CN108771543A - Falls Among Old People detection method and system under a kind of true environment based on big data - Google Patents
Falls Among Old People detection method and system under a kind of true environment based on big data Download PDFInfo
- Publication number
- CN108771543A CN108771543A CN201810338008.7A CN201810338008A CN108771543A CN 108771543 A CN108771543 A CN 108771543A CN 201810338008 A CN201810338008 A CN 201810338008A CN 108771543 A CN108771543 A CN 108771543A
- Authority
- CN
- China
- Prior art keywords
- behavior
- big data
- elderly
- database
- data
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 230000005540 biological transmission Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 21
- 230000002093 peripheral effect Effects 0.000 claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 59
- 230000001133 acceleration Effects 0.000 claims description 22
- 238000000605 extraction Methods 0.000 claims description 13
- 230000003542 behavioural effect Effects 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000003909 pattern recognition Methods 0.000 abstract description 2
- 230000006399 behavior Effects 0.000 description 105
- 230000001960 triggered effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000037081 physical activity Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
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—Measuring 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 or 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)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Physiology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Alarm Systems (AREA)
Abstract
本发明公开了一种基于大数据的真实环境下老人跌倒检测方法及系统,属于模式识别和人体行为识别技术领域,本发明要解决的技术问题为目前已有的跌倒检测系统及方法准确性差、不能满足个体的差异性以及无法获得老人跌倒实验数据,采用的技术方案为:①一种基于大数据的真实环境下老人跌倒检测方法,该方法是基于大数据平台,利用可穿戴设备和物联网技术构建一个真实环境下老人跌倒检测系统,通过可穿戴设备采集老人真实环境下的日常行为数据,通过物联网技术将数据传送到大数据平台。②一种基于大数据的真实环境下老人跌倒检测系统,该系统包括可穿戴设备、外设报警设备和大数据平台,可穿戴设备包括传感器、单片机和无线传输模块。
The invention discloses a fall detection method and system for the elderly in a real environment based on big data, which belongs to the technical field of pattern recognition and human behavior recognition. The technical problem to be solved by the invention is that the current fall detection system and method have poor accuracy, Unable to meet individual differences and unable to obtain experimental data on falls of the elderly, the technical solution adopted is: ① A method for detecting falls of the elderly in a real environment based on big data. This method is based on a big data platform, using wearable devices and the Internet of Things Technology builds a fall detection system for the elderly in a real environment, collects daily behavior data of the elderly in a real environment through wearable devices, and transmits the data to the big data platform through the Internet of Things technology. ②A fall detection system for the elderly in a real environment based on big data. The system includes wearable devices, peripheral alarm devices and a big data platform. Wearable devices include sensors, single-chip microcomputers and wireless transmission modules.
Description
技术领域technical field
本发明涉及模式识别和人体行为识别技术领域,具体地说是一种基于大数据的真实环境下老人跌倒检测方法及系统。The invention relates to the technical field of pattern recognition and human behavior recognition, in particular to a method and system for detecting falls of the elderly in a real environment based on big data.
背景技术Background technique
基于可穿戴设备的跌倒检测系统一般佩戴于胸部、腰部、腿部及腕部等部位。通过在设备中加入相关的姿态传感器,从而形成可穿戴检测设备,采集实验对象在运动过程中通过传感器输出的数据来分析并检测跌倒行为。穿戴式设备还有一个优点,它可采集到其他基于视频或环境的跌倒检测系统所不能采集到的生理指标,如血压、心电等信息。TatungUniversity的Shang-Lin Hsieh等提出一种腕式跌倒检测系统,通过实验检测出系统获得良好的平均灵敏度和特异性。Pannurat,N.等人提出了自动跌倒看控系统。Shany,T.等利用可穿戴式传感器进行人体行为识别和跌倒检测。Habib,M.A.等利用智能手机的进行跌倒性检测。Casilari,E.等人提出了基于Android系统的跌倒检测方案。Yuan,J等人提出利用高效的中断驱动算法来进行跌倒检测和人的日常行为识别。Vavoulas,G.等利用智能手机完成来人体的跌倒检测。Medrano,C.等提出来利用智能手机获取加速度的新方法来进行跌倒检测。López,J.D.等人利用多个加速度融合构建了行为检测系统。Koshmak,G.A.等人结合Android系统和生理性检测来进行跌倒检测。国内很多研究者也纷纷提出很多有关跌倒检测的方法,但大多都是关于算法改进或者利用不同的传感器的结合来实现跌倒检测,并且都是采用青年志愿者来模拟跌倒和日常行为的形式以获取实验数据,这些检测算法一旦应用于真实的老人跌倒数据样本中,其跌倒检测准确率大大降低了。Fall detection systems based on wearable devices are generally worn on the chest, waist, legs, and wrists. By adding relevant posture sensors to the device, a wearable detection device is formed, and the data output by the sensor during the movement of the subject is collected to analyze and detect the fall behavior. Another advantage of the wearable device is that it can collect physiological indicators, such as blood pressure and ECG, which cannot be collected by other video or environment-based fall detection systems. Shang-Lin Hsieh of Tatung University et al. proposed a wrist-type fall detection system. Through experiments, it was found that the system obtained good average sensitivity and specificity. Pannurat, N. et al proposed an automatic fall monitoring system. Shany, T. et al. use wearable sensors for human behavior recognition and fall detection. Habib, M.A. et al. use smartphones for fall detection. Casilari, E. et al. proposed a fall detection scheme based on the Android system. Yuan, J et al. proposed the use of efficient interrupt-driven algorithms for fall detection and human daily behavior recognition. Vavoulas, G., etc. used smart phones to complete the fall detection of the human body. Medrano, C. et al proposed a new method of using smartphones to obtain acceleration for fall detection. López, J.D. et al built a behavior detection system using multiple acceleration fusions. Koshmak, G.A. et al combined Android system and physiological detection for fall detection. Many domestic researchers have also proposed many methods of fall detection, but most of them are about algorithm improvement or the combination of different sensors to achieve fall detection, and they all use young volunteers to simulate falls and daily behaviors to obtain Experimental data, once these detection algorithms are applied to real elderly fall data samples, the accuracy of fall detection is greatly reduced.
目前已有的跌倒检测系统存在的问题如下:The existing problems of fall detection systems are as follows:
(一)、已有跌倒检测系统都是以青年志愿者模拟跌倒和日常行为获取实验数据,虽然获得了很高的准确率,但该算法一旦用于真实环境下的老人跌倒检测时,其准确率却大大降低;(1) The existing fall detection system uses young volunteers to simulate falls and daily behaviors to obtain experimental data. Although a high accuracy rate is obtained, once the algorithm is used for the fall detection of the elderly in a real environment, its accuracy rate is greatly reduced;
(二)、跌倒检测系统不能够满足个体的差异性,具体应用场景中不同用户身高体重不一样,在跌倒检测过程中系统参数也会有所变化,系统参数统一的直接后果是加剧跌倒检测的误差;(2) The fall detection system cannot meet the individual differences. In specific application scenarios, the height and weight of different users are different, and the system parameters will also change during the fall detection process. The direct consequence of the uniform system parameters is to aggravate the fall detection. error;
(三)、在实验过程中不可能让老人去模拟跌倒获取实验数据,即真实的老人跌倒实验数据很难获取。(3), it is impossible to allow the elderly to simulate falls to obtain experimental data during the experiment, that is, it is difficult to obtain the experimental data of real elderly falls.
发明内容Contents of the invention
本发明的技术任务是提供一种基于大数据的真实环境下老人跌倒检测方法及系统,来解决目前已有的跌倒检测系统及方法准确性差、不能满足个体的差异性以及无法获得老人跌倒实验数据的问题。The technical task of the present invention is to provide a method and system for detecting falls of the elderly in a real environment based on big data, to solve the problem that the existing fall detection systems and methods have poor accuracy, cannot satisfy individual differences, and cannot obtain experimental data on falls of the elderly. The problem.
本发明的技术任务是按以下方式实现的,一种基于大数据的真实环境下老人跌倒检测方法,该方法是基于大数据平台,利用可穿戴设备和物联网技术构建一个真实环境下老人跌倒检测系统,通过可穿戴设备采集老人真实环境下的日常行为数据,通过物联网技术将数据传送到大数据平台;具体步骤如下:The technical task of the present invention is achieved in the following manner, a method for detecting the fall of the elderly in a real environment based on big data, the method is based on a big data platform, using wearable devices and Internet of Things technology to build a fall detection method for the elderly in a real environment The system collects the daily behavior data of the elderly in the real environment through wearable devices, and transmits the data to the big data platform through the Internet of Things technology; the specific steps are as follows:
S1、可穿戴设备采集人体活动产生的三轴加速度数据并通过无线网络传输到大数据平台的中央处理系统,下一步执行步骤S2;S1. The wearable device collects the three-axis acceleration data generated by human activities and transmits it to the central processing system of the big data platform through the wireless network, and the next step is to perform step S2;
S2、中央处理系统对采集到的X、Y、Z三轴加速度数据进行特征提取并做归一化处理,下一步执行步骤S3;S2. The central processing system performs feature extraction and normalization processing on the collected X, Y, and Z three-axis acceleration data, and then performs step S3 in the next step;
S3、中央处理系统为行为类数据库存储的行为类数量设定一个阈值,判断大数据平台内的行为类数据库的行为类数量是否低于阀值:S3. The central processing system sets a threshold for the number of behavior classes stored in the behavior database, and judges whether the number of behavior classes in the behavior database in the big data platform is lower than the threshold:
(1)、若是,则大数据平台为预设阶段,下一步跳转至步骤S8;(1), if so, the big data platform is the default stage, and the next step is to jump to step S8;
(2)、若不是,则大数据平台不在预设阶段,下一步执行步骤S4;(2), if not, the big data platform is not in the preset stage, and the next step is to perform step S4;
S4、利用分类器对步骤S2中提取的行为特征进行人体行为类的检测,下一步执行步骤S5;S4. Use the classifier to detect the human behavior class on the behavioral features extracted in step S2, and then perform step S5 in the next step;
S5、根据步骤S4检测出的行为类,中央处理系统将行为类数据库中的行为类与步骤S4检测出的行为类进行对比,判断此行为类是否在行为类数据库中:S5, according to the behavior class detected in step S4, the central processing system compares the behavior class in the behavior class database with the behavior class detected in step S4, and judges whether the behavior class is in the behavior class database:
(1)、若在,则执行步骤S6;(1), if yes, execute step S6;
(2)、若不在,则跳转至步骤S7;(2), if not, jump to step S7;
S6、中央处理系统将步骤S4检测出的行为类与行为类数据库中的跌倒行为类进行比较,判断此行为类是否为跌倒行为:S6, the central processing system compares the behavior class detected in step S4 with the fall behavior class in the behavior class database, and judges whether this behavior class is a fall behavior:
(1)、若是,则执行步骤S7;(1), if so, execute step S7;
(2)、若不是,则执行步骤S9;(2), if not, then execute step S9;
S7、中央处理系统触发报警模块发出报警信号到外设报警设备,外设报警设备发出报警信号提醒老人的子女或者看护人员老人可能出现危险情况,下一步执行步骤S8;S7, the central processing system triggers the alarm module to send an alarm signal to the peripheral alarm device, and the peripheral alarm device sends an alarm signal to remind the children of the elderly or the caregiver that the elderly may be in danger, and the next step is to perform step S8;
S8、问询并确认行为类名称,并将行为类存储到行为类数据库中,下一步执行步骤S9;S8. Inquire and confirm the name of the behavior class, and store the behavior class in the behavior class database, and then execute step S9 in the next step;
S9、将提取到的样本特征添加到对应行为样本数据库中。S9. Add the extracted sample features to the corresponding behavior sample database.
作为优选,所述可穿戴设备是由传感器、无线传输模块和单片机集成。Preferably, the wearable device is integrated with a sensor, a wireless transmission module and a single-chip microcomputer.
作为优选,所述传感器采用ADXL345传感器,无线传输模块采用无线传输模块CC1000。Preferably, the sensor adopts ADXL345 sensor, and the wireless transmission module adopts wireless transmission module CC1000.
作为优选,所述步骤S2中对采集到的X、Y、Z三轴加速度数据进行特征提取具体为:根据采集到的数据分别从时域提取Y、Z两轴上的均值、低于25的分位值和低于75的分为值,在频域上基于Y轴上提取频谱最大频率、5HZ以下的频率分量值和和5HZ以下频谱的峰值。As a preference, the feature extraction of the collected X, Y, and Z three-axis acceleration data in the step S2 is specifically: according to the collected data, extracting the mean values on the Y and Z axes from the time domain, and the values below 25 The quantile value and the sub-value below 75 are extracted in the frequency domain based on the Y-axis to extract the maximum frequency of the spectrum, the frequency component value below 5HZ, and the peak value of the spectrum below 5HZ.
更优地,所述在Y、Z两轴上提取样本数据,即计算在Y、Z两轴上的加速度mag:More preferably, the sample data is extracted on the Y and Z axes, that is, the acceleration mag on the Y and Z axes is calculated:
更优地,所述在时间域上提取Y、Z两轴上的均值为:More preferably, the mean values of the Y and Z axes extracted in the time domain are:
利用函数prctile()求出mag数据的25分位置p25和75分位置p75,同时分别计算出低于p25和低于p75的mag数据的平方和sumsq25和sumsq75。Use the function prctile() to calculate the 25th point p25 and 75th point p75 of the mag data, and calculate the sums of squares sumsq25 and sumsq75 of the mag data lower than p25 and lower than p75 respectively.
更优地,所述在频域上基于Y轴的特征提取,求出Y轴方向上的加速度的离差: More preferably, the feature extraction based on the Y-axis in the frequency domain is used to obtain the dispersion of the acceleration in the Y-axis direction:
对离差进行快速傅里叶变换后,分别求出频谱最大频率maxFreq、5HZ以下的频率分量之sum5HZ和和5HZ以下的频谱的峰值numPeaks。After the fast Fourier transform is performed on the dispersion, the maximum frequency of the spectrum maxFreq, the sum5HZ of the frequency components below 5HZ and the peak value numPeaks of the frequency components below 5HZ are calculated respectively.
更优地,所述步骤S2中提取到的时间域和频域特征量合并成一个特征向量,对特征向量进行归一化处理。More preferably, the time-domain and frequency-domain feature quantities extracted in the step S2 are combined into a feature vector, and the feature vector is normalized.
一种基于大数据的真实环境下老人跌倒检测系统,该系统包括可穿戴设备、外设报警设备和大数据平台,可穿戴设备包括传感器、单片机和无线传输模块,大数据平台包括数据库和中央处理系统,单片机连接并控制传感器和无线传输模块,无线传输模块无线连接中央处理系统,中央处理系统发送报警信息到外设报警设备;A fall detection system for the elderly in a real environment based on big data, the system includes wearable devices, peripheral alarm devices and a big data platform, the wearable device includes sensors, single-chip microcomputers and wireless transmission modules, and the big data platform includes databases and central processing system, the single-chip microcomputer connects and controls the sensor and the wireless transmission module, the wireless transmission module wirelessly connects the central processing system, and the central processing system sends alarm information to the peripheral alarm equipment;
传感器用于采集人体活动产生的三轴加速度的数据;The sensor is used to collect the data of the three-axis acceleration generated by human activities;
单片机用于控制传感器和无线传输模块的工作状态The single chip microcomputer is used to control the working state of the sensor and the wireless transmission module
无线传输模块用于将传感器采集到的数据传输给中央处理系统;The wireless transmission module is used to transmit the data collected by the sensor to the central processing system;
数据库用于分类存储老人真实环境下的日常行为数据;数据库包括行为类数据库和行为样本数据库,行为类数据库用于存储行为类数据,行为样本数据库用于存储行为样本;The database is used to classify and store the daily behavior data of the elderly in the real environment; the database includes a behavior database and a behavior sample database, the behavior database is used to store behavior data, and the behavior sample database is used to store behavior samples;
中央处理系统用于处理接收到的数据并下达处理命令;The central processing system is used to process the received data and issue processing orders;
外设报警设备用于接收中央处理系统发出的报警信息并发出报警信号提醒子女或看护人员老人可能出现危险情况,外设报警设备采用报警器或移动终端。The peripheral alarm device is used to receive the alarm information sent by the central processing system and send out an alarm signal to remind children or caregivers that the elderly may be in danger. The peripheral alarm device uses an alarm or a mobile terminal.
作为优选,所述中央处理系统包括特征处理模块、预设阶段判别模块、分类器、行为类数据比对模块、跌倒行为判别模块、报警模块和数据库创建维护模块;Preferably, the central processing system includes a feature processing module, a preset stage discrimination module, a classifier, a behavioral data comparison module, a fall behavior discrimination module, an alarm module and a database creation and maintenance module;
特征处理模块用于对无线传输模块传输到中央处理系统的三轴加速度度进行特征提取并归一化;The feature processing module is used for feature extraction and normalization of the three-axis acceleration transmitted by the wireless transmission module to the central processing system;
预设阶段判别模块用于判断该老人跌倒检测系统是否处在预设阶段;The preset stage discrimination module is used to judge whether the elderly fall detection system is in the preset stage;
分类器采用基于SVM的分类器,分类器用于对提取的行为特征进行人体行为类的检测;The classifier adopts a classifier based on SVM, and the classifier is used to detect the human behavior class on the extracted behavioral features;
行为类数据比对模块用于判断分类器检测到的行为类是否在已有行为类数据库中;The behavior class data comparison module is used to judge whether the behavior class detected by the classifier is in the existing behavior class database;
跌倒行为判别模块用于判断分类器检测到的行为类是否为跌倒行为;The fall behavior discrimination module is used to judge whether the behavior class detected by the classifier is a fall behavior;
报警模块用于异常情况时发送报警信息给老人的子女或看护人员;The alarm module is used to send alarm information to the children or caregivers of the elderly in abnormal situations;
数据库创建维护模块用于建立数据库,添加行为类数据库和行为样本数据库以及后期的更新管理工作。The database creation and maintenance module is used to establish databases, add behavioral databases and behavioral sample databases, and later update management.
本发明的基于大数据的真实环境下老人跌倒检测方法及系统与现有技术相比具有以下优点:Compared with the prior art, the elderly fall detection method and system based on big data in the present invention have the following advantages:
(一)、本发明能够有效的解决目前很多跌倒检测算法利用年轻人模拟跌倒获取数据,应用到真实环境中的老年人时,其算法的准确率大大降低的问题,本发明在试用阶段,首先存入一些老人日常行为数据作为训练样本,并分好类别,在后续的使用过程中,如果检测到数据库中没有的行为类,则触发报警,并确认该动作是否为跌倒,如果为跌倒,数据库中增加一类,并把数据存入数据库,随着使用时间的增长,数据库中的数据样本不断增加,则跌倒检测的准确率也将不断的提高,实现大数据背景下的老人真实环境的智能跌倒检测,大幅度提高真实环境下老人跌倒检测系统的稳定性、准确率和检测效率;(1), the present invention can effectively solve the problem that many current fall detection algorithms use young people to simulate falls to obtain data, and when applied to the elderly in real environments, the accuracy of the algorithm is greatly reduced. The present invention is in the trial stage, first Store some daily behavior data of the elderly as training samples and classify them into categories. In the subsequent use process, if a behavior category not in the database is detected, an alarm will be triggered and it will be confirmed whether the action is a fall. If it is a fall, the database will Add a category to the database and store the data in the database. As the usage time increases and the data samples in the database continue to increase, the accuracy of fall detection will also continue to improve, realizing the intelligence of the real environment of the elderly under the background of big data. Fall detection, greatly improving the stability, accuracy and detection efficiency of the elderly fall detection system in the real environment;
(二)、本发明以大数据平台为背景,应用物联网技术对真实环境下的老人的行为进行识别检测,尤其针对老人的跌倒进行实时的看控,出现异常情况进行及时的报警处理,通过老人自己真实的行为数据来进行检测识别,能够做到因人而异,可以实现样本的个性化,从而提高了老人行为判别的准确率;(2), the present invention takes the big data platform as the background, applies Internet of Things technology to identify and detect the behavior of the elderly in the real environment, especially for the real-time monitoring and control of the elderly's falls, and timely alarm processing when abnormal conditions occur, through The elderly’s own real behavior data is used for detection and identification, which can vary from person to person, and can realize the personalization of samples, thereby improving the accuracy of the elderly’s behavior discrimination;
(三)本发明应用大数据平台,能够做到因人而异的采集数据样本,使得使用本发明的每个人,都是采集自己的数据样本,且随着使用时间的加长,行为类数据库和对应的样本数据库数据量将越来越多,分类器的检测将会越来越准确,因此能够做到因人而异的跌倒检测,同时也做到了真实环境下的样本采集,更加有利于提高跌倒检测的准确率。(3) The present invention uses a big data platform, which can collect data samples that vary from person to person, so that everyone who uses the present invention collects their own data samples, and as the use time increases, the behavior database and The amount of data in the corresponding sample database will increase, and the detection of the classifier will become more and more accurate. Therefore, it is possible to detect falls that vary from person to person, and at the same time to collect samples in a real environment, which is more conducive to improving Accuracy of fall detection.
附图说明Description of drawings
下面结合附图对本发明进一步说明。The present invention will be further described below in conjunction with the accompanying drawings.
附图1为基于大数据的真实环境下老人跌倒检测方法流程框图;Accompanying drawing 1 is the block diagram of the old man's fall detection method flow chart under the real environment based on big data;
附图2为基于大数据的真实环境下老人跌倒检测系统的结构框图。Accompanying drawing 2 is the structural block diagram of the elderly fall detection system based on big data in the real environment.
具体实施方式Detailed ways
参照说明书附图和具体实施例对本发明的一种基于大数据的真实环境下老人跌倒检测方法及系统作以下详细地说明。A method and system for detecting falls of the elderly in a real environment based on big data of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
实施例:Example:
如附图1所示,本发明的基于大数据的真实环境下老人跌倒检测方法,该方法是基于大数据平台,利用可穿戴设备和物联网技术构建一个真实环境下老人跌倒检测系统,通过可穿戴设备采集老人真实环境下的日常行为数据,通过物联网技术将数据传送到大数据平台;具体步骤如下:As shown in accompanying drawing 1, the elderly fall detection method based on big data in the real environment of the present invention, the method is based on the big data platform, utilizes wearable devices and Internet of Things technology to build a fall detection system for the elderly in a real environment, through the The wearable device collects the daily behavior data of the elderly in the real environment, and transmits the data to the big data platform through the Internet of Things technology; the specific steps are as follows:
S1、由ADXL345传感器、无线传输模块CC1000和单片机集成可穿戴设备采集人体活动产生的三轴加速度数据并通过无线网络传输到大数据平台的中央处理系统,下一步执行步骤S2;S1. The three-axis acceleration data generated by human activities is collected by the ADXL345 sensor, the wireless transmission module CC1000 and the single-chip integrated wearable device, and is transmitted to the central processing system of the big data platform through the wireless network, and the next step is to perform step S2;
S2、中央处理系统对采集到的X、Y、Z三轴加速度数据进行特征提取并做归一化处理,下一步执行步骤S3;S2. The central processing system performs feature extraction and normalization processing on the collected X, Y, and Z three-axis acceleration data, and then performs step S3 in the next step;
S3、中央处理系统为行为类数据库存储的行为类数量设定一个阈值,判断大数据平台内的行为类数据库的行为类数量是否低于阀值:S3. The central processing system sets a threshold for the number of behavior classes stored in the behavior database, and judges whether the number of behavior classes in the behavior database in the big data platform is lower than the threshold:
(1)、若是,则大数据平台为预设阶段,下一步跳转至步骤S8;(1), if so, the big data platform is the default stage, and the next step is to jump to step S8;
(2)、若不是,则大数据平台不在预设阶段,下一步执行步骤S4;(2), if not, the big data platform is not in the preset stage, and the next step is to perform step S4;
S4、利用分类器对步骤S2中提取的行为特征进行人体行为类的检测,下一步执行步骤S5;S4. Use the classifier to detect the human behavior class on the behavioral features extracted in step S2, and then perform step S5 in the next step;
S5、根据步骤S4检测出的行为类,中央处理系统将行为类数据库中的行为类与步骤S4检测出的行为类进行对比,判断此行为类是否在行为类数据库中:S5, according to the behavior class detected in step S4, the central processing system compares the behavior class in the behavior class database with the behavior class detected in step S4, and judges whether the behavior class is in the behavior class database:
(1)、若在,则执行步骤S6;(1), if yes, execute step S6;
(2)、若不在,则跳转至步骤S7;(2), if not, jump to step S7;
S6、中央处理系统将步骤S4检测出的行为类与行为类数据库中的跌倒行为类进行比较,判断此行为类是否为跌倒行为:S6, the central processing system compares the behavior class detected in step S4 with the fall behavior class in the behavior class database, and judges whether this behavior class is a fall behavior:
(1)、若是,则执行步骤S7;(1), if so, execute step S7;
(2)、若不是,则执行步骤S9;(2), if not, then execute step S9;
S7、中央处理系统触发报警模块发出报警信号到外设报警设备,外设报警设备发出报警信号提醒老人的子女或者看护人员老人可能出现危险情况,下一步执行步骤S8;S7, the central processing system triggers the alarm module to send an alarm signal to the peripheral alarm device, and the peripheral alarm device sends an alarm signal to remind the children of the elderly or the caregiver that the elderly may be in danger, and the next step is to perform step S8;
S8、问询并确认行为类名称,并将行为类存储到行为类数据库中,下一步执行步骤S9;S8. Inquire and confirm the name of the behavior class, and store the behavior class in the behavior class database, and then execute step S9 in the next step;
S9、将提取到的样本特征添加到对应行为样本数据库中。S9. Add the extracted sample features to the corresponding behavior sample database.
其中,步骤S2中对采集到的X、Y、Z三轴加速度数据进行特征提取具体为:根据采集到的数据分别从时域提取Y、Z两轴上的均值、低于25的分位值和低于75的分为值,在频域上基于Y轴上提取频谱最大频率、5HZ以下的频率分量值和和5HZ以下频谱的峰值,具体如下:Among them, the feature extraction of the collected X, Y, and Z three-axis acceleration data in step S2 is specifically: according to the collected data, extract the average value on the Y and Z axes from the time domain, and the quantile value lower than 25. In the frequency domain, the maximum frequency of the spectrum, the frequency component value below 5HZ and the peak value of the spectrum below 5HZ are extracted based on the Y-axis in the frequency domain, as follows:
(1)、在Y、Z两轴上提取样本数据,即计算在Y、Z两轴上的加速度mag:(1) Extract sample data on the Y and Z axes, that is, calculate the acceleration mag on the Y and Z axes:
(2)、在时间域上提取Y、Z两轴上的均值为:(2), extracting the mean value on the Y and Z axes in the time domain is:
利用函数prctile()求出mag数据的25分位置p25和75分位置p75,同时分别计算出低于p25和低于p75的mag数据的平方和sumsq25和sumsq75。Use the function prctile() to calculate the 25th point p25 and 75th point p75 of the mag data, and calculate the sums of squares sumsq25 and sumsq75 of the mag data lower than p25 and lower than p75 respectively.
(3)、在频域上基于Y轴的特征提取,求出Y轴方向上的加速度的离差:(3), in the frequency domain, based on the feature extraction of the Y axis, the dispersion of the acceleration in the Y axis direction is obtained:
对离差进行快速傅里叶变换后,分别求出频谱最大频率maxFreq、5HZ以下的频率分量之sum5HZ和和5HZ以下的频谱的峰值numPeaks;After the fast Fourier transform is performed on the dispersion, the maximum frequency maxFreq of the spectrum, the sum5HZ of the frequency components below 5HZ and the peak value numPeaks of the frequency spectrum below 5HZ are respectively obtained;
(4)、将提取到的时间域和频域特征量合并成一个特征向量,对特征向量进行归一化处理。(4) Merge the extracted time-domain and frequency-domain feature quantities into one feature vector, and normalize the feature vector.
实施例2:Example 2:
如附图2所示,本发明的基于大数据的真实环境下老人跌倒检测系统,该系统包括可穿戴设备、外设报警设备和大数据平台,可穿戴设备包括传感器、单片机和无线传输模块,大数据平台包括数据库和中央处理系统,单片机连接并控制传感器和无线传输模块,无线传输模块无线连接中央处理系统,中央处理系统发送报警信息到外设报警设备;传感器用于采集人体活动产生的三轴加速度的数据;单片机用于控制传感器和无线传输模块的工作状态无线传输模块用于将传感器采集到的数据传输给中央处理系统;数据库用于分类存储老人真实环境下的日常行为数据;数据库包括行为类数据库和行为样本数据库,行为类数据库用于存储行为类数据,行为样本数据库用于存储行为样本;中央处理系统用于处理接收到的数据并下达处理命令;外设报警设备用于接收中央处理系统发出的报警信息并发出报警信号提醒子女或看护人员老人可能出现危险情况,外设报警设备采用报警器或移动终端。As shown in accompanying drawing 2, the elderly fall detection system based on big data of the present invention in a real environment includes wearable devices, peripheral alarm devices and a big data platform, and wearable devices include sensors, single-chip microcomputers and wireless transmission modules, The big data platform includes a database and a central processing system. The single-chip microcomputer connects and controls the sensor and the wireless transmission module. The wireless transmission module wirelessly connects the central processing system. The central processing system sends alarm information to the peripheral alarm equipment; The data of axial acceleration; the single-chip microcomputer is used to control the working status of the sensor and the wireless transmission module; the wireless transmission module is used to transmit the data collected by the sensor to the central processing system; the database is used to classify and store the daily behavior data of the elderly in the real environment; the database includes Behavior database and behavior sample database, the behavior database is used to store behavior data, the behavior sample database is used to store behavior samples; the central processing system is used to process the received data and issue processing orders; the peripheral alarm device is used to receive the central Process the alarm information sent by the system and send out an alarm signal to remind children or caregivers that the elderly may be in danger. The peripheral alarm equipment adopts an alarm or a mobile terminal.
中央处理系统包括特征处理模块、预设阶段判别模块、分类器、行为类数据比对模块、跌倒行为判别模块、报警模块和数据库创建维护模块;特征处理模块用于对无线传输模块传输到中央处理系统的三轴加速度度进行特征提取并归一化;预设阶段判别模块用于判断该老人跌倒检测系统是否处在预设阶段;分类器采用基于SVM的分类器,分类器用于对提取的行为特征进行人体行为类的检测;行为类数据比对模块用于判断分类器检测到的行为类是否在已有行为类数据库中;跌倒行为判别模块用于判断分类器检测到的行为类是否为跌倒行为;报警模块用于异常情况时发送报警信息给老人的子女或看护人员;数据库创建维护模块用于建立数据库,添加行为类数据库和行为样本数据库以及后期的更新管理工作。The central processing system includes a feature processing module, a preset stage discrimination module, a classifier, a behavioral data comparison module, a fall behavior discrimination module, an alarm module and a database creation and maintenance module; the feature processing module is used to transmit the wireless transmission module to the central processing The three-axis acceleration of the system is feature extracted and normalized; the preset stage discrimination module is used to judge whether the elderly fall detection system is in the preset stage; the classifier adopts a classifier based on SVM, and the classifier is used to classify the extracted behavior features to detect human behavior; the behavior data comparison module is used to judge whether the behavior class detected by the classifier is in the existing behavior class database; the fall behavior discrimination module is used to judge whether the behavior class detected by the classifier is a fall Behavior; the alarm module is used to send alarm information to the children or caregivers of the elderly in abnormal situations; the database creation and maintenance module is used to establish databases, add behavior databases and behavior sample databases, and later update management.
具体工作过程:Specific working process:
(一)、利用单片机和传感器采集人体活动产生的三轴加速度的数据,并利用无线传输模块传输数据到大数据平台的中央处理系统;(1), utilize single-chip microcomputer and sensor to collect the data of three-axis acceleration that human body activity produces, and utilize wireless transmission module to transmit data to the central processing system of big data platform;
(二)、中央处理系统对收到的数据通过特征处理模块进行特征提取并归一化处理,并通过预设阶段判别模块判别该系统是否处于预设阶段:(2), the central processing system performs feature extraction and normalization processing on the received data through the feature processing module, and judges whether the system is in the preset stage through the preset stage discrimination module:
(Ⅰ)、若中央处理系统在开始使用的阶段设置为预设阶段,则通过数据库创建维护模块需要对个人的一些日常行为动作类进行添加及采集数据样本,为后期的分类器检测提供样本;(I), if the central processing system is set to the default stage at the initial stage of use, then through the database creation and maintenance module, it is necessary to add some daily behaviors and actions of individuals and collect data samples to provide samples for later classifier detection;
(Ⅱ)、当处在正常使用阶段后,对采集到的数据特征用分类器进行检测,并通过行为类数据比对模块判断其行为类是否在数据库中:(II), when it is in the normal use stage, use the classifier to detect the collected data features, and judge whether the behavior class is in the database through the behavior data comparison module:
(ⅰ)、若此行为类在行为类数据库中,则再继续通过跌倒行为判别模块判断是否为跌倒行为:(ⅰ), if the behavior class is in the behavior class database, then continue to judge whether it is a fall behavior by the fall behavior discrimination module:
①、若是跌倒,则触发报警模块报警;①. If it falls, the alarm module will be triggered to alarm;
②、若不是跌倒行为,则将提取到的数据特征添加到对应行为类的数据样本库中;②. If it is not a fall behavior, add the extracted data features to the data sample library of the corresponding behavior class;
(ⅱ)、若行为类不在行为类数据库中,即分类器检测到行为类是未知的行为,则首先触发报警模块报警,同时外设报警设备发出报警信号(因为行为类数据库中的日常行为已经存入,如果检测到未知的行为类,则就有跌倒的嫌疑,为了安全起见先触发报警);而后确认此行为类名称,并通过数据库创建维护模块将此新行为类存入行为类数据库中,同时将数据特征添加到对应的行为类数据库中。(ii), if the behavior class is not in the behavior class database, that is, the classifier detects that the behavior class is an unknown behavior, then at first the alarm module is triggered to report to the police, and the peripheral alarm device sends an alarm signal (because the daily behavior in the behavior class database has already been If an unknown behavior class is detected, there is a suspicion of falling, and the alarm will be triggered first for safety reasons); then confirm the name of the behavior class, and store this new behavior class into the behavior class database through the database creation and maintenance module , and add the data feature to the corresponding behavior database at the same time.
通过上面具体实施方式,所述技术领域的技术人员可容易的实现本发明。但是应当理解,本发明并不限于上述的具体实施方式。在公开的实施方式的基础上,所述技术领域的技术人员可任意组合不同的技术特征,从而实现不同的技术方案。Through the above specific implementation manners, those skilled in the technical field can easily realize the present invention. However, it should be understood that the present invention is not limited to the specific embodiments described above. On the basis of the disclosed embodiments, those skilled in the art can arbitrarily combine different technical features, so as to realize different technical solutions.
除说明书所述的技术特征外,均为本专业技术人员的已知技术。Except for the technical features described in the instructions, all are known technologies by those skilled in the art.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810338008.7A CN108771543B (en) | 2018-04-16 | 2018-04-16 | A method and system for elderly fall detection 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 | A method and system for elderly fall detection in real environment based on big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108771543A true CN108771543A (en) | 2018-11-09 |
CN108771543B 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 | A method and system for elderly fall detection in real environment based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108771543B (en) |
Citations (7)
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 volume measuring system |
US20140330171A1 (en) * | 2013-05-03 | 2014-11-06 | National Taiwan University | Method and device for monitoring postural and movement balance for fall prevention |
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 |
-
2018
- 2018-04-16 CN CN201810338008.7A patent/CN108771543B/en active Active
Patent Citations (7)
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 volume measuring system |
US20140330171A1 (en) * | 2013-05-03 | 2014-11-06 | National Taiwan University | Method and device for monitoring postural and movement balance for fall prevention |
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 |
---|
DYLAN DROVER 等: "Faller Classification in Older Adults Using Wearable Sensors Based on Turn and Straight-Walking Accelerometer-Based Features", 《SENSORS》 * |
彭欣然: "基于多传感器的人体姿态识别系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN108771543B (en) | 2020-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105125221B (en) | Detecting system and method are fallen down in cloud service in real time | |
CN103886715B (en) | A kind of tumble detection method for human body | |
CN105310696B (en) | A kind of fall detection model building method and corresponding fall detection method and device | |
WO2017049957A1 (en) | Intelligent falling detection and alarming apparatus and processing method thereof | |
CN207970089U (en) | Fall detection system for analyzing severity of fall and wearing device thereof | |
CN105708470B (en) | Based on doppler detector and the united fall detection system of sensor and method | |
CN110287825B (en) | Tumble action detection method based on key skeleton point trajectory analysis | |
CN105118236A (en) | Paralysis falling detection and prevention device and processing method thereof | |
US20160210835A1 (en) | Human body tumbling detection method and device and mobile terminal system | |
CN205050303U (en) | Human paralysis of intelligence is monitoring devices | |
CN103211599A (en) | Method and device for monitoring tumble | |
CN203898284U (en) | Living anomaly detection device for old people | |
CN106407996A (en) | Machine learning based detection method and detection system for the fall of the old | |
CN114469076B (en) | Identity-feature-fused fall identification method and system for solitary old people | |
CN108937886A (en) | A kind of patient in hospital method for managing security and system | |
CN106388831A (en) | Method for detecting falling actions based on sample weighting algorithm | |
Ye et al. | A falling detection system with wireless sensor for the elderly people based on ergnomics | |
CN104269025A (en) | Wearable type single-node feature and position selecting method for monitoring outdoor tumble | |
CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
CN106650300B (en) | An elderly monitoring system and method based on extreme learning machine | |
CN108958482A (en) | A kind of similitude action recognition device and method based on convolutional neural networks | |
CN107609474A (en) | Body action identification method, device, robot and storage medium | |
Shi et al. | Fall detection system based on inertial mems sensors: Analysis design and realization | |
CN106510686A (en) | Heart disease diagnosis system based on cloud service | |
Nizam et al. | Classification of daily life activities for human fall detection: A systematic review of the techniques and approaches |
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 | ||
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. |