CN109793645B - Supplementary recovered trainer of parkinsonism people gait - Google Patents
Supplementary recovered trainer of parkinsonism people gait Download PDFInfo
- Publication number
- CN109793645B CN109793645B CN201910052596.2A CN201910052596A CN109793645B CN 109793645 B CN109793645 B CN 109793645B CN 201910052596 A CN201910052596 A CN 201910052596A CN 109793645 B CN109793645 B CN 109793645B
- Authority
- CN
- China
- Prior art keywords
- gait
- parkinson
- training
- training device
- normal distribution
- 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.)
- Active
Links
Images
Abstract
The invention discloses a gait rehabilitation training device for assisting a Parkinson's disease person, which comprises: gait training device mainboard, lithium cell, infrared light transmitting unit, waist band, training scheme aid decision-making system. The gait training device comprises a gait training device main board, a waist belt, a lithium battery, an infrared light emitting unit, a lithium battery, a; the training scheme assistant decision-making system provides an accurate gait rehabilitation training scheme for the patient by using a variational self-encoder algorithm, and forwards the scheme to a gait training device in a Bluetooth communication mode. The invention can provide a specific gait rehabilitation training scheme for different Pakins patients and help the patients to carry out gait rehabilitation training.
Description
Technical Field
The invention relates to the field of medical devices and systems, in particular to a gait rehabilitation training device for assisting a Parkinson's disease person.
Background
Parkinson's disease is a common degenerative disease of the nervous system, and is common in the elderly. In people over 65 years old in China, the prevalence rate of the Parkinson disease is about 1.7%. The most prominent pathological change in parkinson's disease is the degenerative death of dopaminergic neurons in the midbrain substantia nigra, thereby causing a marked reduction in striatal dopaminergic neuron content. The exact etiology of this pathological change is still unclear, and genetic factors, environmental factors, aging, oxidative stress, etc. may all be involved in the degenerative death process of dopaminergic neurons.
Parkinson's disease begins with an insidious course and progresses slowly. The first symptoms are often tremors or awkward movements in one limb and further involvement in the contralateral limb. Clinically, resting tremor, bradykinesia, muscular rigidity and gait disturbance of posture are mainly manifested. The disappearance of postural reflexes often appears in the middle and late stages of diseases, patients are not easy to maintain the balance of the body, and the patients may fall down on a slightly uneven road. The Parkinson's disease patient often walks faster and faster, and is not easy to stop walking, which is called a panicle gait. Patients with advanced Parkinson's disease can freeze, which is characterized by sudden and temporary incapability of taking a step while walking, and the feet seem to be stuck on the ground, and need to pause for a few seconds before continuing to move forwards or cannot start again.
Previous studies have shown that if a patient is preceded by a "visual cue," such as a floor grid or zebra crossing, there is limited avoidance of a frozen gait condition. Based on the research, at present, there are various rehabilitation training methods for the panic gait and the frozen gait of the Parkinson disease patient in clinic, for example, the frozen gait problem in the daily life of the Parkinson disease patient is improved by using light bars as visual prompts of the Parkinson disease patient; the metronome and the step song system are used for training and improving the hungry gait problem of the Parkinson disease patient.
The prior art devices of this technical field include: laser-induced walking sticks, laser shoes, and the like. There are certain drawbacks. The laser-induced crutch is large in size and inconvenient to carry, and the laser line is relatively unfixed in front of the body and is influenced by the movement of the upper limb; when there is the barrier in laser shoes the place ahead, the barrier can lead to the fact the laser line to shelter from, can't project correct position, causes the guide failure.
Furthermore, the disadvantages of the prior art devices include: the training scheme in the device is single, and a specific gait rehabilitation training scheme cannot be formulated according to the disease degree of a patient, the age of the patient and the like; the light effect of the light beam in the dark is obvious, and the identification degree of the auxiliary light source is low under strong light.
Disclosure of Invention
Aiming at the problems of the device and the method, the invention provides a gait rehabilitation training device for assisting a Parkinson's disease person.
The invention is realized by the following technical scheme: a gait rehabilitation training device for assisting a Parkinson's disease person comprises a waist belt, a gait training device main board, a lithium battery, an infrared light emitting unit and a training scheme aid decision-making system;
the waist belt is tied to the waist of the Parkinson patient and is used for placing all components of the gait rehabilitation training device of the Parkinson patient;
the gait training device mainboard is fixed on the waist belt and provides control and communication functions for the gait rehabilitation training device of the Parkinson's disease person;
the lithium battery is fixed on the waist belt, is connected with the gait training device mainboard and supplies power to the gait rehabilitation training device of the Parkinson patient;
the infrared light emitting unit is fixed on the waist belt and connected with the gait training device main board to generate infrared light beams for gait rehabilitation training;
the gait training device mainboard comprises a main processor module, and the main processor module is connected with a voltage conversion module, a Bluetooth module, a voice processing module, a serial port communication module, a function key module and a switch circuit module;
the training scheme assistant decision system is communicated with the gait training device mainboard through Bluetooth, and provides an accurate gait rehabilitation training scheme for the Pakins patient.
Preferably, the main processor module adopts an STM32F407 chip, which is a main control chip of the gait training device, and sends a scheduling instruction to each component chip.
The voltage conversion module adopts an LM2596S-3.3V chip, an LM2596S-3.3 chip and a peripheral driving circuit thereof, so that the voltage of a 12V lithium battery is converted into 3.3V voltage, and working voltage is provided for each chip of the gait training device.
The Bluetooth module adopts an NRF51822 chip, an NRF51822 chip and a peripheral driving circuit thereof to realize the communication between the training scheme assistant decision system and the gait training device, and the specific gait training scheme generated by the training scheme assistant decision system is forwarded to the gait training device.
The voice processing module adopts an XFS5152CE chip, an XFS5152CE chip and a peripheral driving circuit thereof to realize the function of generating voice of the gait training device and provide voice indicating signals for gait rehabilitation training of the Parkinson.
The serial port communication module adopts MAX232CSE chips, MAX232CSE chips and peripheral driving circuits thereof, realizes communication between a gait training device main processor chip STM32F407 and a voice processing chip XFS5152CE, and is a data conversion chip.
The function key module is specifically a four-way key circuit, keys K1 and K2 have the function of adjusting the voice volume, wherein K1 is turned up, and K2 is turned down; the key K3 has a Bluetooth communication switching function; the key K4 is the reset function of the main processor of the gait training device.
The switch circuit module adopts a triode switch circuit, the input of the triode circuit is connected with the main processor chip STM32F407, and the output end of the triode circuit is connected with the infrared light emission unit, so that the control of the on-off of infrared light is realized.
Preferably, the waist belt is a customized elastic belt, the length of the elastic belt is adjustable, and the elastic belt is provided with a fixing device structure.
Preferably, the lithium battery has a capacity of 2800mAh, a size of 56 x 22 x 67mm and a weight of 158 g.
Preferably, the infrared light emitting unit is a red light laser lamp device, the diameter of the device is 12mm, the length of the device is 40mm, and the output power is 5 mw.
Preferably, the specific workflow of the training scheme assistant decision system is as follows:
firstly, realizing a variational self-encoder algorithm;
secondly, training a variational self-encoder model by utilizing gait rehabilitation training data of the Parkinson patient in clinical statistics to obtain a program package capable of obtaining an accurate specific treatment scheme according to input information of the Parkinson patient;
then, developing a software system of the training scheme aid decision system by using C # language, and integrating the trained variational self-encoder model into the training scheme aid decision system to obtain the training scheme aid decision system with the function of generating the specific training scheme; inputting information of a Parkinson person into a training scheme assistant decision system installed at a computer end, and calling a variational self-coder model by the training scheme assistant decision system according to the input information to generate a gait training scheme;
and finally, forwarding the generated gait training scheme to a gait training device by a training scheme assistant decision-making system at the computer end through a Bluetooth network.
Preferably, the parkinson's disease person information includes: age, sex, age of illness, grade of illness.
Preferably, the variational self-encoder algorithm is a generative model algorithm, which comprises three parts: encoder, prior, decoder; the method comprises the following specific steps:
(1) constructing a model for generating target data X by using a hidden variable Z by using a variational self-encoder, and setting the hidden variable Z by the variational self-encoder to obey normal distribution;
(2) the statistical Parkinson's disease patient clinical gait rehabilitation training sample is utilized, and the sample data is recorded as follows: { X1,…,XnSample data is denoted as X as a whole, and p (X) denotes the distribution of X, specifically formula (1), where the hidden variable Z is set to follow a standard normal distribution, i.e. p (Z) ═ N (0,1),
(3) setting the posterior distribution p (Z | X) to be a normal distribution, X for a given samplekSetting there to be a special assignment of XkPosterior distribution p (Z | X)k) From p (Z | X)k) Sampling the distribution to obtain an implicit variable Z, and reducing the implicit variable Z into Xk；
(4) Search for specialities XkNormal distribution of p (Z | X)k) Two sets of parameters of (2): mean μ and variance σ2Both are vectors in the present invention;
(5) construction of two neural networks muk＝f(Xk) And log σ2＝f2(Xk) Fitting and calculating the sample XkNormal distribution of p (Z | X)k) To find the mean and variance of the sample XkObtaining normal distribution by the mean value and the variance, and sampling a hidden variable Z from the normal distributionkUsing generators
To obtain
And then minimize the generation
And its corresponding original specimen XkThe difference is given by the formula
Calculating;
(6) in the process of coding by the variational self-coder, the variational self-coder makes all p (Z | X) look at the standard normal distribution, and in the process of decoding, data can be generated by sampling from the standard normal distribution N (0, 1);
(7) the process of making all p (Z | X) in the variational autoencoder model look at N (0,1) is to calculate KL divergence KL (N (mu, sigma) of each independent component normal distribution and the standard normal distribution2) L N (0,1)), the minimum loss is denoted as loss, as shown in equation (2);
(8) from a normal distribution N (μ, σ)2) The method comprises the steps of sampling a hidden variable Z, namely sampling a value from a standard normal distribution N (0,1), expressing the value by using epsilon, and calculating the hidden variable Z by using a formula Z which is mu + epsilon multiplied by sigma, wherein the square root sigma of a mean value mu and a variance is obtained by model training.
The invention has the advantages that: the device has strong light source contrast and can achieve ideal training effect under strong and weak light environment; the waist belt is adopted, so that the carrying and the use are convenient, and the problem that light rays are influenced by the movement of upper limbs is solved; specific gait rehabilitation training schemes can be provided for different Parkinson patients.
Drawings
FIG. 1 is a schematic structural view of the present invention;
FIG. 2 is a functional block diagram of a main board of the gait training device of the invention;
FIG. 3 is a schematic circuit diagram of a main board of the gait training apparatus of the invention;
FIG. 4 is a flow chart of a training scenario aid decision system of the present invention;
FIG. 5 is a schematic diagram of a variational self-coder model according to the present invention;
FIG. 6 is a diagram of a variational self-coder model training process of the present invention;
fig. 7 shows that the variational autocoder sets the hidden variable Z to follow the normal distribution diagram.
Detailed Description
The invention is further described with reference to the following description and embodiments in conjunction with the accompanying drawings.
As shown in fig. 1, a gait rehabilitation training device for assisting a parkinson's disease person comprises a waist belt, a gait training device main board, a lithium battery, an infrared light emitting unit and a training scheme aid decision making system. The gait training device comprises a gait training device main board, a waist belt, a lithium battery, an infrared light emitting unit, a lithium battery, a; the training scheme assistant decision system is a software system installed at a computer end, the core algorithm is a variational self-encoder, an accurate specific gait rehabilitation training scheme is generated according to the input age, sex, age and disease grade of the Parkinson patients, and the precise specific gait rehabilitation training scheme is transmitted to a gait training device in a Bluetooth communication mode for the Parkinson patients to use.
As shown in fig. 2, the main processor module adopts an STM32F407 chip, the voltage conversion module adopts an LM2596S-3.3V voltage conversion chip, the bluetooth module adopts an NRF51822 chip, the voice processing module adopts an XFS5152CE chip, the serial port communication module adopts an MAX232CSE chip, the function key module is specifically a four-way key circuit, and the switch circuit module adopts a triode switch circuit. The input end of the voltage conversion chip LM2596S-3.3V is connected with the lithium battery, the output voltage is 3.3V, and the output is connected with the main processor chip STM32F 407; the function keys K1, K2, K3 and K4 are directly connected with the main processor chip STM32F 407; the input end of the serial port communication chip MAX232CSE is connected with a main processor chip STM32F407, and the output end of the serial port communication chip MAX232CSE is connected with a voice chip XFS5152 CE; the output end of the voice chip XFS5152CE is connected with a loudspeaker; a former circuit of the Bluetooth communication chip NRF51822 is connected with a main processor chip STM32F407, and a latter circuit is connected with a Bluetooth antenna; the input end of the triode switch circuit is connected with the main processor chip STM32F407, and the output end of the triode switch circuit is connected with the infrared light emitting unit laser.
As shown in FIG. 3, STM32F407 is a main processor chip, and STM32F407 is a Cortex-M4 kernel of ARM architecture, supporting a uCOS system. Pins VDD1, VDD2, VDD3 and VDD4 of STM32F407 are connected with a voltage of 3.3V; pins VSS1, VSS2, VSS3 and VSS4 are connected with GND; PD0 and PD1 are serial port communication pins which are respectively connected with R2OUT and T2IN pins of MAX3232 CSE; PA6 and PA7 are clock communication pins which are respectively connected with SWDIO and SWCLK pins of the NRF51822 chip; pins PB12, PB13, PB14 and PB15 are respectively connected with keys K4, K3, K2 and K1; pin PA9 is connected to transistor Q1 through resistor R11.
The LM2596S-3.3V is a voltage conversion chip converting 12V into 3.3V, and the input VCC of the LM2596S-3.3V chip is a lithium battery providing 12V voltage; the LM2596S-3.3V forming circuit comprises a capacitor: c1, C2, C3, C4, resistance: r1, inductance: l1, unidirectional conducting diode: d1; the LM2596S-3.3V chip output is a 3.3V DC voltage.
MAX232CSE is CMOS two RS232 senders and receiver, is the serial ports communication chip, and operating voltage is 3.3V, constitutes the circuit and includes the electric capacity: c5, C6, C7, C8; pins R2OUT and T2IN are respectively connected with PD0 and PD1 of the STM32F407 chip; the pins R2IN, T2OUT are connected to the TXD and RXD of the XFS5152CE chip, respectively.
XFS5152CE is a voice generating chip, and the working voltage is 3.3V; the circuit comprises a capacitor: c9, C10, C11, C12, C13, C14, C15, resistance: r2, R3, R4, R5, R6, R7, R8, R9, R17; the pins TXD, RXD are connected to R2IN and T2OUT of MAX232CSE, respectively.
NRF51822 is a wireless Bluetooth chip, and the working voltage is 3.3V; the circuit comprises a capacitor: c16, C17, C18, C19, C21, C22, C23, resistance: r16, crystal oscillator X1; pins SWDIO, SWCLK are connected to pins PA6, PA7 of STM32F407, respectively.
The constituent circuits of the four function keys K1, K2, K3 and K4 comprise resistors: and R12, R13, R14 and R15 are respectively connected with PB15, PB14, PB13 and PB12 pins of the STM32F407 chip.
The triode Q1 of the triode switching circuit is IN4148, and the triode switching circuit comprises a capacitor: c20, resistance: r10, R11; the input of the triode switch circuit is connected with a pin PA9 of an STM32F407 chip through R11, and the output of the triode switch circuit is connected with an infrared light emitting unit laser.
As shown in fig. 4, in a pyCharm development environment, a variational self-coder algorithm is implemented using python language; secondly, training a variational self-encoder model by utilizing gait rehabilitation training data of the Parkinson patient in clinical statistics to obtain a program package capable of obtaining an accurate specific treatment scheme according to input information of the Parkinson patient; then, developing a software system of the training scheme aid decision system by using C # language, and integrating the trained variational self-encoder model into the training scheme aid decision system to obtain the training scheme aid decision system with the function of generating the specific training scheme; inputting the information of the Parkinson's disease person into a training scheme assistant decision system installed at a computer end, wherein the information comprises the following steps: the age, the sex, the age of a patient and the grade of the patient are determined, and at the moment, the training scheme assistant decision system calls a variational self-coder model according to the input information to generate a gait training scheme; and finally, the training scheme assistant decision-making system at the computer end transmits the generated gait training scheme to the gait training device through the Bluetooth network, and the gait training device can execute the specific gait training scheme to carry out gait rehabilitation training on the Parkinson patients.
As shown in fig. 5 and 6, (1) the variational self-encoder is composed of three parts: encoder, apriori, decoder. The invention utilizes the variational self-encoder to construct a model for generating target data X by an implicit variable Z, and the variational self-encoder sets the implicit variable Z to obey normal distribution as shown in figure 7.
(2) The statistical Parkinson's disease patient clinical gait rehabilitation training sample is utilized, and the sample data is recorded as follows: { X1,…,XnSample data is denoted as X as a whole, and p (X) denotes the distribution of X, specifically formula (1), where the hidden variable Z is set to follow a standard normal distribution, i.e. p (Z) ═ N (0,1),
(3) setting the posterior distribution p (Z | X) to be a normal distribution, X for a given samplekSetting there to be a special assignment of XkPosterior distribution p (Z | X)k) From p (Z | X)k) Sampling the distribution to obtain an implicit variable Z, and reducing the implicit variable Z into Xk；
(4) Search for specialities XkNormal distribution of p (Z | X)k) Two sets of parameters of (2): mean μ and variance σ2Both are vectors in the present invention;
(5) construction of two neural networks muk＝f(Xk) And log σ2＝f2(Xk) Fitting and calculating the sample XkNormal distribution of p (Z | X)k) To find the mean and variance of the sample XkObtaining normal distribution by the mean value and the variance, and sampling a hidden variable Z from the normal distributionkUsing generators
To obtain
And then minimize the generation
And its corresponding original specimen XkThe difference is given by the formula
Calculating;
(6) in the process of coding by the variational self-coder, the variational self-coder makes all p (Z | X) look at the standard normal distribution, prevents the noise from being 0 in the generation process, ensures the generation capability of the model, thus the prior distribution p (Z) ═ N (0,1) can be achieved, and the generation data can also be sampled from the standard normal distribution N (0,1) in the decoding process, and the schematic diagram of the variational self-coder model is shown in fig. 5.
(7) The process of making all p (Z | X) in the variational autoencoder model look at N (0,1) is to calculate KL divergence KL (N (mu, sigma) of each independent component normal distribution and the standard normal distribution2) L N (0,1)), the minimum loss is denoted as loss, as shown in equation (2);
(8) from a normal distribution N (μ, σ)2) The method comprises the steps of sampling a hidden variable Z, namely sampling a value from a standard normal distribution N (0,1), expressing the value by using epsilon, and calculating the hidden variable Z by using a formula Z which is mu + epsilon multiplied by sigma, wherein the square root sigma of a mean value mu and a variance is obtained by model training.
The invention improves the light source generating device, redesigns and develops all functional parts of the gait rehabilitation training device, particularly adopts the waist belt as the fixing structure of the device, can effectively solve the problem that light rays are influenced by the movement of upper limbs, and adopts the light source with strong contrast to ensure that the auxiliary light source can achieve ideal effect under various environments. In addition, the invention also comprises a training scheme assistant decision-making system which can make a specific gait rehabilitation training scheme according to the information of ages, medical histories and the like of different Parkinson patients.
Claims (6)
1. The utility model provides an auxiliary Parkinson's disease people gait rehabilitation training device which characterized in that: the gait training device comprises a waist belt, a gait training device main board, a lithium battery, an infrared light emitting unit and a training scheme auxiliary decision making system;
the waist belt is tied to the waist of the Parkinson patient and is used for placing all components of the gait rehabilitation training device of the Parkinson patient;
the gait training device mainboard is fixed on the waist belt and provides control and communication functions for the gait rehabilitation training device of the Parkinson's disease person;
the lithium battery is fixed on the waist belt, is connected with the gait training device mainboard and supplies power to the gait rehabilitation training device of the Parkinson patient;
the infrared light emitting unit is fixed on the waist belt and connected with the gait training device main board to generate infrared light beams for gait rehabilitation training;
the gait training device mainboard comprises a main processor module, and the main processor module is connected with a voltage conversion module, a Bluetooth module, a voice processing module, a serial port communication module, a function key module and a switch circuit module;
the training scheme auxiliary decision system is communicated with a gait training device mainboard through Bluetooth, and provides an accurate gait rehabilitation training scheme for the Pakins patient;
the specific working flow of the training scheme assistant decision system is as follows:
firstly, realizing a variational self-encoder algorithm;
secondly, training a variational self-encoder model by utilizing gait rehabilitation training data of the Parkinson patient in clinical statistics to obtain a program package capable of obtaining an accurate specific treatment scheme according to input information of the Parkinson patient;
then, developing a software system of the training scheme aid decision system by using C # language, and integrating the trained variational self-encoder model into the training scheme aid decision system to obtain the training scheme aid decision system with the function of generating the specific training scheme; inputting information of a Parkinson person into a training scheme assistant decision system installed at a computer end, and calling a variational self-coder model by the training scheme assistant decision system according to the input information to generate a gait training scheme;
finally, the training scheme assistant decision-making system of the computer end transmits the generated gait training scheme to a gait training device through a Bluetooth network;
the variational self-encoder algorithm is a generation model algorithm and comprises three parts: encoder, prior, decoder; the method comprises the following specific steps:
(1) constructing a model for generating target data X by using a hidden variable Z by using a variational self-encoder, and setting the hidden variable Z by the variational self-encoder to obey normal distribution;
(2) the statistical Parkinson's disease patient clinical gait rehabilitation training sample is utilized, and the sample data is recorded as follows: { X1,…,XnSample data is denoted as X as a whole, and p (X) denotes the distribution of X, specifically formula (1), where the hidden variable Z is set to follow a standard normal distribution, i.e. p (Z) ═ N (0,1),
(3) setting the posterior distribution p (Z | X) to be a normal distribution, X for a given samplekSetting there to be a special assignment of XkPosterior distribution p (Z | X)k) From p (Z | X)k) Sampling the distribution to obtain an implicit variable Z, and reducing the implicit variable Z into Xk；
(4) Search for specialities XkNormal distribution of p (Z | X)k) Two sets of parameters of (2): mean μ and variance σ2Both are vectors;
(5) construction of two neural networks muk＝f(Xk) And log σ2＝f2(Xk) Fitting and calculating the sample XkNormal distribution of p (Z | X)k) To find the mean and variance of the sample XkObtaining normal distribution by the mean value and the variance, and sampling a hidden variable Z from the normal distributionkUsing generators
To obtain
And then minimize the generation
And its corresponding original specimen XkThe difference is given by the formula
Calculating;
(6) in the process of coding by the variational self-coder, the variational self-coder makes all p (Z | X) look at the standard normal distribution, and in the process of decoding, data can be generated by sampling from the standard normal distribution N (0, 1);
(7) the process of making all p (Z | X) in the variational autoencoder model look at N (0,1) is to calculate KL divergence KL (N (mu, sigma) of each independent component normal distribution and the standard normal distribution2) L N (0,1)), the minimum loss is denoted as loss, as shown in equation (2);
(8) from a normal distribution N (μ, σ)2) The method comprises the steps of sampling a hidden variable Z, namely sampling a value from a standard normal distribution N (0,1), expressing the value by using epsilon, and calculating the hidden variable Z by using a formula Z which is mu + epsilon multiplied by sigma, wherein the square root sigma of a mean value mu and a variance is obtained by model training.
2. The gait rehabilitation training device for assisting the Parkinson's disease person according to claim 1, characterized in that: the utility model discloses a bluetooth module, including main processor module, voice processing module, serial ports communication module, main processor module, voltage conversion module, bluetooth module, voice processing module, main processor module adopts the STM32F407 chip, voltage conversion module adopts LM2596S-3.3V voltage conversion chip, bluetooth module adopts the NRF51822 chip, voice processing module adopts the XFS5152CE chip, serial ports communication module adopts the MAX232CSE chip, function button module specifically is four ways keying circuit, the switch circuit module adopts triode switch circuit.
3. The gait rehabilitation training device for assisting the Parkinson's disease person according to claim 1, characterized in that: the waist belt is a custom-made elastic belt.
4. The gait rehabilitation training device for assisting the Parkinson's disease person according to claim 1, characterized in that: the lithium battery has a capacity of 2800mAh, a size of 56 x 22 x 67mm and a weight of 158 g.
5. The gait rehabilitation training device for assisting the Parkinson's disease person according to claim 1, characterized in that: the infrared light emitting unit is a red light laser lamp device, the diameter of the device is 12mm, the length of the device is 40mm, and the output power is 5 mw.
6. The gait rehabilitation training device for assisting the Parkinson's disease person according to claim 1, characterized in that: the information of the Parkinson's disease people comprises: age, sex, age of illness, grade of illness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910052596.2A CN109793645B (en) | 2019-01-21 | 2019-01-21 | Supplementary recovered trainer of parkinsonism people gait |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910052596.2A CN109793645B (en) | 2019-01-21 | 2019-01-21 | Supplementary recovered trainer of parkinsonism people gait |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109793645A CN109793645A (en) | 2019-05-24 |
| CN109793645B true CN109793645B (en) | 2021-07-13 |
Family
ID=66559826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910052596.2A Active CN109793645B (en) | 2019-01-21 | 2019-01-21 | Supplementary recovered trainer of parkinsonism people gait |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109793645B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111899844B (en) * | 2020-09-28 | 2021-11-23 | 平安科技（深圳）有限公司 | Sample generation method and device, server and storage medium |
| CN114366557A (en) * | 2021-12-31 | 2022-04-19 | 华南理工大学 | Man-machine interaction system and method for lower limb rehabilitation robot |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201503882A (en) * | 2013-07-18 | 2015-02-01 | Stone & Resource Ind R & D Ct | Indicating device and method for gait |
| CN105534678A (en) * | 2015-12-02 | 2016-05-04 | 华馨伊 | Rehabilitation training system based on internet data management |
| CN205251971U (en) * | 2015-10-19 | 2016-05-25 | 陈新红 | Guide stick that guide parkinson disease and dyskinesia patient walked |
| CN106693280A (en) * | 2016-12-29 | 2017-05-24 | 深圳市臻络科技有限公司 | Virtual-reality-based Parkinsonism training method, system and device |
| JP2017148594A (en) * | 2017-05-08 | 2017-08-31 | 有限会社ホームケア渡部建築 | Walking assist device |
| CN107485844A (en) * | 2017-09-27 | 2017-12-19 | 广东工业大学 | A kind of limb rehabilitation training method, system and embedded device |
| CN108098736A (en) * | 2016-11-24 | 2018-06-01 | 广州映博智能科技有限公司 | A kind of exoskeleton robot auxiliary device and method based on new perception |
| CN108392795A (en) * | 2018-02-05 | 2018-08-14 | 哈尔滨工程大学 | A kind of healing robot Multimode Controlling Method based on Multi-information acquisition |
| CN110300542A (en) * | 2016-07-25 | 2019-10-01 | 开创拉布斯公司 | Use the method and apparatus of wearable automated sensor prediction muscle skeleton location information |
-
2019
- 2019-01-21 CN CN201910052596.2A patent/CN109793645B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TW201503882A (en) * | 2013-07-18 | 2015-02-01 | Stone & Resource Ind R & D Ct | Indicating device and method for gait |
| CN205251971U (en) * | 2015-10-19 | 2016-05-25 | 陈新红 | Guide stick that guide parkinson disease and dyskinesia patient walked |
| CN105534678A (en) * | 2015-12-02 | 2016-05-04 | 华馨伊 | Rehabilitation training system based on internet data management |
| CN110300542A (en) * | 2016-07-25 | 2019-10-01 | 开创拉布斯公司 | Use the method and apparatus of wearable automated sensor prediction muscle skeleton location information |
| CN108098736A (en) * | 2016-11-24 | 2018-06-01 | 广州映博智能科技有限公司 | A kind of exoskeleton robot auxiliary device and method based on new perception |
| CN106693280A (en) * | 2016-12-29 | 2017-05-24 | 深圳市臻络科技有限公司 | Virtual-reality-based Parkinsonism training method, system and device |
| JP2017148594A (en) * | 2017-05-08 | 2017-08-31 | 有限会社ホームケア渡部建築 | Walking assist device |
| CN107485844A (en) * | 2017-09-27 | 2017-12-19 | 广东工业大学 | A kind of limb rehabilitation training method, system and embedded device |
| CN108392795A (en) * | 2018-02-05 | 2018-08-14 | 哈尔滨工程大学 | A kind of healing robot Multimode Controlling Method based on Multi-information acquisition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109793645A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Luo et al. | A low-cost end-to-end sEMG-based gait sub-phase recognition system | |
| KR102550887B1 (en) | Method and apparatus for updatting personalized gait policy | |
| CN109793645B (en) | Supplementary recovered trainer of parkinsonism people gait | |
| CN104606868B (en) | A kind of Intelligent bracelet for alleviating Parkinsonian's freezing of gait | |
| CN109794042A (en) | A kind of body gait based on cloud platform and lower limb harmony rehabilitation training platform | |
| CN103268419A (en) | Health management system with waistband-type monitoring device and cloud through internet of things and operation method | |
| CN108309303B (en) | Wearable intelligent monitoring of gait that freezes and helps capable equipment | |
| CN111696645A (en) | Hand exoskeleton rehabilitation training device and method based on surface electromyographic signals | |
| CN105342767A (en) | Intelligent wheelchair based on control of mobile terminal | |
| CN109567812A (en) | Gait analysis system based on Intelligent insole | |
| CN109498375A (en) | A kind of human motion intention assessment control device and control method | |
| US20210267486A1 (en) | System and method for gait monitoring and improvement | |
| CN113576467A (en) | Wearable real-time gait detection system integrating plantar pressure sensor and IMU | |
| CN111588597A (en) | Intelligent interactive walking training system and implementation method thereof | |
| CN110543922A (en) | real-time walking mode identification method based on knee joint exoskeleton | |
| Zhang et al. | Implementing an FPGA system for real-time intent recognition for prosthetic legs | |
| Dong et al. | A low-cost framework for the recognition of human motion gait phases and patterns based on multi-source perception fusion | |
| CN109350928A (en) | A kind of R-Button game old man healing hand function training aids | |
| CN101828982B (en) | Ankle and foot rehabilitation device | |
| Sun et al. | Programmable neural processing on a smartdust for brain-computer interfaces | |
| CN204636626U (en) | A kind of artificial limb system with perceptible feedback function | |
| CN211271430U (en) | Control system of intelligent bionic knee joint | |
| Wei et al. | The mechanical and system design of finger training rehabilitation device based on speech recognition | |
| Lee et al. | A review on neural network based gait estimation methods | |
| CN208225260U (en) | A kind of intelligent medical auxiliary recovery handrail system |
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 |