CN103989480B - Knee osteoarthritis motion monitoring method based on Android system - Google Patents
Knee osteoarthritis motion monitoring method based on Android system Download PDFInfo
- Publication number
- CN103989480B CN103989480B CN201410259896.5A CN201410259896A CN103989480B CN 103989480 B CN103989480 B CN 103989480B CN 201410259896 A CN201410259896 A CN 201410259896A CN 103989480 B CN103989480 B CN 103989480B
- Authority
- CN
- China
- Prior art keywords
- acceleration
- thigh
- acceleration transducer
- axis
- human body
- 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
Abstract
The present invention relates to knee osteoarthritis motion monitoring field, particularly a kind of knee osteoarthritis motion monitoring method based on Android system, it is characterized in that: be worn on the acceleration transducer signals on human body thigh and shank by wireless acquisition device collection, and transfer signals on Android mobile terminal by wireless transmission method, by the signal processing system arranging on described Android mobile terminal, by Bayes's filtering algorithm, the acceleration signal collecting is carried out to filtering, and by rule induction, action norm is identified. The present invention can identify the action lack of standardization occurring in patient moving preferably, can meet the application requirements of motion monitoring.
Description
Technical field
The present invention relates to knee osteoarthritis (KneeOsteoarthritis, KOA) motion monitoring field, particularly onePlant the knee osteoarthritis motion monitoring method based on Android system.
Background technology
Knee osteoarthritis motion monitoring is specially for knee osteoarthritis patient carries out a set of of normative rehabilitation trainingMonitoring system. Carry out to specification rehabilitation training and can effectively strengthen and go down on one's knees muscular strength and stretch knee muscular strength, stable, symptom to the state of an illnessAlleviate the effect of all playing, and ground lack of standardization rehabilitation training will increase the weight of the kneed burden of patient, cause the deterioration of the state of an illness. CauseThis research for motion of knee joint monitoring becomes a kind of necessary. At present, the Main Means of human motion monitoring has based on PCImage analytical method and two kinds of acceleration analysis. Image analysis technology to experimental situation illumination condition require high, system is huge, makeHigh price is expensive, portability is poor, and live effect is poor; And acceleration analysis technology based on PC involves great expense equally, be not easy toUser carries.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, provide a kind of kneecap based on Android system to closeSave scorching motion monitoring method, the hardware device cost that the method has simply, uses is low, and can identify preferably patient's fortuneMove the middle action lack of standardization occurring, can meet the application requirements of motion monitoring.
For achieving the above object, technical scheme of the present invention is: a kind of fortune of the knee osteoarthritis based on Android systemMoving monitoring method, is characterized in that: be worn on the acceleration sensing on human body thigh and shank by wireless acquisition device collectionDevice signal, and transfer signals on Android mobile terminal by wireless transmission method, end moved by described AndroidThe signal processing system arranging on end, carries out filtering by Bayes's filtering algorithm by the acceleration signal collecting, and by ruleInduction is identified action norm.
In an embodiment of the present invention, described wireless acquisition device comprises microprocessor and is connected with this microprocessorWireless transmitter module; The output of described acceleration transducer is connected with described microprocessor through signal conditioning circuit.
In an embodiment of the present invention, described wireless transmitter module is bluetooth serial ports module.
In an embodiment of the present invention, described acceleration transducer comprises that being worn on first on human body thigh accelerates to passSensor and be worn on the second acceleration sensor on human body shank, and the X-axis of this first and second acceleration transducer is parallel to human bodySagittal plane downwards, Y-axis be parallel to human body sagittal plane left, Z axis is parallel to human body frontal plane backward.
In an embodiment of the present invention, in the time of collection signal, person to be measured need complete following training action: trainer lies low and faces upwardSleeping, one leg bending, one leg stretches, and it is static that bent leg keeps, and straight leg carries out slow smoothness to be raised, and elevation angle is about 30 °, protectsAfter holding 5s, slowly put down, every group 10 times.
In an embodiment of the present invention, described Bayes's filtering algorithm is expansion Kalman filtering algorithm, and it is based onSub-optimal filters under little variance criterion, mainly, by the system of nonlinear model and observational equation are done to Taylor expansion, protectsStay single order item and ignore other higher order terms and realize linearisation.
In an embodiment of the present invention, the system state equation of described expansion Kalman filtering algorithm and output equation are publicShown in formula (1) ~ (3):
(1)
(2)
(3)
In formula、、For system state variables, and be respectively large and small leg elevation angle, angular speed, angular acceleration; ItsMiddle i=1,2, i=1 represents the data of thigh, i=2 represents the data of shank; y1(k)，y2And y (k)3(k)，y4(k) represent respectivelyThe Z axis of the acceleration transducer on k moment thigh and shank and X-axis acceleration signal observation data, acceleration transducer Y-axisDue to perpendicular to motion of knee joint plane, acceleration value is 0; G is acceleration of gravity 9.8m/s2，For adopting of acquisition systemIn the sample cycle, l is lower limb femur length, d1For hip joint is to the distance of sensor one, d2For knee joint is to the distance of sensor two.
In an embodiment of the present invention, the model state angle by described rule induction, bayesian algorithm being estimatedDegree, angular speed and angular acceleration data are carried out normalization identification, j1，e1，w1，a1Lift leg angle, thigh and calf angle for what setPoor, angular speed, angular acceleration threshold value; j2，e2，w2，a2For the angle of actual measurement, thigh and calf differential seat angle, angular speed, accelerate at angleDegree value; In iterative process, if e1<e2, make the feedback that please keep thigh and calf to stretch; If w2>w1And a2>a1, doGo out to lift the too fast feedback of leg speed; If do not have continuous 5s to occur j2>j1, make the feedback of retention time deficiency.
In an embodiment of the present invention, use in the API of Android high through expansion Kalman filtering data acquisition after treatmentThe SurfaceView control of level is drawn oscillogram and reference axis thereof.
In an embodiment of the present invention, after described identification, enter by the TextToSpeech calling in the API of AndroidRow voice feedback.
The invention has the beneficial effects as follows that adopting wireless data acquisition system to obtain is worn on adding on human body thigh and shankSpeed sensor signal, Android mobile terminal carries out filtering by Bayes's filtering algorithm to the acceleration signal collecting,And by rule induction, action norm is identified and feedback, algorithm is simple and practical, system is little, and is easy to carry, fromAnd allow knee osteoarthritis patient rehabilitation training voluntarily.
Below in conjunction with drawings and the specific embodiments, the present invention is described in further detail.
Brief description of the drawings
Fig. 1 is the overall structure schematic diagram of the embodiment of the present invention.
Fig. 2 is the wireless acquisition system structural representation of the embodiment of the present invention.
Fig. 3 is the Android systems soft ware frame diagram of the embodiment of the present invention.
Fig. 4 is the knee osteoarthritis motion physiotherapy method physical model figure of the embodiment of the present invention.
Fig. 5 is each state variable time series chart that in the embodiment of the present invention, EKF estimates.
Fig. 6 is action norm identification process figure in the embodiment of the present invention.
Detailed description of the invention
The knee osteoarthritis motion monitoring method that the present invention is based on Android system, shows in the overall structure shown in Fig. 1In intention, knee osteoarthritis patient degree of will speed up sensor one and acceleration transducer two be worn on respectively human body thigh andOn shank, and require the X-axis of acceleration transducer be parallel to human body sagittal plane downward direction, Y-axis be parallel to human body sagittal plane toLeft is parallel to human body frontal plane backward directions to, Z axis. Normative rehabilitation training is lain on the back for trainer lies low, one leg bending,One leg stretches, and it is static that bent leg keeps, and straight leg carries out slow smoothness to be raised, and elevation angle is about 30 °, keeps slowly putting after 5sUnder, every group 10 times. In the wireless acquisition system structural representation shown in Fig. 2, comprise sensor, signal conditioning circuit, Wei ChuReason device, wireless transmitter module and Android mobile terminal. In the Android systems soft ware frame diagram shown in Fig. 3, signalProcessing comprises codomain conversion, Bayes's filtering algorithm and the identification of rule induction to action norm of acceleration signal,And make feedback.
In the present embodiment, above-mentioned microprocessor is 51 processor of single chip computer, using 51 single-chip microcomputers as master controller collection3-axis acceleration sensor signal.
In the present embodiment, above-mentioned wireless transmitter module is bluetooth serial ports module, by bluetooth serial ports module degree of will speed upSignal is transferred on Android mobile terminal.
In the present embodiment, above-mentioned Bayes's filtering algorithm is expansion Kalman filtering algorithm (ExtendedKalmanFilter, EKF), EKF is the sub-optimal filters based under minimum variance criterion, main by by the system of nonlinear model withObservational equation is Taylor and launches, and retains single order item and ignore other higher order terms and realize linearisation, although EKF is not necessarily optimum, but it is worked finely and becomes the method the most classical in Nonlinear Filtering Problem and that be used widely of processing. Native systemNonlinear state space model as shown in Figure 4, therefrom can show that system state equation and output equation are formula (1) ~ (3)Shown in.
(1)
(2)
(3)
In formula、、For system state variables, and be respectively large and small leg elevation angle, angular speed, angular acceleration (itsMiddle i=1,2), i=1 represents the data of thigh, i=2 represents the data of shank. y1(k)，y2And y (k)3(k)，y4(k) represent respectivelyThe Z axis of the acceleration transducer on k moment thigh and shank and X-axis acceleration signal observation data, acceleration transducer YAxle is due to perpendicular to motion of knee joint plane, and acceleration value is 0; G is acceleration of gravity 9.8m/s2，For acquisition systemIn the sampling period, l is lower limb femur length, d1For hip joint is to the distance of sensor one, d2For knee joint is to the distance of sensor twoFrom.
In the present embodiment, middle-and-high-ranking with the API of Android through expansion Kalman filtering data acquisition after treatmentSurfaceView control is drawn at a high speed oscillogram and reference axis thereof. Waveform shown in Fig. 5 is exactly each state change that EKF estimatesAmount time series, can find out that from scheming user trains angle, angular speed and the angle of lifting leg carrying out straight leg elevation rehabilitation in detailAcceleration. According to the state variable estimating, adopt rule induction to identify accurately in user's rehabilitation trainingExisting action lack of standardization (comprise too short, motion leg bending of retention time, lift leg speed too fast), and by calling Android'sTextToSpeech in API carries out voice feedback. As shown in Figure 6, in the present embodiment, by described rule induction to shellfishModel state angle, angular speed and the angular acceleration data that this algorithm of leaf estimates carried out normalization identification, j1，e1，w1，a1ForThat sets lifts leg angle, thigh and calf differential seat angle, angular speed, angular acceleration threshold value; j2，e2，w2，a2For the angle of actual measurement, largeShank differential seat angle, angular speed, angular acceleration values; In iterative process, if e1<e2, make and please keep thigh and calf to stretchFeedback; If w2>w1And a2>a1, make and lift the too fast feedback of leg speed; If do not have continuous 5s to occur j2>j1, make guarantorHold the feedback of deficiency of time.
Claims (3)
1. the knee osteoarthritis motion monitoring method based on Android system, is characterized in that: fill by wireless collectionPut and gather the acceleration transducer signals being worn on human body thigh and shank, and transfer signals to by wireless transmission methodOn Android mobile terminal, by the signal processing system arranging on described Android mobile terminal, calculated by Bayes's filteringThe acceleration signal collecting is carried out filtering by method, and by rule induction, action norm is identified; Described pattra leavesThis filtering algorithm is that system state equation and the output equation of expansion Kalman filtering algorithm is shown in formula (1)～(3):
In formulaωi(k)、αi(k) be system state variables, and be respectively large and small leg elevation angle, angular speed, angle accelerationDegree; Wherein i=1,2, i=1 represents the data of thigh, i=2 represents the data of shank; y1(k)，y2(k) represent respectively the k momentThe Z axis of the acceleration transducer of thigh and X-axis acceleration signal observation data; y3(k)，y4(k) represent respectively k moment shankOn Z axis and the X-axis acceleration signal observation data of acceleration transducer, the acceleration transducer Y on human body thigh and shankAxle is due to perpendicular to motion of knee joint plane, and acceleration value is 0; G is acceleration of gravity 9.8m/s2，TsFor adopting of acquisition systemIn the sample cycle, l is lower limb femur length, d1For hip joint is to the distance of the acceleration transducer of thigh, d2For knee joint is to shankThe distance of acceleration transducer; Middle-and-high-ranking with the API of Android through expansion Kalman filtering data acquisition after treatmentSurfaceView control is drawn oscillogram and reference axis thereof; After described identification by calling in the API of AndroidTextToSpeech carries out voice feedback;
Wherein acceleration transducer comprises the first acceleration transducer being worn on human body thigh and is worn on human body shankThe second acceleration transducer, and the X-axis of this first and second acceleration transducer be parallel to human body sagittal plane downwards, Y-axis is parallel toHuman body sagittal plane left, Z axis is parallel to human body frontal plane backward;
Described Bayes's filtering algorithm is expansion Kalman filtering algorithm, and it is the suboptimal filtering based under minimum variance criterionDevice, mainly launches by the system of nonlinear model and observational equation are done to Taylor, reservation single order item and ignore other high-ordersItem is realized linearisation;
The model state angle, angular speed and the angular acceleration data that bayesian algorithm are estimated by described rule inductionCarry out normalization identification,e1，ω1，α1Lift leg angle, thigh and calf differential seat angle, angular speed, angular acceleration threshold value for what set;e2，ω2，α2For the angle of actual measurement, thigh and calf differential seat angle, angular speed, angular acceleration values; In iterative process, if e1<e2, make the feedback that please keep thigh and calf to stretch; If ω2>ω1And α2>α1, make and lift the too fast feedback of leg speed; AsFruit does not have continuous 5s to occurMake the feedback of retention time deficiency.
2. the knee osteoarthritis motion monitoring method based on Android system according to claim 1, its feature existsIn: the wireless transmitter module that described wireless acquisition device comprises microprocessor and is connected with this microprocessor; Described accelerationThe output of degree sensor is connected with described microprocessor through signal conditioning circuit.
3. the knee osteoarthritis motion monitoring method based on Android system according to claim 2, its feature existsIn: described wireless transmitter module is bluetooth serial ports module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410259896.5A CN103989480B (en) | 2014-06-12 | 2014-06-12 | Knee osteoarthritis motion monitoring method based on Android system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410259896.5A CN103989480B (en) | 2014-06-12 | 2014-06-12 | Knee osteoarthritis motion monitoring method based on Android system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103989480A CN103989480A (en) | 2014-08-20 |
| CN103989480B true CN103989480B (en) | 2016-05-04 |
Family
ID=51304001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410259896.5A Active CN103989480B (en) | 2014-06-12 | 2014-06-12 | Knee osteoarthritis motion monitoring method based on Android system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103989480B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104613964A (en) * | 2015-01-30 | 2015-05-13 | 中国科学院上海高等研究院 | Pedestrian positioning method and system for tracking foot motion features |
| CN106618584B (en) * | 2015-11-10 | 2019-11-22 | 北京纳通科技集团有限公司 | A method of for monitoring user's lower extremity movement |
| CN106901928A (en) * | 2017-04-18 | 2017-06-30 | 广州医软智能科技有限公司 | A kind of sick bed control device and its autocontrol method |
| PL422126A1 (en) * | 2017-07-05 | 2019-01-14 | Inforin Spółka Z Ograniczoną Odpowiedzialnością | Method for monitoring and the monitoring system |
| CN109480854A (en) * | 2018-12-27 | 2019-03-19 | 重庆市北碚区中医院 | A kind of device for healing and training and application thereof of combination sensor |
| CN111700622B (en) * | 2020-07-03 | 2021-02-02 | 四川大学华西医院 | Leg lifting angle detection device |
| CN112315458B (en) * | 2020-11-23 | 2021-08-20 | 山东大学 | Movement dysfunction recognition device, system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010034308A2 (en) * | 2008-09-27 | 2010-04-01 | Humotion Gmbh | Capturing biometric data of a group of persons |
| CN202282004U (en) * | 2011-06-02 | 2012-06-20 | 上海巨浪信息科技有限公司 | Mobile health management system based on context awareness and activity analysis |
| CN103110410A (en) * | 2013-03-13 | 2013-05-22 | 太原理工大学 | Intelligent thermometer for Android mobile phone |
| CN203122372U (en) * | 2013-03-12 | 2013-08-14 | 李晓龙 | Real-time health monitoring and intelligent warning system based on Android technology and Internet of Things |
| CN103549947A (en) * | 2013-10-28 | 2014-02-05 | 上海理工大学 | Real-time and accurate electrocardiographic wave drawing method of smartphone platforms |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005006024A1 (en) * | 2005-02-08 | 2006-10-05 | Deutsche Telekom Ag | Device for monitoring vital signs frail |
| US9037530B2 (en) * | 2008-06-26 | 2015-05-19 | Microsoft Technology Licensing, Llc | Wearable electromyography-based human-computer interface |
-
2014
- 2014-06-12 CN CN201410259896.5A patent/CN103989480B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010034308A2 (en) * | 2008-09-27 | 2010-04-01 | Humotion Gmbh | Capturing biometric data of a group of persons |
| CN202282004U (en) * | 2011-06-02 | 2012-06-20 | 上海巨浪信息科技有限公司 | Mobile health management system based on context awareness and activity analysis |
| CN203122372U (en) * | 2013-03-12 | 2013-08-14 | 李晓龙 | Real-time health monitoring and intelligent warning system based on Android technology and Internet of Things |
| CN103110410A (en) * | 2013-03-13 | 2013-05-22 | 太原理工大学 | Intelligent thermometer for Android mobile phone |
| CN103549947A (en) * | 2013-10-28 | 2014-02-05 | 上海理工大学 | Real-time and accurate electrocardiographic wave drawing method of smartphone platforms |
Non-Patent Citations (1)
| Title |
|---|
| KOA运动疗法规范性的研究;陈志卿 等;《计算机仿真》;20140430;第31卷(第4期);摘要，第247-251页，图1-3 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103989480A (en) | 2014-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103989480B (en) | Knee osteoarthritis motion monitoring method based on Android system | |
| CN103083027B (en) | Gait phase distinguishing method based on lower limb joint movement information | |
| Jiang | Combination of wearable sensors and internet of things and its application in sports rehabilitation | |
| CN104317196B (en) | A kind of upper-limbs rehabilitation training robot control method based on virtual reality | |
| CN110072678A (en) | The mankind for moving auxiliary are intended to detection system | |
| CN103584919B (en) | Multi-modal bio signal synchronous detecting system and method | |
| CN203417440U (en) | Composite sensing system for wearable pneumatic lower limb rehabilitation robot | |
| CN105528613A (en) | Behavior identification method based on GPS speed and acceleration data of smart phone | |
| CN104881118B (en) | A kind of donning system for being used to capture human upper limb locomotion information | |
| CN104147770A (en) | Inertial-sensor-based wearable hemiplegia rehabilitation apparatus and strap-down attitude algorithm | |
| CN102679964B (en) | Gait parameter measurement system and data processing device and method thereof | |
| Wang et al. | Human Gait Recognition System Based on Support Vector Machine Algorithm and Using Wearable Sensors. | |
| CN108175639A (en) | The bionical dynamic knee joint system in the wearable list source of one kind and its control method | |
| CN107802268B (en) | A kind of human elbow anterior flexion and rear stretching and the outer instantaneous spiral shell shaft measurement method of forearm medial rotation rotation | |
| Chen et al. | Design and voluntary motion intention estimation of a novel wearable full-body flexible exoskeleton robot | |
| CN106923942A (en) | Upper and lower extremities motion assistant system based on the control of human body electromyographic signal | |
| CN108227905A (en) | A kind of Gamecontrol system based on surface electromyogram signal | |
| Gouwanda et al. | Periodical gait asymmetry assessment using real-time wireless gyroscopes gait monitoring system | |
| CN206322115U (en) | A kind of Gamecontrol system based on surface electromyogram signal | |
| Dong et al. | Wireless body area sensor network for posture and gait monitoring of individuals with Parkinson's disease | |
| Sun et al. | An auto-calibration approach to robust and secure usage of accelerometers for human motion analysis in FES therapies | |
| CN102989156B (en) | A kind of training of the archery based on action recognition technology accessory system | |
| CN110197727A (en) | Upper limb modeling method and motion function assessment system based on artificial neural network | |
| CN208970186U (en) | Health detecting system for wearable device | |
| Tsai et al. | Deep learning model to recognize the different progression condition patterns of manual wheelchair users for prevention of shoulder pain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |