A sleep brain activity monitor based on liquid metal

Abstract

The present invention discloses a sleep brain activity monitor based on liquid metal, including a sensing unit for acquiring the sleep EEG signal data of the subject to be measured and transmitting it to a signal amplifier; a signal amplifier for amplifying and processing the sleep EEG signal data and transmitting it to a liquid metal storage pool; a liquid metal storage pool for deforming according to the signal received and processed by the signal amplifier; a sleep brain activity monitor host for monitoring the deformation of the liquid metal in the liquid metal storage pool to acquire the change in the sleep brain wave frequency of the subject to be measured, and then acquire the sleep stage of the subject to be measured; a display and storage device for displaying and storing monitoring data. Based on the good performance of liquid metal, the present invention can deduce the change in the sleep brain wave frequency of the human body according to the change in liquid metal for different received signals, and can effectively realize the monitoring of the sleep activity state of the human brain and the storage of information.

Description

Technical Field

[0001] The present invention belongs to the technical field of sleep monitors, and in particular to a sleep brain activity monitoring device based on liquid metal. Background Art

[0002] In recent years, with the accelerated pace of life and the surge in work pressure, people's sleep problems have become increasingly prominent. According to survey data, about 27% of the world's population has varying degrees of sleep disorders. And with the further development of society, social environment, living conditions and other issues will further increase the incidence of insomnia, seriously affecting people's physical and mental health, and reducing people's quality of life and work efficiency. Long-term poor sleep can also cause a series of mental and physical diseases, such as depression, cardiovascular disease, etc.

[0003] Paying attention to sleep quality is closely related to human physical health. With the development of society, more and more people have begun to realize the importance of good sleep quality and have begun to consciously monitor their sleep.

[0004] Polysomnography is a commonly used sleep breathing monitoring instrument, which includes the detection of multiple signals, including EEG, electrooculogram, electromyography, electrocardiogram, pulse wave, blood oxygen, oral and nasal airflow, chest breathing, abdominal breathing, snoring, body position, body movement, blood pressure, video, audio signals, etc. By monitoring these signals all night, the patient's sleep quality can be objectively evaluated. However, the equipment is complex and not easy to operate; it puts a heavy physiological and psychological burden on the person being tested.

[0005] Therefore, it is very necessary to develop a sleep monitoring device with simple operation, few monitoring parameters and low cost under the existing technology. Summary of the invention

[0006] The purpose of the present invention is to provide a sleep brain activity monitor based on liquid metal to address the problems existing in the above-mentioned prior art.

[0007] The technical solution for achieving the purpose of the present invention is: a sleep brain activity monitor based on liquid metal, including a sensor unit, a signal amplifier, a liquid metal storage tank, a sleep brain activity monitor host, and a display and storage device;

[0008] The sensing unit is used to obtain the sleep EEG signal data of the subject and transmit it to the signal amplifier;

[0009] The signal amplifier is used to amplify the sleep EEG signal data and transmit it to the liquid metal storage tank;

[0010] The liquid metal storage tank is used to deform according to the signal received and processed by the signal amplifier;

[0011] The sleep brain activity monitor host is used to monitor the deformation of the liquid metal in the liquid metal storage tank to obtain the change in the sleep brain wave frequency of the subject being measured, and then obtain the sleep stage of the subject being measured;

[0012] The display and storage device is used to display and store monitoring data.

[0013] Furthermore, the sensing unit includes an EEG patch and a wireless signal transmission module which is arranged on the EEG patch and establishes a communication connection with the EEG patch; the EEG patch is fixed to the head of the subject and is used to monitor sleep brain waves.

[0014] Furthermore, the signal amplifier is connected to the liquid metal storage tank via a radio frequency coaxial cable.

[0015] Furthermore, the liquid metal storage tank comprises liquid metal and sodium hydroxide solution, wherein the liquid metal serves as a positive electrode and the sodium hydroxide solution serves as a negative electrode, and the liquid metal changes in length according to the signal received and processed by the signal amplifier.

[0016] Furthermore, the liquid metal changes in length according to the signal received and processed by the signal amplifier, specifically: the length of the liquid metal becomes one quarter of the wavelength of the sleep brain wave.

[0017] Furthermore, the sleep brain activity monitor also includes a main operation module as a core, which is used to send instructions to other components of the sleep brain activity monitor to drive each component to work and communicate.

[0018] Further, the sleep brain wave frequencies include delta waves, theta waves, alpha waves, beta waves, and gamma waves;

[0019] The relationship between the sleep brain wave frequency and the sleep stage includes: the wakeful period, which is dominated by beta waves; the non-rapid eye movement sleep period, including S1, S2, S3 and S4, among which S1 is dominated by alpha and theta waves, S2 is dominated by theta waves, and S3 and S4 are dominated by delta waves; and the rapid eye movement period, whose brain wave characteristics are similar to those of the wakeful period.

[0020] Furthermore, the obtaining of the change in the sleep brain wave frequency of the measured object, and then obtaining the sleep stage of the measured object, is specifically obtained through a machine learning algorithm, including: using a data set related to the sleep brain wave frequency and the sleep stage to train a machine learning model, and then using the trained model to perform real-time discrimination on the measured data and output the corresponding sleep stage;

[0021] Specifically include:

[0022] Step 1, constructing a data set; selecting several single-channel sleep EEG data of several subjects from the Sleep-EDF data set of the PhysioNet database, removing the data of the unreadable stage, and merging the S3 and S4 stages of deep sleep into the SS stage, and the processed data form a data set;

[0023] Step 2, dividing the data set into a training set and a test set;

[0024] Step 3, using the data set to train a one-dimensional convolutional neural network to generate a sleep stage discrimination model;

[0025] Step 4: Use the sleep stage discrimination model to discriminate the measured sleep brain wave frequency and output the corresponding sleep stage.

[0026] Compared with the prior art, the present invention has the following significant advantages: based on the good performance of liquid metal, for different received signals, the changes in the human body's sleep brain wave frequency can be deduced according to the changes in the liquid metal, which can effectively monitor the human brain's sleep activity state and the storage of information.

[0027] The present invention is further described in detail below in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 Schematic diagram of a liquid metal-based sleep brain activity monitor.

[0029] Figure 2 A schematic diagram of model training in one embodiment.

[0030] Figure 3 It is a schematic diagram of the change of liquid metal length with different sleeping conditions in one embodiment.

[0031] Figure 4 The figure is a schematic diagram of the real-time monitoring process of a sleep brain activity monitor based on liquid metal in one embodiment. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0033] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0034] In one embodiment, a sleep brain activity monitor based on liquid metal is provided, comprising a sensor unit, a signal amplifier 1, a liquid metal storage tank, a sleep brain activity monitor host 3, and a display and storage device 6;

[0035] The sensing unit is used to obtain the sleep EEG signal data of the subject and transmit it to the signal amplifier;

[0036] The signal amplifier is used to amplify the sleep EEG signal data and transmit it to the liquid metal storage tank;

[0037] The liquid metal storage tank is used to deform according to the signal received and processed by the signal amplifier;

[0038] The sleep brain activity monitor host is used to monitor the deformation of the liquid metal in the liquid metal storage tank to obtain the change in the sleep brain wave frequency of the subject being measured, and then obtain the sleep stage of the subject being measured;

[0039] The display and storage device is used to display and store monitoring data.

[0040] Furthermore, in one of the embodiments, the sensing unit includes an EEG patch, and a wireless signal transmission module disposed on the EEG patch and establishing a communication connection with the EEG patch; the EEG patch is fixed to the head of the subject and is used to monitor sleep brain waves.

[0041] Furthermore, in one of the embodiments, the signal amplifier 1 is connected to the liquid metal storage tank via a radio frequency coaxial cable 2 .

[0042] Furthermore, in one embodiment, the liquid metal storage tank includes liquid metal 4 and sodium hydroxide solution 5, wherein the liquid metal 4 serves as a positive electrode and the sodium hydroxide solution 5 serves as a negative electrode, and the liquid metal 4 changes in length according to the signal received and processed by the signal amplifier 1.

[0043] Here, preferably, the length of the liquid metal becomes one quarter of the wavelength of the sleep brain wave.

[0044] Furthermore, in one of the embodiments, the sleep brain activity monitor also includes a main operation module as a core, which is used to send instructions to other components of the sleep brain activity monitor to drive each component to work and communicate.

[0045] In some embodiments herein, the main operation module includes an automatic operation mode and a manual operation mode (button 7 etc.).

[0046] Furthermore, in one embodiment, the sleep brain wave frequencies include delta waves (0.5-3 Hz), theta waves (4-7 Hz), alpha waves (8-13 Hz), beta waves (14-30 Hz), and gamma waves (30-80 Hz).

[0047] The relationship between the sleep brain wave frequency and the sleep stage includes: the wakeful period, which is dominated by beta waves; the non-rapid eye movement sleep period, including S1, S2, S3 and S4, among which S1 is dominated by alpha and theta waves, S2 is dominated by theta waves, and S3 and S4 are dominated by delta waves; and the rapid eye movement period, whose brain wave characteristics are similar to those of the wakeful period.

[0048] Further, in one of the embodiments, the obtaining of the change in the sleep brain wave frequency of the subject, and then obtaining the sleep stage of the subject, is specifically obtained through a machine learning algorithm, including: using a data set related to the sleep brain wave frequency and the sleep stage to train a machine learning model, and then using the trained model to perform real-time discrimination on the measured data and output the corresponding sleep stage;

[0049] Specifically include:

[0050] Step 1, constructing a data set; selecting several single-channel sleep EEG data of several subjects from the Sleep-EDF data set of the PhysioNet database, removing the data of the unreadable stage, and merging the S3 and S4 stages of deep sleep into the SS stage, and the processed data form a data set;

[0051] Here preferably, the sampling frequency of the data is 100 Hz and the sample length is set to 20 seconds.

[0052] Step 2, dividing the data set into a training set and a test set;

[0053] Step 3: Use the data set to train a one-dimensional convolutional neural network to generate a sleep stage discrimination model, such as Figure 2 As shown;

[0054] Step 4: Use the sleep stage discrimination model to discriminate the measured sleep brain wave frequency and output the corresponding sleep stage.

[0055] Here, in some embodiments, the convolutional neural network includes a convolutional layer, a pooling layer, a convolutional layer, a pooling layer, a flattening layer and a fully connected layer connected in sequence; wherein the activation function used by the convolutional layer is relu, the activation function of the fully connected layer is softmax, the model samples the Adam optimizer, and the loss function is the cross entropy loss function.

[0056] like Figure 3As shown in the figure, the length of the liquid metal will change with the frequency of the received sleep brain waves. Using this characteristic, the change of the human sleep brain wave frequency can be deduced. Taking 20 seconds as a unit, the metal length detection data stored in the memory is extracted, converted into sleep brain wave frequency, sampled at a frequency of 100Hz, and input into the trained convolutional neural network. The model outputs the real-time sleep status of the person being tested and displays it on the monitor. The real-time detection process of the detector is as follows: Figure 4 shown.

[0057] The present invention is based on the good performance of liquid metal. For different received signals, the changes in the human body's sleep brain wave frequency are deduced according to the changes in the liquid metal, and the sleep activity of the human brain can be effectively monitored.

[0058] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A sleep brain activity monitor based on liquid metal, characterized in that: It includes a sensor unit, a signal amplifier, a liquid metal storage tank, a sleep brain activity monitor host, and display and storage devices; The sensing unit is used to obtain the sleep EEG signal data of the subject and transmit it to the signal amplifier; The signal amplifier is used to amplify the sleep EEG signal data and transmit it to the liquid metal storage tank; The liquid metal storage tank is used to deform according to the signal received and processed by the signal amplifier; The sleep brain activity monitor host is used to monitor the deformation of the liquid metal in the liquid metal storage tank to obtain the change in the sleep brain wave frequency of the subject being measured, and then obtain the sleep stage of the subject being measured; The display and storage device is used to display and store monitoring data; The liquid metal storage tank comprises liquid metal and sodium hydroxide solution, wherein the liquid metal serves as a positive electrode and the sodium hydroxide solution serves as a negative electrode, and the liquid metal changes in length according to the signal received and processed by the signal amplifier; The liquid metal changes in length according to the signal received and processed by the signal amplifier, specifically: the length of the liquid metal becomes one quarter of the wavelength of the sleep brain wave.

2. The liquid metal-based sleep brain activity monitor according to claim 1, characterized in that: The sensing unit includes an EEG patch and a wireless signal transmission module which is arranged on the EEG patch and establishes a communication connection with the EEG patch; the EEG patch is fixed to the head of the subject and is used to monitor sleep brain waves.

3. The liquid metal-based sleep brain activity monitor according to claim 1, characterized in that: The signal amplifier is connected to the liquid metal storage tank via a radio frequency coaxial cable.

4. The liquid metal-based sleep brain activity monitor according to claim 1, characterized in that: The sleep brain activity monitor also includes a main operation module as a core, which is used to send instructions to other components of the sleep brain activity monitor to drive each component to work and communicate.

5. The liquid metal-based sleep brain activity monitor according to claim 4, characterized in that: The main operation module includes an automatic operation mode and a manual operation mode.

6. The liquid metal-based sleep brain activity monitor according to claim 1, characterized in that: The sleep brain wave frequencies include delta waves, theta waves, alpha waves, beta waves, and gamma waves; The relationship between the sleep brain wave frequency and the sleep stage includes: the wakeful period, which is dominated by beta waves; the non-rapid eye movement sleep period, including S1, S2, S3 and S4, among which S1 is dominated by alpha and theta waves, S2 is dominated by theta waves, and S3 and S4 are dominated by delta waves; and the rapid eye movement period, whose brain wave characteristics are similar to those of the wakeful period.

7. The liquid metal-based sleep brain activity monitor according to claim 1, characterized in that: The obtaining of the change in the sleep brain wave frequency of the measured object, and then obtaining the sleep stage of the measured object, is specifically obtained through a machine learning algorithm, including: using a data set related to the sleep brain wave frequency and the sleep stage to train a machine learning model, and then using the trained model to perform real-time discrimination on the measured data and output the corresponding sleep stage; Specifically include: Step 1, constructing a data set; selecting several single-channel sleep EEG data of several subjects from the Sleep-EDF data set of the PhysioNet database, removing the data of the unreadable stage, and merging the S3 and S4 stages of deep sleep into the SS stage, and the processed data form a data set; Step 2, dividing the data set into a training set and a test set; Step 3, using the data set to train a one-dimensional convolutional neural network to generate a sleep stage discrimination model; Step 4: Use the sleep stage discrimination model to discriminate the measured sleep brain wave frequency and output the corresponding sleep stage.

8. The liquid metal-based sleep brain activity monitor according to claim 7, characterized in that: The convolutional neural network includes a convolutional layer, a pooling layer, a convolutional layer, a pooling layer, a flattening layer and a fully connected layer connected in sequence; the activation function used in the convolutional layer is relu, the activation function of the fully connected layer is softmax, the model samples an Adam optimizer, and the loss function is a cross entropy loss function.

Images