CN105268171A - Gait monitoring method, gait monitoring device and wearable device - Google Patents
Gait monitoring method, gait monitoring device and wearable device Download PDFInfo
- Publication number
- CN105268171A CN105268171A CN201510561183.9A CN201510561183A CN105268171A CN 105268171 A CN105268171 A CN 105268171A CN 201510561183 A CN201510561183 A CN 201510561183A CN 105268171 A CN105268171 A CN 105268171A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- training
- characteristic
- running process
- 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.)
- Granted
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application provides a gait monitoring method, a gait monitoring device and a wearable device. The method comprises acquiring a plurality of data segments corresponding to touchdown of a foot when a user is running, determining feature data used for analyzing the gait from the plurality of data segments; inputting the feature data into a trained mathematic model to obtain a gait monitoring result of the user's running process. By adopting the technical scheme provided by the invention, a user can correctly know his gait without professional guidance, and appropriately adjust his gait according to the gait monitoring result, the user's running level can be raised, and sports injury can be prevented.
Description
Technical field
The application relates to wearable device technical field, particularly relates to a kind of gait monitoring method, device and wearable device.
Background technology
Along with the development of society and the raising of people's living standard, body-building becomes the important need of people gradually.In China, nationwide fitness programs have developed into a mass movement.And run as a kind of simple body-building, be more and more subject to doting on of people.But the jog mode of mistake may cause athletic injury to human body to some extent, it is extremely important to running crowd therefore correctly to carry out road-work.And the crowd that major part carries out road-work can not get the guidance of professional person, can only by learn by oneself and self-observation adjust running posture.
Summary of the invention
In view of this, the application provides a kind of new technical scheme, and user can be made to make suitable adjustment by the gait monitoring result in running process to gait, improves the running level of user and avoids athletic injury.
For achieving the above object, the application provides technical scheme as follows:
According to the first aspect of the application, propose a kind of gait monitoring method, comprising:
Obtain the sole of user in running process to contact to earth multiple data segments corresponding in process;
The characteristic of carrying out gait analysis is determined from described multiple data segment;
Described characteristic is input in the Mathematical Modeling of having trained, obtains the gait monitoring result of described user in running process.
According to the second aspect of the application, propose a kind of gait monitoring device, comprising:
First acquisition module, to contact to earth multiple data segments corresponding in process for obtaining the sole of user in running process;
First determination module, the described multiple data segment for getting from described first acquisition module determines the characteristic of carrying out gait analysis;
First computing module, is input in the Mathematical Modeling of having trained for the described characteristic determined by described first determination module, obtains the gait monitoring result of described user in running process.
According to the third aspect of the application, propose a kind of wearable device, described wearable device comprises:
Processor; For storing the memory of described processor executable;
Wherein, described processor, is configured to:
Obtain the sole of user in running process to contact to earth multiple data segments corresponding in process;
The characteristic of carrying out gait analysis is determined from described multiple data segment;
Described characteristic is input in the Mathematical Modeling of having trained, obtains the gait monitoring result of described user in running process.
From above technical scheme, the application achieves and monitors the gait of user in running process, thus can enable user under not having professional person to instruct, also correctly can be familiar with the gait of oneself, and make suitable adjustment according to the gait of gait monitoring result to user, improve the running level of user and avoid athletic injury.
Accompanying drawing explanation
Figure 1A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment one of the present invention;
The data that the front foot that Figure 1B shows Figure 1A illustrated embodiment lands are at the schematic diagram of time domain;
The data that the metapedes that Fig. 1 C shows Figure 1A illustrated embodiment lands are at the schematic diagram of time domain;
Fig. 2 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment two of the present invention;
Fig. 2 B shows data segment that front foot that Fig. 2 A illustrated embodiment obtains the lands schematic diagram in time domain;
Fig. 2 C shows data segment that metapedes that Fig. 2 A illustrated embodiment obtains the lands schematic diagram in time domain;
Fig. 3 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment three of the present invention;
The data that the front foot that Fig. 3 B shows Fig. 3 A illustrated embodiment lands are at the schematic diagram of frequency domain;
The data that the metapedes that Fig. 3 C shows Fig. 3 A illustrated embodiment lands are at the schematic diagram of frequency domain;
Fig. 4 shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment four of the present invention;
Fig. 5 shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment five of the present invention;
Fig. 6 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment six of the present invention;
Fig. 6 B shows the model schematic based on SVMs of Fig. 6 A illustrated embodiment;
Fig. 7 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment seven of the present invention;
Fig. 7 B shows the model schematic based on decision tree of Fig. 7 A illustrated embodiment;
Fig. 8 shows the structural representation of the wearable device according to an exemplary embodiment of the present invention;
Fig. 9 shows the structural representation of the gait monitoring device according to an exemplary embodiment of the present invention;
Figure 10 shows the structural representation of the gait monitoring device according to another exemplary embodiment of the present invention;
Figure 11 shows the structural representation of gait monitoring device in accordance with a further exemplary embodiment of the present invention.
Detailed description of the invention
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the application.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that some aspects of the application are consistent.
Only for describing the object of specific embodiment at term used in this application, and not intended to be limiting the application." one ", " described " and " being somebody's turn to do " of the singulative used in the application and appended claims is also intended to comprise most form, unless context clearly represents other implications.It is also understood that term "and/or" used herein refer to and comprise one or more project of listing be associated any or all may combine.
Term first, second, third, etc. may be adopted although should be appreciated that to describe various information in the application, these information should not be limited to these terms.These terms are only used for the information of same type to be distinguished from each other out.Such as, when not departing from the application's scope, the first information also can be called as the second information, and similarly, the second information also can be called as the first information.Depend on linguistic context, word as used in this " if " can be construed as into " ... time " or " when ... time " or " in response to determining ".
To general running personage Lai Eryan, the main contents of jog mode comprise cadence, join speed and gait.Cadence represents user's quantity of taking a step per minute, join the running time of speed expression needed for user every kilometer, and the mode that the sole of gait expression user in running process lands, in actual running process, the difference of the order that lands according to each position of sole, gait is divided into forward roll, rear heel lands and full sole lands.According to the actual needs, forward roll and full sole can be landed is collectively referred to as front foot and lands, and is landed by rear heel and be called that metapedes lands, or forward roll is called front foot lands, and is landed by rear heel and full sole lands and is collectively referred to as metapedes and lands.The above-mentioned different sorting technique of gait, the gait monitoring method all by the application realizes.The application is by monitoring the gait of user in running process, thus can enable user under not having professional person to instruct, also correctly can be familiar with the gait of oneself, and make suitable adjustment according to the gait of gait monitoring result to user, improve the running level of user and avoid athletic injury.
For being further described the application, provide the following example:
Figure 1A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment one of the present invention, the data that the front foot that Figure 1B shows Figure 1A illustrated embodiment lands are at the schematic diagram of time domain, and the data that the metapedes that Fig. 1 C shows Figure 1A illustrated embodiment lands are at the schematic diagram of time domain; The present embodiment can be realized by the gait monitoring device be arranged on running equipment, and wherein, running equipment can include but not limited to running shoes, shoe-pad and socks etc.This gait monitoring device installation site on running equipment includes but not limited to the sole of running shoes, vamp and heel position, the arch of foot position of shoe-pad, and the stocking leg of socks etc., as shown in Figure 1A, gait monitoring method comprises the steps:
Step 101, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 102, determines the characteristic of carrying out gait analysis from multiple data segment;
Step 103, is input to characteristic in the Mathematical Modeling of having trained, obtains the gait monitoring result of user in running process.
In a step 101, can gather the sensing data of user in running process by sensor, this sensing data can by including but not limited to be collected by sensors such as acceleration transducer, gyroscope and magnetometers.From sensing data, identify sole to contact to earth data segment corresponding in process.As illustrated in figures ib and 1 c, the sensing data of one that collects in user's running process for the acceleration transducer dimension wherein of marking time, wherein, Figure 1B show user's front foot land brief acceleration sensor gather data, Fig. 1 C show user's metapedes land brief acceleration sensor gather data, in the data of this sensor, front foot lands in the process of contacting to earth that lands with metapedes to there being higher crest, there is in respective crest both sides the trough of different shape, by detecting the data characteristics of the trough of crest and crest both sides, thus the data segment that user is corresponding in the sole that each walks contacts to earth process can be determined, and then the step number that user runs can be detected in whole running process, and multiple data segments that this step number is corresponding.When adopting multiple dimension data of same sensor, then user's each step in running process all can data segment corresponding to corresponding multiple dimension in the process of contacting to earth, further, when there being multiple sensor to gather, each sensor in multiple sensor all can collect data segment corresponding to respective different dimensions, the application for the purpose of simplifying the description, only carries out exemplary illustration with the data of acceleration transducer dimension; It will be understood by those skilled in the art that, the processing mode of the data of the different dimensions that different sensors collects can see the associated description of the application, and the description of the data of a dimension of acceleration transducer in the application can not form the restriction to the application.
In a step 102, in one embodiment, the characteristic of carrying out gait analysis can be determined to multiple data segment in time domain; In another embodiment, can determine the characteristic of carrying out gait analysis to multiple data segment at frequency domain, detailed description refers to following Fig. 3 A and embodiment illustrated in fig. 4, does not first describe in detail at this.
In step 103, in one embodiment, gait monitoring result can be considered as a binary classification problems, namely judge that user is that front foot lands or metapedes lands according to the characteristic extracted.In one embodiment, the Mathematical Modeling of having trained can for the Mathematical Modeling based on biomechanical analysis, land according to front foot and the mechanics difference that lands of metapedes, formulate the feature templates that front foot lands and metapedes lands respectively, and by the method for Dynamic Programming, the data characteristics of user is mated with given feature templates, judge it is that front foot lands or metapedes lands according to matching distance, wherein, in feature templates, the parameter value of each dimensional feature can iteration adjustment by experiment.In another embodiment, the Mathematical Modeling of having trained can be machine learning Mathematical Modeling, and the front foot data known by a large amount of gait or metapedes data carry out the parameter training of Mathematical Modeling, and the Gait Recognition of will the parameter model obtained be trained to be used for user data.In one embodiment, machine learning Mathematical Modeling includes but not limited to Distance conformability degree model, perceptron model, supporting vector machine model, decision-tree model, etc.
Seen from the above description, the embodiment of the present invention realizes monitoring the gait of user in running process by above-mentioned steps 101-step 103, thus can enable user under not having professional person to instruct, also correctly can be familiar with the gait of oneself, and make suitable adjustment according to the gait of gait monitoring result to user, improve the running level of user and avoid athletic injury.
Fig. 2 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment two of the present invention, Fig. 2 B shows the front foot that Fig. 2 A illustrated embodiment obtains and lands at the schematic diagram of the data segment of time domain, and Fig. 2 C shows data segment that metapedes that Fig. 2 A illustrated embodiment obtains the lands schematic diagram in time domain; As shown in Figure 2 A, comprise the steps:
Step 201, determines whether user is in running state;
Step 202, if user is in running state, obtains the sensing data of user in running process;
Step 203, carries out signal filtering to sensing data;
Step 204, the user that the sensing data after detection filter detects each step sole in running process contacts to earth crest corresponding in process and trough;
Step 205, the crest corresponding according to each step and trough determine that the sole of user in running process contacts to earth multiple data segments corresponding in process.
In step 201, can be determined by the step number in the unit interval whether user is in running state, such as, when detecting that the step number of user within the unit interval reaches setting step number, then determine that user is in running state, wherein, setting step number can be determined by actual tests.
In step 203 to step 205, sensing data is carried out to signal filtering includes but not limited to LPF, Kalman leads filtering, medium filtering etc.The time point of user when contacting to earth can being determined, intercepting the data segment before and after contacting to earth according to time point when contacting to earth.Data segment before and after contacting to earth can see Fig. 2 B and Fig. 2 C, thus can by the non-data filtering of contacting to earth in process in running process outside two vertical lines.
In the present embodiment, to contact to earth multiple data segments corresponding in process by obtaining the sole of user in running process after sensing data is carried out pretreatment, thus make unnecessary data not participate in the process in later stage, reduce amount of calculation, improve computational efficiency, improve the precision of gait analysis simultaneously.
Fig. 3 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment three of the present invention, the data that the front foot that Fig. 3 B shows Fig. 3 A illustrated embodiment lands are at the schematic diagram of frequency domain, and the data that the metapedes that Fig. 3 C shows Fig. 3 A illustrated embodiment lands are at the schematic diagram of frequency domain; The present embodiment carries out exemplary illustration to obtain characteristic by the data segment of front and back of contacting to earth at frequency domain, as shown in Figure 3A, comprises the steps:
Step 301, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 302, carries out FFT conversion to multiple data segment, obtains multiple data segment at energy spectrum corresponding to frequency domain;
Step 303, energy spectrum determines the characteristic representing Energy distribution, and wherein, the characteristic of Energy distribution is used for carrying out gait analysis;
Step 304, will be used for representing that the characteristic of Energy distribution is input in the Mathematical Modeling of having trained, and obtains the gait monitoring result of user in running process.
The description of step 301 and step 304 see the description of related embodiment, can be not described in detail in this.
In step 302 and step 303, by data segment when contacting to earth is carried out FFT conversion, obtain the energy spectrum information of sensing data section at frequency domain, as shown in Fig. 3 B and Fig. 3 C, embody front foot to land and metapedes lands each self-corresponding process Energy distribution on a different frequency of contacting to earth, such as, can by suing for peace to the energy spectrum in the process of contacting to earth, obtain the gross energy in the process of contacting to earth, using the characteristic of gross energy as Energy distribution, again such as, to setting frequency range (such as, between 1-25Hz or 25Hz-50Hz) energy spectrum identify, using the characteristic of the energy values of given frequency range as Energy distribution.
In the present embodiment, by sensing data section corresponding in the process of contacting to earth is transformed into the analysis that frequency domain carries out data characteristics, land from metapedes different energy spectrums corresponding distributed, therefore by determining representing that the characteristic of Energy distribution can improve the degree of accuracy of Gait Recognition greatly on energy spectrum because front foot lands.
Fig. 4 shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment four of the present invention; The present embodiment, to obtain characteristic and composition graphs 2B and Fig. 2 C carries out exemplary illustration by the data segment before and after contacting to earth in time domain, as shown in Figure 4, comprises the steps:
Step 401, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 402, each self-corresponding average, crest feature, trough feature, peak valley concussion value and peak valley spacing are determined within the time period that each data segment is corresponding to multiple data segment, wherein, average, crest feature, trough feature, peak valley concussion value and peak valley spacing are as the data characteristics for carrying out gait analysis;
Step 403, is input to average, crest feature, trough feature, peak valley concussion value and peak valley spacing in the Mathematical Modeling of having trained, obtains the gait monitoring result of user in running process.
The description of step 401 and step 403 see the description of related embodiment, can be not described in detail in this.
As shown in fig. 2 b and fig. 2 c, the data instance of the dimension collected with acceleration transducer carries out exemplary illustration, the average of the data segment contacted to earth in process represents the acceleration average in the process of contacting to earth, crest represents the peak-peak in the process of contacting to earth, trough represents the minimum trough value (the peak-to-peak minimum trough value of the such as vertical line of two shown in Fig. 2 B and Fig. 2 C and ripple) in the process of contacting to earth, the difference of peak valley concussion value and maximum crest value and minimum trough value, peak valley spacing and between maximum crest and minimum trough at a distance of the number number of sampled point.
In the present embodiment, by by the average in sensing data section corresponding in the process of contacting to earth, crest feature, trough feature, peak valley concussion value and peak valley spacing are as the data characteristics for carrying out gait analysis, because front foot lands the average that to have landed corresponding from metapedes different, crest feature, trough feature, peak valley concussion value and peak valley spacing, the data characteristics of these time domains can separately as the input of the Mathematical Modeling of having trained, in addition, also can as the input of the Mathematical Modeling of having trained together with the data characteristics of frequency domain, thus improve the precision of result of calculation.Compared with the data characteristics of frequency domain, the data characteristics due to time domain does not need to carry out FFT conversion, and therefore the data characteristics of time domain has the low advantage of computation complexity.
Fig. 5 shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment five of the present invention; The present embodiment for the Mathematical Modeling of having trained for Distance conformability degree model carries out exemplary illustration, when similarity model of adjusting the distance carries out parameter training, need the front foot data determining to comprise in training data and metapedes data, wherein, training data is for training Distance conformability degree model, then calculate the second distributed constant of the first corresponding in Distance conformability degree model distributed constant of front foot data and metapedes data correspondence in Distance conformability degree model respectively, the first distributed constant and the second distributed constant can determine Distance conformability degree model.
As shown in Figure 5, comprise the steps:
Step 501, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 502, determines the characteristic of carrying out gait analysis from multiple data segment;
Step 503, carries out Similarity Measure with the first distributed constant in Distance conformability degree model and the second distributed constant respectively by characteristic, obtains the first similarity and the second similarity;
Step 504, determines the gait monitoring result of user in running process according to the first similarity and the second similarity.
The description of step 501 and step 502 see the description of above-mentioned related embodiment, can be not described in detail in this.
In step 503, in one embodiment, can by including but not limited to obtain the first similarity in the application and the second similarity by Euclidean distance of the prior art, mahalanobis distance etc., first similarity and the second similarity are inversely proportional to the Euclidean distance calculated or mahalanobis distance, also be, Euclidean distance or mahalanobis distance less, value corresponding to similarity is larger.The present embodiment obtains the first similarity in the application and second-phase like not carrying out expansions description to how by Euclidean distance, mahalanobis distance, can with reference to prior art.
In step 504, first similarity and the second similarity can be compared, using the gait corresponding to the higher value in the first similarity and the second similarity as gait monitoring result, such as, if the first similarity is greater than the second similarity, represent the Euclidean distance that the first similarity is corresponding or mahalanobis distance less, the gait that then this data segment is corresponding is that front foot corresponding to the first similarity lands, if, first similarity is less than the second similarity, represent the Euclidean distance that the second similarity is corresponding or mahalanobis distance less, the gait that then this data segment is corresponding is that metapedes corresponding to the second similarity lands.
In the present embodiment, by characteristic is carried out Similarity Measure with the first distributed constant in Distance conformability degree model and the second distributed constant respectively, obtain the first similarity and the second similarity, the gait monitoring result of user in running process is determined by the first similarity and the second similarity, thus by the conversion of gait monitoring problem in order to binary classification problems, the degree of accuracy of gait monitoring result can also be improved constantly by the statistical model parameter using mass data to obtain.
Fig. 6 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment six of the present invention, and Fig. 6 B shows the model schematic based on SVMs of Fig. 6 A illustrated embodiment; The present embodiment for the Mathematical Modeling of having trained for supporting vector machine model carries out exemplary illustration, as shown in Figure 6B, when carrying out parameter training to supporting vector machine model, the front foot data (in Fig. 6 B shown in "×") determining to comprise in training data and metapedes data (in Fig. 6 B, " Ο " is shown), wherein, training data is used for Training Support Vector Machines model; Training one according to front foot data and metapedes data makes front foot land and Optimal Separating Hyperplane function that spacing distance that metapedes lands between two corresponding classifications is maximum, as shown in Figure 6B, obtain two support vector hyperplane and an Optimal Separating Hyperplane by training data, this Optimal Separating Hyperplane is the Optimal Separating Hyperplane function that front foot lands and metapedes lands.As shown in Figure 6A, comprise the steps:
Step 601, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 602, determines the characteristic of carrying out gait analysis from multiple data segment;
Step 603, is input to Optimal Separating Hyperplane function, obtains Output rusults by characteristic;
Step 604, determines the gait monitoring result of user in running process according to Output rusults.
Described in the present embodiment and above-mentioned Fig. 5, embodiment is similar, by characteristic is input to Optimal Separating Hyperplane function, obtain Output rusults, the gait monitoring result of user in running process is determined according to Output rusults, thus by the conversion of gait monitoring problem in order to binary classification problems, the degree of accuracy of gait monitoring result can also be improved constantly by the Optimal Separating Hyperplane using mass data to obtain.
Fig. 7 A shows the schematic flow sheet of the gait monitoring method according to an exemplary embodiment seven of the present invention, and Fig. 7 B shows the model schematic based on decision tree of Fig. 7 A illustrated embodiment; The present embodiment is carry out exemplary illustration based on the model of decision tree for the Mathematical Modeling of having trained, when carrying out parameter training to the model of decision tree, determine the front foot data that comprise in training data and metapedes data, wherein, training data is for training the model of decision tree; By the threshold value of each node in the front foot data in training data and metapedes data iterative estimate decision tree, wherein, the relative theory of decision tree refers to prior art, and the application is not described in detail; As shown in Figure 7 A, comprise the steps:
Step 701, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process;
Step 702, determines the characteristic of carrying out gait analysis from multiple data segment;
Step 703, compares the threshold value that characteristic is corresponding with this node at each node of decision tree, to determine the next node in decision tree;
Step 704, determines the gait monitoring result of user in running process according to the final leaf node of characteristic in decision tree.
As shown in Figure 7 B, comprise 5 nodes for decision tree and carry out exemplary illustration, at first node 711 place, first threshold corresponding with this node for first node characteristic of correspondence data is compared, to determine that the next node in decision tree is second node 712 or the 3rd node 713, if first node characteristic of correspondence data is greater than first threshold, then decision-making enters second node 712, if first node characteristic of correspondence data is less than or equal to first threshold, then decision-making enters the 3rd node 713.If enter second node 712, then Second Threshold corresponding with this node for second node 712 characteristic of correspondence data is compared, determine that front foot lands or metapedes lands according to comparative result, if enter the 3rd node 713, then the 3rd corresponding with this node for the 3rd node 713 characteristic of correspondence data threshold value is compared, the 4th node 714 is entered or metapedes lands according to comparative result decision-making, if decision-making enters into the 4th node 714, then the 4th corresponding with this node for the 4th node 714 characteristic of correspondence data threshold value is compared, the 5th node 715 is entered or metapedes lands according to comparative result decision-making, if decision-making enters into the 5th node 715, then the 5th corresponding with this node for the 5th node 715 characteristic of correspondence data threshold value is compared, that front foot lands or metapedes lands according to comparative result decision-making.
It will be understood by those skilled in the art that, the example by training the decision tree obtained to decision tree is only shown in Fig. 7 B, wherein, the threshold value that each node is corresponding, and determine that redirect result that data characteristics and magnitude relationship and then the decision-making of corresponding threshold value go out (namely, the output judged result of present node or present node jump to and judge next time), all obtained by repetitive exercise, therefore Fig. 7 B is only an exemplary description and can not forms restriction to the application.
Known by foregoing description, described in the present embodiment and above-mentioned Fig. 5 and Fig. 6 A, embodiment is similar, the gait monitoring result of user in running process is determined according to the final leaf node of characteristic in decision tree, thus by the conversion of gait monitoring problem in order to binary classification problems, the degree of accuracy of gait monitoring result can also be improved constantly by the decision tree threshold parameter using mass data to obtain.
Pass through above-described embodiment, large-sized analytic instrument in the laboratory that the application can make ordinary person not use sports science to study carries out the gait analysis of specialty, and under the prerequisite instructed not having professional person, correctly can be familiar with the gait of oneself, and make suitable adjustment according to the result of gait analysis, thus reach raising running level and avoid athletic injury.
Corresponding to above-mentioned gait monitoring method, the application also proposed the schematic configuration diagram of the wearable device of the exemplary embodiment according to the application shown in Fig. 8.Please refer to Fig. 8, at hardware view, this wearable device comprises processor, internal bus, network interface, internal memory and nonvolatile memory, certainly also may comprise the hardware required for other business.Processor reads corresponding computer program and then runs in internal memory from nonvolatile memory, logic level is formed and realizes gait monitoring device.Certainly, except software realization mode, the application does not get rid of other implementations, mode of such as logical device or software and hardware combining etc., that is the executive agent of following handling process is not limited to each logical block, also can be hardware or logical device.
Fig. 9 is the structural representation of the gait monitoring device according to an exemplary embodiment of the present invention; As shown in Figure 9, this gait monitoring device can comprise: the first acquisition module 91, first determination module 92, first computing module 93.Wherein:
First acquisition module 91, to contact to earth multiple data segments corresponding in process for obtaining the sole of user in running process;
First determination module 92, the multiple data segments for getting from the first acquisition module 91 determine the characteristic of carrying out gait analysis;
First computing module 93, is input in the Mathematical Modeling of having trained for the characteristic determined by the first determination module 92, obtains the gait monitoring result of user in running process.
Figure 10 shows the structural representation of the gait monitoring device according to another exemplary embodiment of the present invention, and device also can comprise:
Second determination module 94, contacts to earth before multiple data segments corresponding in process for obtaining the sole of user in running process at the first acquisition module 91, determines whether user is in running state;
Second acquisition module 95, if determine that user is in running state for the second determination module 94, obtains the sensing data of user in running process;
Pretreatment module 96, carries out pretreatment for the sensing data got the second acquisition module 95, obtains the sole of user in running process and to contact to earth multiple data segments corresponding in process, obtain for the first acquisition module 91.
In one embodiment, pretreatment module can 96 to comprise:
Filter unit 961, for carrying out signal filtering to sensing data;
First detecting unit 962, the user detected for the filtered sensing data of detection filter unit 961 each step sole in running process contacts to earth corresponding crest and trough in process;
First determining unit 963, the crest that each step for detecting according to the first detecting unit 962 is corresponding and trough determine that the sole of user in running process contacts to earth multiple data segments corresponding in process.
In one embodiment, the first determination module 92 can comprise:
FFT converter unit 921, for carrying out FFT conversion to multiple data segment, obtains multiple data segment at energy spectrum corresponding to frequency domain;
Second determining unit 922, on the energy spectrum obtained at FFT converter unit 921, determine the characteristic representing Energy distribution, wherein, the characteristic of Energy distribution is used for carrying out gait analysis.
In one embodiment, the first determination module 92 can comprise:
3rd determining unit 923, for determining each self-corresponding average, crest feature, trough feature, peak valley concussion value and peak valley spacing to multiple data segment within the time period that each data segment is corresponding, wherein, average, crest feature, trough feature, peak valley concussion value and peak valley spacing are used for carrying out gait analysis.
Figure 11 shows the structural representation of gait monitoring device in accordance with a further exemplary embodiment of the present invention, and in one embodiment, the Mathematical Modeling of having trained is Distance conformability degree model, and device also can comprise:
3rd determination module 97, for when similarity model of adjusting the distance carries out parameter training, determine the front foot data that comprise in training data and metapedes data, wherein, training data is for training Distance conformability degree model;
First training module 98, the second distributed constant of metapedes data correspondence in Distance conformability degree model that the first distributed constant and the 3rd determination module for calculating front foot data correspondence in Distance conformability degree model that the 3rd determination module 97 is determined respectively are determined;
First computing module 93 comprises:
First computing unit 931, for characteristic is carried out Similarity Measure with the first distributed constant and the second distributed constant respectively, obtains the first similarity and the second similarity;
4th determining unit 932, determines the gait monitoring result of user in running process for the first similarity of calculating according to the first computing unit 931 and the second similarity.
In one embodiment, the Mathematical Modeling of having trained is supporting vector machine model, and device also can comprise:
4th determination module 99, for when carrying out parameter training to supporting vector machine model, determines the front foot data that comprise in training data and metapedes data, and wherein, training data is used for Training Support Vector Machines model;
Second training module 11, an Optimal Separating Hyperplane function making the spacing distance between front foot and two classifications corresponding to metapedes maximum is trained, the classification function that Optimal Separating Hyperplane function lands as front foot and metapedes lands for the front foot data determined according to the 4th determination module 99 and metapedes data;
First computing module 93 can comprise:
Second computing unit 933, for characteristic is input to Optimal Separating Hyperplane function, obtains Output rusults;
5th determining unit 934, the Output rusults for calculating according to the second computing unit 933 determines the gait monitoring result of user in running process.
In one embodiment, the Mathematical Modeling of having trained is the model based on decision tree, and device also can comprise:
5th determination module 12, for when carrying out parameter training to the model of decision tree, determine the front foot data that comprise in training data and metapedes data, wherein, training data is for training the model of decision tree;
3rd training module 13, for the threshold value of each node in the front foot data in the training data determined by the 5th determination module 12 and metapedes data iterative estimate decision tree;
First computing module 93 can comprise:
Comparing unit 935, compares the threshold value that characteristic is corresponding with this node for each node decision tree, to determine the next node in decision tree;
6th determining unit 936, for determining the gait monitoring result of user in running process according to the final leaf node of characteristic in decision tree.
Pass through above-described embodiment, large-sized analytic instrument in the laboratory that ordinary person can be made not use sports science to study carries out the gait analysis of specialty, and under the prerequisite instructed not having professional person, correctly can be familiar with the gait of oneself, and make suitable adjustment according to the result of gait analysis, thus reach raising running level and avoid athletic injury.
Those skilled in the art, at consideration description and after putting into practice invention disclosed herein, will easily expect other embodiment of the application.The application is intended to contain any modification of the application, purposes or adaptations, and these modification, purposes or adaptations are followed the general principle of the application and comprised the undocumented common practise in the art of the application or conventional techniques means.Description and embodiment are only regarded as exemplary, and true scope and the spirit of the application are pointed out by claim below.
Also it should be noted that, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, commodity or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, commodity or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, commodity or the equipment comprising described key element and also there is other identical element.
The foregoing is only the preferred embodiment of the application, not in order to limit the application, within all spirit in the application and principle, any amendment made, equivalent replacements, improvement etc., all should be included within scope that the application protects.
Claims (17)
1. a gait monitoring method, is characterized in that, described method comprises:
Obtain the sole of user in running process to contact to earth multiple data segments corresponding in process;
The characteristic of carrying out gait analysis is determined from described multiple data segment;
Described characteristic is input in the Mathematical Modeling of having trained, obtains the gait monitoring result of described user in running process.
2. method according to claim 1, is characterized in that, the described acquisition sole of user in running process contact to earth multiple data segments corresponding in process step before, described method also comprises:
Determine whether user is in running state;
If user is in running state, obtain the sensing data of user in running process;
Pretreatment is carried out to described sensing data, obtains the sole of described user in running process and to contact to earth multiple data segments corresponding in process.
3. method according to claim 2, is characterized in that, describedly carries out pretreatment to described sensing data, obtains the sole of described user in running process and to contact to earth multiple data segments corresponding in process, comprising:
Signal filtering is carried out to described sensing data;
The user detected in described sensing data after detection filter each step sole in running process contacts to earth crest corresponding in process and trough;
The crest corresponding according to each step described and trough determine that the sole of described user in running process contacts to earth multiple data segments corresponding in process.
4. method according to claim 1, is characterized in that, describedly determines the characteristic of carrying out gait analysis from described multiple data segment, comprising:
FFT conversion is carried out to described multiple data segment, obtains described multiple data segment at energy spectrum corresponding to frequency domain;
Described energy spectrum determines the characteristic representing Energy distribution, and wherein, the characteristic of described Energy distribution is used for carrying out gait analysis.
5. method according to claim 1, is characterized in that, describedly determines the characteristic of carrying out gait analysis from described multiple data segment, comprising:
Each self-corresponding average, crest feature, trough feature, peak valley concussion value and peak valley spacing are determined within the time period that each data segment is corresponding to described multiple data segment, wherein, described average, crest feature, trough feature, peak valley concussion value and peak valley spacing are used for carrying out gait analysis.
6. method according to claim 1, is characterized in that, described Mathematical Modeling of having trained is Distance conformability degree model, and described method also comprises:
When carrying out parameter training to described Distance conformability degree model, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training described Distance conformability degree model;
Calculate the second distributed constant of the first corresponding in described Distance conformability degree model distributed constant of described front foot data and described metapedes data correspondence in described Distance conformability degree model respectively;
Describedly described characteristic to be input in the Mathematical Modeling of having trained, to obtain the gait monitoring result of described user in running process, comprising:
Described characteristic is carried out Similarity Measure with described first distributed constant and described second distributed constant respectively, obtains the first similarity and the second similarity;
The gait monitoring result of described user in running process is determined according to described first similarity and described second similarity.
7. method according to claim 1, is characterized in that, described Mathematical Modeling of having trained is supporting vector machine model, and described method also comprises:
When carrying out parameter training to described supporting vector machine model, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training described supporting vector machine model;
An Optimal Separating Hyperplane function making the spacing distance between front foot and two classifications corresponding to metapedes maximum is trained, the classification function that described Optimal Separating Hyperplane function lands as front foot and metapedes lands according to described front foot data and described metapedes data;
Describedly described characteristic to be input in the Mathematical Modeling of having trained, to obtain the gait monitoring result of described user in running process, comprising:
Described characteristic is input to described Optimal Separating Hyperplane function, obtains Output rusults;
The gait monitoring result of described user in running process is determined according to described Output rusults.
8. method according to claim 1, is characterized in that, described Mathematical Modeling of having trained is the model based on decision tree, and described method also comprises:
When carrying out parameter training to the model of described decision tree, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training the model of described decision tree;
By the threshold value of each node in decision tree described in the described front foot data in described training data and described metapedes data iterative estimate;
Describedly described characteristic to be input in the Mathematical Modeling of having trained, to obtain the gait monitoring result of described user in running process, comprising:
At each node of described decision tree, the threshold value that described characteristic is corresponding with this node is compared, to determine the next node in described decision tree;
The gait monitoring result of described user in running process is determined according to the final leaf node of described characteristic in described decision tree.
9. a gait monitoring device, is characterized in that, described device comprises:
First acquisition module, to contact to earth multiple data segments corresponding in process for obtaining the sole of user in running process;
First determination module, the described multiple data segment for getting from described first acquisition module determines the characteristic of carrying out gait analysis;
First computing module, is input in the Mathematical Modeling of having trained for the described characteristic determined by described first determination module, obtains the gait monitoring result of described user in running process.
10. device according to claim 9, is characterized in that, described device also comprises:
Second determination module, contacts to earth before multiple data segments corresponding in process for obtaining the sole of user in running process at described first acquisition module, determines whether user is in running state;
Second acquisition module, if determine that described user is in running state for described second determination module, obtains the sensing data of user in running process;
Pretreatment module, carries out pretreatment for the described sensing data got described second acquisition module, obtains the sole of described user in running process and to contact to earth multiple data segments corresponding in process.
11. devices according to claim 10, is characterized in that, described pretreatment module comprises:
Filter unit, for carrying out signal filtering to described sensing data;
First detecting unit, the user detected for the described sensing data after detecting described filtering unit filters each step sole in running process contacts to earth corresponding crest and trough in process;
First determining unit, the crest corresponding for each step described in detecting according to described first detecting unit and trough determine that the sole of described user in running process contacts to earth multiple data segments corresponding in process.
12. devices according to claim 9, is characterized in that, described first determination module comprises:
FFT converter unit, for carrying out FFT conversion to described multiple data segment, obtains described multiple data segment at energy spectrum corresponding to frequency domain;
Second determining unit, on the described energy spectrum obtained at described FFT converter unit, determine the characteristic representing Energy distribution, wherein, the characteristic of described Energy distribution is used for carrying out gait analysis.
13. devices according to claim 9, is characterized in that, described first determination module comprises:
3rd determining unit, for determining each self-corresponding average, crest feature, trough feature, peak valley concussion value and peak valley spacing to described multiple data segment within the time period that each data segment is corresponding, wherein, described average, crest feature, trough feature, peak valley concussion value and peak valley spacing are used for carrying out gait analysis.
14. devices according to claim 9, is characterized in that, described Mathematical Modeling of having trained is Distance conformability degree model, and described device also comprises:
3rd determination module, for when carrying out parameter training to described Distance conformability degree model, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training described Distance conformability degree model;
First training module, the second distributed constant of described metapedes data correspondence in described Distance conformability degree model that the first distributed constant and described 3rd determination module for calculating described front foot data correspondence in described Distance conformability degree model that described 3rd determination module is determined respectively are determined;
Described first computing module comprises:
First computing unit, for described characteristic is carried out Similarity Measure with described first distributed constant and described second distributed constant respectively, obtains the first similarity and the second similarity;
4th determining unit, determines the gait monitoring result of described user in running process for described first similarity that calculates according to described first computing unit and described second similarity.
15. devices according to claim 9, is characterized in that, described Mathematical Modeling of having trained is supporting vector machine model, and described device also comprises:
4th determination module, for when carrying out parameter training to described supporting vector machine model, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training described supporting vector machine model;
Second training module, an Optimal Separating Hyperplane function making the spacing distance between front foot and two classifications corresponding to metapedes maximum is trained, the classification function that described Optimal Separating Hyperplane function lands as front foot and metapedes lands for the described front foot data determined according to described 4th determination module and described metapedes data;
Described first computing module comprises:
Second computing unit, for described characteristic is input to described Optimal Separating Hyperplane function, obtains Output rusults;
5th determining unit, the described Output rusults for calculating according to described second computing unit determines the gait monitoring result of described user in running process.
16. devices according to claim 9, is characterized in that, described Mathematical Modeling of having trained is the model based on decision tree, and described device also comprises:
5th determination module, for when carrying out parameter training to the model of described decision tree, determine the front foot data that comprise in training data and metapedes data, wherein, described training data is for training the model of described decision tree;
3rd training module, for the threshold value of each node in decision tree described in the described front foot data in the described training data determined by described 5th determination module and described metapedes data iterative estimate;
Described first computing module comprises:
Comparing unit, compares the threshold value that described characteristic is corresponding with this node for each node described decision tree, to determine the next node in described decision tree;
6th determining unit, for determining the gait monitoring result of described user in running process according to the final leaf node of described characteristic in described decision tree.
17. 1 kinds of wearable devices, is characterized in that, described wearable device comprises:
Processor; For storing the memory of described processor executable;
Wherein, described processor, is configured to:
Obtain the sole of user in running process to contact to earth multiple data segments corresponding in process;
The characteristic of carrying out gait analysis is determined from described multiple data segment;
Described characteristic is input in the Mathematical Modeling of having trained, obtains the gait monitoring result of described user in running process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510561183.9A CN105268171B (en) | 2015-09-06 | 2015-09-06 | gait monitoring method, device and wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510561183.9A CN105268171B (en) | 2015-09-06 | 2015-09-06 | gait monitoring method, device and wearable device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105268171A true CN105268171A (en) | 2016-01-27 |
| CN105268171B CN105268171B (en) | 2018-09-18 |
Family
ID=55138540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510561183.9A Active CN105268171B (en) | 2015-09-06 | 2015-09-06 | gait monitoring method, device and wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105268171B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108404382A (en) * | 2018-02-24 | 2018-08-17 | 上海康斐信息技术有限公司 | A kind of algorithm and system of adaptive training plan generation |
| CN109256187A (en) * | 2018-08-27 | 2019-01-22 | 爱动超越人工智能科技（北京）有限责任公司 | A kind of running posture suggesting system for wearing and method based on multimode motion sensor data |
| CN109260673A (en) * | 2018-11-27 | 2019-01-25 | 北京羽扇智信息科技有限公司 | A kind of movement method of counting, device, equipment and storage medium |
| CN110575177A (en) * | 2019-09-10 | 2019-12-17 | 电子科技大学 | Gait classification and quantification method based on Mahalanobis distance |
| CN111753924A (en) * | 2020-07-03 | 2020-10-09 | 济南傲谷智控科技有限公司 | Four-footed robot foot end touchdown detection method based on supervised training |
| CN113457106A (en) * | 2020-03-31 | 2021-10-01 | 荣耀终端有限公司 | Running posture detection method and wearable device |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4216817A4 (en) * | 2020-09-25 | 2024-08-28 | Walkbeat Ab | System and method for analyzing gait-related health and performance of an equine animal |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030139692A1 (en) * | 2000-02-04 | 2003-07-24 | Eric Barrey | Method for analysing irregularities in human locomotion |
| CN1705956A (en) * | 2002-10-29 | 2005-12-07 | 索尼株式会社 | Gait waveform feature extracting method and individual identification system |
| CN101477618A (en) * | 2008-12-18 | 2009-07-08 | 上海交通大学 | Process for pedestrian step gesture periodic automatic extraction from video |
| CN102670207A (en) * | 2012-05-15 | 2012-09-19 | 北京大学 | Gait analysis method based on plantar pressure |
| JP2013022188A (en) * | 2011-07-20 | 2013-02-04 | Nippon Telegr & Teleph Corp <Ntt> | Gait analyzing method, gait analyzer, and program of the same |
| CN103519819A (en) * | 2012-07-06 | 2014-01-22 | 王振兴 | Gait analysis method and gait analysis system |
| CN103876756A (en) * | 2014-04-18 | 2014-06-25 | 南京工程学院 | Lower limb power-assisted exoskeleton robot gait pattern identification method and system |
| CN104299003A (en) * | 2014-11-02 | 2015-01-21 | 天津理工大学 | Gait recognition method based on similar rule Gaussian kernel function classifier |
-
2015
- 2015-09-06 CN CN201510561183.9A patent/CN105268171B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030139692A1 (en) * | 2000-02-04 | 2003-07-24 | Eric Barrey | Method for analysing irregularities in human locomotion |
| CN1705956A (en) * | 2002-10-29 | 2005-12-07 | 索尼株式会社 | Gait waveform feature extracting method and individual identification system |
| CN101477618A (en) * | 2008-12-18 | 2009-07-08 | 上海交通大学 | Process for pedestrian step gesture periodic automatic extraction from video |
| JP2013022188A (en) * | 2011-07-20 | 2013-02-04 | Nippon Telegr & Teleph Corp <Ntt> | Gait analyzing method, gait analyzer, and program of the same |
| CN102670207A (en) * | 2012-05-15 | 2012-09-19 | 北京大学 | Gait analysis method based on plantar pressure |
| CN103519819A (en) * | 2012-07-06 | 2014-01-22 | 王振兴 | Gait analysis method and gait analysis system |
| CN103876756A (en) * | 2014-04-18 | 2014-06-25 | 南京工程学院 | Lower limb power-assisted exoskeleton robot gait pattern identification method and system |
| CN104299003A (en) * | 2014-11-02 | 2015-01-21 | 天津理工大学 | Gait recognition method based on similar rule Gaussian kernel function classifier |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN108404382A (en) * | 2018-02-24 | 2018-08-17 | 上海康斐信息技术有限公司 | A kind of algorithm and system of adaptive training plan generation |
| CN109256187A (en) * | 2018-08-27 | 2019-01-22 | 爱动超越人工智能科技（北京）有限责任公司 | A kind of running posture suggesting system for wearing and method based on multimode motion sensor data |
| CN109260673A (en) * | 2018-11-27 | 2019-01-25 | 北京羽扇智信息科技有限公司 | A kind of movement method of counting, device, equipment and storage medium |
| CN110575177A (en) * | 2019-09-10 | 2019-12-17 | 电子科技大学 | Gait classification and quantification method based on Mahalanobis distance |
| CN110575177B (en) * | 2019-09-10 | 2020-12-15 | 电子科技大学 | Gait classification and quantification method based on Mahalanobis distance |
| CN113457106A (en) * | 2020-03-31 | 2021-10-01 | 荣耀终端有限公司 | Running posture detection method and wearable device |
| CN111753924A (en) * | 2020-07-03 | 2020-10-09 | 济南傲谷智控科技有限公司 | Four-footed robot foot end touchdown detection method based on supervised training |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105268171B (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105268171A (en) | Gait monitoring method, gait monitoring device and wearable device | |
| US11660024B2 (en) | Method and system for analyzing human gait | |
| US9179862B2 (en) | Method and system for assessing locomotive bio-rhythms | |
| Yoneyama et al. | Accelerometry-based gait analysis and its application to Parkinson's disease assessment—part 1: detection of stride event | |
| AU2010286471B2 (en) | Characterizing a physical capability by motion analysis | |
| US20120137795A1 (en) | Rating a physical capability by motion analysis | |
| WO2019069417A1 (en) | Biological information processing device, biological information processing system, biological information processing method, and storage medium | |
| KR20210046121A (en) | Apparatus and method for identify patients with parkinson's disease and patients with podarthritis by performing neural network analysis by various detection information | |
| CN106725512A (en) | Motion monitoring method, device and wearable device | |
| Donahue et al. | Estimation of ground reaction force waveforms during fixed pace running outside the laboratory | |
| Akhund et al. | Human IoT Interaction Approach for Modeling Human Walking Patterns Using Two-Dimensional Levy Walk Distribution. | |
| US20090012921A1 (en) | Method for identifying a person's posture | |
| JP7489729B2 (en) | Method for preventing falls and device for carrying out such method | |
| Wang et al. | Human motion phase segmentation based on three new features | |
| D’Arco et al. | U2FSM: Unsupervised Square Finite State Machine for Gait Events Estimation from Instrumented Insoles | |
| Babu et al. | Classification of human gait: Swing and stance phases using sum-vector analysis | |
| Sowmiya et al. | A hybrid approach using bidirectional neural networks for human activity recognition | |
| Ghazali et al. | Investigation on the effect of different window size in segmentation for common sport activity | |
| Kalischewski et al. | Activity recognition for indoor movement and estimation of travelled path | |
| Ramli et al. | Automated Detection of Gait Events and Travel Distance Using Waist-worn Accelerometers Across a Typical Range of Walking and Running Speeds | |
| CN118448006B (en) | Patient rehabilitation scheme recommendation method and system for orthopedics department | |
| US20230181057A1 (en) | Systems and Methods of Longitudinal Analysis of Human Running Gait Metrics | |
| Meland | Automated detection and classification of movement cycles in cross-country skiing through analysis of inertial sensor data movement patterns | |
| Yee et al. | Anthro-Gait: A Study on the Relation of Gait Variable Score (GVS) based deviation to Anthropometrics for Filipino Gait Analysis | |
| CN118633929A (en) | Gait evaluation system and method based on wearable sensing network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |