CN108771543B - Old man falling detection method and system in real environment based on big data - Google Patents
Old man falling detection method and system in real environment based on big data Download PDFInfo
- Publication number
- CN108771543B CN108771543B CN201810338008.7A CN201810338008A CN108771543B CN 108771543 B CN108771543 B CN 108771543B CN 201810338008 A CN201810338008 A CN 201810338008A CN 108771543 B CN108771543 B CN 108771543B
- Authority
- CN
- China
- Prior art keywords
- behavior
- data
- database
- big data
- module
- 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.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
- A61B5/1117—Fall detection
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
- A61B5/0022—Monitoring a patient using a global network, e.g. telephone networks, internet
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Networks & Wireless Communication (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a method and a system for detecting falling of old people under a real environment based on big data, belonging to the technical field of mode identification and human behavior identification, aiming at solving the technical problems that the existing falling detection system and method have poor accuracy, cannot meet individual difference and cannot obtain old people falling experiment data, and adopting the technical scheme that: the method is based on a big data platform, a system for detecting the falling of the old people in the real environment is constructed by using wearable equipment and the Internet of things technology, the wearable equipment is used for collecting daily behavior data of the old people in the real environment, and the data are transmitted to the big data platform through the Internet of things technology. The old people falling detection system based on big data in a real environment comprises wearable equipment, peripheral alarm equipment and a big data platform, wherein the wearable equipment comprises a sensor, a single chip microcomputer and a wireless transmission module.
Description
Technical Field
The invention relates to the technical field of pattern recognition and human behavior recognition, in particular to a method and a system for detecting falling of old people in a real environment based on big data.
Background
Fall detection systems based on wearable devices are generally worn on the chest, waist, legs, wrists and other parts. The wearable detection equipment is formed by adding the related attitude sensors into the equipment, and the data output by the sensors in the motion process of the experimental object is collected to analyze and detect the falling behavior. The wearable device has the advantage that physiological indexes, such as blood pressure, electrocardio and the like, which cannot be acquired by other video or environment-based fall detection systems can be acquired. Shang-Lin Hsieh et al of TatungUniversity propose a wrist-type fall detection system, and the system is detected through experiments to obtain good average sensitivity and specificity. Pannurat, n. Shany, t. et al utilize wearable sensors for human behavior recognition and fall detection. The Habib, m.a. et al utilizes smart phones for fall detection. Casilari, e. et al propose fall detection schemes based on the Android system. Yuan, J et al propose to utilize an efficient interrupt-driven algorithm for fall detection and human routine behavior identification. The fall detection of a human body is completed by using a smart phone by the vacuums, g. Mederano, C. and the like propose a new method for obtaining acceleration by using a smart phone to perform fall detection. Lopez, J.D. et al have constructed a behavior detection system using multiple accelerations in fusion. Koshmak, g.a. et al combine the Android system and physiological detection for fall detection. Many researchers in China also propose many methods related to fall detection in many times, but most of the methods relate to algorithm improvement or fall detection realized by combining different sensors, and young volunteers are adopted to simulate fall and daily behaviors to obtain experimental data, once the detection algorithms are applied to real old people fall data samples, the fall detection accuracy is greatly reduced.
The problems with currently existing fall detection systems are as follows:
the existing fall detection system obtains experimental data by simulating fall and daily behaviors of young volunteers, and although the accuracy is high, the accuracy of the algorithm is greatly reduced once the algorithm is used for fall detection of old people in a real environment;
(II) the fall detection system cannot meet individual difference, the height and the weight of different users are different in a specific application scene, system parameters are changed in the fall detection process, and the direct effect of the uniform system parameters is that the fall detection error is aggravated;
and thirdly, the old people cannot be subjected to simulated falling to acquire experimental data in the experimental process, namely the real experimental data of falling of the old people is difficult to acquire.
Disclosure of Invention
The invention provides a method and a system for detecting the falling of old people in a real environment based on big data, and aims to solve the problems that the existing falling detection system and method are poor in accuracy, cannot meet individual difference and cannot obtain old people falling experiment data.
The technical task of the invention is realized in the following way, the method for detecting the falling of the old people in the real environment based on big data is based on a big data platform, a system for detecting the falling of the old people in the real environment is constructed by using wearable equipment and the Internet of things technology, the wearable equipment is used for collecting daily behavior data of the old people in the real environment, and the data is transmitted to the big data platform through the Internet of things technology; the method comprises the following specific steps:
s1, the wearable device collects three-axis acceleration data generated by human body activity and transmits the three-axis acceleration data to a central processing system of a big data platform through a wireless network, and the next step is executed in step S2;
s2, the central processing system performs feature extraction and normalization processing on the acquired X, Y, Z triaxial acceleration data, and the next step is executed in the step S3;
s3, judging whether the preset stage is:
(1) if yes, the big data platform is in a preset stage, and the next step is shifted to step S8;
(2) if not, the big data platform is not in the preset stage, and the step S4 is executed next;
s4, detecting human body behavior by using the classifier on the behavior characteristics extracted in the step S2, and executing the step S5;
s5, according to the behavior class detected in the step S4, the central processing system compares the behavior class in the behavior class database with the behavior class detected in the step S4, and judges whether the behavior class is in the behavior class database:
(1) if yes, go to step S6;
(2) if not, jumping to step S7;
and S6, comparing the behavior class detected in the step S4 with the falling behavior class in the behavior class database by the central processing system, and judging whether the behavior class is falling behavior:
(1) if yes, go to step S7;
(2) if not, go to step S9;
s7, the central processing system triggers the alarm module to send an alarm signal to the peripheral alarm device, the peripheral alarm device sends the alarm signal to remind children of the old or nursing personnel that the old is possibly dangerous, and the next step is executed in step S8;
s8, inquiring and confirming the name of the behavior class, storing the behavior class in a behavior class database, and executing the step S9;
and S9, adding the extracted sample characteristics into the corresponding behavior sample database.
Preferably, the wearable device is integrated by a sensor, a wireless transmission module and a single chip microcomputer.
Preferably, the sensor is an ADXL345 sensor, and the wireless transmission module is a wireless transmission module CC 1000.
Preferably, the step S2 of extracting features of the acquired X, Y, Z triaxial acceleration data specifically includes: according to the collected data, an average value on two axes of Y, Z, a quantile value lower than 25 and a quantile value lower than 75 are respectively extracted from the time domain, and the maximum frequency of the frequency spectrum, the frequency component value below 5Hz and the peak value of the frequency spectrum below 5Hz are extracted on the basis of the Y axis on the frequency domain.
More preferably, sample data is extracted in Y, Z two axes, i.e. the acceleration mag in Y, Z two axes is calculated:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. thezRefers to the acceleration value acquired by the wearable sensor on the Z-axis.
Preferably, the average value of Y, Z on two axes in the time domain is:
wherein A isyiRepresenting the i-th acceleration acquired by the wearable sensor on the Y axisSample values; a. theziRepresenting the ith acceleration sample value acquired by the wearable sensor on the Z axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
the 25 quantile p25 and 75 quantile p75 of the mag data are found by using the function prctile (), and the square sum sumsq25 and sumsq75 of the mag data lower than p25 and lower than p75 are calculated, respectively.
More preferably, the dispersion of the acceleration in the Y-axis direction is found based on the feature extraction of the Y-axis in the frequency domain:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. theyiThe method comprises the steps of representing an ith acceleration sample value acquired by a wearable sensor on a Y axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
after performing fast fourier transform on the dispersion, the maximum frequency maxFreq of the spectrum, sum5Hz of frequency components of 5Hz or less, and the peak numPeaks of the spectrum of 5Hz or less are obtained.
Preferably, the time domain feature quantities and the frequency domain feature quantities extracted in step S2 are combined into one feature vector, and the feature vector is normalized.
A system for detecting falling of old people under a real environment based on big data comprises wearable equipment, peripheral alarm equipment and a big data platform, wherein the wearable equipment comprises a sensor, a single chip microcomputer and a wireless transmission module;
the sensor is used for acquiring data of triaxial acceleration generated by human body activity;
the singlechip is used for controlling the working states of the sensor and the wireless transmission module
The wireless transmission module is used for transmitting the data acquired by the sensor to the central processing system;
the database is used for storing daily behavior data of the old in a classified manner under the real environment; the database comprises a behavior class database and a behavior sample database, wherein the behavior class database is used for storing behavior class data, and the behavior sample database is used for storing behavior samples;
the central processing system is used for processing the received data and issuing a processing command;
the peripheral alarm device is used for receiving alarm information sent by the central processing system and sending an alarm signal to remind children or nursing personnel and old people of possible dangerous conditions, and the peripheral alarm device adopts an alarm or a mobile terminal.
Preferably, the central processing system comprises a feature processing module, a preset stage judging module, a classifier, a behavior data comparison module, a falling behavior judging module, an alarm module and a database establishing and maintaining module;
the characteristic processing module is used for extracting and normalizing the characteristics of the triaxial acceleration transmitted to the central processing system by the wireless transmission module;
the old man falling detection system comprises a preset stage judgment module, a storage module and a control module, wherein the preset stage judgment module is used for judging whether the old man falling detection system is in a preset stage;
the classifier adopts a classifier based on SVM, and is used for detecting the human body behavior class of the extracted behavior characteristics;
the behavior class data comparison module is used for judging whether the behavior class detected by the classifier is in the existing behavior class database or not;
the falling behavior judging module is used for judging whether the behavior class detected by the classifier is a falling behavior;
the alarm module is used for sending alarm information to children or nursing staff of the old people in abnormal conditions;
the database creating and maintaining module is used for creating a database, adding a behavior database and a behavior sample database and performing later updating management work.
Compared with the prior art, the old people falling detection method and system based on big data in the real environment have the following advantages:
the invention can effectively solve the problem that the accuracy of the algorithm is greatly reduced when a plurality of current fall detection algorithms are applied to old people in a real environment by using a young person to simulate fall to acquire data Accuracy and detection efficiency;
the behavior of the old people in the real environment is identified and detected by using the Internet of things technology with a big data platform as the background, particularly, the old people can be watched and controlled in real time when falling down, the alarm is timely processed when abnormal conditions occur, the old people can be detected and identified by using the real behavior data of the old people, the old people can be different from person to person, the individuation of samples can be realized, and the accuracy of the behavior judgment of the old people is improved;
and thirdly, the invention can be used for acquiring data samples according to different people by applying a large data platform, so that each person using the invention can acquire own data samples, the data volume of the behavior database and the corresponding sample database is more and more increased along with the increase of the using time, and the detection of the classifier is more and more accurate, thereby being capable of performing fall detection according to different people, simultaneously acquiring samples under a real environment, and being more beneficial to improving the accuracy of the fall detection.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a flow chart of a method for detecting falling of old people in a real environment based on big data;
fig. 2 is a block diagram of a fall detection system for old people in a real environment based on big data.
Detailed Description
The method and system for detecting falls of old people in real environment based on big data according to the present invention will be described in detail below with reference to the drawings and specific embodiments of the specification.
Example (b):
as shown in the attached drawing 1, the method for detecting the falling of the old people in the real environment based on the big data is based on a big data platform, a system for detecting the falling of the old people in the real environment is constructed by using wearable equipment and the internet of things technology, the wearable equipment is used for collecting daily behavior data of the old people in the real environment, and the internet of things technology is used for transmitting the data to the big data platform; the method comprises the following specific steps:
s1, acquiring triaxial acceleration data generated by human body activities by an ADXL345 sensor, a wireless transmission module CC1000 and a single chip microcomputer integrated wearable device, transmitting the triaxial acceleration data to a central processing system of a big data platform through a wireless network, and executing the step S2;
s2, the central processing system performs feature extraction and normalization processing on the acquired X, Y, Z triaxial acceleration data, and the next step is executed in the step S3;
s3, judging whether the preset stage is:
(1) if yes, the big data platform is in a preset stage, and the next step is shifted to step S8;
(2) if not, the big data platform is not in the preset stage, and the step S4 is executed next;
s4, detecting human body behavior by using the classifier on the behavior characteristics extracted in the step S2, and executing the step S5;
s5, according to the behavior class detected in the step S4, the central processing system compares the behavior class in the behavior class database with the behavior class detected in the step S4, and judges whether the behavior class is in the behavior class database:
(1) if yes, go to step S6;
(2) if not, jumping to step S7;
and S6, comparing the behavior class detected in the step S4 with the falling behavior class in the behavior class database by the central processing system, and judging whether the behavior class is falling behavior:
(1) if yes, go to step S7;
(2) if not, go to step S9;
s7, the central processing system triggers the alarm module to send an alarm signal to the peripheral alarm device, the peripheral alarm device sends the alarm signal to remind children of the old or nursing personnel that the old is possibly dangerous, and the next step is executed in step S8;
s8, inquiring and confirming the name of the behavior class, storing the behavior class in a behavior class database, and executing the step S9;
and S9, adding the extracted sample characteristics into the corresponding behavior sample database.
In step S2, the feature extraction of the collected X, Y, Z triaxial acceleration data specifically includes: according to the collected data, an average value on two axes of Y, Z, a quantile value lower than 25 and a quantile value lower than 75 are respectively extracted from a time domain, and the maximum frequency of a frequency spectrum, the frequency component value below 5Hz and the peak value of the frequency spectrum below 5Hz are extracted on the basis of the Y axis on a frequency domain, specifically as follows:
(1) sample data is extracted in Y, Z two axes, i.e. acceleration mag in Y, Z two axes is calculated:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. thezRefers to the acceleration value acquired by the wearable sensor on the Z-axis.
(2) And Y, Z, extracting the mean value of two axes in the time domain as follows:
wherein A isyiRepresenting wearable relaysAcquiring an ith acceleration sample value on a Y axis by the sensor; a. theziRepresenting the ith acceleration sample value acquired by the wearable sensor on the Z axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
the 25 quantile p25 and 75 quantile p75 of the mag data are found by using the function prctile (), and the square sum sumsq25 and sumsq75 of the mag data lower than p25 and lower than p75 are calculated, respectively.
(3) And extracting the characteristics based on the Y axis in the frequency domain to obtain the acceleration dispersion in the Y axis direction:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. theyiThe method comprises the steps of representing an ith acceleration sample value acquired by a wearable sensor on a Y axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
after fast Fourier transform is carried out on the dispersion, the maximum frequency maxFreq of the frequency spectrum, sum5Hz of frequency components below 5Hz and the peak numPeaks of the frequency spectrum below 5Hz are respectively obtained;
(4) and combining the extracted time domain and frequency domain characteristic quantities into a characteristic vector, and carrying out normalization processing on the characteristic vector.
Example 2:
as shown in fig. 2, the old people falling detection system based on big data in real environment of the invention comprises wearable equipment, peripheral alarm equipment and a big data platform, wherein the wearable equipment comprises a sensor, a single chip microcomputer and a wireless transmission module; the sensor is used for acquiring data of triaxial acceleration generated by human body activity; the singlechip is used for controlling the working state wireless transmission module of the sensor and the wireless transmission module and transmitting the data acquired by the sensor to the central processing system; the database is used for storing daily behavior data of the old in a classified manner under the real environment; the database comprises a behavior class database and a behavior sample database, wherein the behavior class database is used for storing behavior class data, and the behavior sample database is used for storing behavior samples; the central processing system is used for processing the received data and issuing a processing command; the peripheral alarm device is used for receiving alarm information sent by the central processing system and sending an alarm signal to remind children or nursing personnel and old people of possible dangerous conditions, and the peripheral alarm device adopts an alarm or a mobile terminal.
The central processing system comprises a feature processing module, a preset stage judging module, a classifier, a behavior data comparison module, a falling behavior judging module, an alarm module and a database establishing and maintaining module; the characteristic processing module is used for extracting and normalizing the characteristics of the triaxial acceleration transmitted to the central processing system by the wireless transmission module; the old man falling detection system comprises a preset stage judgment module, a storage module and a control module, wherein the preset stage judgment module is used for judging whether the old man falling detection system is in a preset stage; the classifier adopts a classifier based on SVM, and is used for detecting the human body behavior class of the extracted behavior characteristics; the behavior class data comparison module is used for judging whether the behavior class detected by the classifier is in the existing behavior class database or not; the falling behavior judging module is used for judging whether the behavior class detected by the classifier is a falling behavior; the alarm module is used for sending alarm information to children or nursing staff of the old people in abnormal conditions; the database creating and maintaining module is used for creating a database, adding a behavior database and a behavior sample database and performing later updating management work.
The specific working process is as follows:
the method comprises the following steps that (A), a single chip microcomputer and a sensor are used for collecting data of three-axis acceleration generated by human body activity, and a wireless transmission module is used for transmitting the data to a central processing system of a big data platform;
and (II) the central processing system performs feature extraction and normalization processing on the received data through a feature processing module, and judges whether the system is in a preset stage or not through a preset stage judging module:
if the central processing system is set as a preset stage at the stage of starting to use, a database creation and maintenance module is used for adding some daily behavior and action classes of an individual and collecting data samples, so as to provide samples for later-stage classifier detection;
(II) after the normal use stage, detecting the collected data characteristics by using a classifier, and judging whether the behavior class is in the database or not by using a behavior class data comparison module:
if the behavior class is in the behavior class database, the falling behavior judging module is used for judging whether the behavior is a falling behavior:
firstly, if the person falls down, an alarm module is triggered to alarm;
secondly, if the behavior is not a falling behavior, adding the extracted data features into a data sample library of the corresponding behavior class;
(ii) if the behavior class is not in the behavior class database, namely the classifier detects that the behavior class is unknown, firstly triggering an alarm module to give an alarm, and simultaneously sending an alarm signal by peripheral alarm equipment (because the daily behaviors in the behavior class database are stored, if the unknown behavior class is detected, the alarm is suspected of falling down, and the alarm is triggered firstly for safety); and then confirming the name of the behavior class, storing the new behavior class into a behavior class database through a database creation and maintenance module, and simultaneously adding the data characteristics into the corresponding behavior class database.
The present invention can be easily implemented by those skilled in the art from the above detailed description. It should be understood, however, that the intention is not to limit the invention to the particular embodiments described. On the basis of the disclosed embodiments, a person skilled in the art can combine different technical features at will, thereby implementing different technical solutions.
In addition to the technical features described in the specification, the technology is known to those skilled in the art.
Claims (9)
1. A method for detecting the falling of old people in a real environment based on big data is characterized in that the method is based on a big data platform, a system for detecting the falling of old people in the real environment is constructed by using wearable equipment and the Internet of things technology, the wearable equipment is used for collecting daily behavior data of the old people in the real environment, and the Internet of things technology is used for transmitting the data to the big data platform; the method comprises the following specific steps:
s1, the wearable device collects three-axis acceleration data generated by human body activity and transmits the three-axis acceleration data to a central processing system of a big data platform through a wireless network, and the next step is executed in step S2;
s2, the central processing system performs feature extraction and normalization processing on the acquired X, Y, Z triaxial acceleration data, and the next step is executed in the step S3;
s3, judging whether the preset stage is:
(1) if yes, the big data platform is in a preset stage, and the next step is shifted to step S8;
(2) if not, the big data platform is not in the preset stage, and the step S4 is executed next;
s4, detecting human body behavior by using the classifier on the behavior characteristics extracted in the step S2, and executing the step S5;
s5, according to the behavior class detected in the step S4, the central processing system compares the behavior class in the behavior class database with the behavior class detected in the step S4, and judges whether the behavior class is in the behavior class database:
(1) if yes, go to step S6;
(2) if not, jumping to step S7;
and S6, comparing the behavior class detected in the step S4 with the falling behavior class in the behavior class database by the central processing system, and judging whether the behavior class is falling behavior:
(1) if yes, go to step S7;
(2) if not, go to step S9;
s7, the central processing system triggers the alarm module to send an alarm signal to the peripheral alarm device, the peripheral alarm device sends the alarm signal to remind children of the old or nursing personnel that the old is possibly dangerous, and the next step is executed in step S8;
s8, inquiring and confirming the name of the behavior class, storing the behavior class in a behavior class database, and executing the step S9;
and S9, adding the extracted sample characteristics into the corresponding behavior sample database.
2. The method for detecting the fall of the old man in the real environment based on the big data as claimed in claim 1, wherein the wearable device is integrated by a sensor, a wireless transmission module and a single chip microcomputer.
3. The method for detecting the fall of the old people in the real environment based on the big data as claimed in claim 2, wherein the sensor is ADXL345 sensor, and the wireless transmission module is CC 1000.
4. The method for detecting the fall of the old man under the real environment based on the big data as claimed in claim 1, wherein the step S2 of performing feature extraction on the collected X, Y, Z triaxial acceleration data specifically comprises: according to the collected data, an average value on two axes of Y, Z, a quantile value lower than 25 and a quantile value lower than 75 are respectively extracted from the time domain, and the maximum frequency of the frequency spectrum, the frequency component value below 5Hz and the peak value of the frequency spectrum below 5Hz are extracted on the basis of the Y axis on the frequency domain.
5. The method for detecting the fall of the old people under the real environment based on the big data as claimed in claim 4, wherein sample data is extracted in Y, Z two axes, namely acceleration mag in Y, Z two axes is calculated:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. thezRefers to the acceleration value acquired by the wearable sensor on the Z-axis.
6. The old man fall detection method based on big data in real environment according to claim 4 or 5, wherein the mean value of Y, Z two axes in time domain is:
wherein A isyiThe method comprises the steps of representing an ith acceleration sample value acquired by a wearable sensor on a Y axis; a. theziRepresenting the ith acceleration sample value acquired by the wearable sensor on the Z axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
the 25 quantile p25 and 75 quantile p75 of the mag data are found by using the function prctile (), and the square sum sumsq25 and sumsq75 of the mag data lower than p25 and lower than p75 are calculated, respectively.
7. The method for detecting the falling of the old people under the real environment based on the big data as claimed in claim 6, wherein the method is characterized by extracting features based on the Y axis in the frequency domain, namely solving the dispersion of the acceleration in the Y axis direction:
wherein A isyRepresenting the acceleration value acquired by the wearable sensor on the Y axis; a. theyiThe method comprises the steps of representing an ith acceleration sample value acquired by a wearable sensor on a Y axis; n refers to n acceleration sample values respectively obtained by the wearable sensor on Y and Z;
after performing fast fourier transform on the dispersion, the maximum frequency maxFreq of the spectrum, sum5Hz of frequency components of 5Hz or less, and the peak numPeaks of the spectrum of 5Hz or less are obtained.
8. The method for detecting the fall of the elderly people under the real environment based on big data as claimed in claim 7, wherein the time domain and frequency domain feature quantities extracted in the step S2 are combined into one feature vector, and the feature vector is normalized.
9. A system for detecting falling of old people under a real environment based on big data is characterized by comprising wearable equipment, peripheral alarm equipment and a big data platform, wherein the wearable equipment comprises a sensor, a single chip microcomputer and a wireless transmission module;
the sensor is used for acquiring data of triaxial acceleration generated by human body activity;
the singlechip is used for controlling the working states of the sensor and the wireless transmission module
The wireless transmission module is used for transmitting the data acquired by the sensor to the central processing system;
the database is used for storing daily behavior data of the old in a classified manner under the real environment; the database comprises a behavior class database and a behavior sample database, wherein the behavior class database is used for storing behavior class data, and the behavior sample database is used for storing behavior samples;
the central processing system is used for processing the received data and issuing a processing command; the central processing system comprises a feature processing module, a preset stage judging module, a classifier, a behavior data comparison module, a falling behavior judging module, an alarm module and a database establishing and maintaining module;
the characteristic processing module is used for extracting and normalizing the characteristics of the triaxial acceleration transmitted to the central processing system by the wireless transmission module;
the old man falling detection system comprises a preset stage judgment module, a storage module and a control module, wherein the preset stage judgment module is used for judging whether the old man falling detection system is in a preset stage;
the classifier adopts a classifier based on SVM, and is used for detecting the human body behavior class of the extracted behavior characteristics;
the behavior class data comparison module is used for judging whether the behavior class detected by the classifier is in the existing behavior class database or not;
the falling behavior judging module is used for judging whether the behavior class detected by the classifier is a falling behavior;
the alarm module is used for sending alarm information to children or nursing staff of the old people in abnormal conditions;
the database creating and maintaining module is used for creating a database, adding a behavior database and a behavior sample database and performing later updating management work;
the peripheral alarm device is used for receiving alarm information sent by the central processing system and sending an alarm signal to remind children or nursing personnel and old people of possible dangerous conditions, and the peripheral alarm device adopts an alarm or a mobile terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810338008.7A CN108771543B (en) | 2018-04-16 | 2018-04-16 | Old man falling detection method and system in real environment based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810338008.7A CN108771543B (en) | 2018-04-16 | 2018-04-16 | Old man falling detection method and system in real environment based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108771543A CN108771543A (en) | 2018-11-09 |
| CN108771543B true CN108771543B (en) | 2020-11-03 |
Family
ID=64033724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810338008.7A Active CN108771543B (en) | 2018-04-16 | 2018-04-16 | Old man falling detection method and system in real environment based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108771543B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0816986A2 (en) * | 1996-07-03 | 1998-01-07 | Hitachi, Ltd. | Method, apparatus and system for recognizing motions |
| CN102707305A (en) * | 2012-06-06 | 2012-10-03 | 山东大学 | Tumble detecting and positioning system and method |
| CN103565440A (en) * | 2012-08-07 | 2014-02-12 | 法玛科技顾问股份有限公司 | Brain volumetric measuring system |
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN105590409A (en) * | 2016-02-26 | 2016-05-18 | 江苏大学 | Human body tumble detection method and human body tumble detection system based on big data |
| CN106037635A (en) * | 2016-05-11 | 2016-10-26 | 南京邮电大学 | Intelligent early warning system based on wearable device and early warning method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI562100B (en) * | 2013-05-03 | 2016-12-11 | Ind Tech Res Inst | Device and method for monitoring postural and movement balance for fall prevention |
-
2018
- 2018-04-16 CN CN201810338008.7A patent/CN108771543B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0816986A2 (en) * | 1996-07-03 | 1998-01-07 | Hitachi, Ltd. | Method, apparatus and system for recognizing motions |
| CN102707305A (en) * | 2012-06-06 | 2012-10-03 | 山东大学 | Tumble detecting and positioning system and method |
| CN103565440A (en) * | 2012-08-07 | 2014-02-12 | 法玛科技顾问股份有限公司 | Brain volumetric measuring system |
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN105590409A (en) * | 2016-02-26 | 2016-05-18 | 江苏大学 | Human body tumble detection method and human body tumble detection system based on big data |
| CN106037635A (en) * | 2016-05-11 | 2016-10-26 | 南京邮电大学 | Intelligent early warning system based on wearable device and early warning method |
Non-Patent Citations (2)
| Title |
|---|
| Faller Classification in Older Adults Using Wearable Sensors Based on Turn and Straight-Walking Accelerometer-Based Features;Dylan Drover 等;《Sensors》;20170607;1321 * |
| 基于多传感器的人体姿态识别系统;彭欣然;《中国优秀硕士学位论文全文数据库 信息科技辑》;20180215;I140-494 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108771543A (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Fall detection based on dual-channel feature integration | |
| Kau et al. | A smart phone-based pocket fall accident detection, positioning, and rescue system | |
| Lim et al. | Fall‐detection algorithm using 3‐axis acceleration: combination with simple threshold and hidden Markov model | |
| CN106228200B (en) | Action identification method independent of action information acquisition equipment | |
| CN105913614A (en) | Method and device of monitoring tumbling, intelligent wearable device and tumbling alarm system | |
| Garcia-Ceja et al. | Long-term activity recognition from accelerometer data | |
| KR101797854B1 (en) | System and method for fall detection using smart band | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN110675596B (en) | Fall detection method applied to wearable terminal | |
| CN108109336A (en) | A kind of human body tumble recognition methods based on acceleration transducer | |
| CN109620184A (en) | Mobile phone-wearable device integral type human body burst injury real-time monitoring alarming method | |
| CN114469076B (en) | Identity-feature-fused fall identification method and system for solitary old people | |
| Ye et al. | A falling detection system with wireless sensor for the elderly people based on ergnomics | |
| CN104468981A (en) | School bullying detection method based on smart phone platform | |
| CN104297519A (en) | Human motion attitude identification method and mobile terminal | |
| CN106971203B (en) | Identity recognition method based on walking characteristic data | |
| CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
| CN107169334B (en) | The user authen method based on straight punch motion detection for hand wearable device | |
| Shi et al. | Fall detection system based on inertial mems sensors: Analysis design and realization | |
| Kambhampati et al. | Unified framework for triaxial accelerometer‐based fall event detection and classification using cumulants and hierarchical decision tree classifier | |
| Xie et al. | ART: adaptive and real-time fall detection using COTS smart watch | |
| Ye et al. | Research of fall detection and alarm applications for the elderly | |
| CN108771543B (en) | Old man falling detection method and system in real environment based on big data | |
| Hai et al. | PCA-SVM algorithm for classification of skeletal data-based eigen postures | |
| Chen et al. | Improve the Accuracy of Fall Detection Based on Artificial Intelligence Algorithm. |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210414 Address after: No.716, 7th floor, building 4, No.99 Guangfu Road, Wuhou District, Chengdu, Sichuan 610000 Patentee after: Chengdu yishenrui Technology Co.,Ltd. Address before: 250353 Qilu University of technology, No. 3501, Changqing University Road, Jinan City, Shandong Province Patentee before: Qilu University of Technology Effective date of registration: 20210414 Address after: 201800 room jt2200, building 6, 1288 Yecheng Road, Jiading District, Shanghai Patentee after: Shanghai Hailong Xinji Software Co.,Ltd. Address before: No.716, 7th floor, building 4, No.99 Guangfu Road, Wuhou District, Chengdu, Sichuan 610000 Patentee before: Chengdu yishenrui Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |