A - Method and Apparatus for Indoor-Outdoor Transition Detector with Barometer - Google Patents

Abstract

A building access detection method and device using a barometer are proposed. The building access detection device using a barometer proposed in the present invention comprises: an air pressure data collection unit for collecting air pressure data based on a difference in air pressure generated when a user passes through a door using an air pressure sensor; a preprocessing and feature extraction unit for preprocessing and extracting features for machine learning on the collected air pressure data; an event detection unit for detecting a user's door passage event based on a change in air pressure data through machine learning on the preprocessing and extracted features; and a signal control unit for controlling to block or receive a GPS signal transmitted to a user's smart wearable device and a smart terminal interworking with the smart wearable device depending on the detected user's door passage event. A technical problem to be achieved by the present invention is to provide an indoor/outdoor detection method and device for distinguishing whether a user is inside or outside a building in order to provide important information for a location-based service (LBS).

Description

Method and Apparatus for Indoor-Outdoor Transition Detector with Barometer

The present invention relates to a method and apparatus for detecting entrance to a building using a barometer.

The smart clothing business is attracting attention as a growth engine in the wearable device field as the market is expected to expand along with the growing demand for wearable devices, although in the initial stage of market formation. Overseas, it is being promoted by startups, sports brands, IT industry and fashion clothing industry collaboration, etc., and attempts to develop various clothing from functional wear to casual wear are continuing. However, in Korea, awareness of smart clothing is still low compared to smart watches and bands. Nevertheless, smart clothing is the field with the highest annual growth rate among wearable devices.

In order to develop smart clothing, textile/ICT convergence technology, commercialization, and technological advancement are required. For this, close cooperation between the fashion and IT industries is required. It is necessary to consider supplementing technical weaknesses such as safety, washability, and comfort improvement, and preoccupation with core technologies that will be used in clothing.

1 is a diagram illustrating a consumer awareness survey and global wearable device shipment forecast for wearable devices.

As shown in Figure 1, consumer awareness of wearable devices including smart clothing, smart shoes, smart jewelry, smart headgear, smart wristbands, smart glasses and smart watches is increasing, and global wearable device shipments are expected to gradually increase accordingly. seems to be

Korean Patent Publication No. 10-2020-0123062 (2020.10.28)

An object of the present invention is to provide an indoor/outdoor detection method and apparatus for discriminating whether a user is indoors or outdoors in a building in order to provide important information for a Location Based Service (LBS). It is an object of the present invention to provide advertisements, disaster text messages, location tracking services, etc. according to a user's location, such as a shopping mall, through the method and apparatus for detecting access to a building using a barometer proposed in the present invention.

In one aspect, the method for detecting entrance to a building using a barometer proposed in the present invention includes the steps of collecting air pressure data according to a pressure difference generated when a user passes through a door by using a barometric pressure sensor of a smart wearable device, the collected air pressure data Step of preprocessing and extracting features for machine learning of The method may include controlling to block or receive a GPS signal transmitted to the user's smart wearable device and a smart terminal interworking with the smart wearable device.

In the steps of preprocessing and extracting features for machine learning on the collected atmospheric pressure data, a sliding window technique is used to understand the flow of the collected atmospheric pressure data, and sliding to correct abnormal data. A moving average filter is applied to the barometric pressure values within the window, and the min-max normalization is applied to all barometric pressure data collected to apply the machine learning to the same scale, and the rate of change (Rate) is applied. of change), mean-crossing rate, standard deviation, RMS (Root Mean Square), RSS (Root sum square), Interquartile Range, Kurtosis, and Absolute value difference) is extracted.

The step of detecting the user's door passing event according to the change of the atmospheric pressure data through machine learning of the pre-processed and extracted features is to divide the atmospheric pressure data into a plurality of groups for machine learning of the pre-processed and extracted features, and then The process of randomly selecting one group from among the groups and verifying the remaining learned groups, and randomly selecting one group among a plurality of groups and verifying the remaining learned groups is repeated as many as the number of groups.

The step of controlling to block or receive the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device according to the detected user's door passing event is when the user enters the building when the door passing event is detected , the step of blocking the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device, and when a door passing event that the user exits the building is detected, receiving the blocked GPS signal again. When the user enters the building and the GPS signal is blocked, the last GPS signal is fixed to control the building unit location tracking.

In another aspect, the building access detection device using a barometer proposed in the present invention uses a barometric pressure sensor to collect barometric data according to a difference in barometric pressure that occurs when a user passes through a door, the collected barometric pressure A preprocessing and feature extraction unit that extracts preprocessing and features for machine learning of data, an event detector that detects a user's door passing event according to a change in atmospheric pressure data through machine learning of preprocessing and extracted features, and a detected and a signal controller for controlling to block or receive a GPS signal transmitted to the user's smart wearable device and a smart terminal interworking with the smart wearable device according to the user's door passing event.

It is possible to provide important information for LBS (Location Based Service), such as advertisements, disaster text messages, location tracking services, etc. according to the location of a user such as a shopping mall, through the method and apparatus for detecting access to a building using a barometer according to embodiments of the present invention have. Through the proposed barometer-using building access detection method and device, it is possible to improve the high battery consumption and low reliability indoors of the existing location tracking using GPS in the building unit location tracking technology. In addition, by grafting the technology of the present invention with smart clothing, it is possible to solve the existing disadvantages of late discovery by entering buildings when infants and the elderly are missing, and when wearing smart clothing incorporating the technology of the present invention, research institute It has great potential for development into various technologies, such as detecting when an important facility such as an important facility has gone outside and operating a security device in a building.

1 is a diagram illustrating a consumer awareness survey and global wearable device shipment forecast for wearable devices.
2 is a diagram for explaining a position data error that occurs due to GPS multipath according to the prior art.
3 is a flowchart illustrating a method of detecting entrance to a building using a barometer according to an embodiment of the present invention.
4 is a diagram showing the configuration of a building access detection device using a barometer according to an embodiment of the present invention.
5 is a diagram illustrating a sudden change in atmospheric pressure observed when a user goes out from indoors to outdoors according to an embodiment of the present invention.
6 is a schematic diagram for explaining a building access detection process using a barometer according to an embodiment of the present invention.
7 is a diagram illustrating a result of learning six machine learning classifiers for each sentence type according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Indoor/outdoor detection using a door passing event according to an embodiment of the present invention is a technology for discriminating whether a user is indoors or outdoors in a building. The proposed indoor and outdoor detection can provide important information to LBS (Location Based Service). For example, advertisements according to the user's location such as a shopping mall, disaster text messages, location tracking services, etc. may be provided.

The door passing event refers to an event when a user passes through a door of a building, and this door passing event may give an important hint to indoor/outdoor detection. A technology that informs a specific building that a user has entered is a great help in providing LBS. For example, in the case of missing children and the elderly, it is difficult to locate them if they are inside a building, which is more time consuming.

Building unit location tracking technology according to an embodiment of the present invention can help to make a quick judgment in a situation requiring such an accurate location.

The location tracking technology according to the prior art can be roughly divided into a method using a GPS and a method using a sensor of a smart terminal.

2 is a diagram for explaining a position data error that occurs due to GPS multipath according to the prior art.

Indoor and outdoor detection technology using GPS can provide highly accurate location information outdoors. However, in an environment where GPS signals are disturbed, such as indoors, there is a problem in that the accuracy of location information is very poor due to a GPS multipath error and a non-line-of-sight (NLOS) problem. As shown in FIG. 2 , the position data error caused by the GPS multipath may appear up to 800 m.

Also, the GPS is a sensor having the largest amount of battery consumption among sensors in a smart terminal.

Indoor/outdoor detection technology using smart terminals is a detection method using a combination of several sensors, such as light, magnetic, and cell tower sensors. However, since the location of the smart terminal is not fixed in real life (eg, in a user's hand, in a bag, in a pocket, etc.), it is difficult to apply the results of the prior art to real life.

3 is a flowchart illustrating a method of detecting entrance to a building using a barometer according to an embodiment of the present invention.

The proposed building access detection method using a barometer is a step 310 of collecting air pressure data according to the difference in air pressure that occurs when a user passes through a door using a barometric pressure sensor of a smart wearable device, and machine learning for the collected air pressure data. Step 320 of pre-processing and extracting features for the purpose of detecting the user's door passing event according to the change of atmospheric pressure data through machine learning for the pre-processing and extracted features (330) and the detected user's door passing event and controlling to block or receive a GPS signal transmitted to the user's smart wearable device and a smart terminal interworking with the smart wearable device according to the user's smart wearable device ( 340 ).

In step 310, the barometric pressure data according to the barometric pressure difference generated when the user passes through the door is collected by using the barometric pressure sensor of the smart wearable device. A smart wearable device according to an embodiment of the present invention may include smart clothing, smart shoes, smart jewelry, smart headgear, smart wristband, smart glasses, and a smart watch.

Most buildings are equipped with HVAC (Heating, Ventilating and Air Conditioning) systems. Under the influence of these systems, there is a difference in temperature and pressure between the inside and outside of the building.

The air pressure sensor of the smart wearable device according to an embodiment of the present invention may detect a large change in air pressure that occurs when a user opens a building door.

In step 320, pre-processing and features are extracted for machine learning on the collected atmospheric pressure data.

A sliding window technique is used to understand the flow of the collected atmospheric pressure data, and a moving average filter is applied to atmospheric pressure values within the sliding window to correct abnormal data. Thereafter, all collected atmospheric pressure data to be applied to machine learning are unified to the same scale through Min-max normalization.

The extracted features are rate of change, mean-crossing rate, standard deviation, RMS (Root Mean Square), RSS (Root sum square), Interquartile Range, and kurtosis ( Kurtosis) and absolute value difference.

In step 330, a user's door passing event according to a change in atmospheric pressure data is detected through pre-processing and machine learning for the extracted features.

After dividing the atmospheric pressure data into a plurality of groups for pre-processing and machine learning of the extracted features, one group is randomly selected among the plurality of groups and the remaining learned groups are verified. Thereafter, the process of randomly selecting one group from among the plurality of groups and verifying the remaining learned groups is repeated as many as the number of the plurality of groups.

In step 340, according to the detected user's door passing event, the user's smart wearable device and the GPS signal transmitted to the smart terminal interworking with the smart wearable device are controlled to be blocked or received.

When an event that the user enters the building is detected, the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device is blocked. On the other hand, when an event that the user exits the building is detected, the blocked GPS signal is received again.

When the user enters the building and the GPS signal is blocked, the last GPS signal is fixed to control the building unit location tracking. Hereinafter, a method and apparatus for detecting entrance to a building using a barometer according to an embodiment of the present invention will be described in more detail with reference to FIGS. 4 to 6 .

4 is a diagram showing the configuration of a building access detection device using a barometer according to an embodiment of the present invention.

The proposed building access detection device 400 using a barometer includes a barometric pressure data collection unit 410 , a pre-processing and feature extraction unit 420 , an event detection unit 430 , and a signal control unit 440 .

The air pressure data collection unit 410 includes an air pressure sensor. The barometric pressure data according to the barometric pressure difference generated when the user passes through the door is collected by using the barometric pressure sensor of the barometric pressure data collecting unit 410 .

Most buildings are equipped with HVAC (Heating, Ventilating and Air Conditioning) systems. Under the influence of these systems, there is a difference in temperature and pressure between the inside and outside of the building.

5 is a diagram illustrating a sudden change in atmospheric pressure observed when a user goes out from indoors to outdoors according to an embodiment of the present invention.

The air pressure sensor of the smart wearable device according to an embodiment of the present invention may detect a large change in air pressure that occurs when a user opens a building door (see FIG. 5 ). In addition, there is an advantage of consuming a small amount of energy compared to the GPS sensor.

A smart wearable device, for example, a smart watch is fixed on a user's wrist most of the time. In addition to smart watches, smart wearable devices such as smart clothes, smart shoes, smart jewelry, smart headgear, smart wristbands, and smart glasses are fixed as worn by the user most of the time.

This means that the smart wearable device is the most physically closest to the user among other mobile devices, which is an optimal device for representing the user's surrounding environment.

6 is a schematic diagram for explaining a building access detection process using a barometer according to an embodiment of the present invention.

According to an embodiment of the present invention, a first atmospheric pressure data collection agent (eg, Tizen based) and a second data to be linked thereto are collected in order to detect a door passing event using a barometric pressure sensor in the smart wearable device An agent (eg, based on Android) may be used (see FIG. 6(a) ).

According to an embodiment of the present invention, atmospheric pressure data may be collected at a sampling rate of 10 Hz (see FIG. 6(b)).

The barometric pressure data collection process is as follows: First, the second data collection agent sends a signal to the first atmospheric pressure data collection agent. The first Tizen agent receives the signal and starts collecting barometric pressure data. In order to use supervised learning in machine learning, the second data collection agent provides the user's current situation (eg, indoors, through a door, outdoors) as ground truth.

In order to reflect the various environments according to the embodiment of the present invention, experiments were conducted in various places such as a library and a shopping mall. In addition, for application to various environments according to an embodiment of the present invention, data were collected by dividing the passing door type into four types: automatic door, revolving door, sliding door, and sliding door. Using the collected data, the air pressure pattern learning and classification using machine learning is performed (refer to FIG. 6(c)).

Thereafter, when an event through which the user enters the building is detected through learning, the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device is blocked, and the user enters the building and the GPS signal is blocked, the last GPS signal is fixed to control to perform building unit location tracking (refer to FIG. 6(d)).

The pre-processing and feature extraction unit 420 extracts pre-processing and features for machine learning on the collected atmospheric pressure data.

According to an embodiment of the present invention, the pre-processing and feature extraction unit 420 uses a sliding window technique to understand the flow of the collected atmospheric pressure data. For example, the length can be set to 3 seconds to accommodate a series of processes in which the user opens, passes, and closes a door.

The barometric pressure sensor is a sensor that responds sensitively to small changes in the environment. Accordingly, a moving average filter may be applied to barometric pressure values within the sliding window in order to correct abnormal data that may be generated by certain factors.

In order to apply the processed data to the machine learning classifier, it is necessary to unify the processed data to the same scale. To this end, a min-max normalization technique is applied to all atmospheric pressure data.

Then, feature extraction is performed on the atmospheric pressure data to apply to machine learning.

The extracted features are Rate of change, Mean-crossing rate, Standard deviation, RMS (Root Mean Square), RSS (Root sum square), Interquartile Range (3rd quartile) value - quartile value), kurtosis, and absolute value difference (absolute value of maximum-minimum value within the sliding window).

The event detection unit 430 detects a user's door passing event according to a change in atmospheric pressure data through pre-processing and machine learning for the extracted features.

The event detector 430 detects a door passing event after learning the features extracted from the atmospheric pressure data in machine learning.

A machine learning tool according to an embodiment of the present invention uses WEKA. A total of six machine learning classifiers for machine learning are used: Random Forest, J48 Decision Tree, Naive Bayes, Bayes Net, Supported Vector Machine (SVM), and Locally Weighted Learning (LWL). When performing such machine learning, the K-fold cross validation technique showed the highest accuracy.

K-cross-validation is a learning method in which the data is randomly divided into K groups, and then the procedure of training K-1 groups and verifying them with the remaining one dataset is repeated K times. In order to check whether there is a difference according to the type of the above-mentioned statement, the learning is carried out by dividing the data for each statement.

The signal controller 440 controls to block or receive a GPS signal transmitted to the user's smart wearable device and a smart terminal interworking with the smart wearable device according to the detected user's door passing event.

The signal controller 440 blocks the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device when a door passing event through which the user enters the building is detected. On the other hand, when the event that the user exits the building is detected, the blocked GPS signal is received again. When the user enters the building and the GPS signal is blocked, the signal controller 440 fixes the last GPS signal and controls the building unit location tracking to be performed.

7 is a diagram illustrating a result of learning six machine learning classifiers for each sentence type according to an embodiment of the present invention.

In order to find out about the detection accuracy of the door passing event for the type of door according to an embodiment of the present invention, an automatic door (FIG. 7(a)), a revolving door (FIG. 7(b)), a push door (FIG. 7(c)), Learning was carried out for a total of four doors (Fig. 7(d)) to pull.

7 shows the learning accuracy of six classifiers for each sentence type.

When looking at the overall average, the automatic statement showed the highest accuracy, and by classifier, the Random Forest classifier showed the highest accuracy with an average accuracy of 88.53%. Table 1 shows the results of applying the random forest classifier to the entire data.

<Table 1>

A real-time Building Level Location Tracking System can be built by integrating the machine learning results according to an embodiment of the present invention and the GPS in the smart terminal. This real-time building unit location tracking system can be implemented on a board such as Arduino and applied to smart clothing.

According to an embodiment of the present invention, by using the barometric pressure sensor built into the smart wearable device, it is possible to detect the user's door passing event to perform the building unit location tracking.

This building unit location tracking technology can improve the disadvantages of location tracking using the existing GPS, such as high battery consumption and low reliability indoors. In addition, it is a technology developed one step further from the existing indoor/outdoor detection technology, which merely identifies whether a user is indoors or outdoors.

By combining the building access detection technology using the barometer according to an embodiment of the present invention with the technology to find out which building (eg, shopping mall, library, etc.) the user enters, it is used to provide notifications, advertisements, etc. suitable for the place. usability can be increased.

By combining the building access detection technology using a barometer according to an embodiment of the present invention with smart clothing, it is possible to solve the existing disadvantages of late detection by entering a building when infants and the elderly are missing, and important facilities such as research institutes There is a great potential for development into various technologies, such as detecting when you are outside and operating a security device in a building.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable array (FPA), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be embodied in The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (8)

collecting air pressure data according to a pressure difference generated when a user passes through a door by using a pressure sensor of a smart wearable device;
Pre-processing and extracting features for machine learning on the collected atmospheric pressure data;
Detecting a user's door passing event according to a change in atmospheric pressure data through pre-processing and machine learning for the extracted features; and
Controlling to block or receive the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device according to the detected user's door passing event
A method of detecting entrance to a building using a barometer comprising a. According to claim 1,
The steps of preprocessing and extracting features for machine learning on the collected atmospheric pressure data are:
A sliding window technique is used to understand the flow of the collected atmospheric pressure data, and a moving average filter is applied to the atmospheric pressure values in the sliding window to correct abnormal data, and the machine Unify to the same scale through Min-max normalization on all atmospheric pressure data collected to apply to learning,
Rate of change, Mean-crossing rate, Standard deviation, RMS (Root Mean Square), RSS (Root sum square), Interquartile Range, Kurtosis and Absolute Extracting features including absolute value difference
A method of detecting entrance to a building using a barometer. According to claim 1,
The step of detecting the user's door passing event according to the change of atmospheric pressure data through machine learning of the pre-processed and extracted features,
After dividing the atmospheric pressure data into a plurality of groups for pre-processing and machine learning of the extracted features, one group is randomly selected from among the plurality of groups to verify the remaining learned groups, and one group from the plurality of groups is selected. The process of selecting randomly and verifying the remaining learned groups is repeated as many as the number of groups.
A method of detecting entrance to a building using a barometer. According to claim 1,
The step of controlling to block or receive the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device according to the detected user's door passing event,
blocking the GPS signal transmitted to the user's smart wearable device and the smart terminal interworking with the smart wearable device when the user's entrance into the building event is detected; and
When a user exits the building and a door pass event is detected, the step of re-receiving the blocked GPS signal
including,
When the user enters the building and the GPS signal is blocked, the last GPS signal is fixed to control the building unit location tracking.
A method of detecting entrance to a building using a barometer. A barometric pressure data collection unit that collects barometric pressure data according to the barometric pressure difference that occurs when the user passes through the door using the barometric pressure sensor:
a pre-processing and feature extraction unit for extracting pre-processing and features for machine learning on the collected atmospheric pressure data;
an event detector for detecting a user's door passing event according to a change in atmospheric pressure data through pre-processing and machine learning for the extracted features; and
A signal control unit controlling to block or receive a GPS signal transmitted to the user's smart wearable device and a smart terminal interworking with the smart wearable device according to the detected user's door passing event
A building access detection device using a barometer comprising a. 6. The method of claim 5,
The preprocessing and feature extraction unit,
A sliding window technique is used to understand the flow of the collected atmospheric pressure data, and a moving average filter is applied to the atmospheric pressure values in the sliding window to correct abnormal data, and the machine Unify to the same scale through Min-max normalization on all atmospheric pressure data collected to apply to learning,
Rate of change, Mean-crossing rate, Standard deviation, RMS (Root Mean Square), RSS (Root sum square), Interquartile Range, Kurtosis and Absolute Extracting features including absolute value difference
Building access detection device using barometer. 6. The method of claim 5,
The event detection unit,
After dividing the atmospheric pressure data into a plurality of groups for pre-processing and machine learning of the extracted features, one group is randomly selected from among the plurality of groups to verify the remaining learned groups, and one group from the plurality of groups is selected. The process of selecting randomly and verifying the remaining learned groups is repeated as many as the number of groups.
Building access detection device using barometer. 6. The method of claim 5,
signal control unit,
When a door pass event that a user enters into a building is detected, the user's smart wearable device and the GPS signal transmitted to the smart terminal interworking with the smart wearable device are blocked,
When a door pass event is detected when the user leaves the building, the blocked GPS signal is received again;
When the user enters the building and the GPS signal is blocked, the last GPS signal is fixed to control the building unit location tracking.
Building access detection device using barometer.

Images