CN116636847A - Emotion assessment method and system based on wrist wearable equipment - Google Patents
Emotion assessment method and system based on wrist wearable equipment Download PDFInfo
- Publication number
- CN116636847A CN116636847A CN202310647253.7A CN202310647253A CN116636847A CN 116636847 A CN116636847 A CN 116636847A CN 202310647253 A CN202310647253 A CN 202310647253A CN 116636847 A CN116636847 A CN 116636847A
- Authority
- CN
- China
- Prior art keywords
- emotion
- wake
- establishing
- titer
- fuzzy inference
- 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
- 230000008451 emotion Effects 0.000 title claims abstract description 151
- 210000000707 wrist Anatomy 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 230000002452 interceptive effect Effects 0.000 claims abstract description 9
- 230000033001 locomotion Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 58
- 210000003205 muscle Anatomy 0.000 claims description 14
- 230000036760 body temperature Effects 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 7
- 241000220317 Rosa Species 0.000 claims description 5
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 5
- 239000008280 blood Substances 0.000 claims description 5
- 210000004369 blood Anatomy 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 229910052760 oxygen Inorganic materials 0.000 claims description 5
- 239000001301 oxygen Substances 0.000 claims description 5
- 210000003857 wrist joint Anatomy 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 14
- 238000009826 distribution Methods 0.000 description 13
- 230000037007 arousal Effects 0.000 description 10
- 230000005611 electricity Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 230000003993 interaction Effects 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 5
- 230000002996 emotional effect Effects 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000013079 data visualisation Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 241001659863 Panna Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000994 depressogenic effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008909 emotion recognition Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000009545 invasion Effects 0.000 description 1
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000007704 transition Effects 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
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- 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
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychiatry (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Child & Adolescent Psychology (AREA)
- Educational Technology (AREA)
- Developmental Disabilities (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an emotion assessment method and system based on wrist wearable equipment, wherein the method carries out interactive motion of wrist rehabilitation on a tested person, and physiological signals are acquired from the wrist wearable equipment worn by the tested person; establishing a first fuzzy inference rule base by taking the physiological signal as input and the wake-up titer as output, establishing a wake-up titer model, and calculating the value of the wake-up titer; establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label; the numerical value of each emotion label is displayed through a visual chart, and the emotion state of the tested person is obtained through analysis; according to the invention, a membership model between multidimensional physiological signals, wake-up titers and emotions can be established through accurate and real-time physiological signal measurement, so that the emotion state of a tested person can be effectively estimated, and a complete wrist portable wearable equipment system is developed for a user.
Description
Technical Field
The invention relates to an emotion assessment method and an emotion assessment system, in particular to an emotion assessment method and an emotion assessment system based on wrist wearable equipment.
Background
Emotion assessment in a product experience is mostly subjective assessment, and subjective questionnaire scale assessment such as positive-negative emotion scale (pannas) is used. The result has weaker timeliness and low association degree with the product design, but the method for objectively measuring the physiological signals and the method for analyzing the data obtain the user invasion degree of the product experience emotion assessment, which has the advantages of longer assessment period and higher cost. The general processing logic of the existing emotion assessment method comprises data preprocessing, feature extraction, data training, feature vector, dimension reduction processing, data comparison and emotion/emotion recognition, wherein subjective and objective modes are difficult to be effectively combined, if the duration of an experiment and experience process is long, the emotion assessment result is easy to be inaccurate, the data processing and analysis process is long, and the data hysteresis is provided; and special equipment is needed to be worn for measuring physiological signals such as brain electricity, the threshold of professional equipment is high, the data analysis cost is high, the invasiveness to users, particularly patients in the rehabilitation process is high, and the measurement accuracy is influenced.
Disclosure of Invention
The invention aims to: the invention aims to provide an emotion assessment method based on wrist wearable equipment, which has high accuracy and strong synchronism; the second purpose of the invention is to provide the emotion assessment system based on the wrist wearable equipment, which is high in accuracy and high in synchronism.
The technical scheme is as follows: the emotion assessment method based on the wrist wearable equipment comprises the following steps:
(1) The method comprises the steps that a tested person performs interactive movement of wrist rehabilitation, and physiological signals are obtained from wrist wearable equipment worn by the tested person;
(2) Establishing a first fuzzy inference rule base by taking the physiological signal as input and the wake-up titer as output, establishing a wake-up titer model, and calculating the value of the wake-up titer;
(3) Establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label;
(4) And displaying the numerical value of each emotion label through a visual chart, and analyzing to obtain the emotion state of the tested person.
Further, the step (2) specifically includes:
(2.1) normalizing the physiological signal data criteria to establish a first input membership function;
(2.2) establishing a first output membership function of the wakeup titer;
(2.3) establishing a first fuzzy inference rule base of the physiological signal and the wake-up titer, and encapsulating and adding the first fuzzy inference rule base into a fuzzy inference rule tool box of MATLAB;
and (2.4) calculating a wake-up titer value, establishing a scatter diagram by taking the titer as a horizontal axis and the wake-up as a vertical axis, and analyzing the wake-up titer trend.
The first input membership function is a trapezoidal function and a triangular function; the first output membership function is a triangular function.
Further, the step (3) specifically includes:
(3.1) establishing a second input membership function of wake-up titers;
(3.2) establishing a second output membership function of the emotion tag;
(3.3) establishing a second fuzzy inference rule base of the wake-up titer and the emotion label, and encapsulating and adding the second fuzzy inference rule base into a fuzzy inference rule toolbox of MATLAB;
(3.4) calculating each emotion tag value.
The second input membership function and the second output membership function are both trapezoidal functions.
Further, the step (4) specifically includes:
and establishing a rose histogram or mapping a color chart of emotion values based on time series data according to the values of the emotion labels, and analyzing the emotion states and emotion changes of the testee.
Further, the physiological signal in the step (1) is at least three of muscle electric signals, skin electric signals, body temperature data and heart rate blood oxygen data.
Further, the emotion tags of step (3) and step (4) include fun, boring, challenging, exciting and frustrating.
The emotion assessment system based on the wrist wearable equipment comprises:
the wrist wearable device is used for acquiring physiological signals from the wrist wearable device worn by the tested person by using the sensing module when the tested person performs interactive motions of wrist joint rehabilitation;
the emotion assessment module is used for taking the physiological signal as input and the wake-up titer as output to establish a first fuzzy inference rule base, establishing a wake-up titer model and calculating the value of the wake-up titer; establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label; and displaying the numerical value of each emotion label through a visual chart, and analyzing to obtain the emotion state of the tested person.
The computer readable storage medium stores a computer program which when executed by a processor realizes the emotion assessment method based on the wrist wearable device.
The beneficial effects are that: compared with the prior art, the invention has the advantages that: (1) Establishing a membership model between multidimensional physiological signals, wake-up titers and emotions by establishing a twice membership model and a fuzzy reasoning rule base, and performing data visualization presentation; the problems of strong hysteresis and weak synchronism of the obtained emotion estimation result when emotion estimation is carried out by using physiological signal data of muscle electricity, skin temperature, heart rate and blood oxygen concentration are solved, and the operability of the physiological signal data is improved; the influence on the testee is small, and the emotion state and emotion change of the testee can be accurately estimated; (2) Through the embedded development technology of the sensor and the system, the problems of high cost, weak portability, poor synchronism and low accuracy of using multidimensional physiological signal measuring equipment and data analysis are solved during emotion assessment; the system develops a complete wrist portable wearable device system for a user, a sensing module of the system can be intelligently controlled by a control module so as to measure multidimensional physiological signals, and the system finally acquires and stores multidimensional physiological signal data of a tested person; (3) The interactive experience of the wrist portable wearable equipment system provides an emerging method for carrying out emotion assessment and visualization on multidimensional physiological signals for users.
Drawings
Fig. 1 is a flowchart of an emotion assessment method based on a wrist wearable device.
FIG. 2 is a block diagram of a fuzzy system with wake-up titers corresponding to multidimensional physiological signals according to an embodiment of the present invention.
FIG. 3 is a graph of membership functions of a multidimensional physiological signal in an embodiment of the present invention.
Fig. 4 is a three-dimensional visual curved surface diagram of a wake-up valence model corresponding to multidimensional physiological signal data in an embodiment of the present invention.
FIG. 5 is a data distribution and spatial mapping diagram of wake-up titer models in an embodiment of the present invention.
Fig. 6 is a block diagram of a fuzzy system of wake-up valence versus emotion tags in an embodiment of the present invention.
Fig. 7 is a three-dimensional visual curved surface diagram of a wake-up valence corresponding emotion tag model in an embodiment of the present invention.
FIG. 8 is a visual diagram of emotion assessment of wake-up titer versus emotion tag model in an embodiment of the present invention.
Fig. 9 is a block diagram of an emotion assessment system based on a wrist wearable device of the present invention.
FIG. 10 is an interface diagram of an emotion estimation system of the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 1, the emotion assessment method based on the wrist wearable device includes three parallel crossing steps: a main step, namely emotion assessment based on fuzzy reasoning; and two branch steps, namely executing emotion assessment for the wrist wearable device and the operator which are worn by the tested and measure physiological signals respectively.
According to the wrist wearable device, an operator selects wearing parts (left wrist and right wrist) of the wearable device of the tested person, and after the wearable device is safely worn, experiment preparation before emotion assessment is completed.
And a second branch step, collecting multidimensional physiological signal data as the data input of emotion estimation. The main flow is as follows: the operator wears the wearable device on the wrist according to the experiment, and simultaneously, the first branch step is parallel, the operator starts the related experiment, and then the data is saved as the data input of the main emotion assessment step.
In the emotion assessment main step based on fuzzy reasoning, according to the experimental basic requirements, the measured physiological signals are selected to be muscle electric signals, skin electric signals and infrared body temperature data, and the emotion label to be assessed by an operator has five dimensions, namely fun, boring, challenging, exciting and frustrating. The tested performs the interactive movement of wrist rehabilitation according to the requirement of an operator.
The main steps are divided into two stages:
the first stage is to build a model that converts the multidimensional physiological signal into wake-up titers. In order to utilize the continuity of physiological data, each physiological signal data is input in parallel according to the complete time sequence during acquisition, and finally the data is output in the time sequence. The model for converting physiological data signals into wake-up titers has three inputs, respectively muscle electrical signals, skin electrical signals and body temperature data, and two outputs, namely wake-up and titers, as shown in fig. 2. Wherein the input is multidimensional physiological signal standardized data and is in a range of [0,1 ]; the output is the maximum possible value for wakeup and potency, and is in the [0,1] range.
In the first phase (the multidimensional physiological signal data corresponds to the wake-up titers), the following four steps are mainly carried out:
step 1-1, constructing an input signal distribution histogram and a membership function
Considering the intuitiveness of the representation and the distribution characteristic of the physiological signals, the membership function is mainly constructed by adopting a triangle function and a trapezoid function, and the corresponding formulas are (1) and (2) respectively.
Where x is an input variable and a, b, c, d is a parameter defining a shape, respectively.
An input membership function is constructed based on statistical characteristics of the input muscle electricity, skin electricity, and body temperature data signal samples. When the membership function is determined, the three-dimensional physiological signal data is required to be in the same time sequence in the acquisition process, and the rule of real-time acquisition of the wrist wearable equipment acquisition data is met, so that the membership function can be well matched. In addition, taking into consideration the differences of various physiological signal value ranges and the imbalance of signal values caused by individual differences, a minimum-maximum (min-max) normalization method is adopted to compare the values of three physiological data signals, and finally the data is scaled to the [0,1] range.
Wherein,,and X i Respectively representing the original value and normalized value of the signal, X min And X max Respectively minimum and maximum. The final three physiological signal data obtained 42038 GSR-EMG-SKT sample sizes.
Fig. 3 is a membership function generated for each input signal using statistical characteristics of the signal distribution histogram. The statistical features of the data, that is, the Mean (Mean) and standard deviation (Standard Deviation, SD) of each input signal are calculated, respectively, are used to define the shape and inflection point of the membership function. As shown in fig. 3 (a), membership functions suitable for distribution of samples of the myoelectric data input signal are low (low), high (high) trapezoidal functions and medium-valued triangular functions. As shown in fig. 3 (b), membership functions suitable for the distribution of the skin electrical data input signal samples are defined as low (low), high (high) trapezoidal functions and medium low (mid_low), medium high (mid_high) triangular functions. As shown in fig. 3 (c), membership functions suitable for the distribution of the body temperature data input signal samples are defined as low (low), high (high) trapezoidal functions and medium-valued triangular functions. Wherein the trapezoidal function is used to eliminate ambiguity of the extremum.
Step 1-2, outputting membership function
The membership functions of the two outputs (i.e., wake-up and titers) are evenly distributed over the entire range. Therefore, the membership functions of wake-up and potency are five description distributions, namely triangle functions of very low (veryLow), low (Low), medium (Medium), high (high) and very high (veryHigh), as shown in the output module of FIG. 3.
Step 1-3, fuzzy inference rule base of corresponding wake-up titers of multidimensional physiological signal data
When the first fuzzy inference rule base is constructed, the emotion theory of multi-dimensional physiological signal mapping awakening and valence needs to be summarized. Where arousal (arousal) is mainly generated by muscle electricity, and potency (value) is mainly generated by skin electricity and body temperature data. The fuzzy inference rules are finally determined and directly encapsulated into the fuzzy inference rules toolbox of MATLAB. In addition, a model three-dimensional curved surface corresponding to wake-up titers based on the multi-dimensional physiological signal data after center deblurring is shown in fig. 4, which shows the relationship between input (muscle electricity, skin electricity and body temperature) and output (wake-up and titers) in the range of the discourse domain.
In the overall view, the skin electrical value is positively correlated with the degree of arousal and happy arousal, so that the arousal value is a smoother linear surface when the skin electrical and body temperature data are dominant, as shown in fig. 4 (a). Skin balance data is utilized because muscle electrical data sometimes does not provide sufficient information to predict potency. When the emotion fluctuation is large, such as happiness, sadness, assault, startle, etc., the heart rate is accelerated, and the blood flow is promoted, so that the value of the body temperature may also fluctuate, mainly in a positive correlation trend, as shown in (b) of fig. 4.
Step 1-4, fuzzy inference results in the first stage
And (3) inputting the membership function of the multidimensional physiological signal into a fuzzy reasoning rule base, and calculating to obtain a numerical value corresponding to the wake-up titer. The wake-up valence values of the 5-bit test objects (P1, P2, P6, P7 and P9) are calculated for evaluation respectively, and the data are visualized in a rectangular coordinate system in a scatter diagram mode. Since the data amount of each physiological signal to be tested is different, the abscissa axis is redefined according to the average division of the right angle space, the abscissa axis is the potency, and the ordinate axis is the arousal. In fig. 5, (a), (b), (c), (d), and (e) are wake-up space maps of the test pieces P1, P2, P6, P7, and P9, respectively. Wherein, P9 has wrist rehabilitation experience, and P1, P2, P6 and P7 have no wrist rehabilitation experience.
From the data visualization of fig. 5, the following evaluation results can be mainly obtained:
1. in the experiment, the emotion states are primarily analyzed according to a two-dimensional emotion theory model, and 5 emotion states tested in three stages are respectively obtained as table 1.
TABLE 1 emotional states under wake valence model
2. In the whole experimental process, the trend of the overall arousal titer can be seen, and the efficacy value shows a transition trend from negative to positive to negative, which means that the emotion to be tested gradually transits from a negative state to a positive state in the wrist rehabilitation process.
The second stage is to construct a model of the emotion tags corresponding to the wake-up titers. The second stage of the emotion model is to use the data information of the wake-up titers obtained in the first stage to infer different emotion labels, reflect the emotion experience of the tested person in the rehabilitation interaction process, and pertinently evaluate the emotion and the rehabilitation state of the tested person in the wrist joint rehabilitation process. It is generally recommended to select 3 or more physiological signals, the data enrichment degree is high, the data processing cost is low, and the accuracy of the analytically obtained emotion tag is relatively high.
Because the operator selects the wrist wearable equipment system to collect 3 real-time multidimensional physiological signal data, namely muscle electricity, skin electricity and body temperature data, and the method for comprehensively evaluating emotion by the three is less in research at present, in order to fully utilize rich and continuous physiological signal data, the time space sequence of the whole arousal titer is modeled, continuous indexes of emotion experience are created, five-dimensional emotion is fed back, emotion labels are respectively interesting, boring, challenging, exciting and frustrating, the interaction and rehabilitation are closely related, and finally a fuzzy reasoning model from arousal titer to emotion labels is established. The model of wake-up titers versus emotion tags has two inputs (wake and titers) and five outputs (boring, challenging, exciting, frustrating and fun). In the second stage, there are mainly two steps:
step 2-1, input and output signal distribution histogram and membership function construction
When determining the membership functions of the input and output, the membership functions are expressed as the maximum membership functions possible, and the values are distributed in [0,1]. The input membership function distribution is 6 trapezoidal functions, and the numerical distribution is very low (veryLow), low (Low), medium-low (mid Low), medium-high (mid high), high (high) and very high (veryhigh); the output membership function distributions are 4 trapezoidal functions, and the numerical distributions are very low (veryLow), low (Low), medium (Medium), and high (high), respectively, as shown in FIG. 6.
Step 2-2, establishing a fuzzy inference rule base of emotion labels corresponding to wake-up titers
When the second model reasoning rule base is established, the fuzzy reasoning rule base is established according to the existing wake-up valence space mapping principle, and the fuzzy reasoning rule base is directly packaged and added into a fuzzy reasoning rule tool box of MATLAB. Three-dimensional visual curved surface diagrams of five emotion labels are obtained, and fig. 7 is shown. Five emotion labels are visually presented, namely (a) in fig. 7 is interesting, (b) in fig. 7 is challenging, (c) in fig. 7 is boring, (d) in fig. 7 is depressed, and (e) in fig. 7 is active, and a three-dimensional model of the emotion label corresponding to the wake-up titer is built by integrating five curved surfaces.
Step 2-3, fuzzy reasoning result
And after the wake-up valence membership function is put into a fuzzy inference rule base, calculating to obtain accurate values corresponding to the five emotion labels. 5 bits of emotion label data corresponding to the tested are calculated respectively, the data are displayed into two forms of visual graphs, and the two forms of visual graphs of the data can display the tested emotion state from two dimensions of emotion change and rehabilitation interaction time sequence respectively. The first is a rose histogram, and emotion data is presented in polar coordinates in the form of a histogram, so that subsequent emotion assessment, comparison and analysis are facilitated. Wherein blue represents fun, orange represents challenge, yellow represents boring, purple represents depression, and green represents vitality. The second is a time series data-based emotion value mapping color chart, wherein the numbers 1 to 5 on the abscissa represent fun, challenge, boring, depression and vitality, the values on the ordinate represent the time series from small to large, and the block colors represent the current emotion values, as shown in fig. 8, and the wake-up titers of fig. 8 (a), (b), (c), (d) and (e) are emotion evaluation visualization charts of emotion label models corresponding to the tested P1, P2, P6, P7 and P9, respectively.
Through emotion assessment analysis in the two stages, the emotion assessment result is finally obtained as follows:
1. in the rose histogram in the data visualization, the emotion state presented is analyzed from the emotion change dimension as shown in table 2 below. It can be seen that the emotional states of P1, P2, P7, P9 all turn positive, and the emotional state of P6 turns negative.
TABLE 2 wake up titers correspond to emotional states under emotion tag model (correspond to rose histogram in FIG. 8)
2. And analyzing the dimension of the whole rehabilitation interaction time sequence according to the data-visualized emotion numerical value color mapping chart, and presenting the emotion state as shown in the table 3. Wherein, the tested P1, P2, P7 and P9 all show neutral and negative emotion tendencies, and P6 shows emotion tendencies from negative to positive to negative. On one hand, as the whole rehabilitation environment and the wrist wearable equipment are worn with certain invasiveness, the rehabilitation process is boring, and the emotion state trend consistent with subjective feedback is presented, so that the feasibility of the emotion label model corresponding to the arousal titer is proved to a certain extent. On the other hand, the result can be used as an important requirement iteration product requirement library, and the interesting and interactive performance of wrist joint rehabilitation interaction is used as an important index to carry out product system design iteration.
TABLE 3 wake up titers correspond to emotional states under the emotion tag model (to emotion numerical color map in FIG. 8)
As shown in fig. 9, the emotion assessment system based on a wrist wearable device of the present invention includes:
the wrist wearable device is used for acquiring physiological signals from the wrist wearable device worn by the tested person by using the sensing module when the tested person performs interactive motions of wrist joint rehabilitation;
the sensing module of the wrist wearable equipment comprises a muscle electric sensor module, a skin electric sensor module, an infrared body temperature sensor module and a heart rate blood oxygen sensor module, and muscle electric signal data, skin electric signal data, body temperature data and heart rate blood oxygen data can be measured respectively. In the perception module, the collected physiological signal data are smooth data signals, so that emotion assessment is convenient to follow-up. In particular, in the muscle sensor module, the ADC data processing unit is integrated, so that the output data of the module is not raw muscle electrical data, but a data signal amplified, corrected, and smoothed by the ADC.
The wrist wearable device further comprises a data transmission module, wherein the data transmission module is used for data transmission by using a communication sensor, such as a WiFi transmission module, and the communication module is used for communication by using a USART serial port and is connected with the client. The main flow is to connect the router, carry on the network communication; and connecting with a server, uploading and acquiring measurement data.
The wrist wearable equipment further comprises a control module, mainly a singlechip minimum unit, and is used for system control of the wrist wearable equipment, and mainly controlling the sensing module and the data transmission module.
The emotion assessment module is used for taking the physiological signal as input and the wake-up titer as output to establish a first fuzzy inference rule base, establishing a wake-up titer model and calculating the value of the wake-up titer; establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label; and displaying the numerical value of each emotion label through a visual chart, and analyzing to obtain the emotion state of the tested person.
Based on the emotion assessment method and system based on the wrist wearable device, an operator can adjust the wearable device according to experimental requirements and emotion assessment results, and an iteration loop of overall product system design and experimental interaction can be formed, and a specific platform interface is shown in fig. 10.
The computer readable storage medium stores a computer program which when executed by a processor realizes the emotion assessment method based on the wrist wearable device.
The computer-readable storage media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The processor is configured to execute the computer program stored in the memory to implement the steps in the method according to the above-mentioned embodiments.
Claims (10)
1. The emotion assessment method based on the wrist wearable equipment is characterized by comprising the following steps of:
(1) The method comprises the steps that a tested person performs interactive movement of wrist rehabilitation, and physiological signals are obtained from wrist wearable equipment worn by the tested person;
(2) Establishing a first fuzzy inference rule base by taking the physiological signal as input and the wake-up titer as output, establishing a wake-up titer model, and calculating the value of the wake-up titer;
(3) Establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label;
(4) And displaying the numerical value of each emotion label through a visual chart, and analyzing to obtain the emotion state of the tested person.
2. The emotion assessment method based on a wrist wearable device according to claim 1, wherein step (2) specifically comprises:
(2.1) normalizing the physiological signal data criteria to establish a first input membership function;
(2.2) establishing a first output membership function of the wakeup titer;
(2.3) establishing a first fuzzy inference rule base of the physiological signal and the wake-up titer, and encapsulating and adding the first fuzzy inference rule base into a fuzzy inference rule tool box of MATLAB;
and (2.4) calculating a wake-up valence value, establishing a scatter diagram by taking the valence as a horizontal axis and the wake-up as a vertical axis, and analyzing the emotion change trend based on the wake-up valence.
3. The emotion estimation method based on the wrist wearable device according to claim 2, wherein the first input membership function is a trapezoidal function and a triangular function; the first output membership function is a triangular function.
4. The emotion assessment method based on a wrist wearable device according to claim 1, wherein step (3) specifically comprises:
(3.1) establishing a second input membership function of wake-up titers;
(3.2) establishing a second output membership function of the emotion tag;
(3.3) establishing a second fuzzy inference rule base of the wake-up titer and the emotion label, and encapsulating and adding the second fuzzy inference rule base into a fuzzy inference rule toolbox of MATLAB;
(3.4) calculating the numerical value of each emotion label.
5. The emotion assessment method of claim 4, wherein the second input membership function and the second output membership function are both trapezoidal functions.
6. The emotion estimation method based on the wrist wearable device according to claim 1, wherein the step (4) specifically includes:
and establishing a rose histogram or mapping a color chart of emotion values based on time series data according to the values of the emotion labels, and analyzing the emotion states and emotion changes of the testee.
7. The emotion assessment method based on a wrist wearable device according to claim 1, wherein the physiological signal of step (1) is at least 3 of a muscle electrical signal, a skin electrical signal, body temperature data, and heart rate blood oxygen data.
8. The method of claim 1, wherein the emotion tags of step (3) and step (4) include fun, boring, challenging, exciting and frustrating.
9. An emotion assessment system based on a wrist wearable device, comprising:
the wrist wearable device is used for acquiring physiological signals from the wrist wearable device worn by the tested person by using the sensing module when the tested person performs interactive motions of wrist joint rehabilitation;
the emotion assessment module is used for taking the physiological signal as input and the wake-up titer as output to establish a first fuzzy inference rule base, establishing a wake-up titer model and calculating the value of the wake-up titer; establishing a second fuzzy inference rule base by taking the awakening titer as input and the emotion labels as output, establishing an emotion label model, and calculating the numerical value of each emotion label; and displaying the numerical value of each emotion label through a visual chart, and analyzing to obtain the emotion state of the tested person.
10. A computer readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the emotion assessment method based on a wrist wearable device according to any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310647253.7A CN116636847B (en) | 2023-06-02 | 2023-06-02 | Emotion assessment method and system based on wrist wearable equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310647253.7A CN116636847B (en) | 2023-06-02 | 2023-06-02 | Emotion assessment method and system based on wrist wearable equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116636847A true CN116636847A (en) | 2023-08-25 |
CN116636847B CN116636847B (en) | 2024-07-30 |
Family
ID=87615154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310647253.7A Active CN116636847B (en) | 2023-06-02 | 2023-06-02 | Emotion assessment method and system based on wrist wearable equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116636847B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8708884B1 (en) * | 2013-03-11 | 2014-04-29 | The United States Of America As Represented By The Secretary Of The Army | Systems and methods for adaptive mitigation of motion sickness |
US20140247155A1 (en) * | 2013-03-04 | 2014-09-04 | Hello Inc. | Methods using a mobile device to monitor an individual's activities, behaviors, habits or health parameters |
CN109620262A (en) * | 2018-12-12 | 2019-04-16 | 华南理工大学 | A kind of Emotion identification system and method based on wearable bracelet |
WO2023012818A1 (en) * | 2021-07-31 | 2023-02-09 | Sparcolife Digital Healthcare Technologies Private Limited | A non-invasive multimodal screening and assessment system for human health monitoring and a method thereof |
-
2023
- 2023-06-02 CN CN202310647253.7A patent/CN116636847B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140247155A1 (en) * | 2013-03-04 | 2014-09-04 | Hello Inc. | Methods using a mobile device to monitor an individual's activities, behaviors, habits or health parameters |
US8708884B1 (en) * | 2013-03-11 | 2014-04-29 | The United States Of America As Represented By The Secretary Of The Army | Systems and methods for adaptive mitigation of motion sickness |
CN109620262A (en) * | 2018-12-12 | 2019-04-16 | 华南理工大学 | A kind of Emotion identification system and method based on wearable bracelet |
WO2023012818A1 (en) * | 2021-07-31 | 2023-02-09 | Sparcolife Digital Healthcare Technologies Private Limited | A non-invasive multimodal screening and assessment system for human health monitoring and a method thereof |
Non-Patent Citations (2)
Title |
---|
SIIRTOLA P, TAMMINEN S, CHANDRA G, IHALAPATHIRANA A, RÖNING J. PREDICTING EMOTION WITH BIOSIGNALS: A COMPARISON OF CLASSIFICATION : "Predicting Emotion with Biosignals: A Comparison of Classification and Regression Models for Estimating Valence and Arousal Level Using Wearable Sensors.", SENSORS (BASEL), pages 2 - 21 * |
ZHANG Q, LEE M.: "Analyzing the dynamics of emotional scene sequence using recurrent neuro-fuzzy network", 《COGN NEURODYN》, pages 48 - 56 * |
Also Published As
Publication number | Publication date |
---|---|
CN116636847B (en) | 2024-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR100464821B1 (en) | Method for estimating emotion using physiological signal | |
Kasten et al. | Two-dimensional time-dependent vortex regions based on the acceleration magnitude | |
JP2020034849A (en) | Work support device, work support method, and work support program | |
US20110296331A1 (en) | Generation of a best-fit rigged body model | |
CN108888277A (en) | Psychological test method, system and terminal device | |
CN111062260B (en) | Automatic generation method of face-beautifying recommendation scheme | |
CN116440425B (en) | Intelligent adjusting method and system of LED photodynamic therapeutic instrument | |
JP7070252B2 (en) | Performance measuring device, performance measuring method and performance measuring program | |
CN111887867A (en) | Method and system for analyzing character formation based on expression recognition and psychological test | |
Wei et al. | Real-time facial expression recognition for affective computing based on Kinect | |
JP7070253B2 (en) | Performance measuring device, performance measuring method and performance measuring program | |
CN109558005A (en) | A kind of adaptive man-machine interface configuration method | |
CN106510736B (en) | Psychological condition determination method and system based on multidimensional psychological condition index | |
US20220180027A1 (en) | Method and apparatus for generating a design for a technical system of product | |
US20210369140A1 (en) | Body shape data acquisition system, body shape data acquisition program, and computer-readable non-transitory storage medium | |
CN116740909A (en) | Monitoring and early warning method and system based on wearable device information interaction | |
CN113160970A (en) | Index data analysis method, device, equipment and storage medium | |
CN116636847B (en) | Emotion assessment method and system based on wrist wearable equipment | |
US20220012262A1 (en) | Multidimensional data visualization apparatus, method, and program | |
AU2021101372A4 (en) | Human Body Shape Prediction System Based on Human Body Size Database | |
CN116911810A (en) | Intelligent cloud interview system and method based on virtual simulation | |
Xu et al. | Affective experience modeling based on interactive synergetic dependence in big data | |
CN106845391B (en) | Atmosphere field identification method and system in home environment | |
CN113870980A (en) | Visual obstetrical image examination processing method and device | |
KR101514291B1 (en) | Computer-executive sensibility energy measuring method |
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 |