Intelligent thermal comfort degree adjusting system based on quaternion characteristic driving and massage chair

Abstract

The invention discloses an intelligent thermal comfort degree adjusting system based on quaternion characteristic driving and a massage chair. The system comprises an electroencephalogram signal acquisition module, a central processing module and a temperature adjusting module. The central processing module is used for performing discrete wavelet transform on the electroencephalogram signals to obtain de-noised electroencephalogram signals; performing quaternary principal component analysis on the de-noised electroencephalogram signal to obtain a quaternary principal component feature; and performing support vector machine classification on the quaternary principal component features to obtain the thermal comfort classification of the user. The system can accurately and timely adjust the temperature.

Description

Technical Field

[0001] The present invention relates to the field of massage chair control, and more specifically, to an intelligent thermal comfort adjustment system and a massage chair based on quaternion feature drive. Background Art

[0002] In the current era, massage chairs are accepted and used by more and more people. In addition to the normal massage function, massage chairs also have a certain temperature adjustment function, making the user more comfortable when receiving massage.

[0003] Traditional massage chairs are equipped with manual temperature adjustment switches or voice adjustment switches. Both of these adjustment methods require users to actively click buttons or speak before they can adjust. Therefore, the user experience is poor and the adjustment response is slow. Another type of massage chair is equipped with a temperature sensor adjustment switch. Although this adjustment method uses the method of detecting the user's body surface temperature for adjustment, due to the different temperature comfort ranges of different user groups, it leads to poor user experience, untimely temperature adjustment, and the adjusted temperature cannot accurately meet user needs.

[0004] The prior art discloses a method for brain wave detection linked to a massage chair, including an EEG collector collecting brain wave signals of different frequency bands from a person, the EEG collector analyzing the collected brain wave signals, the brain wave signals mainly analyzed are θ waves and α waves, and the frequency of the θ waves, the power of the θ waves, the frequency of the α waves and the power of the α waves are obtained, and the EEG collector sends the obtained frequency of the θ waves, the power of the θ waves, the frequency of the α waves and the power of the α waves to the controller of the massage chair. The present invention automatically collects brain wave signals of a person through an EEG collector, and the EEG collector automatically controls the massage chair to perform automatic and precise massage according to the analysis results, so as to relieve fatigue, relax the body and mind or improve sleep. This method does not process and extract brain waves, and the massage chair itself does not involve a temperature adjustment method or system. Summary of the invention

[0005] The present invention aims to address the defect that the regulating system in the prior art cannot accurately and timely adjust the temperature to adapt to the thermal comfort of the user; and provides an intelligent thermal comfort regulating system and a massage chair driven by quaternion characteristics.

[0006] The primary purpose of the present invention is to solve the above technical problems. The technical solution of the present invention is as follows:

[0007] The intelligent thermal comfort adjustment system based on quaternion feature drive is characterized by comprising: an EEG signal acquisition module, a central processing module, and a temperature adjustment module;

[0008] The EEG signal acquisition module is used to collect the user's brain waves, obtain EEG signals, and send the EEG signals to the central processing module;

[0009] The central processing module is used to perform discrete wavelet transform on the EEG signal to obtain a denoised EEG signal; perform quaternary principal component analysis on the denoised EEG signal to obtain quaternary principal component features; perform support vector machine classification on the quaternary principal component features to obtain a user's thermal comfort classification; and send the thermal comfort classification to the temperature adjustment module;

[0010] The temperature adjustment module adjusts the temperature according to the user's thermal comfort classification.

[0011] Furthermore, the formula including the denoised EEG signal is as follows:

[0012]

[0013] N represents the total number of sampling points, m and n represent the sampling point numbers, k represents the coefficient number, h[n] represents the low-pass filter of the nth sampling point, g[n] represents the high-pass filter of the nth sampling point, a k [m] represents the approximation coefficient of the mth sampling point at the kth time point, d k [m] Detail coefficient of the mth sampling point at the kth time point;

[0014] The formula for the approximation coefficient at the kth time point is as follows:

[0015]

[0016] m and n represent the sampling point numbers, N represents the total number of sampling points, and x k [m] represents the signal of the mth sampling point at the kth time point, and h[n] represents the low-pass filter of the nth sampling point;

[0017] The formula for the detail coefficient at the kth time point is as follows:

[0018]

[0019] m and n represent the sampling point numbers, N represents the total number of sampling points, x[m] represents the signal of the mth sampling point at the kth time point, and g[n] represents the high-pass filter of the nth sampling point;

[0020] Furthermore, the denoised EEG signals include: α wave, β wave, θ wave, and δ wave;

[0021] The denoised EEG signal can be decomposed into the following forms:

[0022] q[n]=α+βi+θj+δk

[0023] n represents the sampling point number, i, j, k represent three orthogonal unit vectors in the quaternion, α represents α wave, β represents β wave, θ represents θ wave, and δ represents δ wave.

[0024] Furthermore, the formula of the quaternary principal component feature is as follows:

[0025] Z=Y T ·X

[0026] X represents the four-element EEG data matrix, and Y represents the eigenvector projection matrix.

[0027] Furthermore, the formula of the four-element EEG data matrix is ​​as follows:

[0028]

[0029] n and p represent the sampling point numbers, A(n) is formed by concatenating the denoised EEG signal q[n] row by row, and N represents the total number of sampling points.

[0030] Furthermore, the calculation formula of the eigenvector projection matrix is ​​as follows:

[0031]

[0032] δ represents the eigenvalue, I represents the unit matrix, X represents the quaternary EEG data matrix, y represents the eigenvector, det(XX T -δI) indicates the T -δI) Find the determinant;

[0033] All eigenvectors y that satisfy this equation form the eigenvector projection matrix Y:

[0034] Y=(y1,y2,y3,...,y M )

[0035] M represents the total number of eigenvalues.

[0036] A massage chair with intelligent temperature regulation, comprising: a massage chair body and an intelligent thermal comfort regulation system based on quaternion feature drive;

[0037] Among them, the temperature adjustment module and the central processing module are arranged in the massage chair body, and the electroencephalogram signal acquisition module is arranged outside the massage chair body.

[0038] Furthermore, the EEG signal acquisition module includes 8 groups of frontal and parietal electrodes, 4 groups of subcranial electrodes, and 4 groups of temporal electrodes.

[0039] Furthermore, the temperature regulating module includes electric heating wire or carbon fiber heating film.

[0040] Furthermore, the temperature regulating module includes a liquid cooling system and a micro fan.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The present invention acquires brain waves of the user to obtain brain waves; performs discrete wavelet transform on the brain waves to obtain denoised brain waves; performs quaternary principal component analysis on the denoised brain waves to obtain quaternary principal component features; performs support vector machine classification on the quaternary principal component features to obtain the user's thermal comfort classification; and adjusts the temperature according to the user's thermal comfort classification; accurately and timely adjusts the temperature to improve the user's comfort;

[0043] The above-mentioned adjustment system is applied to a massage chair, which can accurately and timely adjust the temperature and improve the user's comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a structural diagram of the intelligent thermal comfort adjustment system based on quaternion feature drive provided in Example 1.

[0045] Figure 2 This is a flow chart of a massage chair temperature adjustment method provided in Example 1.

[0046] Figure 3 This is a structural diagram of a massage chair with intelligent temperature regulation provided in Example 1. DETAILED DESCRIPTION

[0047] The drawings are for illustrative purposes only and should not be construed as limiting the present patent;

[0048] In order to better illustrate the present embodiment, some parts in the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0049] It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0050] The technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0051] Example 1

[0052] like Figure 1 As shown, the intelligent thermal comfort adjustment system based on quaternion feature drive is characterized by comprising: an EEG signal acquisition module, a central processing module, and a temperature adjustment module;

[0053] The EEG signal acquisition module is used to collect the user's brain waves, obtain EEG signals, and send the EEG signals to the central processing module;

[0054] The central processing module is used to perform discrete wavelet transform on the EEG signal to obtain a denoised EEG signal; perform quaternary principal component analysis on the denoised EEG signal to obtain quaternary principal component features; perform support vector machine classification on the quaternary principal component features to obtain a user's thermal comfort classification; and send the thermal comfort classification to the temperature adjustment module;

[0055] The temperature adjustment module adjusts the temperature according to the user's thermal comfort classification.

[0056] In a specific embodiment, Figure 2 As shown, a massage chair temperature adjustment method comprises:

[0057] S1: Collect the user's brain waves to obtain brain wave signals;

[0058] S2: performing discrete wavelet transform on the EEG signal to obtain a denoised EEG signal;

[0059] S3: performing a four-element principal component analysis on the denoised EEG signal to obtain four-element principal component features;

[0060] S4: Perform support vector machine classification on the four-element principal component features to obtain the user's thermal comfort classification;

[0061] S5: Adjust the temperature of the massage chair according to the user's thermal comfort classification.

[0062] It should be noted that EEG signals are very weak and are easily affected by various internal and external interferences, such as power line interference, myoelectric artifacts, eye movement artifacts, electrocardiographic artifacts, etc. These noises will significantly reduce the signal-to-noise ratio of EEG signals and mask the EEG activities that are expected to be analyzed. In order to improve the quality of acquisition and the accuracy of EEG signal analysis, it is necessary to perform denoising.

[0063] Furthermore, the formula including the denoised EEG signal is as follows:

[0064]

[0065] N represents the total number of sampling points, m and n represent the sampling point numbers, k represents the coefficient number, h[n] represents the low-pass filter of the nth sampling point, g[n] represents the high-pass filter of the nth sampling point, a k [m] represents the approximation coefficient of the mth sampling point at the kth time point, d k [m] Detail coefficient of the mth sampling point at the kth time point;

[0066] The formula for the approximation coefficient at the kth time point is as follows:

[0067]

[0068] m and n represent the sampling point numbers, N represents the total number of sampling points, and x k [m] represents the signal of the mth sampling point at the kth time point, and h[n] represents the low-pass filter of the nth sampling point;

[0069] The formula for the detail coefficient at the kth time point is as follows:

[0070]

[0071] m and n represent the sampling point numbers, N represents the total number of sampling points, x[m] represents the signal of the mth sampling point at the kth time point, and g[n] represents the high-pass filter of the nth sampling point;

[0072] It should be noted that the discrete wavelet transform utilizes the multi-resolution analysis characteristics of the wavelet transform to decompose the signal into different frequency and time scales, thereby effectively separating the signal from the noise. The discrete wavelet transform can decompose the signal into components of different frequency bands, so that the signal can be analyzed in both the time domain and the frequency domain, thereby more effectively processing the EEG signal with time localization characteristics, and has strong adaptability.

[0073] Furthermore, the denoised EEG signals include: α wave, β wave, θ wave, and δ wave;

[0074] The denoised EEG signal can be decomposed into the following forms:

[0075] q[n]=α+βi+θj+δk

[0076] n represents the sampling point number, i, j, k represent three orthogonal unit vectors in the quaternion, α represents α wave, β represents β wave, θ represents θ wave, and δ represents δ wave.

[0077] Furthermore, the formula of the quaternary principal component feature is as follows:

[0078] Z=Y T ·X

[0079] X represents the four-element EEG data matrix, and Y represents the eigenvector projection matrix.

[0080] Furthermore, the formula of the four-element EEG data matrix is ​​as follows:

[0081]

[0082] n and p represent the sampling point numbers, A(n) is formed by concatenating the denoised EEG signal q[n] row by row, and N represents the total number of sampling points.

[0083] Furthermore, the calculation formula of the eigenvector projection matrix is ​​as follows:

[0084]

[0085] δ represents the eigenvalue, I represents the unit matrix, X represents the quaternary EEG data matrix, y represents the eigenvector, det(XX T -δI) indicates the T -δI) Find the determinant;

[0086] All eigenvectors y that satisfy this equation form the eigenvector projection matrix Y:

[0087] Y=(y1,y2,y3,...,y M )

[0088] M represents the total number of eigenvalues.

[0089] It should be noted that all eigenvalues ​​δ must satisfy Each eigenvalue δ corresponds one-to-one to an eigenvector y.

[0090] It should be noted that the above formula is derived using the following quaternion basic operations:

[0091] Assume that the two quaternions are:

[0092] q1=r1+x1i+y1j+z1k

[0093] q2=r2+x2i+y2j+z2k

[0094] The basic operation relationship is:

[0095] ij=k,jk=i,ki=j

[0096] ijk=i 2 =j 2 =-1

[0097] The addition of quaternions is:

[0098] q1·q2=<q1,q2> =r1r2+x1x2+y1y2+z1z2

[0099] The conjugate of a quaternion is:

[0100]

[0101] The Hamiltonian product of quaternions is:

[0102]

[0103] It should be noted that the four-element principal component analysis can more comprehensively express the relationship between data than the traditional principal component analysis method, and has nonlinear properties, so it can better capture the nonlinear relationship in the data, better preserve the characteristics and structure of the data, and better maintain the amount of information in the process of dimensionality reduction. Directly using principal component analysis for feature extraction without using the four-element principal component analysis will ignore the coupling relationship of signals in different frequency bands and ignore potential information, which will lead to deviations in judging the user's thermal comfort.

[0104] A massage chair with intelligent temperature regulation, comprising: a massage chair body and an intelligent thermal comfort regulation system based on quaternion feature drive;

[0105] Among them, the temperature adjustment module and the central processing module are arranged in the massage chair body, and the electroencephalogram signal acquisition module is arranged outside the massage chair body.

[0106] Furthermore, the EEG signal acquisition module includes 8 groups of frontal and parietal electrodes, 4 groups of subcranial electrodes, and 4 groups of temporal electrodes.

[0107] In a specific embodiment, the electrode is composed of an electrode sheet and a signal amplifier. The electrode sheet can directly contact the scalp and is responsible for monitoring the user's current EEG signal. The signal amplifier is responsible for amplifying weak EEG signals. The electrode impedance test is performed before use to ensure that the impedance value of the electrode is within an acceptable range.

[0108] In a specific embodiment, the sampling rate is 256 Hz, so as to ensure that sufficient time resolution can be collected for subsequent frequency analysis. The acquisition time is one minute, and a total of 16 channels of signals are collected.

[0109] Furthermore, the temperature regulating module includes electric heating wire or carbon fiber heating film.

[0110] In a specific embodiment, electric heating wires or carbon fiber heating films are embedded inside the massage chair and embedded in key contact parts such as the backrest, seat cushion and armrests. This heating method can increase the local temperature in a short time and provide rapid heat supplement; for example, the heating of the backrest, seat cushion, neck, waist, legs and other areas can be independently controlled, and more detailed temperature control can be achieved through zone heating.

[0111] Furthermore, the temperature regulating module includes a liquid cooling system and a micro fan.

[0112] In a specific embodiment, the cooling module includes two types, one is a fan or airflow system with a built-in micro fan that introduces cool air and diffuses it to the user's skin surface through breathable materials. The fan lowers the temperature of the user's body surface through circulating airflow and takes away excess heat. The intensity of the fan can be independently controlled in different areas. The other is a liquid cooling method. Liquid cooling pipes are placed in the seat cushion and backrest of the massage chair to achieve more comfortable temperature control.

[0113] In a specific embodiment, Figure 3 As shown, it includes: a massage chair body, an EEG signal acquisition module 1, and a central processing module 2. Among them, the temperature adjustment module includes a heating module 3 and a cooling module 4.

[0114] The same or similar reference numerals correspond to the same or similar components;

[0115] The terms used in the drawings to describe positional relationships are only used for illustrative purposes and should not be construed as limiting this patent;

[0116] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. Intelligent thermal comfort adjustment system based on quaternion feature drive, characterized in that: include: EEG signal acquisition module, central processing module, temperature regulation module; The EEG signal acquisition module is used to collect the user's brain waves, obtain EEG signals, and send the EEG signals to the central processing module; The central processing module is used to perform discrete wavelet transform on the EEG signal to obtain a denoised EEG signal; Performing a four-element principal component analysis on the denoised EEG signal to obtain four-element principal component features; The four-element principal component features are classified by support vector machine to obtain the user's thermal comfort classification; and sending the thermal comfort classification to a temperature adjustment module; The temperature adjustment module adjusts the temperature according to the user's thermal comfort classification.

2. According to claim 1, the intelligent thermal comfort adjustment system based on quaternion feature drive is characterized in that: The formula including the denoised EEG signal is as follows: N represents the total number of sampling points, m and n represent the sampling point numbers, k represents the coefficient number, h[n] represents the low-pass filter of the nth sampling point, g[n] represents the high-pass filter of the nth sampling point, a k [m] represents the approximation coefficient of the mth sampling point at the kth time point, d k [m] Detail coefficient of the mth sampling point at the kth time point; The formula for the approximation coefficient at the kth time point is as follows: m and n represent the sampling point numbers, N represents the total number of sampling points, and x k [m] represents the signal of the mth sampling point at the kth time point, and h[n] represents the low-pass filter of the nth sampling point; The formula for the detail coefficient at the kth time point is as follows: m and n represent the sampling point numbers, N represents the total number of sampling points, x[m] represents the signal of the mth sampling point at the kth time point, and g[n] represents the high-pass filter of the nth sampling point.

3. According to claim 2, the intelligent thermal comfort adjustment system based on quaternion feature drive is characterized in that: The denoised EEG signals include: α wave, β wave, θ wave, and δ wave; The denoised EEG signal can be decomposed into the following forms: q[n]=α+βi+θj+δk n represents the sampling point number, i, j, k represent three orthogonal unit vectors in the quaternion, α represents α wave, β represents β wave, θ represents θ wave, and δ represents δ wave.

4. According to claim 3, the intelligent thermal comfort adjustment system based on quaternion feature drive is characterized in that: The formula of the quaternary principal component feature is as follows: Z=Y T ·X X represents the four-element EEG data matrix, and Y represents the eigenvector projection matrix.

5. The intelligent thermal comfort adjustment system based on quaternion feature drive according to claim 4 is characterized in that: The formula of the four-element EEG data matrix is ​​as follows: n and p represent the sampling point numbers, A(n) is formed by concatenating the denoised EEG signal q[n] row by row, and N represents the total number of sampling points.

6. The intelligent thermal comfort adjustment system based on quaternion feature drive according to claim 4 is characterized in that: The calculation formula of the eigenvector projection matrix is ​​as follows: δ represents the eigenvalue, I represents the unit matrix, X represents the quaternary EEG data matrix, y represents the eigenvector, det(XX T -δI) indicates the T -δI) Find the determinant; All eigenvectors y that satisfy this equation form the eigenvector projection matrix Y: <h2 style=";text-align:left;direction:ltr">Y = (y1, y2, y3,..., y)<h2 style=";text-align:left;direction:ltr"> M <h2 style=";text-align:left;direction:ltr"> ) M represents the total number of eigenvalues.

7. A massage chair with intelligent temperature regulation, characterized in that: include: A massage chair body and an intelligent thermal comfort adjustment system based on quaternion feature drive as claimed in any one of claims 1 to 6; Among them, the temperature adjustment module and the central processing module are arranged in the massage chair body, and the electroencephalogram signal acquisition module is arranged outside the massage chair body.

8. The intelligent temperature-adjustable massage chair according to claim 7, characterized in that: The EEG signal acquisition module includes 8 groups of frontal and parietal electrodes, 4 groups of subcranial electrodes, and 4 groups of temporal electrodes.

9. The intelligent temperature-adjustable massage chair according to claim 7, characterized in that: The temperature adjustment module includes electric heating wire or carbon fiber heating film.

10. The intelligent temperature-adjustable massage chair according to claim 7, characterized in that: The temperature regulating module includes a liquid cooling system and a micro fan.

Images