CN112263244A - Gait-based fatigue degree evaluation system and method - Google Patents
Gait-based fatigue degree evaluation system and method Download PDFInfo
- Publication number
- CN112263244A CN112263244A CN202010968205.4A CN202010968205A CN112263244A CN 112263244 A CN112263244 A CN 112263244A CN 202010968205 A CN202010968205 A CN 202010968205A CN 112263244 A CN112263244 A CN 112263244A
- Authority
- CN
- China
- Prior art keywords
- gait
- fatigue
- information
- template
- walking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
- A61B5/1038—Measuring plantar pressure during gait
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6804—Garments; Clothes
- A61B5/6807—Footwear
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a gait-based fatigue degree evaluation system and a gait-based fatigue degree evaluation method, wherein the method comprises the following steps of: designing a fatigue test to acquire normal gait and fatigue gait of a person to be evaluated, and acquiring normal gait and fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information; segmenting gait cycle of the gait signal, and carrying out abnormity detection and normalization on the acquired cycle signal so as to extract a normal walking template and a fatigue walking template of each person; and extracting and processing the current gait information, generating a current gait template, and calculating the distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue degree evaluation result. The method can perform more accurate and coherent fatigue evaluation on each person in real time, can continuously obtain the gait fatigue value of the user, and is simple and easy to implement.
Description
Technical Field
The invention relates to the technical field of fatigue evaluation, in particular to a gait-based fatigue degree evaluation system and method.
Background
The fatigue degree is an important factor of the gait change of the user, and the research and the quantification of the gait fatigue degree have important significance for a plurality of problems, for example, the research shows that the fatigue can obviously change the gait characteristics of the old people, so that the falling probability of the old people is obviously influenced, and the evaluation of the gait fatigue degree of the old people has important significance for preventing the old people from falling. In addition, reasonable evaluation of the gait fatigue is also of great significance to training of athletes or health monitoring of ordinary people.
In the related art, the fatigue is evaluated mainly based on various biological signals including electroencephalogram signals, electromyogram signals, inertial sensor signals, video signals such as facial expressions, eye rotations, and the like, and then the fatigue is classified by using a machine learning or neural network method.
However, the related art has the following disadvantages:
1) many currently acquired information cannot effectively evaluate the gait fatigue degree, for example, expression, video or electroencephalogram signals are related to mental fatigue, and the correlation with the gait fatigue of a user is not great. The information such as blood oxygen, pulse, heart rate and the like can only reflect the strenuous degree of the user movement, and the relevance with the gait fatigue degree is not large. Such as blood oxygen, pulse and heart rate of a user can be greatly changed after strenuous exercise, but the gait and fatigue of the user can be recovered after a short rest without being obviously changed.
2) The information extraction equipment and method of the current method are too complex, for example, the information acquisition such as myoelectricity acquisition, electrocardio acquisition, pulse acquisition, blood oxygen acquisition and the like is very difficult, and the information extraction equipment and method are also very complex for users to use and difficult to apply to actual life.
3) For inaccurate quantification of fatigue, many current methods measure fatigue by user self-expression or by means of a motion conscious scale. The measurement method is largely determined by subjective will of users, and lacks objective evaluation criteria and basis. The experimental method for obtaining the fatigue is also inaccurate, and if the fatigue is obtained by adopting the running mode of the running machine, the obtained fatigue is mostly related to the heart and lung functions of the user and is not related to the gait fatigue of the user caused by walking. Muscle fatigue caused by strenuous exercise can be recovered in a short time, and is different from long-term fatigue caused after walking.
4) The existing method mostly adopts a machine learning or neural network mode to grade the fatigue degree, firstly, the obtained fatigue degree is not a linear continuous index, and secondly, the gait fatigue of each person cannot be well evaluated. Because one person's gait is related to a large number of musculoskeletal and nervous systems, the fatigue of the corresponding muscles and the change of gait corresponding to the fatigue of each person's gait can be very different, even the gait fatigue of people of different ages, such as children, adults and the old, is very different. This is difficult to consider or embody in methods using multi-sample trained machine learning or neural network algorithms.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, a first objective of the present invention is to provide a gait-based fatigue evaluation method, which can perform more accurate and consistent fatigue evaluation on each person in real time, can continuously obtain a gait fatigue value of a user, and is simple and easy to implement.
A second object of the present invention is to provide a gait-based fatigue evaluation system.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a gait-based fatigue assessment method, including the following steps: designing a fatigue test to acquire normal gait and fatigue gait of a person to be evaluated, and acquiring normal gait and fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information; segmenting gait cycle of gait signals, carrying out abnormity detection and normalization on the collected periodic signals, detecting and removing abnormal periodic signals so as to extract a normal walking template and a fatigue walking template of each person; and evaluating the motion state of the user in real time, extracting gait information of the person to be evaluated during walking to generate a current gait template, and calculating the distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue degree evaluation result.
According to the gait-based fatigue degree evaluation method disclosed by the embodiment of the invention, the equipment used for detecting the fatigue degree is sufficient and simple, the flow of acquiring the fatigue gait is relatively accurate, and the gait information vectors of each person in the non-fatigue and fatigue states are obtained, so that more accurate and coherent fatigue evaluation can be carried out on each person in real time, the gait fatigue value of the user can be continuously obtained, and the method is simple and easy to implement.
In addition, the gait-based fatigue evaluation method according to the above embodiment of the invention may further have the following additional technical features:
further, in one embodiment of the invention, the fatigue test comprises one or more of a squatting mode related to lower limb fatigue as a mode for acquiring gait fatigue, a squatting mode for measuring speed, and a mode for utilizing exercise and rest circulation.
Further, in one embodiment of the present invention, the acquiring normal and fatigue gait information of the wearer by the various inertial sensors in combination with the gait acquisition shoe comprises: acquiring pressure information of the sole and information of footstep movement of the wearer during walking through the gait acquisition shoes; acquiring motion information of the wearer through the plurality of inertial sensors.
Further, in an embodiment of the present invention, after extracting the gait information of the person to be evaluated, the method further includes: filtering the gait information by using a low-pass filter to remove high-frequency noise signals, carrying out mode identification on the gait information, and extracting the gait information of the walking state.
Further, in an embodiment of the present invention, the segmenting the gait signal into gait cycles includes: an extreme value detection method is adopted, and signals between extreme points are used as signals of a gait cycle; or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
Further, in one embodiment of the present invention, the fatigue is calculated by the formula:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
In order to achieve the above object, a second aspect of the present invention provides a gait-based fatigue evaluation system, including: the system comprises an acquisition module, a fatigue test module and a fatigue test module, wherein the acquisition module is used for designing a fatigue test to acquire the normal gait and the fatigue gait of a person to be evaluated, and acquiring the normal gait and the fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information; the extraction module is used for extracting the gait information of a person to be evaluated, segmenting the gait signal into gait cycles, carrying out abnormity detection and normalization on the acquired periodic signal, detecting and removing the abnormal periodic signal so as to extract a normal walking template and a fatigue walking template of each person; and the calculation module is used for evaluating the motion state of the user in real time, extracting gait information of the person to be evaluated during walking to generate a current gait template, and calculating the distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue degree evaluation result.
According to the gait-based fatigue evaluation system disclosed by the embodiment of the invention, the equipment used for detecting the fatigue is simple, the flow of acquiring the fatigue gait is relatively accurate, and the gait information vectors of each person in the non-fatigue and fatigue states are obtained, so that more accurate and coherent fatigue evaluation can be carried out on each person in real time, the gait fatigue value of the user can be continuously obtained, and the gait fatigue evaluation system is simple and easy to implement.
In addition, the gait-based fatigue evaluation system according to the above-described embodiment of the invention may further have the following additional technical features:
further, in one embodiment of the invention, the fatigue test comprises one or more of a squatting mode related to lower limb fatigue as a mode for acquiring gait fatigue, a squatting mode for measuring speed, and a mode for utilizing exercise and rest circulation.
Further, in an embodiment of the present invention, the collecting module is further configured to collect information of pressure and foot motion of the sole of the foot of the wearer during walking through the gait collecting shoe; acquiring motion information of the wearer through the plurality of inertial sensors.
Further, in an embodiment of the present invention, the method further includes: and the preprocessing module is used for filtering the gait information by using a low-pass filter to remove high-frequency noise signals after extracting the gait information of the person to be evaluated, and carrying out mode identification on the gait information to extract the gait information in a walking state.
Further, in an embodiment of the present invention, the extracting module is further configured to use an extremum detection method to use a signal between the extremum points as a signal of a gait cycle; or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
Further, in one embodiment of the present invention, the fatigue is calculated by the formula:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart of a gait-based fatigue assessment method according to an embodiment of the invention;
fig. 2 is a flowchart of a method for extracting fatigue gait information according to an embodiment of the invention;
FIG. 3 is a schematic diagram of before and after alignment using DTW for time alignment according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating abnormal cycle information after being removed according to the difference degree calculated by the DTW according to the embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a fatigue calculation according to an embodiment of the present invention;
FIG. 6 is a schematic view of another fatigue calculation according to an embodiment of the present invention;
fig. 7 is an exemplary diagram of a gait-based fatigue assessment system according to an embodiment of the invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Hereinafter, a gait-based fatigue evaluation system and method according to an embodiment of the present invention will be described with reference to the accompanying drawings, and first, a gait-based fatigue evaluation method according to an embodiment of the present invention will be described with reference to the accompanying drawings.
Specifically, fig. 1 is a schematic flow chart of a gait-based fatigue assessment method according to an embodiment of the present invention.
As shown in fig. 1, the gait-based fatigue evaluation method includes the following steps:
in step S101, a fatigue test is designed to obtain a normal gait and a fatigue gait of a person to be evaluated, and normal and fatigue gait information of the wearer is collected by a plurality of inertial sensors in combination with gait collection shoes to extract fatigue degree information based on the gait information.
The fatigue test can be designed in one or more ways, such as: the method adopts the squatting and rising related to the fatigue of the lower limbs as a mode for obtaining the fatigue of the gait, adopts a mode of objective measurement of squatting and rising speed measurement instead of subjective evaluation of a user, and utilizes a mode of motion-rest circulation to obtain the long-term fatigue instead of short-term fatigue of the gait.
In one embodiment of the invention, normal and fatigue gait information of a wearer is collected by a variety of inertial sensors in combination with a gait collection shoe, including: the method comprises the steps that pressure information of soles and information of foot step movement of a wearer during walking are collected through gait collection shoes; the wearer's motion information is collected by a variety of inertial sensors.
It can be understood that, by comprehensively considering the difficulty of information acquisition and the correlation between data and gait fatigue, the invention adopts a mode of combining various inertial sensor modules with gait acquisition shoes to acquire gait information.
Specifically, the gait shoe can collect pressure information of the sole during walking, including the main stress points (first to fifth phalanges, heel, thumb, heel, etc.) of the sole, and information of the movement of the sole, including a three-axis accelerometer, a three-axis angular velocity meter and a three-axis magnetometer. The inertial sensor module can also measure the motion information of the current wearing position, and comprises a three-axis accelerometer, a three-axis angular velocity meter and a three-axis magnetometer. These modules can be easily attached to various parts of the body, including the thighs, calves, knees, waist, chest, etc., by means of a fit or strap.
The method for extracting the fatigue gait information will be described below by an example, as shown in fig. 2, specifically as follows:
before the experiment, the user needs to be ensured not to have excessive physical labor within three days before collection, and long-time walking and movement are not carried out on the collection day. The user wears the equipment to walk freely for a period of time, and the normal gait of the user is extracted and stored. Then, the user can do the squatting and rising movement according to the own will, and researches show that the lower limb fatigue generated by the squatting and rising movement is most related to the gait fatigue. Measuring the user's squat speed by video or other means allows the user to rest for 5 to 10 minutes after every period of time, such as 10 minutes, to enable rapid recovery from short-term fatigue. This cycle of exercising and resting is repeated until the user's squat speed drops below a certain percentage, e.g., below 50%, of the initial speed, assuming that it has reached a state of fatigue. The user can freely walk for a period of time by wearing the equipment, and the fatigue gait of the user is extracted and stored.
In step S102, gait information of the person to be evaluated is extracted, gait cycles of the gait signals are divided, anomaly detection and normalization are performed on the acquired cycle signals, and the anomalous cycle signals are detected and removed, so as to extract a normal walking template and a fatigue walking template of each person.
In one embodiment of the present invention, after extracting the gait information of the person to be evaluated, the method further includes: filtering the gait information by using a low-pass filter to remove high-frequency noise signals, carrying out mode identification on the gait information, and extracting the gait information of the walking state.
Specifically, the preprocessing of the gait information includes: 1. preprocessing the extracted gait information, and filtering the signal by a low-pass filter to remove a high-frequency noise signal. 2. The gait is subjected to pattern recognition, and is determined to be in a walking state instead of a standing or static state. One possible implementation is to use a time window and perform cumulative calculation on the energy of gait signals of each dimension in the window, and determine by using a thresholding method or a machine learning (such as a support vector machine or a decision tree), and the signal energy of one or a plurality of dimensions below a threshold can be considered as a static or slightly moving signal rather than a walking state.
Further, in one embodiment of the present invention, the segmenting the gait signal into gait cycles comprises: an extreme value detection method is adopted, and signals between extreme points are used as signals of a gait cycle; or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
Specifically, the gait information is extracted as follows:
first, the gait signal is divided into gait cycles, and an extremum detection method (maximum or minimum of local signals) can be adopted, and the signal between extremum points is taken as a signal of one cycle. The other method is to judge through a step pressure signal, detect the time of the foot from the ground and the time of the foot from the ground again by setting a threshold value in a dividing way, and take the signal between the time of the foot from the ground and the time of the foot from the ground again as a signal of a gait cycle. The abnormal detection and normalization are carried out on the collected periodic signals, the abnormal periodic signals can be detected by a DTW (Dynamic Time Warping) method, the similarity between the collected gait information and the gait information of other periods in each gait period can be detected by the DTW, the gait period information with larger difference is removed, and the information of each gait period is aligned.
And generating a gait template for the collected gait information. The method is characterized in that gait information of a plurality of gait cycles is extracted, normalization is carried out on the gait information to ensure that the gait information of each gait cycle has the same length, then the average value of the gait information is extracted to be used as a gait template, and the gait template can be expressed as a high-dimensional vector mathematically.
The specific process can be expressed as that firstly gait information of N periods is collected:
{M1(t),M2(t),…,Mi(t),…,MN(t)}
wherein M isi(t)＝{mi1(t),mi2(t),…,miF(t) for signals acquired in various dimensions, e.g. mi1(t) is a pressure signal of the foot low sensor 1, mi2(t) is a signal on the acceleration X axis of the sole inertial sensor, and so on.
Because the time of each gait cycle has a certain difference, corresponding to M1(t),M2(t) … have different lengths, and the signals of gait cycle are normalized by difference method to become equal length signals. Furthermore, because the gait information of each cycle is different in time, it is necessary to align the time using DTW, as shown in fig. 3.
The abnormal period information is also removed by using the difference degree calculated by the DTW, as shown in FIG. 4.
The information after processing can be expressed as: { M1(n),M2(n),…,Mi(n),…,MK(n)}；
Template information extraction:
extracting the template for each person to walk normally
Template for walking with fatigue
In step S103, the motion state of the user is evaluated in real time, gait information of the person to be evaluated while walking is extracted to generate a current gait template, and the distance between the current gait template and the normal walking template and the fatigue walking template is calculated to obtain a fatigue evaluation result.
It can be understood that, in the evaluation, the walking state is firstly determined according to the gait pattern recognition, and the gait information is extracted and processed to generate the template.
In particular, the described system may collect gait information of a user in real time for one or several cycles. And performing the same preprocessing and periodic extraction on the gait information to generate a template. And calculating the distance d1 between the current gait template and the non-fatigue walking template and the distance between the current gait template and the fatigue template. Possible ways to calculate the distance include absolute distance, euclidean distance, DTW distance. The advantage of using the DTW distance is that no prior normalization of the current gait template is required. Fatigue is defined as:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
When the user is not tired, d1 is 0, and the fatigue degree is 0; when the user is very tired, d2 is 0, and the degree of fatigue is 100%, as shown in fig. 5.
Since gait is determined by multiple systems such as motor, muscle, brain memory, etc., the gait templates are unique for different persons and have significantly different characteristics from each other, which can be reflected in each person's template
And
the direction in space may be significantly different, and it is difficult for the conventional method using a statistical model or the neural network to consider the difference of each person. The method of the present invention may well include such variability for different people, as shown in fig. 6.
In summary, the method of the embodiment of the invention has the following beneficial effects:
(1) the embodiment of the invention is sufficient and simple for the equipment used for detecting the fatigue degree. The sufficiency is shown in that research shows that the influence of fatigue on gait is very large, so that the gait information is sufficiently extracted to measure the fatigue degree. On the other hand, as for the extraction of gait information, a large number of studies have shown that it is sufficient to extract inertial sensor information attached to the body, particularly the lower limbs, and pressure information of the sole portion for acquiring gait information. The portable gait shoes and the inertial sensors adopted by the scheme are simple in use, do not influence the expression of normal gait of the user, and do not limit the movement and the activity range of the user.
(2) The flow of acquiring the fatigue gait in the embodiment of the invention is relatively accurate. The fatigue scale and the user self-evaluation mode are related to the subjective will and the overall feeling of the user, and the individual difference is large. According to the scheme, the squatting speed of the user is measured, the user is allowed to have a rest at intervals, and the influence of short-term fatigue is eliminated. In addition, research shows that the squatting mode is a mode for effectively obtaining the fatigue of the lower limbs of the user, and the squatting mode has larger correlation with the gait fatigue. The method provided by the embodiment of the invention can be objectively evaluated, and the accuracy is greatly improved correspondingly.
(3) Since each person's gait is unique, which is also true for fatigue gait, it is not accurate to evaluate the change in gait as a whole in a machine learning manner. The characteristics of each person when fatigued are different, for example, the lower leg of some people is fatigued more easily, and the achilles tendon of some people is fatigued more easily, which reflects that the high-dimensional vector obtained by the measured gait information in the scheme can be different obviously in direction. The gait information vector of each person in the fatigue-free and fatigue state is obtained by the scheme of the embodiment, so that the fatigue evaluation of each person is more accurate and coherent, and the gait fatigue value of the user can be continuously obtained.
Next, a gait-based fatigue evaluation system proposed according to an embodiment of the invention will be described with reference to the drawings.
Fig. 7 is a block diagram of a gait-based fatigue assessment system according to an embodiment of the invention.
As shown in fig. 7, the gait-based fatigue evaluation system 10 includes: an acquisition module 100, an extraction module 200 and a calculation module 300.
The system comprises an acquisition module 100, a fatigue test module and a fatigue detection module, wherein the acquisition module 100 is used for designing a fatigue test to acquire a normal gait and a fatigue gait of a person to be evaluated, and acquiring normal and fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information; the extraction module 200 is used for extracting gait information of a person to be evaluated, segmenting gait cycles of gait signals, performing abnormity detection and normalization on the acquired periodic signals, detecting and removing abnormal periodic signals so as to extract a normal walking template and a fatigue walking template of each person; the calculation module 300 is configured to evaluate the motion state of the user in real time, extract gait information of the person to be evaluated during walking to generate a current gait template, and calculate a distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue evaluation result. The system 10 of the embodiment of the invention can perform more accurate and coherent fatigue evaluation on each person, can continuously obtain the gait fatigue value of the user, and is simple and easy to implement.
Further, in one embodiment of the invention, the fatigue test comprises one or more of a squatting mode related to lower limb fatigue as a mode for acquiring gait fatigue, a squatting mode for measuring speed, and a mode for utilizing exercise and rest circulation.
Further, in an embodiment of the present invention, the collecting module 100 is further configured to collect information of pressure and foot motion of the sole of the foot of the wearer during walking through the gait collecting shoe; the wearer's motion information is collected by a variety of inertial sensors.
Further, in an embodiment of the present invention, the system 10 of an embodiment of the present invention further includes: and a preprocessing module. The preprocessing module is used for filtering the gait information by using a low-pass filter to remove high-frequency noise signals after extracting the gait information of the person to be evaluated, and carrying out mode identification on the gait information to extract the gait information of the walking state.
Further, in an embodiment of the present invention, the extracting module 200 is further configured to use an extremum detecting method to use a signal between the extremum points as a signal of a gait cycle; or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
Further, in one embodiment of the present invention, the fatigue is calculated by the formula:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
It should be noted that the foregoing explanation of the embodiment of the gait-based fatigue degree assessment method is also applicable to the gait-based fatigue degree assessment system of this embodiment, and is not repeated here.
According to the gait-based fatigue evaluation system provided by the embodiment of the invention, the equipment used for detecting the fatigue is simple, the flow of acquiring the fatigue gait is relatively accurate, and the gait information vectors of each person in the non-fatigue and fatigue state are obtained, so that more accurate and coherent fatigue evaluation can be carried out on each person in real time, the gait fatigue value of the user can be continuously obtained, and the gait fatigue evaluation system is simple and easy to realize.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A gait-based fatigue assessment method is characterized by comprising the following steps:
designing a fatigue test to acquire normal gait and fatigue gait of a person to be evaluated, and acquiring normal gait and fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information;
extracting gait information of a person to be evaluated, segmenting gait cycles of the gait signals, carrying out abnormity detection and normalization on the acquired periodic signals, detecting and removing abnormal periodic signals so as to extract a normal walking template and a fatigue walking template of each person; and
and evaluating the motion state of the user in real time, extracting gait information of the person to be evaluated during walking to generate a current gait template, and calculating the distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue degree evaluation result.
2. The method of claim 1, wherein the fatigue test comprises one or more of the group consisting of using squats associated with lower limb fatigue as a means to achieve gait fatigue, using squats to measure speed, and using a cycle of exercise and rest.
3. The method of claim 1, wherein said collecting normal and fatigue gait information of the wearer by a plurality of inertial sensors in combination with gait collection shoes comprises:
acquiring pressure information of the sole and information of footstep movement of the wearer during walking through the gait acquisition shoes; collecting motion information of the wearer through the plurality of inertial sensors;
after the gait information of the person to be evaluated is extracted, the method further comprises the following steps:
filtering the gait information by using a low-pass filter to remove high-frequency noise signals, carrying out mode identification on the gait information, and extracting the gait information of the walking state.
4. The method of claim 1, wherein the segmenting the gait signal into gait cycles comprises:
an extreme value detection method is adopted, and signals between extreme points are used as signals of a gait cycle;
or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
5. The method of claim 1, wherein the fatigue is calculated by the formula:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
6. A gait-based fatigue assessment system, comprising:
the system comprises an acquisition module, a fatigue test module and a fatigue test module, wherein the acquisition module is used for designing a fatigue test to acquire the normal gait and the fatigue gait of a person to be evaluated, and acquiring the normal gait and the fatigue gait information of a wearer by combining various inertial sensors with gait acquisition shoes so as to extract fatigue degree information based on the gait information;
the extraction module is used for extracting the gait information of a person to be evaluated, segmenting the gait signal into gait cycles, carrying out abnormity detection and normalization on the acquired periodic signal, detecting and removing the abnormal periodic signal so as to extract a normal walking template and a fatigue walking template of each person; and
and the calculation module is used for evaluating the motion state of the user in real time, extracting gait information of the person to be evaluated during walking to generate a current gait template, and calculating the distance between the current gait template and the normal walking template and the fatigue walking template to obtain a fatigue degree evaluation result.
7. The system of claim 6, wherein the fatigue test comprises one or more of a squat associated with lower limb fatigue as a means to achieve gait fatigue, a squat speed test, and a motion and rest cycle.
8. The system of claim 6, wherein the collection module is further configured to collect information on pressure of the sole and information on foot movement of the wearer during walking through the gait collection shoe; collecting motion information of the wearer through the plurality of inertial sensors; .
After the gait information of the person to be evaluated is extracted, the method further comprises the following steps:
and the preprocessing module is used for filtering the gait information by using a low-pass filter to remove high-frequency noise signals, carrying out mode identification on the gait information and extracting the gait information in a walking state.
9. The system of claim 6, wherein the extraction module is further configured to use an extremum detection method to treat the signal between the extremum points as a signal of one gait cycle; or, the judgment is carried out through the step pressure signal, so that the time for separating and detecting the foot from the ground and the time for separating the foot from the ground again are divided through a preset threshold value, and the signal between the foot separation from the ground and the separation from the ground again is used as the signal of one gait cycle.
10. The system of claim 6, wherein the fatigue is calculated by the formula:
wherein d is1Is the distance between the current gait template and the template of normal walking, d2The distance between the current gait template and the template for fatigue walking.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968205.4A CN112263244A (en) | 2020-09-15 | 2020-09-15 | Gait-based fatigue degree evaluation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010968205.4A CN112263244A (en) | 2020-09-15 | 2020-09-15 | Gait-based fatigue degree evaluation system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112263244A true CN112263244A (en) | 2021-01-26 |
Family
ID=74349002
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010968205.4A Pending CN112263244A (en) | 2020-09-15 | 2020-09-15 | Gait-based fatigue degree evaluation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112263244A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113080996A (en) * | 2021-04-08 | 2021-07-09 | 大同千烯科技有限公司 | Electrocardiogram analysis method and device based on target detection |
| CN113284601A (en) * | 2021-06-10 | 2021-08-20 | 上海大学 | Cloud platform management system based on laser gait detection |
| CN113331829A (en) * | 2021-06-09 | 2021-09-03 | 吉林大学 | Sole information monitoring method and intelligent insole device |
| CN117100255A (en) * | 2023-10-25 | 2023-11-24 | 四川大学华西医院 | Method for judging fall prevention based on neural network model and related products |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105962929A (en) * | 2015-03-13 | 2016-09-28 | 胡渐佳 | Brain wave data sectional-type recording method and device, and brain wave data sectional-type displaying device |
| CN107212890A (en) * | 2017-05-27 | 2017-09-29 | 中南大学 | A kind of motion identification and fatigue detection method and system based on gait information |
| CN108742637A (en) * | 2018-05-31 | 2018-11-06 | 北京辰安科技股份有限公司 | Physical condition detection method and detecting system based on Gait Recognition device |
-
2020
- 2020-09-15 CN CN202010968205.4A patent/CN112263244A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105962929A (en) * | 2015-03-13 | 2016-09-28 | 胡渐佳 | Brain wave data sectional-type recording method and device, and brain wave data sectional-type displaying device |
| CN107212890A (en) * | 2017-05-27 | 2017-09-29 | 中南大学 | A kind of motion identification and fatigue detection method and system based on gait information |
| CN108742637A (en) * | 2018-05-31 | 2018-11-06 | 北京辰安科技股份有限公司 | Physical condition detection method and detecting system based on Gait Recognition device |
Non-Patent Citations (1)
| Title |
|---|
| 刘家锋: "《模式识别》", 31 August 2014, 哈尔滨工业大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113080996A (en) * | 2021-04-08 | 2021-07-09 | 大同千烯科技有限公司 | Electrocardiogram analysis method and device based on target detection |
| CN113331829A (en) * | 2021-06-09 | 2021-09-03 | 吉林大学 | Sole information monitoring method and intelligent insole device |
| CN113331829B (en) * | 2021-06-09 | 2022-08-05 | 吉林大学 | Sole information monitoring method and intelligent insole device |
| CN113284601A (en) * | 2021-06-10 | 2021-08-20 | 上海大学 | Cloud platform management system based on laser gait detection |
| CN117100255A (en) * | 2023-10-25 | 2023-11-24 | 四川大学华西医院 | Method for judging fall prevention based on neural network model and related products |
| CN117100255B (en) * | 2023-10-25 | 2024-01-23 | 四川大学华西医院 | Method for judging fall prevention based on neural network model and related products |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Celik et al. | Gait analysis in neurological populations: Progression in the use of wearables | |
| Taborri et al. | Sport biomechanics applications using inertial, force, and EMG sensors: A literature overview | |
| Yoneyama et al. | Accelerometry-based gait analysis and its application to Parkinson's disease assessment—part 1: detection of stride event | |
| CN112263244A (en) | Gait-based fatigue degree evaluation system and method | |
| EP3468450B1 (en) | Method and system for analyzing human gait | |
| KR102107379B1 (en) | Method for Prediction Frailty Using Triple Axis Motion Meter, Prediction Frailty System using Triple Axis Motion Meter and Wearable Prediction Frailty Device | |
| Muscillo et al. | An adaptive Kalman-based Bayes estimation technique to classify locomotor activities in young and elderly adults through accelerometers | |
| Merchán-Baeza et al. | Reliability in the parameterization of the functional reach test in elderly stroke patients: a pilot study | |
| Hutabarat et al. | Recent advances in quantitative gait analysis using wearable sensors: A review | |
| Panagiota et al. | Assessment of human gait speed and energy expenditure using a single triaxial accelerometer | |
| Lou et al. | IMU-based gait phase recognition for stroke survivors | |
| US20070118044A1 (en) | Method and device for identifying; measuring and analyzing abnormal neurological responses | |
| Lueken et al. | Estimation of stride time variability in unobtrusive long-term monitoring using inertial measurement sensors | |
| Aubol et al. | Tibial acceleration reliability and minimal detectable difference during overground and treadmill running | |
| Jiang et al. | Exploration of gait parameters affecting the accuracy of force myography-based gait phase detection | |
| Wong et al. | Activity recognition and stress detection via wristband | |
| Suriani et al. | Optimal accelerometer placement for fall detection of rehabilitation patients | |
| Perez et al. | A smartphone-based system for clinical gait assessment | |
| Gruber et al. | Monitoring gait complexity as an indicator for running-related injury risk in collegiate cross-country runners: A proof-of-concept study | |
| Dehzangi et al. | Activity detection using fusion of multi-pressure sensors in insoles | |
| Yuwono et al. | Unsupervised segmentation of heel-strike IMU data using rapid cluster estimation of wavelet features | |
| Mandalapu et al. | Developing computational models for personalized ACL injury classification | |
| Zaeni et al. | Classification of the Stride Length based on IMU Sensor using the Decision Tree | |
| Kim et al. | Abnormal Gait Recognition based on Integrated Gait Features in Machine Learning | |
| Qin et al. | A smart phone based gait monitor system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210126 |
|
| RJ01 | Rejection of invention patent application after publication |