CN110400446B - Method for detecting drowning of swimming pool - Google Patents
Method for detecting drowning of swimming pool Download PDFInfo
- Publication number
- CN110400446B CN110400446B CN201910711521.0A CN201910711521A CN110400446B CN 110400446 B CN110400446 B CN 110400446B CN 201910711521 A CN201910711521 A CN 201910711521A CN 110400446 B CN110400446 B CN 110400446B
- Authority
- CN
- China
- Prior art keywords
- value
- oxygen saturation
- heart rate
- time axis
- sliding window
- 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.)
- Expired - Fee Related
Links
- 206010013647 Drowning Diseases 0.000 title claims abstract description 36
- 230000009182 swimming Effects 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims abstract description 26
- 239000013598 vector Substances 0.000 claims abstract description 74
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000000605 extraction Methods 0.000 claims abstract description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 55
- 229910052760 oxygen Inorganic materials 0.000 claims description 55
- 239000001301 oxygen Substances 0.000 claims description 55
- 238000012544 monitoring process Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 239000012634 fragment Substances 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 150000001875 compounds Chemical class 0.000 claims description 3
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 claims description 2
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 claims description 2
- 230000003247 decreasing effect Effects 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 230000006378 damage Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009189 diving Effects 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
- A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
-
- 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
- G08B21/08—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water
- G08B21/088—Alarms for ensuring the safety of persons responsive to the presence of persons in a body of water, e.g. a swimming pool; responsive to an abnormal condition of a body of water by monitoring a device worn by the person, e.g. a bracelet attached to the swimmer
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physiology (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Physics & Mathematics (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention provides a method for detecting drowning in a swimming pool, which comprises the steps of carrying out data preprocessing, feature vector extraction, feature vector preprocessing, judger calculation and result processing on collected data; the physiological parameters of the human body are processed and analyzed, so that the automatic detection and judgment of the drowning condition of the swimming pool are completed; by extracting the characteristic vector and using an One Class SVM model, various physiological parameters of a human body are comprehensively and reasonably utilized, so that the drowning detection rate is up to 99.9% when the false detection rate under the normal swimming condition is 2%, and the accurate detection of the drowning condition is fully ensured under the condition of low false detection; the method adopts the methods of time axis sliding window slicing and the like, realizes continuous and real-time detection on the time axis, has less resource consumption and is beneficial to being deployed to the mobile terminal.
Description
Technical Field
The invention relates to information analysis, in particular to a method for detecting drowning in a swimming pool.
Background
Along with the construction of urban community swimming pools. The phenomenon of death caused by drowning in the swimming pool is gradually highlighted. At present, rescue measures are enhanced in a swimming pool, for example, rescue workers are added, and warning boards for preventing diving and warning the depth of water are set, but the defects of reducing the freedom degree of swimmers and entertainment are caused; meanwhile, wearing products such as a plurality of current bracelets can accurately measure various physiological parameters of a human body, but a reasonable, effective and timely method for carrying out drowning judgment by using the measured physiological parameters is lacked at present.
Disclosure of Invention
The invention aims to provide a method for detecting drowning in a swimming pool, which is used for analyzing physiological parameters of a human body and timely and accurately judging the occurrence of the drowning condition;
in order to achieve the aim, the invention provides a method for detecting drowning in a swimming pool, which comprises the steps of carrying out data preprocessing, feature vector extraction, feature vector preprocessing, judger calculation and result processing on collected data;
the collected data comprises age, gender, heart rate monitoring data and oxygen saturation value;
the data preprocessing comprises gender digitization, time axis sliding window slicing, heart rate monitoring data calculation and oxygen saturation value calculation;
the gender is digitalized, wherein 1 is used for male, and-1 is used for female;
in the time axis sliding window slicing, on a time axis, data with fixed time intervals are used as a time window, namely a group of calculation data, the time window moves on the time axis, and a plurality of groups of calculation data are intercepted;
calculating the heart rate monitoring data, namely calculating the minimum value, the mean value and the maximum value of the heart rate monitoring data in a time axis sliding window fragment, and the direction of the maximum value of the heart rate change rate absolute value;
the heart rate change rate is the change amount of the heart rate in unit time, the heart rate increase is a positive value, and the heart rate decrease is a negative value;
the maximum value of the heart rate change rate absolute value is the maximum value of the heart rate change rate absolute value in a time axis sliding window;
the direction of the maximum absolute value of the heart rate change rate is positive or negative of the maximum absolute value of the heart rate change rate, the direction is 1 when the direction is positive, and the direction is-1 when the direction is negative;
calculating the oxygen saturation value, namely calculating the minimum value, the mean value and the maximum value of the oxygen saturation value in a time axis sliding window fragment, and the direction of the maximum value of the oxygen saturation value change rate absolute value;
the oxygen saturation change rate is the change amount of the oxygen saturation value in unit time, and the oxygen saturation value is increased to be a positive value in unit time and decreased to be a negative value;
the maximum value of the absolute value of the change rate of the oxygen saturation value is the maximum value of the absolute value of the change rate of the oxygen saturation value in a time axis sliding window;
the direction of the maximum value of the oxygen saturation value change rate is positive or negative of the oxygen saturation value change rate of the maximum value of the oxygen saturation value change rate, the direction is positive and 1, and the direction is negative and 1;
the characteristic vector extraction comprises the age, the gender, the time interval of the time axis sliding window, the calculation of heart rate monitoring data and the result of oxygen saturation settlement in the time axis sliding window;
the feature vector is formed by the following steps:
V＝{a,g,Δt,hmin,hmean,hmax,|h'|max,dh,omin,omean,omax,|o'|max,do}
wherein a is age, g is gender, Δ t is time axis sliding window time interval, hmin、hmean、hmaxRespectively the minimum value, the average value and the maximum value of the heart rate monitoring data in the time axis sliding window slicing; | h'maxMaximum absolute value of rate of change of heart rate, dhThe direction of the maximum absolute value of the heart rate change rate; omin、omean、omaxRespectively the minimum value, the average value and the maximum value of the oxygen saturation value in the time axis sliding window slice; | o'maxFor the maximum absolute value of the rate of change of the oxygen saturation value, doIs the direction of the maximum value of the absolute value of the rate of change of the oxygen saturation value;
preprocessing the feature vector, respectively normalizing the dimensions of the feature vector, namely subtracting a mean vector from the feature vector, and performing point division on a variance vector to obtain a normalized feature vector, wherein the formula is as follows:
in the formula, M is a mean vector,
is a variance vector;
the mean vector and the variance vector are obtained by calculating all dimension elements of the feature vectors of all samples and are constant values;
the decision device calculates, sends the preprocessed normalized feature vector to a swimming pool drowning detection model, and outputs an operation result;
the swimming pool drowning detection model is a One Class SVM model, a Gaussian kernel function is selected, and offline training is completed;
the operation result is that the input normalized feature vector is normal (+1) or abnormal (-1);
the result processing outputs whether the drowning is detected according to the calculation result of the decision device,
when the output of the judger is normal (-1), carrying out detection judgment on a time axis sliding window fragment;
when the output of the decision device is abnormal (-1), the detection is stopped, and the output is judged to be drowned.
Further, in the feature vector preprocessing, for the mean vector and the variance vector,
m0＝m1＝m2＝m7＝m12＝0
δ0＝δ1＝δ2＝δ7＝δ12＝1
wherein the mean and variance results correspond to age, gender, time axis sliding window time interval, direction of the maximum absolute value of rate of change of heart rate, and direction of the maximum absolute value of rate of change of oxygen saturation, respectively;
the invention has the following beneficial effects:
the invention provides a method for detecting drowning in a swimming pool, which completes automatic detection judgment of the drowning condition of the swimming pool by processing and analyzing physiological parameters of a human body; by extracting the characteristic vector and using an One Class SVM model, various physiological parameters of a human body are comprehensively and reasonably utilized, so that the drowning detection rate is up to 99.9% when the false detection rate under the normal swimming condition is 2%, and the accurate detection of the drowning condition is fully ensured under the condition of low false detection; the method adopts the methods of time axis sliding window slicing and the like, realizes continuous and real-time detection on the time axis, has less resource consumption and is beneficial to being deployed to the mobile terminal.
Drawings
Fig. 1 is a flow chart of a method of detecting drowning in a swimming pool.
FIG. 2 is a schematic diagram of time-axis sliding window slicing.
Detailed Description
The present invention is described in detail below by way of examples, it should be noted that the following examples are only for illustrating the present invention and should not be construed as limiting the scope of the present invention, and those skilled in the art can make some insubstantial modifications and adaptations of the present invention based on the above-described disclosure.
Example 1
A method for detecting drowning in a swimming pool is disclosed, as shown in figure 1, data acquisition and data preprocessing, feature vector extraction, feature vector preprocessing, judger calculation and result processing are carried out;
wherein the collected data comprises age, gender, heart rate monitoring data and oxygen saturation value;
data preprocessing is carried out to finish gender digitization, time axis sliding window fragmentation, heart rate monitoring data calculation and oxygen saturation value calculation;
wherein, the sex is digitalized, and the use 1 represents a male, and the use-1 represents a female; the time axis sliding window slicing is shown in fig. 2, in which on the time axis, data at fixed time intervals is used as a time window as a set of calculation data, the time window moves on the time axis, and a plurality of sets of calculation data are intercepted; the time window duration is delta t, and the sliding window fragment moving duration of the adjacent time axis is step ts；
Calculating heart rate monitoring data into a method for calculating the minimum value, the mean value and the maximum value of the heart rate change rate absolute value of the heart rate monitoring data in a time axis sliding window fragment;
the heart rate change rate is the change quantity of the heart rate in unit time, the heart rate increase is a positive value, and the heart rate decrease is a negative value; the maximum value of the absolute value of the heart rate change rate is the maximum value of the absolute value of the heart rate change rate in a time axis sliding window; the direction of the maximum absolute value of the heart rate change rate is positive or negative of the maximum absolute value of the heart rate change rate, the direction is 1 when the direction is positive, and the direction is-1 when the direction is negative;
calculating the oxygen saturation value, namely calculating the minimum value, the mean value and the maximum value of the oxygen saturation value in a time axis sliding window fragment, and the direction of the maximum value of the oxygen saturation value change rate absolute value and the maximum value of the oxygen saturation value change rate absolute value;
the oxygen saturation change rate is the change amount of the oxygen saturation value in unit time, and the oxygen saturation value is increased to be a positive value in unit time and reduced to be a negative value;
the maximum value of the absolute value of the change rate of the oxygen saturation value is the maximum value of the absolute value of the change rate of the oxygen saturation value in a time axis sliding window;
the direction of the maximum value of the absolute value of the oxygen saturation value change rate is positive or negative of the oxygen saturation value change rate which is the maximum value of the absolute value of the oxygen saturation value change rate, the direction is 1 when the direction is positive, and the direction is-1 when the direction is negative;
extracting characteristic vectors, wherein the characteristic vectors comprise age, gender, time interval of a time axis sliding window, heart rate monitoring data calculation and oxygen saturation settlement results; the characteristic vector composition form is as follows:
V＝{a,g,Δt,hmin,hmean,hmax,|h'|max,dh,omin,omean,omax,|o'|max,do}
wherein a is age, g is gender, Δ t is time axis sliding window time interval, hmin、hmean、hmaxRespectively the minimum value, the average value and the maximum value of the heart rate monitoring data in the time axis sliding window slicing; | h'maxMaximum absolute value of rate of change of heart rate, dhThe direction of the maximum absolute value of the heart rate change rate; omin、omean、omaxRespectively the minimum value, the average value and the maximum value of the oxygen saturation value in the time axis sliding window slice; | o'maxFor the maximum absolute value of the rate of change of the oxygen saturation value, doIs the direction of the maximum value of the absolute value of the rate of change of the oxygen saturation value;
for the feature vector preprocessing process, it is necessary to normalize each dimension of the feature vector, that is, subtracting the mean vector from the feature vector, and performing point division on the variance vector to obtain a normalized feature vector, as follows:
in the formula, M is a mean vector,
is a variance vector; the mean vector and the variance vector are obtained by calculating all dimension elements of the feature vectors of all samples, are related to the distribution of training samples and are constant values in the using process;
considering that the quantified values of age and gender, the time axis sliding window time interval, the direction of the maximum absolute value of the heart rate change rate and the direction of the maximum absolute value of the oxygen saturation change rate are not suitable for normalization quantification, the corresponding mean value and variance are fixed and set as follows:
m0＝m1＝m2＝m7＝m12＝0
δ0＝δ1＝δ2＝δ7＝δ12＝1
the decision device calculates, sends the normalized eigenvector after pretreatment into a swimming pool drowning detection model, and outputs an operation result; the swimming pool drowning detection model is a One Class SVM model, a Gaussian kernel function is selected, and offline training is completed; the operation result is that the input normalized feature vector is normal (+1) or abnormal (-1);
and finally, processing a result, namely outputting whether the drowning is detected according to the calculation result of the decision device, wherein the specific operation is as follows:
when the output of the judger is normal (-1), carrying out detection judgment on a time axis sliding window fragment;
when the output of the decision device is abnormal (-1), the detection is stopped, and the output is judged to be drowned.
Example 2:
in the method for detecting drowning in the swimming pool, the drowning detection model of the swimming pool is trained offline; training the classification model mainly by adopting a mode of collecting, sorting and marking a training set so as to obtain a swimming pool drowning detection model with better performance;
the positive example is a normalized feature vector extracted from data collected when the swimming pool of the swimmer swims normally; the negative sample is a normalized feature vector extracted from data collected when a swimmer swimming pool is drowned; the positive sample is labeled 1 and the negative sample is labeled-1;
in the training set data collection and arrangement process, more positive sample data are easy to obtain, while negative sample data are difficult to obtain and less sample data are obtained based on the idiopathy and danger of the swimming pool drowning condition; the training set has the condition that the number of positive samples is far larger than that of negative samples;
aiming at the particularity of the swimming pool drowning detection model in the training set data, the model is selected to be an One Class SVM model, a Gaussian kernel function is selected, and the distribution of positive samples is trained, so that the model has the capability of judging whether the input feature vector is a positive sample;
in the training process, firstly, a training set is determined; feature vectors from all samples in the training set
V＝{a,g,Δt,hmin,hmean,hmax,|h'|max,dh,omin,omean,omax,|o'|max,do}
Respectively calculating the mean value and variance of each dimension of the feature vector to obtain a mean vector M and a variance vector
In the formula (I), the compound is shown in the specification,
an ith dimension element of the feature vector of a jth sample in the training set;
considering the specificity of a specific dimension in the feature vector, setting:
m0＝m1＝m2＝m7＝m12＝0
δ0＝δ1＝δ2＝δ7＝δ12＝1
then, normalization processing is carried out on the characteristic vectors, so that the model is quicker and easier to converge in the training process, and a model with better performance is obtained;
regarding the method for setting the proportion of negative samples in the training process of the One Class SVM model,
the proportion of the negative samples in the training set is calculated as r-1(ii) a The proportion of the negative samples in the training process is set as follows:
under the condition of fixing the training set, the larger the proportion of the negative samples is set, the lower the probability that the negative samples are judged as positive samples, and the larger the proportion of the negative samples is set, so that the positive samples are judged as negative samples at a high probability; therefore, the practicability and functionality of the swimming pool drowning detection model and the hazard severity degree when misjudgment occurs are comprehensively considered, namely when a negative sample is misjudged to be a positive sample, the drowning condition cannot be timely found so as to damage the life of a drowner; the proportion coefficient of the negative sample is set to be increased by 0.3 compared with the true value, the probability that the negative sample is mistakenly judged as the positive sample is reduced under the conditions that the positive sample is increased to be limited and the misjudgment harm degree is not high, and the possibility that a drowning person is not timely discovered is reduced to the maximum extent.
Claims (1)
1. A method for detection of drowning in a swimming pool, characterized by: the method comprises the steps of carrying out data preprocessing, feature vector extraction, feature vector preprocessing, judger calculation and result processing on collected data;
the collected data comprises age, gender, heart rate monitoring data and oxygen saturation value;
the data preprocessing comprises gender digitization, time axis sliding window slicing, heart rate monitoring data calculation and oxygen saturation value calculation;
the gender is digitalized, wherein 1 is used for male, and-1 is used for female;
in the time axis sliding window slicing, on a time axis, data with fixed time intervals are used as a time window, namely a group of calculation data, the time window moves on the time axis, and a plurality of groups of calculation data are intercepted;
calculating the heart rate monitoring data, namely calculating the minimum value, the mean value and the maximum value of the heart rate monitoring data in a time axis sliding window fragment, and the direction of the maximum value of the heart rate change rate absolute value;
the heart rate change rate is the change amount of the heart rate in unit time, the heart rate increase is a positive value, and the heart rate decrease is a negative value;
the maximum value of the heart rate change rate absolute value is the maximum value of the heart rate change rate absolute value in a time axis sliding window;
the direction of the maximum absolute value of the heart rate change rate is positive or negative of the maximum absolute value of the heart rate change rate, the direction is 1 when the direction is positive, and the direction is-1 when the direction is negative;
calculating the oxygen saturation value, namely calculating the minimum value, the mean value and the maximum value of the oxygen saturation value in a time axis sliding window fragment, and the direction of the maximum value of the oxygen saturation value change rate absolute value;
the oxygen saturation change rate is the change amount of the oxygen saturation value in unit time, and the oxygen saturation value is increased to be a positive value in unit time and decreased to be a negative value;
the maximum value of the absolute value of the change rate of the oxygen saturation value is the maximum value of the absolute value of the change rate of the oxygen saturation value in a time axis sliding window;
the direction of the maximum value of the oxygen saturation value change rate is positive or negative of the oxygen saturation value change rate of the maximum value of the oxygen saturation value change rate, the direction is positive and 1, and the direction is negative and 1;
the characteristic vector extraction comprises the age, the gender, the time interval of the time axis sliding window, the heart rate monitoring data calculation and the oxygen saturation calculation result in a time axis sliding window;
the feature vector is formed by the following steps:
in the formula (I), the compound is shown in the specification,
the age is,
Is the sex,
Sliding window time intervals for the time axis
Respectively the minimum value, the average value and the maximum value of the heart rate monitoring data in the time axis sliding window slicing;
is the maximum value of the absolute value of the heart rate change rate,
the direction of the maximum absolute value of the heart rate change rate;
respectively the minimum value, the average value and the maximum value of the oxygen saturation value in the time axis sliding window slice;
is the maximum value of the absolute value of the oxygen saturation value conversion rate,
is the direction of the maximum value of the absolute value of the rate of change of the oxygen saturation value;
preprocessing the feature vector, respectively normalizing the dimensions of the feature vector, namely subtracting a mean vector from the feature vector, and performing point division on a variance vector to obtain a normalized feature vector, wherein the formula is as follows:
in the formula (I), the compound is shown in the specification,
is a vector of the mean value of the vectors,
is a variance vector;
the mean vector and the variance vector are obtained by calculating all dimension elements of the feature vectors of all samples and are constant values;
the decision device calculates, sends the preprocessed normalized feature vector to a swimming pool drowning detection model, and outputs an operation result;
the swimming pool drowning detection model is a One Class SVM model, a Gaussian kernel function is selected, and offline training is completed;
the operation result is an input normalized feature vector, and indicates normal when the input normalized feature vector is +1 and indicates abnormal when the input normalized feature vector is-1;
the result processing outputs whether the drowning is detected according to the calculation result of the decision device,
when the output of the judger is normal, detecting and judging a time axis sliding window fragment;
when the output of the judger is abnormal, stopping detection, and judging the output to be drowned;
in the feature vector preprocessing, for the mean vector and the variance vector,
wherein the mean and variance results correspond to age, gender, time axis sliding window time interval, direction of the maximum absolute value of rate of change of heart rate, and direction of the maximum absolute value of rate of change of oxygen saturation, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910711521.0A CN110400446B (en) | 2019-08-02 | 2019-08-02 | Method for detecting drowning of swimming pool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910711521.0A CN110400446B (en) | 2019-08-02 | 2019-08-02 | Method for detecting drowning of swimming pool |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110400446A CN110400446A (en) | 2019-11-01 |
| CN110400446B true CN110400446B (en) | 2021-03-26 |
Family
ID=68327176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910711521.0A Expired - Fee Related CN110400446B (en) | 2019-08-02 | 2019-08-02 | Method for detecting drowning of swimming pool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400446B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833567B (en) * | 2020-05-30 | 2022-02-18 | 北京方德泳安体育文化有限公司 | Motion detection system based on UWB and nine-axis gyroscope |
| CN114896568B (en) * | 2022-07-13 | 2022-11-01 | 杭州光粒科技有限公司 | Swimming data statistical method, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103006223A (en) * | 2012-12-13 | 2013-04-03 | 中国人民解放军第四军医大学 | Household non-contact sleeping monitoring device and method |
| CN103584840A (en) * | 2013-11-25 | 2014-02-19 | 天津大学 | Automatic sleep stage method based on electroencephalogram, heart rate variability and coherence between electroencephalogram and heart rate variability |
| CN105678963A (en) * | 2016-03-15 | 2016-06-15 | 陕西师范大学 | Intelligent anti-drowning device |
| CN108010273A (en) * | 2017-12-29 | 2018-05-08 | 辽宁工程技术大学 | A kind of drowned detection alarm based on Cloud Server and machine learning algorithm |
| CN108113657A (en) * | 2016-11-30 | 2018-06-05 | 天津职业技术师范大学 | A kind of Driver Fatigue Detection based on D-S evidence theory |
| CN108376456A (en) * | 2018-02-05 | 2018-08-07 | 广东小天才科技有限公司 | A kind of drowned monitoring method and wearable device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9858793B2 (en) * | 2015-04-23 | 2018-01-02 | Asma Saleh HAWSAH | Swimming aid to prevent drowning |
| CN105877766B (en) * | 2016-06-21 | 2019-02-05 | 东北大学 | A kind of state of mind detection system and method based on the fusion of more physiological signals |
| CN108446733A (en) * | 2018-03-19 | 2018-08-24 | 上海玺翎智能科技有限公司 | A kind of human body behavior monitoring and intelligent identification Method based on multi-sensor data |
-
2019
- 2019-08-02 CN CN201910711521.0A patent/CN110400446B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103006223A (en) * | 2012-12-13 | 2013-04-03 | 中国人民解放军第四军医大学 | Household non-contact sleeping monitoring device and method |
| CN103584840A (en) * | 2013-11-25 | 2014-02-19 | 天津大学 | Automatic sleep stage method based on electroencephalogram, heart rate variability and coherence between electroencephalogram and heart rate variability |
| CN105678963A (en) * | 2016-03-15 | 2016-06-15 | 陕西师范大学 | Intelligent anti-drowning device |
| CN108113657A (en) * | 2016-11-30 | 2018-06-05 | 天津职业技术师范大学 | A kind of Driver Fatigue Detection based on D-S evidence theory |
| CN108010273A (en) * | 2017-12-29 | 2018-05-08 | 辽宁工程技术大学 | A kind of drowned detection alarm based on Cloud Server and machine learning algorithm |
| CN108376456A (en) * | 2018-02-05 | 2018-08-07 | 广东小天才科技有限公司 | A kind of drowned monitoring method and wearable device |
Non-Patent Citations (2)
| Title |
|---|
| 可穿戴式系统心电信号压缩感知与心律失常分类研究;华晶;《中国博士学位论文全文数据库 医药卫生科技辑》;20180515(第5期);第71页 * |
| 基于多生理信息融合的情绪识别方法;颜红博;《中国优秀硕士学位论文全文数据库 医药卫生科技辑》;20141115(第11期);第36-39页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110400446A (en) | 2019-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728223A (en) | Helmet wearing identification method based on deep learning | |
| CN110400446B (en) | Method for detecting drowning of swimming pool | |
| CN111436944B (en) | Falling detection method based on intelligent mobile terminal | |
| US9576199B2 (en) | Method and device for calculating number and moving direction of pedestrians | |
| CN108647582A (en) | Goal behavior identification and prediction technique under a kind of complex dynamic environment | |
| CN115691026A (en) | Intelligent early warning monitoring management method for forest fire prevention | |
| CN108615050B (en) | Human body posture distinguishing method based on support vector machine | |
| CN113935666B (en) | Building decoration wall tile abnormity evaluation method based on image processing | |
| CN104538041A (en) | Method and system for detecting abnormal sounds | |
| CN108021888B (en) | Fall detection method | |
| CN107248252B (en) | Efficient forest fire detection system | |
| CN108009574B (en) | Track fastener detection method | |
| CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN108919241B (en) | Underwater signal time-frequency endpoint parameter estimation method based on constant false alarm detection | |
| CN113887324A (en) | Fire point detection method based on satellite remote sensing data | |
| CN112068120A (en) | micro-Doppler time-frequency plane individual soldier squad identification method based on two-dimensional Fourier transform | |
| CN117289778B (en) | Real-time monitoring method for health state of industrial control host power supply | |
| CN113179389A (en) | System and method for identifying crane jib of power transmission line dangerous vehicle | |
| CN110837028B (en) | Method for rapidly identifying partial discharge mode | |
| CN106023143B (en) | Wave height monitoring and pre-alarming method at a kind of sea-spanning bridge con struction | |
| CN103366163B (en) | Face detection system and method based on incremental learning | |
| CN108537105B (en) | Dangerous behavior identification method in home environment | |
| CN115330792A (en) | Sewage detection method and system based on artificial intelligence | |
| CN111855946B (en) | Water quality analysis method based on fish behavior analysis |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210326 |