CN108968918A - The wearable auxiliary screening equipment of early stage Parkinson - Google Patents
The wearable auxiliary screening equipment of early stage Parkinson Download PDFInfo
- Publication number
- CN108968918A CN108968918A CN201810683383.5A CN201810683383A CN108968918A CN 108968918 A CN108968918 A CN 108968918A CN 201810683383 A CN201810683383 A CN 201810683383A CN 108968918 A CN108968918 A CN 108968918A
- Authority
- CN
- China
- Prior art keywords
- sample
- early stage
- phase
- data
- current
- 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.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4076—Diagnosing or monitoring particular conditions of the nervous system
- A61B5/4082—Diagnosing or monitoring movement diseases, e.g. Parkinson, Huntington or Tourette
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- Neurology (AREA)
- Physiology (AREA)
- Veterinary Medicine (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Signal Processing (AREA)
- Neurosurgery (AREA)
- Power Engineering (AREA)
- Artificial Intelligence (AREA)
- Psychiatry (AREA)
- Developmental Disabilities (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses the wearable auxiliary screening equipment of early stage Parkinson a kind of, belong to technical field of data processing, the present invention obtains 3-axis acceleration and three axis angular rates, gait phase is divided by phase parted pattern to 3-axis acceleration and three axis angular rates, phase character when acquisition, time domain data is extracted from 3-axis acceleration and three axis angular rates, and frequecy characteristic is converted by the time domain data, to it is described current when phase character and current frequency feature carry out principal component analysis processing, obtain main gait feature, early stage Parkinson screening is carried out by preliminary screening model according to the main gait feature, avoid gait feature single, and it is simpler to obtain characterization step, screening efficiency is high, accuracy is good, solves the difficulty of early stage Parkinson's screening.
Description
Technical field
The present invention relates to technical field of data processing, in particular to the wearable auxiliary screening of a kind of early stage Parkinson is set
It is standby.
Background technique
Parkinson's disease (Parkinson ' s Disease, PD) is the second largest nerve for being only second to alzheimer's disease at present
Degenerative disease, the whole world have more than 10,000,000 disturbances in patients with Parkinson disease, and this data may be doubled again to the year two thousand fifty.In recent years
Come, the U.S., European Union etc. are all made that Major Strategic is disposed to the research of brain diseases, such as 2020 project of European Union horizon, project
Task includes mobile device monitoring and evaluation disturbances in patients with Parkinson disease symptom and commercial applications exploration etc., and China is also advised in " 13 "
It draws in suggesting and points out, realize " breakthrough of forward position medical technology " in health field.It is mostly obvious in the state of an illness for the diagnosis of PD at present
It is assessed afterwards by doctor's subjective observation, Chinese doctors and patients' resource is unbalance, and certain methods are confined to environment and intrusive disadvantage in addition
It cannot popularize in daily life, so that PD early diagnosis is very difficult.The main method of screening Parkinsonian symptoms is logical at present
It crosses to patient's plantar pressure modeling analysis, classifies to the gait difference of healthy population and Parkinsonian symptoms patient, reach screening trouble
The purpose of person.
2014, Zeng Wei of Longyan School et al. extracted gait plantar pressure feature and carries out neural net model establishing, identification, structure
Dynamic estimator is built, is classified according to the error of characteristic and dynamic estimator, auxiliary screening Parkinsonian's is different
Normal gait；2015, Xu Shengqiang of the Chinese Academy of Sciences et al. extracted three-dimensional force data and plantar pressure data, with GA genetic algorithm
Optimal gait parameter is filtered out, the walking ability of patient republicanism normal person is assessed.
And the signature analysis based on gait plantar pressure, extract the analysis method of gait plantar pressure feature, such method
The gait feature of acquisition is single and acquisition characterization step is cumbersome.
Summary of the invention
To solve above-mentioned all or part of technical problem, the present invention provides a kind of the wearable auxiliary of early stage Parkinson
Help screening equipment.
A kind of wearable auxiliary screening equipment of early stage Parkinson provided by the invention, which is characterized in that the early stage pa
The wearable auxiliary screening equipment of Jin Sen includes: data perception module and main controller；
The data perception module, for acquiring current 3-axis acceleration when user completes deliberate action and working as first three axis
Angular speed；
The main controller, for the current 3-axis acceleration and when first three axis angular rate carries out zero-phase filtering；
The main controller is also used to the filtered current 3-axis acceleration and when first three axis angular rate passes through phase
Parted pattern divides gait phase, phase character when obtaining current；
The main controller is also used to work as from the filtered current 3-axis acceleration and when extracting in first three axis angular rate
Preceding time domain data, and current frequency feature is converted by the current time zone data；
The main controller, be also used to it is described current when phase character and current frequency feature carry out principal component analysis processing,
Obtain main gait feature；
The main controller is also used to carry out early stage Parkinson sieve by preliminary screening model according to the main gait feature
It looks into.
Preferably, the data perception module, three axis of sample when the person that is also used to collecting test completes deliberate action accelerate
Degree and three axis angular rate of sample；
The main controller is also used to obtain to the sample 3-axis acceleration and the progress zero phase filter of three axis angular rate of sample
Wave；
The main controller is also used to using the sample 3-axis acceleration, three axis angular rate of sample and its delay item as word
The candidate item of allusion quotation Ω carries out candidate item selection with random forest in dictionary Ω, by the candidate item training of selection using RBF as core
The SVM of function obtains the phase parted pattern, logical to the filtered sample 3-axis acceleration and three axis angular rate of sample
Cross the phase parted pattern segmentation gait phase, phase character when obtaining sample；
The main controller is also used to extract sample from the filtered sample 3-axis acceleration and three axis angular rate of sample
This time domain data, and sample frequency feature is converted by the sample time-domain data；
The main controller is also used to according to phase character when the sample and the training of sample frequency feature using MCC as screening
The SVM of characteristic function obtains the preliminary screening model.
Preferably, the dictionary Ω is characterized as
Ω={ ax(t-d),ay(t-d),az(t-d),ωx(t-d),ωy(t-d),ωz(t-d) },
Wherein, axRepresentative sample x-axis acceleration, ayRepresentative sample y-axis acceleration, azRepresentative sample z-axis acceleration, ωxGeneration
Table sample this x-axis angular speed, ωyRepresentative sample y-axis angular speed, ωzRepresentative sample z-axis angular speed, d represent delay time, and t is represented
Random times.
Preferably, the MCC is characterized as
Wherein, TP is the quantity of true positives, and TN is true negative quantity, and FP is the quantity of false positive, and FN is the number of false negative
Amount.
Preferably, phase character and phase character respectively includes support phase and swing phase when sample when described current.
Preferably, the current time zone data and sample time-domain data respectively include gait cycle, step-length, stride, leg speed
With at least one in gait symmetry.
Preferably, the wearable auxiliary screening equipment of the early stage Parkinson further include: data storage；
The data storage is stored for the screening results to early stage Parkinson.
Preferably, the wearable auxiliary screening equipment of the early stage Parkinson further include: data link；
The data link, for the screening results in the data storage to be uploaded to cloud.
Preferably, the data link is also used to obtain current network connection status, is connected according to the current network
Screening results in the data storage are uploaded to cloud by state and Preset Transfer mode.
Preferably, the main controller transplanting has RT-Thread real time operating system.
The present invention obtains 3-axis acceleration and three axis angular rates, is divided to 3-axis acceleration and three axis angular rates by phase
Model divides gait phase, phase character when acquisition, time domain data is extracted from 3-axis acceleration and three axis angular rates, and will be described
Time domain data is converted into frequecy characteristic, to it is described current when phase character and current frequency feature carry out principal component analysis processing, obtain
Main gait feature is obtained, early stage Parkinson screening is carried out by preliminary screening model according to the main gait feature, avoids walking
State feature is single and acquisition characterization step is simpler, and screening efficiency is high, and accuracy is good, solves the tired of early stage Parkinson's screening
It is difficult.
Detailed description of the invention
Fig. 1 is the structural block diagram of the wearable auxiliary screening equipment of the early stage Parkinson of one embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Fig. 1 is the structural block diagram of the wearable auxiliary screening equipment of the early stage Parkinson of one embodiment of the present invention；Ginseng
According to Fig. 1, the wearable auxiliary screening equipment of the early stage Parkinson includes: data perception module 100 and main controller 200；
The data perception module 100, for acquiring current 3-axis acceleration when user completes deliberate action and current
Three axis angular rates；
It should be noted that acquiring to be convenient for data, in the present embodiment, the data perception module 100 can pass through
Self-thread gluing is worn at upper limb humerus, respectively at the leg shin bone of left and right and at fifth lumbar vertebra (L5), wherein x-axis along body direction to
On, for y-axis along human body direction of advance, the vertical human body direction of z-axis is outside.After wearing, the wearable of the early stage Parkinson is opened
The power switch of screening equipment is assisted, presses beginning capture button after completing system initialization, first three axis is worked as in record perception at this time
Acceleration, when first three axis angular rate and acquisition the time started.
It will be appreciated that the deliberate action can be to stand up from seat, turning return is sat down again after the 3m that walks, then again
Walking stand up until encountering barrier (such as chair), sits down around returning later, then presses and stop key, a data record
It completes, certainly, other movements also can be used, the present embodiment is without restriction to this.
In the concrete realization, high-precision MPU6050 chip, accelerometer and top can be used in the data perception module 100
The range of spiral shell instrument can be set as ± 4g, ± 500 °/s, and IIC data/address bus is used to read perception data with the frequency of 100Hz.
The main controller 200, for the current 3-axis acceleration and when first three axis angular rate carries out zero-phase filtering；
It should be noted that STM32F4 chip can be used in the main controller, transplanting has RT-Thread real time operating system.
The main controller 200 is also used to the filtered current 3-axis acceleration and when first three axis angular rate passes through
Phase parted pattern divides gait phase, phase character when obtaining current；
In the concrete realization, phase character includes support phase and swing phase when described current.
The main controller 200 is also used to mention from the filtered current 3-axis acceleration and when in first three axis angular rate
Current time zone data are taken, and convert current frequency feature for the current time zone data；
It will be appreciated that the current time zone data include in gait cycle, step-length, stride, leg speed and gait symmetry
At least one of, the current time zone data can be converted into current frequency feature by Fast Fourier Transform (FFT) FFT.
The main controller 200, be also used to it is described current when phase character and current frequency feature carry out principal component analysis at
Reason, obtains main gait feature；
The main controller 200 is also used to carry out early stage pa gold by preliminary screening model according to the main gait feature
Gloomy screening.
For convenient for saving to screening results, in the present embodiment, the wearable auxiliary screening of the early stage Parkinson is set
It is standby further include: data storage 300；
The data storage 300, stores for the screening results to early stage Parkinson.
In the concrete realization, the Micro-SD card that 8G can be used in the data link 300 is realized.
For convenient for carrying out data transmission to screening results, in the present embodiment, the wearable auxiliary of the early stage Parkinson is sieved
Look into equipment further include: data link 400；
The data link 400, for the screening results in the data storage 300 to be uploaded to cloud.
To be convenient for powering, in the present embodiment, can according to power demand, select 3.7v, 300mAh lithium battery and its
Charging chip, and realize that 3.7v to 3.3v pressure stabilizing is powered using RT9313-33 high-performance voltage stabilizing chip, while plus 5 104 electricity
Hold to being that data perception module 100, main controller 200, data storage 300 and data link 400 are powered after power filter.
In the concrete realization, ESP8266WiFi realization can be used in the data link 400.
To be convenient for data, in the present embodiment, the data link 400 is also used to obtain current network connection shape
State uploads the screening results in the data storage 300 according to the current network connection status and Preset Transfer mode
To cloud, the upload of data cloud, online updating may be implemented, be conducive to remote real-time monitoring patient condition and expert diagnosis,
Solution for doctors and patients' resource unevenness problem is a new approaches.
In the concrete realization, alternate mode can be used in the Preset Transfer mode, i.e., directly stores under no network condition
In Micro-SD card, unify to upload data later；In the case where there is network condition directly by data be uploaded to cloud (such as:
Yeelink platform of internet of things), realize cloud storage and real-time remote monitoring.
After uploading cloud, remote doctor can directly checking storehouse database initial data and in conjunction with the screening results carry out most
After diagnose, diagnosis report is directly then returned into patient by the mobile terminals such as cell phone application, completes whole process.
It should be noted that for the ease of the above-mentioned each component of composition, in the present embodiment, a settable circuit board, each portion
Part is set on the circuit board, combined data acquisition, processing, transmission, storage, demand for control design schematic diagram of device and
PCB figure, each component select 0603 specification, complete PCB circuit board production and each module welding debugging of system, wherein circuit board
It can be long 40.08mm, wide 36.08mm, high 1.6mm.
According to circuit board size, pricks and tie up mode and system demand for control, from angle convenient to wear and slim and graceful quality,
3D printing crust of the device is designed, instruction socket, key mouth, SD card plug-and-pull port, debugging mouth, charge port, power supply are reserved on shell and is opened
Critical point, bandage entrance, fixed PCB thread, length, width and height may respectively be: 45mm, 40mm, 18mm.
The present embodiment realizes gait number using the embedded microcontroller chip STM32F4 of embedded RT-Thread operating system
According to acquisition, processing, feature extraction, partial data processing and machine learning algorithm are transplanted to embedded microcontroller by screening of classifying
In chip, therefore Gait Recognition can be realized in mobile terminal without the end PC, that is, the preliminary screening of early stage Parkinson can be with
It does requirement movement by wearable device to complete, method is simple, strong operability, and usable range is extensive.
The present embodiment obtains 3-axis acceleration and three axis angular rates, passes through phase point to 3-axis acceleration and three axis angular rates
Cut model segmentation gait phase, phase character when acquisition extracts time domain data from 3-axis acceleration and three axis angular rates, and by institute
State time domain data and be converted into frequecy characteristic, to it is described current when phase character and current frequency feature carry out principal component analysis processing,
Main gait feature is obtained, early stage Parkinson screening is carried out by preliminary screening model according to the main gait feature, is avoided
Gait feature is single and acquisition characterization step is simpler, and screening efficiency is high, and accuracy is good, solves early stage Parkinson's screening
It is difficult.
For convenient for establishing the phase parted pattern and preliminary screening model, in the present embodiment, the data perception module
100, the person that is also used to collecting test completes three axis angular rate of sample 3-axis acceleration and sample when deliberate action；
The main controller 200 is also used to obtain to the sample 3-axis acceleration and three axis angular rate of sample, zero phase of progress
Position filtering；
The main controller 200, be also used to using the sample 3-axis acceleration, three axis angular rate of sample and its delay item as
The candidate item of dictionary Ω carries out candidate item selection with random forest in dictionary Ω, is with RBF by the candidate item training of selection
The SVM of kernel function obtains the phase parted pattern, to the filtered sample 3-axis acceleration and three axis angular rate of sample
Divide gait phase by the phase parted pattern, phase character when obtaining sample；
In the concrete realization, phase character includes support phase and swing phase when the sample.
It will be appreciated that the dictionary Ω is characterized as
Ω={ ax(t-d),ay(t-d),az(t-d),ωx(t-d),ωy(t-d),ωz(t-d) },
Wherein, axRepresentative sample x-axis acceleration, ayRepresentative sample y-axis acceleration, azRepresentative sample z-axis acceleration, ωxGeneration
Table sample this x-axis angular speed, ωyRepresentative sample y-axis angular speed, ωzRepresentative sample z-axis angular speed, d represent delay time, and t is represented
Random times.
The main controller 200 is also used to mention from the filtered sample 3-axis acceleration and three axis angular rate of sample
This time domain data is sampled, and converts sample frequency feature for the sample time-domain data；
It will be appreciated that the sample time-domain data include in gait cycle, step-length, stride, leg speed and gait symmetry
At least one of, the sample time-domain data can be converted into sample frequency feature by Fast Fourier Transform (FFT) FFT.
The main controller 200 is also used to be repaired according to phase character when the sample to the training of sample frequency feature with horse related
SVM of the coefficient (Matthew ' s correlation coefficient, MCC) as screening characteristic function is obtained described preliminary
Screening model.
In the concrete realization, the MCC is characterized as
Wherein, TP is the quantity of true positives, and TN is true negative quantity, and FP is the quantity of false positive, and FN is the number of false negative
Amount.
By the description of the drawings and specific embodiments, shown from system composition, structure, coefficient Computing Principle, host computer
Several aspects such as interface, process for using describe the embodiments of the present invention in detail.Aforesaid way is currently preferred reality
Mode is applied, for those skilled in the art, on the basis of disclosed by the invention, it is readily conceivable that being carried out
Modification or equivalent replacement are applied to various medical instrument systems, are not limited solely to described in the specific embodiment of the invention
System structure, therefore previously described mode is only preferred, and not restrictive meaning.
The foregoing is merely several specific embodiments of the invention, above embodiments are only used for technical solution of the present invention
The scope of the claims being not intended to limit the present invention is explained with design.Design of all technician in the art in this patent
On the basis of combine the prior art, also should be by by logic analysis, reasoning or the available other technologies scheme of limited experimentation
Think to fall within the scope of the claims of the present invention.
The above embodiments are only used to illustrate the present invention, and not limitation of the present invention, in relation to the common of technical field
Technical staff can also make a variety of changes and modification without departing from the spirit and scope of the present invention, therefore all
Equivalent technical solution also belongs to scope of the invention, and scope of patent protection of the invention should be defined by the claims.
Claims (10)
1. the wearable auxiliary screening equipment of early stage Parkinson a kind of, which is characterized in that the early stage Parkinson's is wearable auxiliary
Helping screening equipment includes: data perception module and main controller；
The data perception module, for acquiring current 3-axis acceleration when user completes deliberate action and working as first three shaft angle speed
Degree；
The main controller, for the current 3-axis acceleration and when first three axis angular rate carries out zero-phase filtering；
The main controller is also used to the filtered current 3-axis acceleration and when first three axis angular rate is divided by phase
Model divides gait phase, phase character when obtaining current；
The main controller is also used to from the filtered current 3-axis acceleration and when extracting current in first three axis angular rate
Numeric field data, and current frequency feature is converted by the current time zone data；
The main controller, be also used to it is described current when phase character and current frequency feature carry out principal component analysis processing, obtain
Main gait feature；
The main controller is also used to carry out early stage Parkinson screening by preliminary screening model according to the main gait feature.
2. the wearable auxiliary screening equipment of early stage Parkinson as described in claim 1, which is characterized in that the data perception
Module, the person that is also used to collecting test complete three axis angular rate of sample 3-axis acceleration and sample when deliberate action；
The main controller is also used to obtain to the sample 3-axis acceleration and the progress zero-phase filtering of three axis angular rate of sample；
The main controller is also used to using the sample 3-axis acceleration, three axis angular rate of sample and its delay item as dictionary Ω
Candidate item, candidate item selection is carried out in dictionary Ω with random forest, by the training of the candidate item of selection using RBF as kernel function
SVM, obtain the phase parted pattern, institute passed through to the filtered sample 3-axis acceleration and three axis angular rate of sample
State phase parted pattern segmentation gait phase, phase character when obtaining sample；
The main controller, when being also used to extract sample from the filtered sample 3-axis acceleration and three axis angular rate of sample
Numeric field data, and sample frequency feature is converted by the sample time-domain data；
The main controller is also used to according to phase character when the sample and the training of sample frequency feature using MCC as screening feature
The SVM of function obtains the preliminary screening model.
3. the wearable auxiliary screening equipment of early stage Parkinson as claimed in claim 2, which is characterized in that the dictionary Ω table
Sign is
Ω={ ax(t-d),ay(t-d),az(t-d),ωx(t-d),ωy(t-d),ωz(t-d) },
Wherein, axRepresentative sample x-axis acceleration, ayRepresentative sample y-axis acceleration, azRepresentative sample z-axis acceleration, ωxRepresentative sample
This x-axis angular speed, ωyRepresentative sample y-axis angular speed, ωzRepresentative sample z-axis angular speed, d represent delay time, and t represents random
Moment.
4. the wearable auxiliary screening equipment of early stage Parkinson as claimed in claim 2, which is characterized in that the MCC characterization
For
Wherein, TP is the quantity of true positives, and TN is true negative quantity, and FP is the quantity of false positive, and FN is the quantity of false negative.
5. the wearable auxiliary screening equipment of early stage Parkinson as described in claim 1, which is characterized in that the current phase
Phase character respectively includes support phase and swing phase when feature and sample.
6. the wearable auxiliary screening equipment of early stage Parkinson as described in claim 1, which is characterized in that the current time zone
Data and sample time-domain data respectively include at least one in gait cycle, step-length, stride, leg speed and gait symmetry.
7. such as the wearable auxiliary screening equipment of early stage Parkinson according to any one of claims 1 to 6, which is characterized in that
The wearable auxiliary screening equipment of the early stage Parkinson further include: data storage；
The data storage is stored for the screening results to early stage Parkinson.
8. the wearable auxiliary screening equipment of early stage Parkinson as claimed in claim 7, which is characterized in that the early stage pa gold
Gloomy wearable auxiliary screening equipment further include: data link；
The data link, for the screening results in the data storage to be uploaded to cloud.
9. the wearable auxiliary screening equipment of early stage Parkinson as claimed in claim 8, which is characterized in that the data transmission
Device is also used to obtain current network connection status, according to the current network connection status and Preset Transfer mode by the number
Cloud is uploaded to according to the screening results in memory.
10. such as the wearable auxiliary screening equipment of early stage Parkinson according to any one of claims 1 to 6, which is characterized in that
The main controller transplanting has RT-Thread real time operating system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810683383.5A CN108968918A (en) | 2018-06-28 | 2018-06-28 | The wearable auxiliary screening equipment of early stage Parkinson |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810683383.5A CN108968918A (en) | 2018-06-28 | 2018-06-28 | The wearable auxiliary screening equipment of early stage Parkinson |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108968918A true CN108968918A (en) | 2018-12-11 |
Family
ID=64538712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810683383.5A Pending CN108968918A (en) | 2018-06-28 | 2018-06-28 | The wearable auxiliary screening equipment of early stage Parkinson |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108968918A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111528842A (en) * | 2020-05-26 | 2020-08-14 | 复嶂环洲生物科技(上海)有限公司 | Quantitative assessment method for Parkinson disease symptoms based on physiological and behavioral indexes |
| CN111544005A (en) * | 2020-05-15 | 2020-08-18 | 中国科学院自动化研究所 | Parkinson's disease dyskinesia quantification and identification method based on support vector machine |
| CN111544006A (en) * | 2020-05-15 | 2020-08-18 | 中国科学院自动化研究所 | Wearable equipment for quantifying and identifying dyskinesia of Parkinson's disease people |
| CN111700620A (en) * | 2020-06-24 | 2020-09-25 | 中国科学院深圳先进技术研究院 | Gait abnormity early-stage identification and risk early warning method and device |
| WO2021258333A1 (en) * | 2020-06-24 | 2021-12-30 | 中国科学院深圳先进技术研究院 | Gait abnormality early identification and risk early-warning method and apparatus |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8246554B2 (en) * | 2007-11-14 | 2012-08-21 | Hitachi Consumer Electronics Co., Ltd. | Living body inspection system, living body inspection apparatus, and living body inspection method |
| CN104127187A (en) * | 2014-08-05 | 2014-11-05 | 戴厚德 | Wearable system and method for cardinal symptom quantitative detection of Parkinson patients |
| CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
| CN104323780A (en) * | 2014-10-30 | 2015-02-04 | 上海交通大学 | Support vector machine-based pedestrian gait classifying system and method |
| CN104398263A (en) * | 2014-12-25 | 2015-03-11 | 中国科学院合肥物质科学研究院 | Method for quantitatively evaluating symptoms of tremor of patient with Parkinson's disease according to approximate entropy and cross approximate entropy |
| CN104434129A (en) * | 2014-12-25 | 2015-03-25 | 中国科学院合肥物质科学研究院 | Quantization evaluating device and method for dyskinesia symptoms of Parkinson and related extrapyramidal diseases |
| CN106228200A (en) * | 2016-10-17 | 2016-12-14 | 中北大学 | A kind of action identification method not relying on action message collecting device |
| CN106237604A (en) * | 2016-08-31 | 2016-12-21 | 歌尔股份有限公司 | Wearable device and the method utilizing its monitoring kinestate |
| CN106419929A (en) * | 2016-11-05 | 2017-02-22 | 上海大学 | Quantitative detection device for equilibrium stability of posture of Parkinson's disease patient |
| CN106971059A (en) * | 2017-03-01 | 2017-07-21 | 福州云开智能科技有限公司 | A kind of wearable device based on the adaptive health monitoring of neutral net |
| CN107016233A (en) * | 2017-03-14 | 2017-08-04 | 中国科学院计算技术研究所 | The association analysis method and system of motor behavior and cognitive ability |
| CN107330249A (en) * | 2017-06-09 | 2017-11-07 | 常州大学 | A kind of Parkinsonian symptoms area of computer aided method of discrimination based on KINECT skeleton datas |
| WO2018028221A1 (en) * | 2016-08-06 | 2018-02-15 | 深圳市前海安测信息技术有限公司 | Wearable device for assisting recovery of patients with parkinson's disease |
-
2018
- 2018-06-28 CN CN201810683383.5A patent/CN108968918A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8246554B2 (en) * | 2007-11-14 | 2012-08-21 | Hitachi Consumer Electronics Co., Ltd. | Living body inspection system, living body inspection apparatus, and living body inspection method |
| CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
| CN104127187A (en) * | 2014-08-05 | 2014-11-05 | 戴厚德 | Wearable system and method for cardinal symptom quantitative detection of Parkinson patients |
| CN104323780A (en) * | 2014-10-30 | 2015-02-04 | 上海交通大学 | Support vector machine-based pedestrian gait classifying system and method |
| CN104398263A (en) * | 2014-12-25 | 2015-03-11 | 中国科学院合肥物质科学研究院 | Method for quantitatively evaluating symptoms of tremor of patient with Parkinson's disease according to approximate entropy and cross approximate entropy |
| CN104434129A (en) * | 2014-12-25 | 2015-03-25 | 中国科学院合肥物质科学研究院 | Quantization evaluating device and method for dyskinesia symptoms of Parkinson and related extrapyramidal diseases |
| WO2018028221A1 (en) * | 2016-08-06 | 2018-02-15 | 深圳市前海安测信息技术有限公司 | Wearable device for assisting recovery of patients with parkinson's disease |
| CN106237604A (en) * | 2016-08-31 | 2016-12-21 | 歌尔股份有限公司 | Wearable device and the method utilizing its monitoring kinestate |
| CN106228200A (en) * | 2016-10-17 | 2016-12-14 | 中北大学 | A kind of action identification method not relying on action message collecting device |
| CN106419929A (en) * | 2016-11-05 | 2017-02-22 | 上海大学 | Quantitative detection device for equilibrium stability of posture of Parkinson's disease patient |
| CN106971059A (en) * | 2017-03-01 | 2017-07-21 | 福州云开智能科技有限公司 | A kind of wearable device based on the adaptive health monitoring of neutral net |
| CN107016233A (en) * | 2017-03-14 | 2017-08-04 | 中国科学院计算技术研究所 | The association analysis method and system of motor behavior and cognitive ability |
| CN107330249A (en) * | 2017-06-09 | 2017-11-07 | 常州大学 | A kind of Parkinsonian symptoms area of computer aided method of discrimination based on KINECT skeleton datas |
Non-Patent Citations (9)
| Title |
|---|
| ARASH SALARIAN ET AL.: "Gait assessment in Parkinson"s disease: Toward an ambulatory system for long-term monitoring", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 * |
| FERHAT ATTAL ET AL.: "Automatic Recognition of Gait Phases Using a Multiple-Regression Hidden Markov Model", 《IEEE/ASME TRANSACTIONS ON MECHATRONICS》 * |
| SAMUEL REINFELDER ET AL.: "Timed Up-and-Go phase segmentation in Parkinson"s disease patients using unobtrusive inertial sensors", 《2015 37TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)》 * |
| 刘遥: "基于惯性传感器的帕金森病上肢运动障碍量化评估方法研究", 《中国博士学位论文全文数据库（医药卫生科技辑）》 * |
| 吴哲君等: "基于SVM的行人步态实时分类方法", 《电子测量技术》 * |
| 汪少初等: "基于惯性传感的人员行进动作识别方法", 《电子测量与仪器学报》 * |
| 温俊丽等: "基于惯性传感器的帕金森患者行走能力评估系统", 《中国医疗器械杂志》 * |
| 王金甲等: "基于深度卷积神经网络的帕金森步态识别", 《中国生物医学工程学报》 * |
| 赵湛等: "基于可穿戴设备的日常压力状态评估研究", 《电子与信息学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111544005A (en) * | 2020-05-15 | 2020-08-18 | 中国科学院自动化研究所 | Parkinson's disease dyskinesia quantification and identification method based on support vector machine |
| CN111544006A (en) * | 2020-05-15 | 2020-08-18 | 中国科学院自动化研究所 | Wearable equipment for quantifying and identifying dyskinesia of Parkinson's disease people |
| CN111544005B (en) * | 2020-05-15 | 2022-03-08 | 中国科学院自动化研究所 | Parkinson's disease dyskinesia quantification and identification method based on support vector machine |
| CN111528842A (en) * | 2020-05-26 | 2020-08-14 | 复嶂环洲生物科技(上海)有限公司 | Quantitative assessment method for Parkinson disease symptoms based on physiological and behavioral indexes |
| CN111700620A (en) * | 2020-06-24 | 2020-09-25 | 中国科学院深圳先进技术研究院 | Gait abnormity early-stage identification and risk early warning method and device |
| WO2021258333A1 (en) * | 2020-06-24 | 2021-12-30 | 中国科学院深圳先进技术研究院 | Gait abnormality early identification and risk early-warning method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108968918A (en) | The wearable auxiliary screening equipment of early stage Parkinson | |
| CN106971059B (en) | Wearable equipment based on neural network self-adaptation health monitoring | |
| CN108209924B (en) | The analysis method of gait feature after a kind of Anterior Cruciate Ligament Ruptures | |
| Bussmann et al. | Measuring daily behavior using ambulatory accelerometry: the Activity Monitor | |
| CN103514302A (en) | Human body gait database and establishment method thereof | |
| CN113496216B (en) | Multi-angle falling high-risk identification method and system based on skeleton key points | |
| CN107423730A (en) | A kind of body gait behavior active detecting identifying system and method folded based on semanteme | |
| CN103126655A (en) | Non-binding goal non-contact pulse wave acquisition system and sampling method | |
| CN105205436A (en) | Gesture identification system based on multiple forearm bioelectric sensors | |
| US20120310370A1 (en) | Systems and methods for providing a neural-machine interface for artificial legs | |
| CN108960155B (en) | Adult gait extraction and anomaly analysis method based on Kinect | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN106210269A (en) | A kind of human action identification system and method based on smart mobile phone | |
| Pan et al. | Motor function assessment of upper limb in stroke patients | |
| CN106726536A (en) | A kind of acupuncture analog signal output method and device | |
| Chuang et al. | A wearable activity sensor system and its physical activity classification scheme | |
| Yu et al. | Human gait analysis based on OpenSim | |
| CN113749644B (en) | Intelligent garment capable of monitoring lumbar vertebra movement of human body and correcting autonomous posture | |
| Ren et al. | Multivariate analysis of joint motion data by Kinect: application to Parkinson’s disease | |
| Kerdjidj et al. | Implementing hand gesture recognition using EMG on the Zynq circuit | |
| CN112488000B (en) | Modeling method and application of whole-body gait motion model with visual-touch fusion | |
| Pandit et al. | Abnormal gait detection by classifying inertial sensor data using transfer learning | |
| CN107092865A (en) | A kind of new Gait Recognition system based on Kinect | |
| CN107330271A (en) | A kind of medical examination method and its device based on high in the clouds big data Internet of Things and intelligent Portrait brand technology | |
| Zhang et al. | Multimodal fusion convolutional neural network based on semg and accelerometer signals for inter-subject upper limb movement classification |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181211 |
|
| RJ01 | Rejection of invention patent application after publication |