CN112201347A - Gait division and feature extraction method based on plantar pressure information - Google Patents

Gait division and feature extraction method based on plantar pressure information Download PDF

Info

Publication number
CN112201347A
CN112201347A CN202011152622.8A CN202011152622A CN112201347A CN 112201347 A CN112201347 A CN 112201347A CN 202011152622 A CN202011152622 A CN 202011152622A CN 112201347 A CN112201347 A CN 112201347A
Authority
CN
China
Prior art keywords
plantar pressure
gait
feature extraction
method based
extraction method
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
Application number
CN202011152622.8A
Other languages
Chinese (zh)
Inventor
韩建达
巫嘉陵
刘培培
于宁波
于洋
朱志中
孙玉波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin Huanhu Hospital (tianjin Neurosurgery Department Institute Tianjin Brain Central Hospital)
Nankai University
Original Assignee
Tianjin Huanhu Hospital (tianjin Neurosurgery Department Institute Tianjin Brain Central Hospital)
Nankai University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin Huanhu Hospital (tianjin Neurosurgery Department Institute Tianjin Brain Central Hospital), Nankai University filed Critical Tianjin Huanhu Hospital (tianjin Neurosurgery Department Institute Tianjin Brain Central Hospital)
Priority to CN202011152622.8A priority Critical patent/CN112201347A/en
Publication of CN112201347A publication Critical patent/CN112201347A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • A61B5/103—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
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Dentistry (AREA)
  • Physiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

A gait division and feature extraction method based on plantar pressure information comprises the steps of carrying out plantar pressure information acquisition on a patient with lower limb movement dysfunction; signal preprocessing is carried out on the collected plantar pressure information; performing gait division based on the pretreated plantar pressure; and extracting conventional kinematic characteristics and plantar pressure index kinetic characteristics. The invention can quantitatively evaluate the variation degree of the plantar pressure among the supporting phases of each gait cycle of a patient in the walking process through the plantar pressure variability index, is favorable for quantitatively evaluating the conditions of unstable posture, uneven force application and the like of the patient, and can provide diagnosis assistance for a doctor in the dynamic characteristics.

Description

Gait division and feature extraction method based on plantar pressure information
Technical Field
The invention relates to the field of digital diagnosis, artificial intelligence and rehabilitation training, in particular to a gait division and feature extraction method based on plantar pressure information.
Background
Muscular problems and axial symptoms in parkinson patients also lead to abnormal gait performance. Gait dysfunction can be used to assess the quality of life, risk of falls and even mortality in parkinson's disease patients. In a patient capable of walking on their own, the unique external force when walking is the Ground Reaction Force (GRF). Therefore, the force measuring insoles are used for recording the GRFs in the vertical direction and analyzing the gaits of the patients, so that the assessment of doctors can be assisted, and most of characteristics for assessing the gaits of the Parkinson's disease are kinematic characteristics such as step frequency, pace speed and the like.
Normal intracranial pressure hydrocephalus (NPH) refers to a group of special clinical syndromes of normal intracranial pressure with ventricular enlargement, hypomnesis, intelligence deterioration, gait instability and urinary incontinence. Gait instability is the first symptom to appear first and occasionally may occur as a decline in intelligence, and following urinary incontinence, gait instability may manifest itself as a slight imbalance. Different from the gait of the Parkinson disease, the gait is the walking rhythm is not changed, and the gait is not flustered and appears in all cases. Often, the patient has a history of falling down, and the serious patient is marked by the inability to walk or stand. The lumbar puncture is an important step for checking the normal-pressure hydrocephalus, after 20-30ml of cerebrospinal fluid is discharged by the patient after the lumbar puncture, the symptoms are obviously improved, the curative effect can last for 12-36 hours, the obvious pace speed is obviously improved after the lumbar puncture, and the like, and quantitative gait analysis is an important basis for evaluating the lumbar puncture effect of the patient.
Disclosure of Invention
The invention provides a gait division and feature extraction method based on plantar pressure information to overcome the defects of the prior art. The method can realize the feature comparison of the same patient in different periods through pretreatment, gait division and feature extraction, can obtain continuous feature observation, and is beneficial to diagnosis of doctors. And carrying out quantitative analysis on the plantar pressure variability in the gait cycle of the subject.
The technical scheme of the invention is as follows: a gait division and feature extraction method based on plantar pressure information comprises the steps of
a. Acquiring plantar pressure information of a patient with lower limb motor dysfunction;
b. signal preprocessing is carried out on the collected plantar pressure information;
c. performing gait division based on the pretreated plantar pressure;
d. and extracting conventional kinematic characteristics and plantar pressure index kinetic characteristics.
Compared with the prior art, the invention has the beneficial effects that:
the invention realizes gait division and feature extraction through signal preprocessing, can realize feature comparison of the same patient in different periods, can obtain continuous feature observation, and is beneficial to diagnosis of doctors. And carrying out quantitative analysis on the plantar pressure variability in the gait cycle of the subject. The invention can realize the extraction of the traditional kinematics characteristics and the extraction of the pressure variability index dynamics characteristics. Through the plantar pressure variability index, the plantar pressure variation degree among the support phases of each gait cycle of a patient in the walking process can be quantitatively evaluated, the quantitative evaluation of the conditions of unstable posture, uneven force application and the like of the patient is facilitated, and diagnosis assistance can be provided for a doctor in the dynamic characteristics.
The gait division and feature extraction method has important early diagnosis and treatment significance for PD and iNPH patients. Gait analysis is systematic research on human body movement, and objective and accurate kinematic analysis and kinetic analysis have important significance for doctors to evaluate the life quality of Parkinson patients.
The technical scheme of the invention is further explained by combining the drawings and the embodiment:
drawings
Fig. 1 is a flow chart of gait segmentation and feature extraction according to the invention.
Detailed Description
With reference to fig. 1, a gait division and feature extraction method based on plantar pressure information according to this embodiment includes:
a. acquiring plantar pressure information of a patient with lower limb motor dysfunction;
b. signal preprocessing is carried out on the collected plantar pressure information;
c. performing gait division based on the pretreated plantar pressure;
d. and extracting conventional kinematic characteristics and plantar pressure index kinetic characteristics.
Example 1, this example further defines: and step a, adopting a wireless transmission type sole pressure acquisition insole to acquire sole pressure information. The wireless transmission force measuring insole is adopted, the pressure acquisition of soles in various environments can be adapted, psychological suggestion can be avoided by the ultrathin force measuring insole and the low-weight data box, and the influence on gait is reduced.
Embodiment 2 and this embodiment are different from embodiment 1 in that: and the signal preprocessing in the step b is to filter by using a low-pass filter with the cut-off frequency of 15-25Hz, remove noise and normalize the amplitude of the plantar pressure signal in the vertical direction through the collected weight information of the patient.
Example 3, this example is a further limitation of example 2: the amplitude normalization processing of the plantar pressure signal refers to dividing the filtered pressure signal by the body weight of the patient, and calculating by the following formula:
Figure BSA0000222755220000021
wherein x (m) is the filtered pressure signal in newtons; w is the patient's weight in newtons; and x' (m) is the plantar pressure signal after the amplitude normalization processing.
Example 4, this example is a gait division based on example 2 and example 3, first planning a periodic movement, and the human gait is a periodic movement, and when the heel of the lower limb of one side touches the ground, it is regarded as the beginning of a gait cycle, and the side foot is known to touch the ground, and the cycle is continued. When the plantar pressure signal is analyzed off line, firstly, data preprocessing is carried out, a threshold value for switching the support phase and the swing phase is set according to the weight of a subject, the period which is greater than the threshold value is the support phase, the period which is less than the threshold value is the swing phase, one gait cycle is from the start of switching the swing phase to the support phase to the end of switching the swing phase to the support phase at the next time. The gait division means that the foot sole pressure in the swing phase is zero according to different characteristics of the foot sole pressure in the processes of the support phase and the swing phase of the lower limbs of the human body, the foot sole pressure in the support phase has an index, the walking cycle of the human body is divided, and time normalization processing is carried out according to the percentage of the gait cycle. Because of the human body specificity, the gait cycles are changed and are not completely the same, the time normalization processing is carried out according to the gait cycle percentage, and the time normalization processing can be carried out according to the sampling frequency and the support phase duration as the support phase time is not completely the same in each gait when the time normalization processing is carried out.
Embodiment 5 and this embodiment provide extraction of pressure variability indexes on the basis of embodiment 4 and embodiment 3, wherein the extraction of kinetic characteristics in step d refers to extraction of support phase pressure variability indexes, the mean value and the standard deviation of the time corresponding to the gait cycle percentage in each gait cycle are calculated by normalizing the amplitude and time of the plantar pressure signal, and finally, the sole pressure variability indexes are obtained by averaging all the standard deviations to serve as the kinetic characteristics.
The pressure variability index is reflected by:
firstly, the average plantar pressure of all gait cycles at the same support phase moment is calculated:
Figure BSA0000222755220000031
secondly, calculating the standard deviation of the corresponding support facies percentage in all gait cycles, and obtaining 100 standard deviations with the range of 0-100% after calculation;
Figure BSA0000222755220000032
then, averaging all 100 standard deviations of 0-100% of the entire supporting phase to obtain the plantar pressure variation index:
Figure BSA0000222755220000033
in the formula, n is the number of the divided gait cycles, j is the percentage of the support phase, and the range is 0-100%; f. ofijThe plantar pressure value at position j for the corresponding i-th gait cycle,
Figure BSA0000222755220000041
mean plantar pressure, SDjIs the standard deviation of the measured data to be measured,
Figure BSA0000222755220000042
is the variation index of plantar pressure.
Through the plantar pressure variation index, the plantar pressure variation degree among the support phases of each gait cycle of a patient in the walking process can be quantitatively evaluated. The device is beneficial to quantitatively evaluating the conditions of unstable posture, uneven force application and the like of the patient, and can provide diagnosis assistance for doctors in the dynamic characteristics.
Embodiment 6, this embodiment is a further definition of the kinematic feature extraction of embodiment 1 and/or embodiment 4: the kinematic feature extraction is to calculate according to the time information of the divided gait cycles and extract the characteristics of the step frequency, the gait cycles, the support phase ratio and the swing phase ratio. Through plantar pressure information, the above kinematic features can be extracted.
Example 7, based on the description of the above embodiments and examples, a gait segmentation and feature extraction method based on plantar pressure information in a specific environment is provided;
the signal source is a pair of lightweight force-measuring insoles, the thickness of each insole is not more than 1.2mm, 100 pressure-sensitive sensors are contained in the whole insole, and the surface area of each pressure-sensitive sensor is less than 6mm multiplied by 8 mm. The insole is matched with a data box, the volume of the data box is 6.5cm multiplied by 4cm multiplied by 1.5cm, the weight of the data box is 43 grams, and a rechargeable lithium polymer battery with 3.7 volts is arranged in the data box. The small and light box is worn on the ankle, and the influence on a patient can be reduced to the maximum extent. Plantar pressure information was transmitted from the data acquisition box to the computer via WiFi, with a sampling frequency of 100Hz, a maximum measurement of 100N, and a resolution of 0.1N/cm2 for each pressure sensitive sensor.
And (3) preparing for wearing equipment and the like, and informing the testee of the walking task, wherein the task paradigm is not fixed and basically requires that the testee has a straight walking task with at least 10 m. In the process of pressure data acquisition, the field is emptied, no acousto-optic interference is kept, and the influence on the gait of the testee is avoided.
The human gait is a cyclic motion, when the heel of the lower limb on one side touches the ground, it is considered as the beginning of a gait cycle, knowing that the foot on that side touches the ground, and the cycle is continued. When the plantar pressure signal is analyzed off line, the data are preprocessed firstly. A low-pass filter with the cut-off frequency of 25Hz is used for original data to remove high-frequency noise in the signal. Then, a threshold value for switching the support phase and the swing phase is set according to the body weight of the subject, and the period greater than the threshold value is considered as the support phase, and the period less than the threshold value is considered as the swing phase. One gait cycle is from the beginning of the swing phase to the support phase to the end of the next swing phase to the support phase.
And then, carrying out amplitude normalization processing on the plantar pressure signal according to the weight of the patient, wherein the specific method is to divide the weight of the patient by the acquired signal. As shown in the following formula, x (m) is the collected sole pressure signal of the patient, and the unit of the filtered signal is Newton; m is the length of the collected plantar pressure signal data; w is the patient's weight in newtons; and x' (m) is the plantar pressure signal after the amplitude normalization processing.
Figure BSA0000222755220000051
A threshold value λ between the support phase and the swing phase is set according to the patient's body weight, and the threshold value λ is set to 5% in this embodiment, according to the experience of using the sole pressure measuring insole. The time when the plantar pressure is greater than λ is considered as the support phase, and the others are considered as the swing phase.
And extracting the support phase, wherein the time of the support phase is not completely the same in each gait, so the time normalization is carried out according to the sampling frequency and the time length of the support phase. The normalization method is to perform cubic spline interpolation on the extracted support phase, and the number of data points of all gait cycle support phases after interpolation is the same and is defined as 0-100%.
And then, traditional kinematic feature extraction is carried out, such as step frequency, gait cycle, support phase proportion, swing phase proportion and the like, and the features can be calculated and extracted according to the time information of the gait cycle divided before.
Extracting the dynamic characteristics of the pressure variability index, and after carrying out amplitude normalization and time normalization on the supporting phase, calculating the following steps:
firstly, solving the average plantar pressure of all gait cycles at the same support phase moment;
Figure BSA0000222755220000052
secondly, calculating the standard deviation of the corresponding support facies percentage in all gait cycles, and obtaining 100 standard deviations with the range of 0-100% after calculation;
Figure BSA0000222755220000053
then, averaging all 100 standard deviations of 0-100% of the whole supporting phase to obtain a plantar pressure variation index;
Figure BSA0000222755220000054
in the formula, n is the number of the divided gait cycles, j is the percentage of the support phase, and the range is 0-100%; f. ofijThe plantar pressure value at position j for the corresponding i-th gait cycle,
Figure BSA0000222755220000055
mean plantar pressure, SDjIs the standard deviation of the measured data to be measured,
Figure BSA0000222755220000056
is the variation index of plantar pressure.
Through the plantar pressure variation index, the plantar pressure variation degree among the support phases of each gait cycle of a patient in the walking process can be quantitatively evaluated. The device is beneficial to quantitatively evaluating the conditions of unstable posture, uneven force application and the like of the patient, and can provide diagnosis assistance for doctors in the dynamic characteristics.
The present invention is not limited to the above embodiments, and those skilled in the art can make various changes and modifications without departing from the scope of the invention.

Claims (8)

1. A gait division and feature extraction method based on plantar pressure information is characterized by comprising the following steps: it comprises
a. Acquiring plantar pressure information of a patient with lower limb motor dysfunction;
b. signal preprocessing is carried out on the collected plantar pressure information;
c. performing gait division based on the pretreated plantar pressure;
d. and extracting conventional kinematics characteristics and plantar pressure variability index dynamics characteristics.
2. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 1, wherein: and (b) acquiring sole pressure information by adopting a wireless transmission type sole pressure acquisition insole in the step a.
3. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 2, wherein: and the signal preprocessing in the step b is to filter by using a low-pass filter with the cut-off frequency of 15-25Hz, remove noise and normalize the amplitude of the plantar pressure signal in the vertical direction through the collected weight information of the patient.
4. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 3, wherein: the plantar pressure signal amplitude normalization processing means that the filtered pressure signal is divided by the body weight of a patient, and the plantar pressure signal amplitude normalization processing is calculated by the following formula:
Figure FSA0000222755210000011
wherein x (m) is the filtered pressure signal in newtons; w is the patient's weight in newtons; and x' (m) is the plantar pressure signal after the amplitude normalization processing.
5. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 4, wherein: in the step c, a threshold value for switching the support phase and the swing phase is set according to the body weight of the subject, the period which is greater than the threshold value is the support phase, the period which is less than the threshold value is the swing phase, the gait division refers to the division of the walking cycle of the human body according to different characteristics of the plantar pressure in the processes of the support phase and the swing phase of the lower limbs of the human body, and the time normalization processing is carried out according to the percentage of the gait cycle.
6. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 5, wherein: the dynamic characteristic extraction in the step d is to support a phase pressure variability index, the amplitude and time normalization is carried out on the plantar pressure signals, the average value and the standard deviation calculation are carried out on the moments corresponding to gait cycle percentages in each gait cycle, and finally the average value of all standard deviations is removed to obtain the plantar pressure variability index which is used as the dynamic characteristic.
7. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 6, wherein: the plantar pressure variability index is reflected by:
firstly, solving the average plantar pressure of all gait cycles at the same support phase moment;
Figure FSA0000222755210000021
secondly, calculating the standard deviation of the corresponding support facies percentage in all gait cycles, and obtaining 100 standard deviations with the range of 0-100% after calculation;
Figure FSA0000222755210000022
then, averaging all 100 standard deviations of 0-100% of the whole supporting phase to obtain a plantar pressure variation index;
Figure FSA0000222755210000023
in the above formula, n is the number of divided gait cycles, and j is the number of support phasesThe content of the component is 0-100%; f. ofijThe plantar pressure value at position j for the corresponding i-th gait cycle,
Figure FSA0000222755210000024
mean plantar pressure, SDjIs the standard deviation of the measured data to be measured,
Figure FSA0000222755210000025
is the variation index of plantar pressure.
8. The gait segmentation and feature extraction method based on plantar pressure information as claimed in claim 5, wherein: the kinematic feature extraction is to calculate according to the time information of the divided gait cycles and extract the characteristics of the step frequency, the gait cycles, the support phase ratio and the swing phase ratio.
CN202011152622.8A 2020-10-16 2020-10-16 Gait division and feature extraction method based on plantar pressure information Pending CN112201347A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011152622.8A CN112201347A (en) 2020-10-16 2020-10-16 Gait division and feature extraction method based on plantar pressure information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011152622.8A CN112201347A (en) 2020-10-16 2020-10-16 Gait division and feature extraction method based on plantar pressure information

Publications (1)

Publication Number Publication Date
CN112201347A true CN112201347A (en) 2021-01-08

Family

ID=74011350

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011152622.8A Pending CN112201347A (en) 2020-10-16 2020-10-16 Gait division and feature extraction method based on plantar pressure information

Country Status (1)

Country Link
CN (1) CN112201347A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113658707A (en) * 2021-08-26 2021-11-16 华南理工大学 Foot varus angle detection modeling method and system
CN115553757A (en) * 2022-12-06 2023-01-03 深圳市第二人民医院(深圳市转化医学研究院) Method and equipment for intelligently screening effective ground reaction force in gait process

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104598722A (en) * 2014-12-25 2015-05-06 中国科学院合肥物质科学研究院 Parkinson patient walking ability evaluation method based on gait time-space parameters and three-dimensional force characteristics
CN110299203A (en) * 2019-08-12 2019-10-01 电子科技大学 A kind of human body abnormal gait recognition methods based on smart phone

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104598722A (en) * 2014-12-25 2015-05-06 中国科学院合肥物质科学研究院 Parkinson patient walking ability evaluation method based on gait time-space parameters and three-dimensional force characteristics
CN110299203A (en) * 2019-08-12 2019-10-01 电子科技大学 A kind of human body abnormal gait recognition methods based on smart phone

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
周安艳等: "视频压力式步态分析系统对正常学龄前儿童的步态分析", 《中国临床康复》 *
李文康等: "基于足底压力的行走能力的测试与评价方法", 《电子测量技术》 *
李飞: "基于表面肌电信号的小儿脑瘫步态肌肉协同分析", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 *
许胜强: "帕金森病患者步态障碍定量评估及量化分级评估方法研究", 《中国博士学位论文全文数据库 医药卫生科技辑》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113658707A (en) * 2021-08-26 2021-11-16 华南理工大学 Foot varus angle detection modeling method and system
CN115553757A (en) * 2022-12-06 2023-01-03 深圳市第二人民医院(深圳市转化医学研究院) Method and equipment for intelligently screening effective ground reaction force in gait process

Similar Documents

Publication Publication Date Title
Di Nardo et al. Assessment of the activation modalities of gastrocnemius lateralis and tibialis anterior during gait: a statistical analysis
CN109480858B (en) Wearable intelligent system and method for quantitatively detecting motor retardation symptoms of Parkinson patients
Hu et al. Benchmark datasets for bilateral lower-limb neuromechanical signals from wearable sensors during unassisted locomotion in able-bodied individuals
KR102556074B1 (en) Wearable Technologies for Joint Health Assessment
Allseits et al. The development and concurrent validity of a real-time algorithm for temporal gait analysis using inertial measurement units
TWI498846B (en) Gait analysis method and gait analysis system
Kugler et al. Automatic recognition of Parkinson's disease using surface electromyography during standardized gait tests
CN112201347A (en) Gait division and feature extraction method based on plantar pressure information
WO2017091736A1 (en) Processing physiological electrical data for analyte assessments
Greene et al. Adaptive estimation of temporal gait parameters using body-worn gyroscopes
Oubre et al. Estimating ground reaction force and center of pressure using low-cost wearable devices
CN111329484A (en) Diabetic foot risk early warning device based on plantar pressure information time-space domain characteristics
Reichmuth et al. A non-invasive wearable bioimpedance system to wirelessly monitor bladder filling
Godiyal et al. Analysis of force myography based locomotion patterns
Bonomi et al. Detecting episodes of brady-and tachycardia using photo-plethysmography at the wrist in free-living conditions
Jiang et al. Exploration of gait parameters affecting the accuracy of force myography-based gait phase detection
Kakarla et al. Accuracy enhancement of total force by capacitive insoles
CN109331406B (en) Lower limb movement capacity quantitative evaluation method and system based on treadmill force platform
CN107427261B (en) Wrist stiffness evaluation device for deep brain stimulation surgery
Nacpil et al. Feasibility assessment of transfer functions describing biomechanics of the human lower limb during the gait cycle
Chee et al. Gait acceleration-based diabetes detection using hybrid deep learning
Pourmoghaddam et al. Identification of changing lower limb neuromuscular activation in PARKINSon's disease during treadmill gait with and without levodopa using a nonlinear analysis index
Richer et al. Unobtrusive real-time heart rate variability analysis for the detection of orthostatic dysregulation
Lo et al. Bayesian analysis of sub-plantar ground reaction force with BSN
Negi et al. Gait analysis-based identification of neurodegenerative diseases using machine learning techniques

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