CN210697629U - Signal acquisition device, mobile terminal and signal analysis system - Google Patents
Signal acquisition device, mobile terminal and signal analysis system Download PDFInfo
- Publication number
- CN210697629U CN210697629U CN201920467327.8U CN201920467327U CN210697629U CN 210697629 U CN210697629 U CN 210697629U CN 201920467327 U CN201920467327 U CN 201920467327U CN 210697629 U CN210697629 U CN 210697629U
- Authority
- CN
- China
- Prior art keywords
- signal
- mobile terminal
- surface electromyographic
- classification information
- electromyographic signals
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Abstract
Disclosed are a signal acquisition device, a mobile terminal and a signal analysis system. The method comprises the steps that a signal acquisition device is used for acquiring surface electromyographic signals and sending the surface electromyographic signals to a mobile terminal, the mobile terminal receives and forwards the surface electromyographic signals, a server receives the surface electromyographic signals sent by the mobile terminal, acquires state classification information of the surface electromyographic signals, and sends the state classification information to the mobile terminal. Thus, the state classification information can be acquired through the surface electromyogram signal to relatively accurately analyze the state of the muscle.
Description
Technical Field
The utility model relates to a signal analysis technical field, concretely relates to signal acquisition device, mobile terminal and signal analysis system.
Background
Surface electromyography (sEMG) is an electrical signal that accompanies muscle contraction, and is an important method for non-invasive detection of muscle activity on the body surface. Because the muscle activity state and the function state are related to a certain degree, the muscle activity state can reflect a certain neuromuscular activity state, and the surface electromyographic signals have important utilization values in the aspects of clinical medicine (such as neuromuscular disease diagnosis), rehabilitation medicine (such as muscle function evaluation), sports science (such as fatigue judgment, exercise technology rationality analysis, non-destructive prediction of muscle fiber types and anaerobic thresholds) and the like. A system capable of relatively accurately analyzing the muscle state from the surface electromyogram signal is lacking at present.
SUMMERY OF THE UTILITY MODEL
In view of this, the utility model provides a signal acquisition device, mobile terminal and signal analysis system can relatively accurately analyze the muscle state according to surface electromyogram signal.
In a first aspect, an embodiment of the present invention provides a signal collecting device for collecting myoelectric signals on the surface of a human body, the device includes:
an acquisition unit configured to acquire a surface electromyography signal;
a control unit; and
a first wireless communication unit configured to transmit the surface electromyogram signal under control of the control unit.
Preferably, the signal acquisition unit includes:
and the at least one electrode paste is used for collecting surface electromyographic signals.
Preferably, the acquisition unit further comprises:
a signal processing circuit connected with the electrode patch and configured to process the surface electromyographic signal;
the processing comprises amplifying and/or rectifying and/or integrating the surface electromyographic signals.
Preferably, the first wireless communication unit is a bluetooth transmission module.
In a second aspect, an embodiment of the present invention provides a mobile terminal, the mobile terminal includes:
the second wireless communication unit is configured to receive and forward the surface electromyographic signals sent by the signal acquisition device and receive state classification information of the surface electromyographic signals; and
a display unit configured to display state classification information of the surface electromyogram signal.
In a third aspect, an embodiment of the present invention provides a signal analysis system, the system includes:
the signal acquisition device is configured to acquire and transmit a surface electromyogram signal;
the mobile terminal is configured to receive and forward the surface electromyographic signals sent by the signal acquisition device; and
the server is configured to receive the surface electromyographic signal sent by the mobile terminal and acquire state classification information of the surface electromyographic signal.
Preferably, the server is further configured to transmit status classification information of the surface electromyogram signal.
Preferably, the mobile terminal is further configured to receive and display the status classification information sent by the server.
The utility model discloses technical scheme passes through signal acquisition device and acquires surface electromyogram signal and sends to mobile terminal, and mobile terminal receives surface electromyogram signal forwards, and the server is received the surface electromyogram signal that mobile terminal sent, and acquire surface electromyogram signal's state classification information, will state classification information sends to mobile terminal. Thus, the state classification information can be acquired through the surface electromyogram signal to relatively accurately analyze the state of the muscle.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
fig. 1 is a schematic structural diagram of a signal analysis system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a signal acquisition device according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for a server to obtain status classification information according to an embodiment of the present invention;
fig. 4 is a signal flow diagram of the server determining status classification information according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a convolutional neural network according to an embodiment of the present invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth in detail. It will be apparent to those skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.
Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout the description and the claims, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
Fig. 1 is a schematic structural diagram of a signal analysis system according to an embodiment of the present invention. As shown in fig. 1, the signal analysis system includes a signal acquisition device 1, a mobile terminal 2, and a server 3. The signal acquisition device 1 is used for acquiring surface electromyogram signals and sending the surface electromyogram signals to the mobile terminal 2. And the mobile terminal 2 forwards the received surface electromyogram signal sent by the signal acquisition device 1 to the server 3. The server 3 acquires the state classification information according to the received surface electromyogram signal and sends the state classification information to the mobile terminal 2. The mobile terminal 2 displays the status classification information.
In the present embodiment, the signal acquisition device 1 and the mobile terminal 2 communicate with each other in a wireless manner. Preferably, the wireless communication mode is a bluetooth communication mode. In particular, Bluetooth (Bluetooth) is a short-range wireless communication technology, and has the advantages of low power, low cost, low time delay and the like. It should be understood that communication may also be via a remote wireless network, such as NB-IoT (Narrow Band Internet of Things), LORA, ZigBee, or GPRS (General Packet Radio Service) wireless networks.
In this embodiment, the mobile terminal 2 may be a dedicated wireless communication terminal, or may be a general-purpose data processing device with a wireless communication function, such as a mobile phone, a tablet computer, a notebook computer, or a desktop computer with a control application program.
In this embodiment, the mobile terminal 2 and the server 3 communicate with each other through a carrier network or a wireless gateway.
In the embodiment, a signal acquisition device is used for acquiring a surface electromyogram signal and sending the surface electromyogram signal to the mobile terminal, the mobile terminal forwards the received surface electromyogram signal to the server, the server acquires state classification information of the server according to the surface electromyogram signal and sends the state classification information to the mobile terminal, and the mobile terminal displays the state classification information. Therefore, the state classification information can be obtained according to the surface electromyogram signal so as to accurately obtain the state of the muscle.
Fig. 2 is a schematic structural diagram of a signal acquisition device according to an embodiment of the present invention. As shown in fig. 2, the signal acquisition apparatus 1 includes an acquisition unit 11, a control unit 12, and a first wireless communication unit 13. Wherein the acquisition unit 11 is configured to acquire a surface electromyography signal. The first wireless communication unit 13 is configured to transmit the surface electromyogram signal under the control of the control unit 12.
In this embodiment, the collecting unit 11 comprises at least one electrode patch for collecting surface electromyographic signals. The acquisition unit 11 of the present embodiment takes two electrode patches as an example, and includes a first electrode patch 11a and a second electrode patch 11 b. Preferably, the electrode paste is a surface electrode pasted on the skin surface of a human body, and the surface electrode can generate a surface electromyographic signal according to the movement of muscles near the position of the surface electrode.
In an optional implementation manner, the acquisition unit 11 further includes a signal processing circuit, connected to the electrode patch, and configured to process the surface electromyogram signal acquired by the electrode patch, where the processing includes amplifying and/or rectifying and/or integrating the surface electromyogram signal.
It should be understood that the collecting unit 11 sends the collected surface electromyogram signal to the first wireless communication unit 13 after being amplified and/or rectified and/or integrated. The collected surface electromyographic signals may also be directly transmitted through the first wireless communication unit 13. Whether the surface electromyographic signals need to be processed or not can be selected according to practical application occasions.
In the present embodiment, the control unit 12 is configured to control the first wireless communication unit 13 to transmit the surface electromyogram signal. Preferably, the control Unit 12 may be implemented by an MCU (micro Controller Unit), a PLC (Programmable Logic Controller), an FPGA (Field Programmable gate Array), a DSP (Digital Signal Processor), or an asic (application specific integrated circuit).
In this embodiment, the first wireless communication unit 13 is a bluetooth transmission module. The Bluetooth transmission module is a chip basic circuit set integrating the Bluetooth function and is used for wireless network communication. Meanwhile, most of general data processing equipment (such as smart phones, tablet computers and the like) with a wireless communication function has a Bluetooth communication function, so that the signal acquisition device and the mobile terminal are more convenient to communicate, and meanwhile, communication cost and module cost can be reduced.
Preferably, the control unit 12 and the first wireless communication unit 13 in the signal acquisition device 1 are integrated in one arm bag for convenient use.
Therefore, the signal acquisition device can acquire the surface electromyogram signal through the acquisition unit, and then the control unit controls the first wireless communication unit to send the surface electromyogram signal to the mobile terminal.
In the present embodiment, the mobile terminal 2 includes a second wireless communication unit and a display unit. The second wireless communication unit is configured to receive and forward the surface electromyographic signal, and receive status classification information of the surface electromyographic signal. The display unit is configured to display status classification information of the surface electromyogram signal.
Preferably, the mobile terminal 2 may be a dedicated wireless communication terminal, or may be a general-purpose data processing device with a wireless communication function, such as a mobile phone, a tablet computer, a notebook computer, or a desktop computer, which is loaded with a control application program.
Therefore, the mobile terminal receives the surface electromyogram signal sent by the signal acquisition device and forwards the surface electromyogram signal to the server.
In the present embodiment, the server 3 is configured to receive the surface electromyogram signal transmitted by the mobile terminal and acquire status classification information of the surface electromyogram signal. The surface electromyographic signal is the comprehensive effect of the electrical activity of superficial muscles and nerve trunks on the surface of the skin, and can reflect the activity of neuromuscular, so that the state of the muscle can be analyzed according to the surface electromyographic signal.
Fig. 3 is a flowchart of a method for a server to obtain status classification information according to an embodiment of the present invention. As shown in fig. 3, the step of acquiring the state classification information of the surface electromyogram signal by the server 3 includes the following steps:
and S310, receiving the surface electromyographic signals to be detected and the contrast surface electromyographic signals in a preset evaluation library.
In the present embodiment, the server 3 receives the surface electromyogram signal transmitted by the mobile terminal 2 and a contrast surface electromyogram signal in a predetermined evaluation library.
And step S320, outputting the first error parameter and the second error parameter through the convolutional neural network.
In the implementation, the convolutional neural network is S-Net, which is a self-designed convolutional neural network, and S-Net is a lightweight convolutional neural network capable of learning the relationship between input and output end to end. And inputting a surface electromyographic signal to be detected and a contrast surface electromyographic signal, and outputting a first error parameter and a second error parameter. Thus, the similarity of the muscle movement patterns represented by the two signals can be calculated according to the first error parameter and the second error parameter. The S-Net has the advantages of small calculated amount, high efficiency, high accuracy and the like, and can find muscle movement characteristics which cannot be directly found by people.
Because there may be more than two sets in the evaluation library when the surface myoelectric signals to be detected are classified, if a common classification method is used, the convolutional neural network needs to classify a plurality of sets according to the number of the sets in the evaluation library, and the sets correspond to a plurality of error parameters. However, for the convolutional neural network, it is more difficult to learn how to regress more than two error parameters. Therefore, the present embodiment converts two or more classification problems into two classification problems by using the idea of Similarity learning. Specifically, the convolutional neural network learns the feature similarity of the two signals, namely the surface electromyographic signal to be detected and the contrast surface electromyographic signal, and then the feature similarity is compared with each set in the evaluation library to obtain the classification information of the surface electromyographic signal to be detected. Instead of learning the direct correspondence of the characteristics of the surface electromyographic signals to be detected to each set in the evaluation library. Therefore, the learning difficulty of the convolutional neural network can be reduced. Meanwhile, by adopting the Simiariteearning idea, the input is changed from the characteristic of one signal to the combination of the characteristics of two signals, thereby achieving the effect of amplifying the training data volume.
And S330, calculating the probability that the surface electromyographic signals to be detected and the compared surface electromyographic signals belong to the same set according to the first error parameter and the second error parameter. .
And step S340, acquiring a set of contrast surface electromyographic signals of which the probabilities meet a preset condition.
And step S350, determining state classification information according to the set of the contrast surface electromyographic signals.
In this embodiment, the evaluation library includes a plurality of sets, where the sets respectively correspond to different error parameters or intervals where the error parameters are located, and a set of contrast surface electromyographic signals where the error parameters satisfy a predetermined condition is obtained.
Fig. 4 is a signal flow diagram of the embodiment of the present invention for determining status classification information by a server. As shown in fig. 4, the server 3 determines the status classification information including the steps of:
in step S410, a surface electromyographic signal to be detected sent by the mobile terminal is received.
In this embodiment, the mobile terminal 2 receives the surface electromyogram signal to be detected sent by the signal acquisition device 1, and forwards the surface electromyogram signal to be detected to the server 3.
In step S420, each comparative-surface myoelectric signal in the evaluation library is acquired.
In this embodiment, the evaluation library includes a plurality of contrast surface electromyographic signals, and the plurality of contrast surface electromyographic signals are divided into different sets according to application scenarios. For example, in response to detecting the degree of fatigue of the muscle, the evaluation library may be divided into three sets of mild fatigue, moderate fatigue, and extreme fatigue. For another example, in response to acquiring a state of parkinson's disease based on rigidity and tremor of muscles, the evaluation library may be scored into five sets of scores ranging from 0 to 5 according to international consolidated parkinson's disease scoring standards.
In step S430, a first error parameter and a second error parameter are acquired.
In this embodiment, error parameters of the surface electromyographic signals to be detected and the comparative surface electromyographic signals are respectively obtained through a convolutional neural network. The error parameters are used for calculating the probability that the surface electromyographic signals to be detected and the contrast surface electromyographic signals belong to the same set.
In step S440, a set matching the error parameters is obtained.
In step S450, state classification information of the muscle is determined from the matching set.
For example, in response to detecting a degree of fatigue of the muscle and the set of matches is moderate fatigue, the state classification information is that the muscle is in a moderate fatigue state. For another example, in response to acquiring the parkinson's disease condition from rigidity and tremor of the muscle, the matched set is a set having a disease score of 3, and the acquired state classification information is a parkinson's disease score of 3.
Therefore, the server 3 can obtain the state classification information of the surface electromyographic signals to be detected.
In step S460, the state classification information is transmitted.
After the server 3 acquires the state classification information of the surface electromyographic signals to be detected, the state classification information is sent to the mobile terminal 2, and the mobile terminal 2 displays the state classification information.
It should be understood that the server of the embodiment of the present invention can be used to analyze not only surface electromyographic signals, but also other types of electrical signals. For example, whether the current power grid has an overcurrent condition can be judged by analyzing each current in the power grid, so that possible dangers can be predicted, and timely treatment can be facilitated.
In one embodiment, the structure of the convolutional neural network S-Net can be referred to FIG. 5 in response to detecting Parkinson' S disease. Fig. 5 is a schematic structural diagram of a convolutional neural network according to an embodiment of the present invention. As shown in fig. 5, the convolutional neural network in the present embodiment includes a normalization layer a, four convolutional layers a1, a2, A3, and a4, and two fully-connected layers C1 and C2. The normalization layer A is used for carrying out characteristic normalization on the characteristic vectors of the surface electromyographic signals to be detected and the contrast surface electromyographic signals. The four convolutional layers A1, A2, A3 and A4 are used for extracting local characteristics of the surface electromyographic signals to be detected and the contrast surface electromyographic signals. And the two full connection layers C1 and C2 are used for acquiring global information according to the local features and outputting the first error parameter and the second error parameter.
In this embodiment, the surface electromyographic signal to be detected and the contrast surface electromyographic signal are 2048-dimensional vectors. Considering that the training data set may still be too small for efficient feature learning, the present embodiment uses twelve hand-made features including Mean Absolute Value (MAV), Mean Square Value (MSV), Root Mean Square (RMS), variance (VAR ), standard deviation (STD), Waveform Length (WL), Willison Amplitude (WAMP), LOG detector (LOG detector, LOG), ramp signal change (slope sign change, SSC), zero crossing number (zeroing, ZC), mean spectral frequency (mean spectral frequency, MSF), and Median Frequency (MF). Thus, a twelve-dimensional feature vector can be represented for each surface electromyogram signal.
In this embodiment, the input of the normalization layer a is a pair of twelve-dimensional feature vectors (12 × 1 × 2) extracted from the surface electromyogram signal to be detected and the contrast surface electromyogram signal, respectively, and is used to perform feature normalization on the input feature vectors to reduce the difference of the data range of the selected features. For example, the WL eigenvalue is typically two orders of magnitude larger than the SSC eigenvalue, which may introduce unnecessary numerical instability to the network, reducing the rate of model convergence during training.
In this embodiment, the normalization layer a is followed by four convolutional layers with a convolutional kernel size of 1 × 1 and a step size of 1. The four convolutional layers use Linear rectification (ReLU ) activation functions and batch normalization to non-linearly map the input 2-dimensional vectors into 64-dimensional vectors, so that the output of the last convolutional layer B4 is 12 64-dimensional vectors (12 1 × 64). Specifically, the linear commutation activation function and batch normalization can be found in the literature: S.Ioffe and C.Szegedy, "Batch normalization: calibrating deep network training by reducing internal covariate shift," arXiv preprinting arXiv:1502.03167,2015.
In this embodiment, the last two layers of the convolutional neural network are fully connected layers C1 and C2, which are used to capture global information and output two error parameters y1 and y 2. Where y1 and y2 are logarithms (logit) values and y1 and y2 are both not size-limiting, i.e., from negative infinity to positive infinity. Therefore, the probability that the surface electromyographic signal to be detected and the contrast surface electromyographic signal belong to or do not belong to the same classification set can be calculated and obtained according to y1 and y 2. Specifically, the following formula can be referred to:
the probability is represented by P, the set of surface electromyographic signals is represented by Sl (), the surface electromyographic signals to be detected are represented by a, and the contrast surface electromyographic signals are represented by b.
In the formula (1), the first and second groups,
and representing that the surface electromyographic signals to be detected and the contrast surface electromyographic signals belong to the same set.
In training the convolutional neural network, assuming that the true labels of the two input signals belong to the same set and the probability p1 of generating the prediction result as belonging to the same set is between 0.5 and 1, i.e. 0.5< p1<1, the characterization prediction result is correct, and at this time, the loss is-log (p 1). If the probability p2 that the generated prediction results belong to the same set is between 0 and 0.5, i.e. 0< p2<0.5, the characterization prediction result is wrong, and at this time, the loss is-log (p 2). Since p1> p2, -log (p1) < -log (p 2). From this, it is understood that the prediction error is larger than the loss of the prediction pair, and the loss of the prediction error is larger than the loss of the prediction error. Based on this, the convolutional neural network can be trained.
Therefore, the surface myoelectric signals to be detected can be classified through the trained convolutional neural network. Specifically, the contrast surface electromyogram signal is divided into i sets of grades, i is 0, 1, 2, 3, 4 according to the international unified parkinson's disease rating standard, and assuming that the number of samples in the set Si is ni, the probability that the surface electromyogram signal to be detected and the contrast surface electromyogram signal belong to the same set can be calculated by referring to the following formula:
therefore, a set of contrast surface electromyographic signals closest to the surface electromyographic signals to be detected is selected according to the formulas (3) and (4). Further, the severity of the Parkinson's disease can be obtained.
In the embodiment, the surface myoelectric signals to be detected are classified by using the convolutional neural network to obtain the closest set so as to obtain the severity of the Parkinson's disease, so that the subjectivity of the Parkinson's disease condition evaluation component table in clinical medicine can be avoided, and the medical efficiency and accuracy are improved.
It should be understood that the structure of the convolutional neural network, the choice of features, the formula, and the classification of the sets in the evaluation library may be adaptively modified according to the specific application.
In the embodiment, a signal acquisition device is used for acquiring a surface electromyogram signal and sending the surface electromyogram signal to the mobile terminal, the mobile terminal forwards the received surface electromyogram signal to the server, the server acquires state classification information of the server according to the surface electromyogram signal and sends the state classification information to the mobile terminal, and the mobile terminal displays the state classification information. Therefore, the state classification information can be obtained according to the surface electromyogram signal so as to accurately obtain the state of the muscle.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included within the protection scope of the present invention.
Claims (5)
1. A signal acquisition device for acquiring a surface electromyographic signal of a human body, the device comprising:
an acquisition unit configured to acquire a surface electromyography signal;
a control unit; and
a first wireless communication unit configured to transmit the surface electromyogram signal under control of the control unit.
2. The apparatus of claim 1, wherein the acquisition unit comprises:
and the at least one electrode paste is used for collecting surface electromyographic signals.
3. The apparatus of claim 2, wherein the acquisition unit further comprises:
a signal processing circuit connected with the electrode patch and configured to process the surface electromyographic signal;
the processing comprises amplifying and/or rectifying and/or integrating the surface electromyographic signals.
4. The apparatus of claim 1, wherein the first wireless communication unit is a bluetooth transmission module.
5. A mobile terminal, characterized in that the mobile terminal comprises:
the second wireless communication unit is configured to receive and forward the surface electromyographic signals sent by the signal acquisition device and receive state classification information of the surface electromyographic signals; and
a display unit configured to display state classification information of the surface electromyogram signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920467327.8U CN210697629U (en) | 2019-04-08 | 2019-04-08 | Signal acquisition device, mobile terminal and signal analysis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920467327.8U CN210697629U (en) | 2019-04-08 | 2019-04-08 | Signal acquisition device, mobile terminal and signal analysis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210697629U true CN210697629U (en) | 2020-06-09 |
Family
ID=70922219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920467327.8U Expired - Fee Related CN210697629U (en) | 2019-04-08 | 2019-04-08 | Signal acquisition device, mobile terminal and signal analysis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210697629U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113729715A (en) * | 2021-10-11 | 2021-12-03 | 山东大学 | Parkinson's disease intelligent diagnosis system based on finger pressure |
| CN114639460A (en) * | 2022-05-16 | 2022-06-17 | 天津医科大学眼科医院 | Cycloplegic demand prediction and paralysis post-diopter refractive state prediction method |
-
2019
- 2019-04-08 CN CN201920467327.8U patent/CN210697629U/en not_active Expired - Fee Related
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113729715A (en) * | 2021-10-11 | 2021-12-03 | 山东大学 | Parkinson's disease intelligent diagnosis system based on finger pressure |
| CN114639460A (en) * | 2022-05-16 | 2022-06-17 | 天津医科大学眼科医院 | Cycloplegic demand prediction and paralysis post-diopter refractive state prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10061389B2 (en) | Gesture recognition system and gesture recognition method | |
| CN103294199B (en) | A kind of unvoiced information identifying system based on face's muscle signals | |
| Fang et al. | Headscan: A wearable system for radio-based sensing of head and mouth-related activities | |
| CN103370968A (en) | Method and apparatus for providing context-aware control of sensors and sensor data | |
| CN108171278B (en) | Motion pattern recognition method and system based on motion training data | |
| Cui et al. | Device-free single-user activity recognition using diversified deep ensemble learning | |
| CN210697629U (en) | Signal acquisition device, mobile terminal and signal analysis system | |
| CN106527716A (en) | Wearable equipment based on electromyographic signals and interactive method between wearable equipment and terminal | |
| CN109512390B (en) | Sleep staging method and wearable device based on EEG time domain multi-dimensional features and M-WSVM | |
| CN112869752B (en) | Electrocardiosignal acquisition device and quality grade evaluation and QRS wave detection method | |
| CN106685590A (en) | Channel state information and KNN (K-Nearest Neighbor)-based indoor human body orientation recognition method | |
| CN107766898A (en) | The three classification mood probabilistic determination methods based on SVM | |
| CN104473648A (en) | Physiological parameter monitoring-combined human body tumble warning and detecting method | |
| CN111053552B (en) | QRS wave detection method based on deep learning | |
| Xiong et al. | An unsupervised compressed sensing algorithm for multi-channel neural recording and spike sorting | |
| CN106845348B (en) | Gesture recognition method based on arm surface electromyographic signals | |
| CN105303771A (en) | Fatigue judging system and method | |
| Zhang et al. | CSI-based location-independent human activity recognition using feature fusion | |
| CN104679967A (en) | Method for judging reliability of psychological test | |
| CN107239147A (en) | A kind of human body context aware method based on wearable device, apparatus and system | |
| CN109965847B (en) | Server and signal analysis system | |
| CN113116363A (en) | Method for judging hand fatigue degree based on surface electromyographic signals | |
| Bastwesy et al. | Wi-nod: Head nodding recognition by wi-fi csi toward communicative support for quadriplegics | |
| CN205163106U (en) | Portable intestines and stomach sound detection device | |
| CN110547806A (en) | gesture action online recognition method and system based on surface electromyographic signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200609 |