CN116798188A - Falling early warning system setting method based on BCG signals - Google Patents
Falling early warning system setting method based on BCG signals Download PDFInfo
- Publication number
- CN116798188A CN116798188A CN202310978259.2A CN202310978259A CN116798188A CN 116798188 A CN116798188 A CN 116798188A CN 202310978259 A CN202310978259 A CN 202310978259A CN 116798188 A CN116798188 A CN 116798188A
- Authority
- CN
- China
- Prior art keywords
- mattress
- signal
- vibration
- bcg
- falling
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 13
- 230000008034 disappearance Effects 0.000 claims description 11
- 208000027418 Wounds and injury Diseases 0.000 claims description 4
- 230000006378 damage Effects 0.000 claims description 4
- 208000014674 injury Diseases 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 13
- 230000010354 integration Effects 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000003750 conditioning effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000029058 respiratory gaseous exchange Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0407—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis
- G08B21/043—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons based on behaviour analysis detecting an emergency event, e.g. a fall
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/04—Alarms for ensuring the safety of persons responsive to non-activity, e.g. of elderly persons
- G08B21/0438—Sensor means for detecting
- G08B21/0461—Sensor means for detecting integrated or attached to an item closely associated with the person but not worn by the person, e.g. chair, walking stick, bed sensor
Landscapes
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Gerontology & Geriatric Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a fall early warning system setting method based on BCG signals, which belongs to the field of health monitoring, and comprises the steps of setting a plurality of sensors below a mattress, defining a dangerous area of the mattress according to the size of the mattress, initializing vibration propagation speed, establishing a fall detection model, performing scene training and the like, so that the condition that a person is in a bed and the position of the person is judged by monitoring the BCG signals, and notifying guardians in advance when judging that a higher fall or fall risk exists, thereby avoiding falling events; the falling detection is comprehensively carried out through the BCG signals and the vibration signals around the bed, so that misjudgment caused by situations such as falling of articles or sitting of a human body is prevented; the whole method adopts non-contact monitoring, does not need wearable equipment or a camera device, avoids discomfort of a user, and protects the privacy of the user; the sensor is flexible and portable to deploy and high in integration level; the monitoring inaccuracy caused by the movement of equipment and human bodies is avoided without depending on information such as pressure and the like; and the fall early warning and the fall detection can be carried out at the same time.
Description
Technical Field
The invention relates to the field of health monitoring, in particular to a fall early warning system setting method based on a BCG signal.
Background
There are many devices for off-bed detection such as acceleration measuring devices worn by the user, camera monitoring mounted opposite the bed, smart mattresses with pressure sensors mounted, floor mats, etc.
Patent CN111882823B discloses a fall-preventing control method, a control device, a terminal device and a storage medium, but the terminal device such as a watch and a bracelet is required to collect initial position parameters and turning motion parameters. The wearable equipment is used for detecting human body falling based on the accelerometer, and can only send out warning to guardianship personnel in and after falling occurrence, so that early warning is difficult to realize. And wearing type equipment elderly people are likely to forget to wear, not wish to wear or forget to charge. The camera monitoring method based on machine vision has mature application, but the camera has the problem of infringing the privacy of a user, and can cause great psychological stress and discomfort to the user. The intelligent mattress floor mat device is heavy, limits the application scene and has high manufacturing cost.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the purposes of the invention is to provide a fall early warning system setting method based on BCG signals without wearing equipment and photographing.
A fall early warning system setting method based on BCG signals comprises the following steps:
disposing a plurality of sensors under the mattress;
defining a dangerous area of the mattress according to the size of the mattress;
initializing the vibration propagation speed: applying vibration to the mattress above the plurality of sensors, and calculating the propagation speed of the vibration in the mattress according to the time difference of the signals received by the plurality of sensors;
establishing a drop detection model: the drop detection model comprises a two-layer SVM model, and the first-layer SVM is used for classifying BCG signals and non-BCG signals; the second layer SVM classifies the non-BCG signals;
scene training: training the drop detection model to enable the drop detection model to perform scene judgment.
Further, the number of the sensors below the mattress is four, and the four sensors are respectively positioned at four corners of the mattress.
Further, the sensor is a high-sensitivity vibration sensor capable of converting weak vibrations generated by vital activities of a human body into BCG signals and collecting vibration signals around a bed.
Further, in the step of initializing the propagation speed of the vibration, the vibration is applied to the mattress position above each sensor, and the signals received by the n sensors are C at each vibration n 2 Two by two time differences according to C between n sensors n 2 Two-by-two distance differences, corresponding C is calculated n 2 The propagation speed can be obtained by applying m times of vibration at different positions n 2 The average value of the propagation speeds is taken as the final propagation speed.
Further, the number of the sensors below the mattress is four, the four sensors are respectively positioned at four corners of the mattress, vibration is applied to the mattress above the four sensors, 6 speeds are generated when each vibration is performed, 24 speeds are generated when four beats are performed, and an average value of the 24 speeds is used as the propagation speed of the vibration in the mattress.
Further, in the scene training step, the trained data includes data of a plurality of types of ground.
Further, in the step of building the drop detection model, the second layer SVM divides the non-BCG signal into: footsteps, falls, and others.
Further, in the scene training step, when the BCG signal is present, it is determined that the person is in the bed; when the heart of the human body is positioned in a dangerous area, judging that the risk of falling exists, and carrying out early warning; when the disappearance of the BCG signal is detected and the falling signal is detected, judging that the personnel falls; when the disappearance of the BCG signal is detected and the foot step signal is detected, the person is judged to go out of bed.
Further, when the disappearance of the BCG signal is detected, and the falling signal is detected, and no step signal exists in the following 10 seconds, judging falling and falling injury, and notifying guardianship personnel; when the disappearance of the BCG signal is detected, the falling signal is detected, and the step signal is detected for the following 10 seconds, the falling is judged to actively climb up.
Compared with the prior art, the falling early warning system setting method based on the BCG signal judges the state of a person in a bed and the position of the person by monitoring the BCG signal, and notifies a guardian in advance when judging that the person has higher falling or falling risk, so that falling events are avoided; the falling detection is comprehensively carried out through the BCG signals and surrounding vibration signals of furniture, so that misjudgment caused by situations such as falling of articles or sitting of human bodies is prevented; the whole method adopts non-contact monitoring, does not need wearable equipment or a camera device, avoids discomfort of a user, and protects the privacy of the user; the sensor is flexible and portable in deployment, high in integration level and suitable for different use scenes such as beds, chairs, sofas and the like; the monitoring inaccuracy caused by the movement of equipment and human bodies is avoided without depending on information such as pressure and the like; and the fall early warning and the fall detection can be carried out at the same time.
Drawings
FIG. 1 is a flow chart of a fall early warning system setting method based on BCG signals of the present invention;
FIG. 2 is a schematic diagram of the sensor arrangement of the fall warning system setup method based on the BCG signal of FIG. 1 when in bed;
FIG. 3 is a schematic illustration of a speed initialization with the sensor of FIG. 2 disposed in a bed;
FIG. 4 is a schematic diagram of dangerous area division of a fall early warning system setting method based on BCG signals;
FIG. 5 is a diagram of sensor signals when a person who is going out of bed is far away in the fall early warning system setting method based on BCG signals of FIG. 1;
fig. 6 is a diagram of sensor signals when a person rises and falls according to the fall early warning system setting method based on BCG signals of fig. 1.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It will be understood that when an element is referred to as being "fixed to" another element, it can be directly on the other element or be present as another intermediate element through which the element is fixed. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. When an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
FIG. 1 is a flowchart of a fall early warning system setting method based on BCG signals, which comprises the following steps:
disposing a plurality of sensors under the mattress;
defining a dangerous area of the mattress according to the size of the mattress;
initializing the vibration propagation speed: applying vibration to the mattress above the plurality of sensors, and calculating the propagation speed of the vibration in the mattress according to the time difference of the signals received by the plurality of sensors;
establishing a drop detection model: the drop detection model comprises a two-layer SVM model, and the first-layer SVM is used for classifying BCG signals and non-BCG signals; the second layer SVM classifies the non-BCG signals;
scene training: training the drop detection model to enable the drop detection model to perform scene judgment.
In this embodiment, the sensor is a high-sensitivity vibration sensor, and can monitor the respiration of the human body, and weak vibration caused by heart beat on the bed, etc., to convert the weak vibration generated by vital activity of the human body into an electrical signal BCG signal and detect the surrounding vibration signal. When the person is in bed, there is no vibration around, only BCG signal. When the person is not in bed, the sensor signal has no BCG signal and is close to a straight line when the surrounding vibration is small. The sensor is connected with a signal conditioning circuit, and the signal conditioning circuit realizes preprocessing operations such as data enhancement, filtering and the like. Specifically, the number of sensors below the mattress is four, and the four sensors are respectively positioned at four corners of the mattress, as shown in fig. 2.
The dangerous area is defined as follows: knowing the size data of the bed in advance includes: length, width of bed and mattress thickness. After determining these parameters, the device will delimit the area at risk of falling. The fall risk zone is set to a zone within 0.2 meters from the bed edge and within 0.5 x L of the bed tail, L being the length of the bed, as shown in fig. 4. When the person on the bed is an infant, the infant is soft in body, unstable in sleeping posture, high in mobility and easy to fall down. After the infant mode is selected in the corresponding program, under the condition that the size data of the bed is unchanged, the area of the falling risk area is enlarged, the dangerous area in the infant mode is an area within 0.25 meter from the edge of the bed and within 0.5 x L from the tail of the bed, and L is the length of the bed. Different dangerous coefficients are set at different positions of the falling risk area, when the falling risk of the position of the heart of the human body is higher than a threshold value, the falling risk is judged, and early warning signals are transmitted to terminal equipment, such as a guardian mobile phone, through wireless communication, so that the guardian is reminded to help the personnel on the bed to adjust the position.
The vibration propagation speed is initialized specifically as follows: applying vibrations to the mattress position above each sensor, each vibration having a time difference between signals received by the plurality of sensors, based on the plurality of sensorsThe difference in distance between the two propagation velocities is calculated, and the average value of the propagation velocities is used as the final propagation velocity. At each vibration, the signals received by the n sensors are C n 2 Two by two time differences according to C between n sensors n 2 Two-by-two distance differences, corresponding C is calculated n 2 The propagation speed can be obtained by applying m times of vibration at different positions n 2 The average value of the propagation speeds is taken as the final propagation speed. In this embodiment, the number of sensors below the mattress is four, the four sensors are respectively located at four corners of the mattress, vibration is applied to the mattress above the four sensors, each vibration generates 6 speeds, four beats generate 24 speeds altogether, and an average value of the 24 speeds is used as the propagation speed of the vibration in the mattress, as shown in fig. 3.
In the step of establishing the drop detection model, the second layer SVM divides the non-BCG signals into: footsteps, falls, and others.
In the scene training step, the trained data contains data of various types of ground, for example: floors, carpets, floor tiles, etc. to ensure versatility of the model. In the scene training step, when the BCG signal exists, determining that the person is in the bed; when the heart of the human body is positioned in a dangerous area, judging that the risk of falling exists, and carrying out early warning; when the disappearance of the BCG signal is detected and the falling signal is detected, judging that the personnel falls; when the disappearance of the BCG signal is detected and the foot step signal is detected, the person is judged to be far away from the bed, and the sensor signal is shown in fig. 5. Further, when the disappearance of the BCG signal is detected, and the falling signal is detected, if no step signal exists in the following 10 seconds, the falling injury is judged, and a guardian is informed of the falling injury, and at the moment, the sensor signal is shown in fig. 6; when the disappearance of the BCG signal is detected, the falling signal is detected, and the step signal is detected for the following 10 seconds, the falling is judged to actively climb up.
Compared with the prior art, the falling early warning system setting method based on the BCG signal judges the state of a person in a bed and the position of the person by monitoring the BCG signal, and notifies a guardian in advance when judging that the person has higher falling or falling risk, so that falling events are avoided; the falling detection is comprehensively carried out through the BCG signals and surrounding vibration signals of furniture, so that misjudgment caused by situations such as falling of articles or sitting of human bodies is prevented; the whole method adopts non-contact monitoring, does not need wearable equipment and camera shooting, does not cause discomfort of a user, and protects the privacy of the user; the sensor is flexible and portable in deployment, high in integration level and suitable for different use scenes such as beds, chairs, sofas and the like; the monitoring inaccuracy caused by the movement of equipment and human bodies is avoided without depending on information such as pressure and the like; and the fall early warning and the fall detection can be carried out at the same time.
The foregoing examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, it is possible to make several modifications and improvements without departing from the concept of the present invention, which are equivalent to the above embodiments according to the essential technology of the present invention, and these are all included in the protection scope of the present invention.
Claims (9)
1. The setting method of the fall early warning system based on the BCG signal is characterized by comprising the following steps:
disposing a plurality of sensors under the mattress;
defining a dangerous area of the mattress according to the size of the mattress;
initializing the vibration propagation speed: applying vibration to the mattress above the plurality of sensors, and calculating the propagation speed of the vibration in the mattress according to the time difference of the signals received by the plurality of sensors;
establishing a drop detection model: the drop detection model comprises a two-layer SVM model, and the first-layer SVM is used for classifying BCG signals and non-BCG signals; the second layer SVM classifies the non-BCG signals;
scene training: training the drop detection model to enable the drop detection model to perform scene judgment.
2. The BCG signal-based fall warning system setting method of claim 1, wherein: the number of the sensors below the mattress is four, and the four sensors are respectively positioned at four corners of the mattress.
3. The BCG signal-based fall warning system setting method of claim 1, wherein: the sensor is a high-sensitivity vibration sensor which can convert weak vibration generated by vital activities of a human body into a BCG signal and can collect vibration signals around a bed.
4. The BCG signal-based fall warning system setting method of claim 1, wherein: in the step of initializing the propagation speed of vibration, vibration is applied to the mattress position above each sensor, and each vibration is performed, a time difference exists between signals received by a plurality of sensors, the propagation speed is calculated according to the distance difference between the plurality of sensors, and an average value of the plurality of propagation speeds is used as a final propagation speed.
5. The BCG signal-based fall warning system setting method of claim 4, wherein: the number of the sensors below the mattress is four, the four sensors are respectively positioned at four corners of the mattress, vibration is applied to the mattress above the four sensors, 6 speeds are generated when each vibration is performed, 24 speeds are generated when four beats are performed, and the average value of the 24 speeds is used as the propagation speed of the vibration in the mattress.
6. The BCG signal-based fall warning system setting method of claim 1, wherein: in the scene training step, the trained data includes data of a plurality of types of ground.
7. The BCG signal-based fall warning system setting method of claim 1, wherein: in the step of establishing the drop detection model, the second layer SVM divides the non-BCG signal into: footsteps, falls, and others.
8. The BCG signal-based fall warning system setting method of claim 7, wherein: in the scene training step, when a BCG signal exists, determining that a person is in a bed; when the heart of the human body is positioned in a dangerous area, judging that the risk of falling exists, and carrying out early warning; when the disappearance of the BCG signal is detected and the falling signal is detected, judging that the personnel falls; when the disappearance of the BCG signal is detected and the foot step signal is detected, the person is judged to go out of bed.
9. The BCG signal-based fall warning system setting method of claim 8, wherein: when the BCG signal is detected to disappear and the falling signal is detected, judging falling and falling injury when no step signal exists in the following 10 seconds, and notifying guardianship personnel; when the disappearance of the BCG signal is detected, the falling signal is detected, and the step signal is detected for the following 10 seconds, the falling is judged to actively climb up.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310978259.2A CN116798188A (en) | 2023-08-04 | 2023-08-04 | Falling early warning system setting method based on BCG signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310978259.2A CN116798188A (en) | 2023-08-04 | 2023-08-04 | Falling early warning system setting method based on BCG signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116798188A true CN116798188A (en) | 2023-09-22 |
Family
ID=88036988
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310978259.2A Pending CN116798188A (en) | 2023-08-04 | 2023-08-04 | Falling early warning system setting method based on BCG signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116798188A (en) |
-
2023
- 2023-08-04 CN CN202310978259.2A patent/CN116798188A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2929837B1 (en) | Method to determine positions and states of an activity monitoring device | |
| CN108042108B (en) | Sleep quality monitoring method and system based on body vibration signals | |
| Yu | Approaches and principles of fall detection for elderly and patient | |
| Wang et al. | An enhanced fall detection system for elderly person monitoring using consumer home networks | |
| CN205041401U (en) | Equipment is worn detection device and is had and wears guardianship device that detects function | |
| US9704369B2 (en) | Autonomous fall monitor using an altimeter with opposed sensing ports | |
| JP5674766B2 (en) | Sensing device for detecting wearing position | |
| Hijaz et al. | Survey of fall detection and daily activity monitoring techniques | |
| US20090161915A1 (en) | Multi-person pose recognition system using a zigbee wireless sensor network | |
| Kepski et al. | Fuzzy inference-based reliable fall detection using Kinect and accelerometer | |
| US20120123277A1 (en) | Method for detecting an extraordinary situation | |
| Ariani et al. | Software simulation of unobtrusive falls detection at night-time using passive infrared and pressure mat sensors | |
| CN103961109A (en) | Human body posture detection device based on acceleration signals and angular speed signals | |
| WO2002061705A1 (en) | System and method for analyizing activity of a body | |
| JP3378540B2 (en) | Abnormality determination device and program recording medium | |
| CN103337132A (en) | Tumble detection method for human body based on three-axis acceleration sensor | |
| KR101856053B1 (en) | A shoe pad for coping with dangerous situation and a method for distinguishing dangerous situation using the same | |
| CN110313917B (en) | Fall-down sensing system and method using daily life movement as judgment reference | |
| US11972863B2 (en) | Wearable sensor and system thereof | |
| Zhong et al. | A real-time pre-impact fall detection and protection system | |
| Nizam et al. | A study on human fall detection systems: Daily activity classification and sensing techniques | |
| Nukala et al. | A real-time robust fall detection system using a wireless gait analysis sensor and an artificial neural network | |
| Srinivasan et al. | Towards automatic detection of falls using wireless sensors | |
| Bianchi et al. | Falls event detection using triaxial accelerometry and barometric pressure measurement | |
| CN116798188A (en) | Falling early warning system setting method based on BCG signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |