CN105848101A - Old people home care monitoring system based on indoor positioning - Google Patents

Abstract

The embodiment of the present invention discloses a home care monitoring system for the elderly based on indoor positioning. The system includes: an indoor positioning module, which is used to locate the indoor position of the elderly to obtain positioning information, and perform early warning according to the positioning information; The sensing module is used to sense the state of the elderly, and performs fall detection according to the state; the processing module is used to process the positioning information, and store the processed positioning information in the fingerprint database. In the embodiment of the present invention, the indoor positioning of the WIFI fingerprint positioning algorithm and the acceleration change analysis of the three-axis sensor are combined to locate the position of the elderly indoors at any time, detect the dangerous situation of the elderly in real time, and call the police if there is any suspicious situation. It enables the elderly at home to deal with the situation at home in time, and can record the living habits and other behaviors of the elderly, so as to realize real-time monitoring of the elderly, reduce manpower consumption, and improve time efficiency.

Description

A home care monitoring system for the elderly based on indoor positioning

technical field

The invention relates to the technical field of data monitoring, in particular to an indoor positioning-based elderly care monitoring system at home.

Background technique

With the intensification of the population aging trend in today's Chinese society, the needs of the elderly for home care are increasing, and the purpose of developing the elderly fall detection system is to be able to detect the elderly's movement status and vital signs at any time, and in case of physical discomfort or accident. When the emergency occurs, an alarm signal is sent to promptly notify the children or the hospital, community, relatives, neighbors, etc. to perform rescue. Realize intelligent care for the elderly. At present, the most popular elderly fall detection systems are mainly divided into: intelligent elderly positioning care system based on ZigBee technology, human body fall alarm based on GSM/GPRS and elderly fall software based on Android platform.

Adopt Zigbee wireless technology, combined with smart card, sensor and embedded system technology, design and develop a set of software and hardware combined with elderly positioning monitoring system, using 2.4GISM frequency band. Background monitoring software integrates geographical information system, database, graphical interface and other technical applications. Zigbee technology uses self-organizing network. The more Zigbee terminals are used, the more accurate Zigbee positioning will be. However, considering that there are many elderly people living alone and there are not enough terminals indoors, it is not possible to use Zigbee for positioning. Meet the basic requirements of accurate positioning; on the other hand, considering that the living space of the elderly living alone is relatively small, the WiFi indoor positioning technology based on the fingerprint positioning algorithm has more advantages than Zigbee positioning.

The human body fall device sends out an alarm through GSM/GPRS when the state of the human body changes, and it is divided into an automatic alarm function for an accidental fall and an active alarm function for emergency situations. GSM/GPRS positioning technology is often used in outdoor positioning. Its timeliness cannot meet the requirements of risk early warning, and the cost is relatively high. And this positioning technology requires an open environment. Once it is indoors, the signal may be weakened by many irregular objects and walls. In this case, GSM/GPRS may not be able to quickly locate or even locate.

A software system developed based on smart phones to detect whether the elderly have fallen. When the elderly fall under different circumstances, the acceleration sensor is used to judge whether the elderly has fallen. After the fall, the software system will call the SMS. The relevant function sends the information of the pre-set content to the guardian of the old man. First of all, the use of the Android platform-based elderly fall software also requires users to have a smart phone, which does not take into account the fact that most elderly people do not use smart phones; in addition, the cost of purchasing a smart phone is relatively high, And for the elderly, it is very inconvenient to carry a smart phone. If you forget to carry it, you cannot guarantee to detect the physical condition of the elderly; moreover, this method of judging a fall is only judged from the direction of acceleration, and the probability of error is quite high, and it cannot effectively warn of risks.

Contents of the invention

The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a home care monitoring system for the elderly based on indoor positioning, which can record the living habits and other behaviors of the elderly, thereby realizing real-time monitoring of the elderly. Reduce manpower consumption and improve time efficiency.

In order to solve the above-mentioned problems, the present invention proposes a home care monitoring system for the elderly based on indoor positioning, and the system includes:

The indoor positioning module is used to locate the indoor position of the elderly to obtain positioning information, and give early warning according to the positioning information;

The danger sensing module is used to sense the state of the elderly and perform fall detection according to the state;

The processing module is used to process the positioning information, and store the processed positioning information in the fingerprint database.

Preferably, the indoor positioning module includes:

The sampling sub-module is used to collect and record the RSSI values of N APs;

The positioning sub-module is used to measure the RSSI values of the current positioning point for N APs, form an N-dimensional vector P, and obtain the positioning area.

Preferably, the sampling sub-module includes:

The initialization unit is used to divide the entire indoor space into areas in units of rooms and name the areas;

The sampler is used to scan at a constant speed along the area boundary, and collect and record the RSSI values of N APs at a certain frequency.

Preferably, the positioning submodule includes:

The measurement unit is used to measure the RSSI values of the current positioning point for N APs to form an N-dimensional vector P;

The query unit is used to query an N-dimensional vector Q closest to the Euclidean distance of P in the fingerprint database to obtain the positioning area.

Preferably, the indoor positioning module further includes:

The test sub-module is used to select test points around obstacles in the area. If the positioning result is found to be wrong, N RSSI values of sampling points collected around the error position are added to the fingerprint database as an N vector.

Preferably, the system also includes:

The storage module is used to store the collected N RSSI values as an N-dimensional vector in the fingerprint database, and record the corresponding area names in the fingerprint database.

Preferably, the system also includes:

The alarm module is used to determine whether it is located in a dangerous high-incidence area according to the position obtained by positioning, and when the stay in this dangerous area exceeds a certain threshold, an alarm is triggered.

Preferably, the hazard sensing module includes:

The acceleration sensor is used to detect the acceleration change of the elderly's body and obtain the state of the elderly;

The detection unit is used for fall detection in this state.

In the embodiment of the present invention, the indoor positioning of the WIFI fingerprint positioning algorithm and the acceleration change analysis of the three-axis sensor are combined to locate the position of the elderly indoors at any time, detect the dangerous situation of the elderly in real time, and call the police if there is any suspicious situation. It enables the elderly at home to deal with the situation at home in time, and can record the living habits and other behaviors of the elderly, so as to realize real-time monitoring of the elderly, reduce manpower consumption, and improve time efficiency.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

FIG. 1 is a schematic diagram of the structure and composition of an elderly home care monitoring system based on indoor positioning according to an embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Fig. 1 is a schematic diagram of the structural composition of an elderly care monitoring system based on indoor positioning in an embodiment of the present invention. As shown in Fig. 1, the system includes:

The indoor positioning module 1 is used to locate the indoor position of the elderly to obtain positioning information, and perform early warning according to the positioning information;

The danger sensing module 2 is used to sense the state of the elderly, and perform fall detection according to the state;

The processing module 3 is used to process the positioning information, and store the processed positioning information in the fingerprint database.

Further, the indoor positioning module 1 includes:

The sampling sub-module is used to collect and record the RSSI values of N APs;

The positioning sub-module is used to measure the RSSI values of the current positioning point for N APs, form an N-dimensional vector P, and obtain the positioning area.

The sampling submodules include:

The initialization unit is used to divide the entire indoor space into areas in units of rooms and name the areas;

The sampler is used to scan at a constant speed along the area boundary, and collect and record the RSSI values of N APs at a certain frequency.

Assuming that N (N is greater than or equal to 3) APs have been installed in the entire indoor space, the entire indoor space is divided into areas in units of rooms. If the room is relatively large, the room is divided into multiple areas on average, and the area is named. The area boundary is scanned at a constant speed. During the scanning process, the sampler collects and records the RSSI values of N APs at a certain frequency. The N RSSI values obtained by each recording are saved in the fingerprint database as an N-dimensional vector and stored in the fingerprint database. Record the corresponding area name in .

Further, the positioning sub-module includes:

The measurement unit is used to measure the RSSI values of the current positioning point for N APs to form an N-dimensional vector P;

The query unit is used to query an N-dimensional vector Q closest to the Euclidean distance of P in the fingerprint database to obtain the positioning area.

In the process of querying the fingerprint database, the kd tree is used to optimize the query efficiency.

Further, the indoor positioning module also includes:

The test sub-module is used to select test points around obstacles in the area. If the positioning result is found to be wrong, N RSSI values of sampling points collected around the error position are added to the fingerprint database as an N vector.

In the process of testing the positioning accuracy, try to select test points around obstacles in the area. If the positioning result is found to be wrong, collect N RSSI values of sampling points around the wrong position and add them to the fingerprint as an N vector. In this way, the reliability of the whole system can be greatly improved.

As shown in Figure 1, the system also includes:

The storage module 4 is used to store the collected N RSSI values as an N-dimensional vector in the fingerprint database, and record the corresponding area names in the fingerprint database.

The alarm module 5 is used to judge whether it is located in a dangerous high-incidence area according to the position obtained by positioning, and trigger an alarm when staying in this dangerous area exceeds a certain threshold.

Further, the danger sensing module 2 includes:

The acceleration sensor is used to detect the acceleration change of the elderly's body and obtain the state of the elderly;

The detection unit is used for fall detection in this state.

In the specific implementation, it is possible to set in advance which areas are dangerous areas, such as toilets and other places where falls are prone to occur. When the location obtained according to the positioning is located in a dangerous high-incidence area, and when staying in this dangerous area exceeds a certain threshold, an alarm will be triggered. Features.

Predict whether the elderly are in danger based on the acceleration changes in the three directions of the x-axis, y-axis and z-axis of the acceleration sensor. In the embodiment of the present invention, a three-axis acceleration sensor ADXL345 is used.

ADXL345 is a three-axis acceleration sensor with digital output based on MEMS technology. ADXL345 has a variable measurement range of ±2g, ±4g, ±8g, ±16g; the highest 13b resolution measurement; fixed 4mg/LSB sensitivity; 3mm×5mm×1mm ultra-small package; 40～145μA ultra-low power consumption; standard Unique I2C or SPI digital interface; 32-level FIFO storage; and various internal motion state detection and flexible interrupt methods. These characteristics make it an ideal accelerometer for fall detection.

ADXL345 first senses and measures the magnitude of the acceleration by the front-end sensing device, and then converts it into a recognizable electrical signal by the sensing electrical signal device, which is an analog signal. The ADXL345 integrated A/D converter converts this analog signal into a digital signal.

The three coordinates of the three-axis acceleration sensor correspond to the coordinates of the human body respectively. The x-axis represents the acceleration change in the left-right direction of the human body, the y-axis represents the acceleration change in the front-back direction of the human body, and the z-axis represents the acceleration change in the vertical direction of the human body. When a person is standing or walking, the acceleration of the z-axis is close to g, and the acceleration of the x-axis and y-axis is close to 0. When the human body falls, the acceleration of the three axes and their vector sum will change. By setting a certain threshold, the acceleration changes of the three axes can be judged to determine whether the elderly has fallen.

ADXL345 Interrupts:

Free_fall: When the acceleration value is below a certain threshold and lasts for more than a certain time, the Free_fall interrupt is set.

Activity: When the acceleration value exceeds a certain threshold, the Activity interrupt is set.

Inactivity: When the acceleration value is lower than a certain threshold and lasts for more than a certain period of time, the Inactivity interrupt is set.

Weightlessness detection: There is a weightlessness phenomenon in the process of the human body falling. Although the weightlessness phenomenon is obvious when there is no free fall, the acceleration vector sum will be less than 1g. Use Free_fall to interrupt the judgment of the weightlessness process in the process of the human body falling. As the first basis for judging the state of the fall.

Impact detection: When the human body collides with the ground when it falls, the acceleration vector sum will produce a peak value. Use the Activity interrupt of ADXL345 to detect. Here you need to set a time threshold. Between the weightlessness detection and the impact detection, set the time interval to 200ms. If the Activity interruption still occurs 200ms after the Free_fall interruption, it is considered that the human body did not fall, or it may be caused by the bending action. Acceleration changes.

Static detection: The human body will not stand up immediately when it falls, and will be in a static state for a while. Since the human body changes from vertical to horizontal, the vector sum of the acceleration will be less than a certain value at this time. Use the Inactivity interrupt of ADXL345 to detect. Set the time interval between Activity interruption and Inactivity interruption to 2s. There should be a static state within 3.5s after the impact. If the time expires and the Inactivity interruption has not occurred, it is considered that there is no fall.

Comparison detection with the initial state: the acceleration of the three axes of the human body after falling is different from that when standing. In order to further detect whether the human body has fallen, the acceleration of the three axes before the fall can be compared with the acceleration after the fall. If the difference between the accelerations of each axis exceeds a certain threshold, it is judged as a fall.

In the embodiment of the present invention, the indoor positioning of the WIFI fingerprint positioning algorithm and the acceleration change analysis of the three-axis sensor are combined to locate the position of the elderly indoors at any time, detect the dangerous situation of the elderly in real time, and call the police if there is any suspicious situation. It enables the elderly at home to deal with the situation at home in time, and can record the living habits and other behaviors of the elderly, so as to realize real-time monitoring of the elderly, reduce manpower consumption, and improve time efficiency.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: Read Only Memory (ROM, Read Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

In addition, the above is a detailed introduction to the elderly home care monitoring system based on indoor positioning provided by the embodiment of the present invention. In this paper, specific examples are used to illustrate the principle and implementation of the present invention. The description of the above embodiment is only used To help understand the method of the present invention and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation and scope of application. In summary, this specification The content should not be construed as a limitation of the invention.

Claims (8)

1. A home-based elderly care monitoring system for the elderly based on indoor positioning, characterized in that the system includes: The indoor positioning module is used to locate the indoor position of the elderly to obtain positioning information, and give early warning according to the positioning information; The danger sensing module is used to sense the state of the elderly and perform fall detection according to the state; The processing module is used to process the positioning information, and store the processed positioning information in the fingerprint database. 2. the old people's home care monitoring system based on indoor positioning as claimed in claim 1, is characterized in that, described indoor positioning module comprises: The sampling sub-module is used to collect and record the RSSI values of N APs; The positioning sub-module is used to measure the RSSI values of the current positioning point for N APs, form an N-dimensional vector P, and obtain the positioning area. 3. the old people's home care monitoring system based on indoor positioning as claimed in claim 2, is characterized in that, described sampling sub-module comprises: The initialization unit is used to divide the entire indoor space into areas in units of rooms and name the areas; The sampler is used to scan at a constant speed along the area boundary, and collect and record the RSSI values of N APs at a certain frequency. 4. the old people's home care monitoring system based on indoor positioning as claimed in claim 2, is characterized in that, described positioning sub-module comprises: The measurement unit is used to measure the RSSI values of the current positioning point for N APs to form an N-dimensional vector P; The query unit is used to query an N-dimensional vector Q closest to the Euclidean distance of P in the fingerprint database to obtain the positioning area. 5. The elderly's home care monitoring system based on indoor positioning as claimed in claim 1 or 2, wherein the indoor positioning module also includes: The test sub-module is used to select test points around obstacles in the area. If the positioning result is found to be wrong, N RSSI values of sampling points collected around the error position are added to the fingerprint database as an N vector. 6. The elderly's home care monitoring system based on indoor positioning as claimed in claim 1, wherein the system further comprises: The storage module is used to store the collected N RSSI values as an N-dimensional vector in the fingerprint database, and record the corresponding area names in the fingerprint database. 7. The elderly's home care monitoring system based on indoor positioning as claimed in claim 1, wherein said system also includes: The alarm module is used to determine whether it is located in a dangerous high-incidence area according to the position obtained by positioning, and when the stay in this dangerous area exceeds a certain threshold, an alarm is triggered. 8. The elderly's home care monitoring system based on indoor positioning as claimed in claim 1, wherein the danger sensing module comprises: The acceleration sensor is used to detect the acceleration change of the elderly's body and obtain the state of the elderly; The detection unit is used for fall detection in this state.