CN109730699A - A kind of emotional prediction method based on vital sign data - Google Patents
A kind of emotional prediction method based on vital sign data Download PDFInfo
- Publication number
- CN109730699A CN109730699A CN201811623025.1A CN201811623025A CN109730699A CN 109730699 A CN109730699 A CN 109730699A CN 201811623025 A CN201811623025 A CN 201811623025A CN 109730699 A CN109730699 A CN 109730699A
- Authority
- CN
- China
- Prior art keywords
- vital sign
- sign data
- data
- nursing
- emotional prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The emotional prediction method based on vital sign data that the present invention provides a kind of, pass through 6 breathing, heart rate, pulse, systolic pressure, diastolic pressure and body temperature vital sign datas, object of nursing mood matching knowledge base is established according to features such as the age of object of nursing, genders, construct object of nursing emotional prediction model, mood by learning handmarking matches knowledge base, reach the emotional change that can analyze in real time prediction object of nursing by the data of patient monitor, improves nursing quality.
Description
Technical field
The emotional prediction method based on vital sign data that the present invention relates to a kind of.
Background technique
Emotional state is extremely complex, by it is a variety of obviously with unconspicuous feature instantiation.The emotional prediction method of mainstream is main
There are three types of: expression, voice and pulse.In existing research, majority is not to identify mood using one of feature, but not
The diversity of the same behavior of mood bring and physiological reaction makes it impossible to by a kind of feature accurate response, therefore, multiple features
Fusion is the inevitable choice of emotional prediction.
But some specific groups, such as patient with severe symptoms and some the elderly's object of nursing, the variation of mood can be very big
The development of the left and right state of an illness of degree.Anger such as sorrow, fears, shies at the moods, it will usually lead to the deterioration of the state of an illness, or even can induce some latent
In the breaking-out of the state of an illness.The moods such as happy, happy, good, it will usually accelerate the rehabilitation degree of the state of an illness.If object of nursing mood can be grasped
Variation, rapid artificial intervention dredge in time, play the role of greatly facilitating for the recovery of the object of nursing state of an illness.But for
For nursing staff, most of mood of object of nursing is all to hide within, does not show and, is difficult to discover out to nurse
The variation of subjects' mood.These three Emotion identification methods of expression, voice and the pulse of mainstream, can only be this using pulse therein
Method is used to predict that the mood of above-mentioned object of nursing, single method to cause accuracy low.
Summary of the invention
The emotional prediction method based on vital sign data that the object of the present invention is to provide a kind of, can accurately identify nursing
Subjects' mood variation.
In order to solve the above-mentioned technical problem, the technical scheme is that
A kind of emotional prediction method based on vital sign data, includes the following steps:
S1: the vital sign data test library of object of nursing is established.
S2: the vital sign data to be measured of each object of nursing is normalized.
S3: by treated, vital sign data to be measured inputs emotional prediction model, carries out emotional prediction to object of nursing.
Preferably, according to features such as the gender of object of nursing and ages, establishing user's life entity in the step S1
Levy data test library.
Preferably, the emotional prediction model construction is as follows in the step S3:
S301: building mood matches knowledge base.
S302: building successively includes the deep neural network of data input layer, hidden layer and data output layer.
S303: the deep neural network is finely adjusted using the vital sign data in mood matching knowledge base, is obtained
Trained deep neural network as emotional prediction model.
Preferably, inputting the vital sign data of the emotional prediction model through past average value processing, calculating formula are as follows:
Wherein, xi, xjFor a vital sign data in vital sign data, h indicates the number of data point.
Preferably, the deep neural network shares five layers, it successively include data input layer, three layers of hidden layer and data
Output layer, the data input layer include 6 input nodes, and each hidden layer includes 100 nodes, the data output
Layer includes 6 output nodes.
Preferably, the vital sign data includes breathing, heart rate, pulse, systolic pressure, diastolic pressure and body temperature.
Preferably, the mood includes anger, sorrow, fears, shies, is happy happy.
Compared with prior art, the invention has the following advantages that
Emotional prediction method of the present invention based on vital sign data, vital sign data can embody emotional change
The diversity of bring physiological behavior, the method based on vital sign data prediction mood can be improved the accuracy of prediction.Separately
Outside, using the vital sign data of patient monitor acquisition object of nursing, emotional prediction is carried out to object of nursing, is improved for nursing pair
The nursing quality of elephant.
Detailed description of the invention
Attached drawing described here is only used for task of explanation, and is not intended to limit model disclosed by the invention in any way
It encloses.In addition, shape and proportional sizes of each component in figure etc. are only schematical, it is used to help the understanding of the present invention, and
It is not the specific shape and proportional sizes for limiting each component of the present invention.Those skilled in the art under the teachings of the present invention, can
Implement the present invention to select various possible shapes and proportional sizes as the case may be.In the accompanying drawings:
Fig. 1 is the flow chart of the emotional prediction method of a specific embodiment of the invention.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, below in conjunction with of the invention real
The attached drawing in example is applied, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described implementation
Example is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without making creative work, all should belong to guarantor of the present invention
The range of shield.
It should be noted that it can directly on the other element when element is referred to as " being set to " another element
Or there may also be elements placed in the middle.When an element is considered as " connection " another element, it, which can be, is directly connected to
To another element or it may be simultaneously present centering elements.Term as used herein " vertical ", " horizontal ", " left side ",
" right side " and similar statement for illustrative purposes only, are not offered as being unique embodiment.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term as used herein in the specification of the present invention is intended merely to description tool
The purpose of the embodiment of body, it is not intended that in the limitation present invention.Term as used herein "and/or" includes one or more phases
Any and all combinations of the listed item of pass.
The variation of everyone mood will certainly cause the vital sign data of body to change.Currently, most of severe
The object of nursing such as patient and some the elderlys are equipped with patient monitor in nursing ward.By analyze the breathing of patient monitor, heart rate,
Pulse, systolic pressure, diastolic pressure and temperature data predict the emotional change situation of object of nursing.According to the variation of mood, in due course
Manpower intervention, guidance improve nursing level.
Referring to Figure 1, the present invention provides a kind of emotional prediction method based on vital sign data, includes the following steps:
S1: the vital sign data test library of object of nursing is established.
S2: the vital sign data to be measured of each object of nursing is normalized.
S3: by treated, vital sign data to be measured inputs emotional prediction model, carries out emotional prediction to object of nursing.
Specifically, between object of nursing, vital sign data can be had differences due to differences such as gender and ages, therefore,
In the step S1, when saving vital sign data, need to write exactly the features such as gender and the age of object of nursing, convenient at the later period
Reason, to establish object of nursing vital sign data test library.Also, vital sign data to be measured needs to carry out before testing
Normalized, quantizes data easy to use, and calculating formula is as follows:
Wherein, xnIndicate object of nursing data to be tested, xMinIndicate the minimum value of the object of nursing test data,
xMaxIndicate the maximum value of the object of nursing test data.
By treated, vital sign data inputs emotional prediction model, carries out emotional prediction to object of nursing.
In the step S3, the emotional prediction model construction is as follows:
S301: building mood matches knowledge base.It there is no a disclosed mood matching knowledge base in the world at present, need certainly
Oneself establishes.Firstly, building vital sign data training library, needs according to the present invention, the features such as acquisition different sexes, age
The vital sign data of volunteer, building vital sign data training library, the vital sign data train every group of life in library
The features such as gender, the age that life sign data marks, convenient for distinguishing；Then, the vital sign data is instructed
Practice library and carry out handmarking, mark the corresponding relationship of vital sign data and mood, constructs the mood matching knowledge base,
In, vital sign data X=(x1, x2, x3, x4, x5, x6) indicate, wherein x1It is breathing, x2It is heart rate, x3It is pulse, x4It is
Systolic pressure, x5It is diastolic pressure, x6It is body temperature, totally 6.Mood Y=(y1, y2, y3, y4, y5, y6), wherein y1Indicate anger, y2Table
Show sorrow, y3Expression is feared, y4Indicate frightened, y5Indicate pleasure, y6Indicate happy, totally 6, each yi, the value of i ∈ [1,6] is 0 or 1, when
Occur being denoted as 1 when this kind of mood, 0 is denoted as when not occurring.Under regular situation, the value range of breathing is 12-20, heart rate
Value range be 60-80, the value range of pulse is 60-80, the value range of systolic pressure is 90-135, the value of diastolic pressure
Range is 60-90, the value range of body temperature is 36.5-37.2.It is observed according to long-term clinical practice, when people is in the mood of anger
In, every value for vital signs of people can all become larger.Wherein, the value range of breathing is 17-20, the value range of heart rate is
70-80, pulse value range be 70-80, the value range of systolic pressure is 100-135, the value range of diastolic pressure is 70-
90, the value range of body temperature is 36.5-37.2；In the mood that people is in sorrow, every value for vital signs of people can all become smaller.
Wherein, the value range of breathing is 12-18, the value range of heart rate is 60-70, the value range of pulse is 60-70, systolic pressure
Value range be 90-115, the value range of diastolic pressure is 60-70, the value range of body temperature is 36.5-37.0；When people is in
In the mood feared, every value for vital signs of people can all become smaller, but heart rate and pulse can become faster, and blood pressure can increase.Wherein,
The value range of breathing is 12-18, the value range of heart rate is 75-80, the value range of pulse is 75-80, systolic pressure takes
Value range is 90-115, the value range of diastolic pressure is 60-70, the value range of body temperature is 36.5-37.0；When people is in frightened
In mood, every value for vital signs of people can all become abnormal big, but body temperature can reduce.Wherein, the value range of breathing
Value range for 17-20, heart rate is 78-80, the value range of pulse is 78-80, the value range of systolic pressure is 100-
135, the value range of diastolic pressure is 80-90, the value range of body temperature is 36.5-36.8；In the mood that people is in happy, people's
Every value for vital signs can all become smaller, and blood pressure is gently in intermediate value.Wherein, the value range of breathing is 12-16, heart rate takes
Value range is 60-70, the value range of pulse is 60-70, the value range of systolic pressure is 100-115, the value model of diastolic pressure
Enclosing for the value range of 80-90, body temperature is 36.8-37.0；In the mood that people is in happy, every value for vital signs of people and
The vital signs values of happy mood are similar, but heartbeat and blood pressure can be gentle.Wherein, the value range of breathing is 14-16, the heart
The value range of rate is 65-70, the value range of pulse is 65-70, the value range of systolic pressure is 100-115, diastolic pressure
Value range is 80-90, the value range of body temperature is 36.8-37.0.
S302: emotional prediction model is constructed, uses deep neural network in the present invention, the deep neural network is depth
Study a kind of frame, deep learning is the branch one is machine learning, be one kind attempt using comprising labyrinth or by
Multiple process layers that multiple nonlinear transformation is constituted carry out the algorithm of higher level of abstraction to data, and deep learning is good with learning automatically
Good feature, avoids the limitation of artificial selected characteristic, reduces complicated manual operation, and adaptability is stronger.The present invention
In, the deep neural network one shares five layers.Wherein, first layer is data input layer, which has input node 6, is corresponded to
6 achievement datas (breathing, heart rate, pulse, systolic pressure, diastolic pressure and body temperature) of vital sign；Layer 5 is data output layer,
The layer has output node 6, corresponding six kinds of moods (anger sorrow, is feared, shies, finding pleasure in, is happy)；Intermediate three layers are hidden layer, every node layer
100.The entire deep neural network number of nodes is (6,100,100,100,6).Specific model is as follows:
Wherein, Sigma function is activation primitive, and f () is Sigma function, and Y indicates mood, and X indicates vital sign number
According to i indicates the visual layers node total number of deep neural network, and j indicates the hidden layer node sum of deep neural network, W, θ table
Show the weight between visible elements and implicit node.
S303: the emotional prediction model is finely adjusted using the vital sign data in mood matching knowledge base, i.e.,
Fine training is carried out to deep neural network with a large amount of vital sign data in mood matching knowledge base, so that institute
The prediction task that deep neural network is more suitable in mood matching knowledge base is stated, trained model is obtained.Based on aspiration
Have many characteristics, such as different genders, age between person, the vital sign data in the mood matching knowledge base is in input model
Before, it needs through past average value processing each single item vital sign data to be subtracted to the average value of a period, calculating formula
Are as follows:
Wherein, xi, xjFor the individual value indicative in vital sign data, h indicates the number of data point, also illustrates that and average
Time segment length.In the present invention, the period select 12 hours, if it is per second have a vital sign data if, i.e. h=12
× 60 × 60=43200.
The present invention is by breathing, heart rate, pulse, 6 systolic pressure, diastolic pressure and body temperature vital sign datas, according to nursing
The features such as age, the gender of object establish object of nursing mood matching knowledge base, construct object of nursing emotional prediction model, pass through
The mood for learning handmarking matches knowledge base, reaches the feelings that prediction object of nursing can be analyzed in real time by the data of patient monitor
Thread variation, improves nursing quality.
It should be understood that above description is to illustrate rather than to be limited.By reading above-mentioned retouch
It states, many embodiments and many applications except provided example all will be apparent for a person skilled in the art
's.Therefore, the range of this introduction should not be determined referring to foregoing description, but should referring to preceding claims and these
The full scope of the equivalent that claim is possessed determines.For comprehensive purpose, all articles and with reference to including patent
The disclosure of application and bulletin is all by reference to being incorporated herein.Appointing for theme disclosed herein is omitted in preceding claims
Where face is not intended to abandon the body matter, also should not be considered as applicant and the theme is not thought of as to disclosed hair
A part of bright theme.
Claims (7)
1. a kind of emotional prediction method based on vital sign data, which comprises the steps of:
S1: the vital sign data test library of object of nursing is established；
S2: the vital sign data to be measured of each object of nursing is normalized；
S3: by treated, vital sign data to be measured inputs emotional prediction model, carries out emotional prediction to object of nursing.
2. the emotional prediction method according to claim 1 based on vital sign data, which is characterized in that the step S1
In, according to features such as the gender of object of nursing and ages, establish object of nursing vital sign data test library.
3. the emotional prediction method according to claim 1 based on vital sign data, which is characterized in that the step S3
In, the emotional prediction model construction is as follows:
S301: building mood matches knowledge base；
S302: building successively includes the deep neural network of data input layer, hidden layer and data output layer；
S303: the deep neural network is finely adjusted using the vital sign data in mood matching knowledge base, is obtained
Trained deep neural network is as emotional prediction model.
4. the emotional prediction method according to claim 3 based on vital sign data, which is characterized in that input the feelings
The vital sign data of thread prediction model is through past average value processing, calculating formula are as follows:
Wherein, xi, xjFor a vital sign data in vital sign data, h indicates the number of data point.
5. the emotional prediction method according to claim 3 based on vital sign data, which is characterized in that the depth mind
Five layers are shared through network, successively includes data input layer, three layers of hidden layer and data output layer, the data input layer includes 6
A input node, each hidden layer include 100 nodes, and the data output layer includes 6 output nodes.
6. the emotional prediction method according to claim 1 based on vital sign data, which is characterized in that the life entity
Levying data includes breathing, heart rate, pulse, systolic pressure, diastolic pressure and body temperature.
7. the emotional prediction method according to claim 1 based on vital sign data, which is characterized in that the mood packet
Anger is included, sorrow, fears, shy, is happy happy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811623025.1A CN109730699A (en) | 2018-12-28 | 2018-12-28 | A kind of emotional prediction method based on vital sign data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811623025.1A CN109730699A (en) | 2018-12-28 | 2018-12-28 | A kind of emotional prediction method based on vital sign data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109730699A true CN109730699A (en) | 2019-05-10 |
Family
ID=66361809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811623025.1A Pending CN109730699A (en) | 2018-12-28 | 2018-12-28 | A kind of emotional prediction method based on vital sign data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109730699A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110349668A (en) * | 2019-07-11 | 2019-10-18 | 四川大学 | A kind of therapeutic scheme aid decision-making method and its system based on BP neural network |
| CN111616722A (en) * | 2020-06-03 | 2020-09-04 | 吕丹青 | Method and system for detecting emotion change and wearable device |
| CN113440122A (en) * | 2021-08-02 | 2021-09-28 | 北京理工新源信息科技有限公司 | Emotion fluctuation monitoring and identification big data early warning system based on vital signs |
| CN114061050A (en) * | 2021-10-27 | 2022-02-18 | 青岛海尔空调器有限总公司 | Method and device for controlling air conditioner and air conditioner |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104573030A (en) * | 2015-01-14 | 2015-04-29 | 哈尔滨工业大学深圳研究生院 | Textual emotion prediction method and device |
| CN105581802A (en) * | 2014-11-17 | 2016-05-18 | 天津点康科技有限公司 | System and method for carrying out real-time judgment on emotional fluctuation |
| CN105615901A (en) * | 2014-11-06 | 2016-06-01 | 中国移动通信集团公司 | Emotion monitoring method and system |
| CN106264568A (en) * | 2016-07-28 | 2017-01-04 | 深圳科思创动实业有限公司 | Contactless emotion detection method and device |
| CN106725473A (en) * | 2016-12-29 | 2017-05-31 | 杭州联络互动信息科技股份有限公司 | A kind of method and device that emotional state is adjusted based on intelligent wearable device |
| CN107169426A (en) * | 2017-04-27 | 2017-09-15 | 广东工业大学 | A kind of detection of crowd's abnormal feeling and localization method based on deep neural network |
| CN107736894A (en) * | 2017-09-24 | 2018-02-27 | 天津大学 | A kind of electrocardiosignal Emotion identification method based on deep learning |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
| CN108814569A (en) * | 2018-05-02 | 2018-11-16 | 南京邮电大学 | Rehabilitation training control device |
-
2018
- 2018-12-28 CN CN201811623025.1A patent/CN109730699A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105615901A (en) * | 2014-11-06 | 2016-06-01 | 中国移动通信集团公司 | Emotion monitoring method and system |
| CN105581802A (en) * | 2014-11-17 | 2016-05-18 | 天津点康科技有限公司 | System and method for carrying out real-time judgment on emotional fluctuation |
| CN104573030A (en) * | 2015-01-14 | 2015-04-29 | 哈尔滨工业大学深圳研究生院 | Textual emotion prediction method and device |
| CN106264568A (en) * | 2016-07-28 | 2017-01-04 | 深圳科思创动实业有限公司 | Contactless emotion detection method and device |
| CN106725473A (en) * | 2016-12-29 | 2017-05-31 | 杭州联络互动信息科技股份有限公司 | A kind of method and device that emotional state is adjusted based on intelligent wearable device |
| CN107169426A (en) * | 2017-04-27 | 2017-09-15 | 广东工业大学 | A kind of detection of crowd's abnormal feeling and localization method based on deep neural network |
| CN107736894A (en) * | 2017-09-24 | 2018-02-27 | 天津大学 | A kind of electrocardiosignal Emotion identification method based on deep learning |
| CN108577865A (en) * | 2018-03-14 | 2018-09-28 | 天使智心（北京）科技有限公司 | A kind of psychological condition determines method and device |
| CN108814569A (en) * | 2018-05-02 | 2018-11-16 | 南京邮电大学 | Rehabilitation training control device |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110349668A (en) * | 2019-07-11 | 2019-10-18 | 四川大学 | A kind of therapeutic scheme aid decision-making method and its system based on BP neural network |
| CN111616722A (en) * | 2020-06-03 | 2020-09-04 | 吕丹青 | Method and system for detecting emotion change and wearable device |
| CN113440122A (en) * | 2021-08-02 | 2021-09-28 | 北京理工新源信息科技有限公司 | Emotion fluctuation monitoring and identification big data early warning system based on vital signs |
| CN113440122B (en) * | 2021-08-02 | 2023-08-22 | 北京理工新源信息科技有限公司 | Emotion fluctuation monitoring and identifying big data early warning system based on vital signs |
| CN114061050A (en) * | 2021-10-27 | 2022-02-18 | 青岛海尔空调器有限总公司 | Method and device for controlling air conditioner and air conditioner |
| CN114061050B (en) * | 2021-10-27 | 2023-06-23 | 青岛海尔空调器有限总公司 | Method and device for controlling air conditioner and air conditioner |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109730699A (en) | A kind of emotional prediction method based on vital sign data | |
| Bochniewicz et al. | Measuring functional arm movement after stroke using a single wrist-worn sensor and machine learning | |
| CN108926338B (en) | Heart rate prediction technique and device based on deep learning | |
| Narayanan et al. | Longitudinal falls-risk estimation using triaxial accelerometry | |
| Cribben et al. | Dynamic connectivity regression: determining state-related changes in brain connectivity | |
| Urgen et al. | EEG theta and Mu oscillations during perception of human and robot actions | |
| Rehg et al. | Mobile health | |
| CN105678066B (en) | The disease autodiagnosis method and system of data training are completed based on field feedback | |
| Pentareddy et al. | Building affective commitment through job characteristics, leadership and empowerment | |
| Nitzsche et al. | Validation of the work-life balance culture scale (WLBCS) | |
| Reiss et al. | Towards robust activity recognition for everyday life: Methods and evaluation | |
| Lim et al. | Adaptive template matching of photoplethysmogram pulses to detect motion artefact | |
| CN111887858A (en) | Ballistocardiogram signal heart rate estimation method based on cross-modal mapping | |
| Lubrano et al. | Impact of ambulatory blood pressure monitoring on the diagnosis of hypertension in children | |
| Chen et al. | A low cost, adaptive mixed reality system for home-based stroke rehabilitation | |
| WO2020261977A1 (en) | Space proposal system and space proposal method | |
| CN111951950A (en) | Three-dimensional data medical classification system, method and device based on deep learning | |
| Hossain et al. | Cognitive load measurement using galvanic skin response for listening tasks | |
| Meerai | Taking up space in the doctor’s office: how my racialized fat body confronts medical discourse | |
| Salingaros | Proposing a biophilic healing index of design and architecture | |
| Hemmelmann | Validity of the EDA-Explorer as a means for artifact rejection and peak detection in electro dermal activity data-analysis | |
| Kumar et al. | Self-efficacy among higher secondary school teachers: an empirical study | |
| CN114582464B (en) | Course personalized recommendation system and method for postpartum exercise | |
| CN114999649B (en) | Old people sign data monitoring and early warning method and system based on deep learning | |
| Azimova et al. | The first steps in artificial intelligence development in medicine in Uzbekistan |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |