WO2018230787A1 - Device and method for analyzing gait by using acceleration sensor worn on ankle - Google Patents
Device and method for analyzing gait by using acceleration sensor worn on ankle Download PDFInfo
- Publication number
- WO2018230787A1 WO2018230787A1 PCT/KR2017/013842 KR2017013842W WO2018230787A1 WO 2018230787 A1 WO2018230787 A1 WO 2018230787A1 KR 2017013842 W KR2017013842 W KR 2017013842W WO 2018230787 A1 WO2018230787 A1 WO 2018230787A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- gait
- acceleration sensor
- patient
- feature
- ankle
- Prior art date
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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0002—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network
- A61B5/0015—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system
- A61B5/0024—Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network characterised by features of the telemetry system for multiple sensor units attached to the patient, e.g. using a body or personal area network
-
- 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
-
- 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
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6829—Foot or ankle
-
- 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
- A61B5/683—Means for maintaining contact with the body
- A61B5/6831—Straps, bands or harnesses
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- 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
- A61B5/7271—Specific aspects of physiological measurement analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
- A61B2562/02—Details of sensors specially adapted for in-vivo measurements
- A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
Definitions
- the present invention relates to a gait analysis device and method using an acceleration sensor worn on the ankle, more specifically gait using an acceleration sensor worn on the ankle that can analyze the gait of a patient having difficulty gait.
- An analysis device and method is provided.
- the gait may be used as a measure to check basic body condition or to find signs of abnormality in the body. Therefore, by analyzing a person's gait, it is possible to examine the state of the body or detect an abnormality in the body early.
- the gait analysis method uses image processing, flow sensors, and wearable sensors.
- Patent Document 1 Korean Patent Publication No. 2012-0085064 (2012.07.31 publication)
- the present invention has been proposed to solve the above problems, an ankle that is attached to the acceleration sensor to the ankle of the patient having difficulty walking, ankle that can analyze the gait of the patient using the signal obtained from the acceleration sensor It is an object of the present invention to provide a gait analysis device and method using an acceleration sensor worn on the.
- Gait analysis device using an acceleration sensor worn on the ankle for achieving the above object, the signal according to the gait of the patient from the acceleration sensor included in the band worn on the patient's ankle Receiving unit for receiving; And preprocessing the signal according to the gait of the received patient, extracting a feature from the preprocessed signal, calculating the energy of the gait using the extracted feature, and calculating a correlation coefficient for the gait characteristics.
- Receiving unit for receiving; And preprocessing the signal according to the gait of the received patient, extracting a feature from the preprocessed signal, calculating the energy of the gait using the extracted feature, and calculating a correlation coefficient for the gait characteristics.
- an analysis unit for analyzing the gait of the for analyzing the gait of the.
- the analysis unit a pre-processing unit for removing noise from the signal; And a feature extractor which extracts a feature on a time domain, a feature on a frequency domain, and an energy feature from the signal from which the noise is removed.
- the preprocessor may remove noise from the signal using a digital low pass filter.
- the feature extractor may extract a feature on a time domain by calculating a vertical component from the preprocessed signal.
- the feature extractor may extract a feature in a frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform.
- the feature extractor may calculate the energy value of the gait by Equation X, and calculate a correlation coefficient for the gait characteristic by Equation Y.
- x i are values converted into a frequency band using an FFT
- w is a window size
- x and y are the values calculated by the energy formula for the walking of the left foot and the right foot
- cov (x, y) is the covariance of x and y
- P is a correlation coefficient value of x and y.
- Step analysis method in the gait analysis device using an acceleration sensor worn on the ankle for achieving the above object, from the acceleration sensor included in the band worn on the patient's ankle
- Receiving a signal according to a gait Preprocessing the signal according to the gait of the received patient; Extracting features from the preprocessed signal; And calculating the energy of the gait using the extracted features and calculating a correlation coefficient for the characteristics of the gait.
- the digital low pass filter may be used to remove noise from the signal.
- Extracting a feature from the preprocessed signal includes: extracting a feature in a time domain by calculating a vertical component in the preprocessed signal; And extracting a feature on a frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform.
- the energy value of the gait is calculated by Equation X
- the gait characteristic is calculated by Equation Y.
- the correlation coefficient can be calculated.
- x i are values converted into a frequency band using an FFT
- w is a window size
- x and y are the values calculated by the energy formula for the walking of the left foot and the right foot
- cov (x, y) is the covariance of x and y
- P is a correlation coefficient value of x and y.
- the gait analysis algorithm can analyze the gait of the patient more accurately.
- FIG. 1 is a view showing a schematic configuration of a gait analysis system according to an embodiment of the present invention
- FIG. 2 is a view showing a stance and a swing according to an embodiment of the present invention
- FIG. 3 is a view showing a schematic configuration of a gait analysis device according to an embodiment of the present invention
- Figure 4 is a diagram showing the flow of the gait analysis method according to an embodiment of the present invention.
- FIG. 1 is a view showing a schematic configuration of a gait analysis system according to an embodiment of the present invention
- Figure 2 is a view showing a stance and a swing according to an embodiment of the present invention
- Figure 3 is a view of the present invention It is a figure which shows schematic structure of the gait analyzer according to the embodiment.
- the gait analysis system includes an acceleration sensor 100 and a gait analyzer 200 attached to an ankle of a patient.
- the patient may be a patient suffering from a neurological disease such as Parkinson's disease.
- a signal generated by the acceleration sensor 100 may be transmitted to the gait analyzer 200.
- the network may be a wireless communication such as Bluetooth.
- the acceleration sensor 100 is for acquiring a signal according to a patient's walking and may be included in a band. Accordingly, the patient may wear the band on the ankle, so that the acceleration sensor 100 may be attached to the ankle of the patient. In this case, as the band is worn on both ankles of the patient, the acceleration sensor 100 included in the band may acquire a signal according to the patient's walking.
- the signal according to the walking of the patient may be a signal generated according to the walking of the patient.
- the acceleration sensor 100 may be a very small Attitude Heading Reference System (AHRS) module having a three-axis acceleration sensor, a three-axis gyroscope, and a three-axis geomagnetic sensor.
- AHRS Attitude Heading Reference System
- the acceleration sensor 100 may support data update and output speeds up to 1000 Hz, and output a pure acceleration value from which gravity components are removed.
- the acceleration sensor 100 according to the present embodiment may be EBIMU-9DOFV2 manufactured by E2BOX.
- the acceleration sensor 100 may include three data output modes, such as an ASCII output mode, a hex (binary) output mode, and a polling output mode. In this embodiment, it is assumed that the ASCII output mode is used as the data output mode.
- the operating power of the three-axis acceleration sensor 100 may use a 4.5V power supplied from a battery (not shown).
- a digital low pass fitter designed inside the sensor may be used to remove noise included in the signal output from the acceleration sensor 100.
- the acceleration sensor 100 since the acceleration sensor 100 is small, it takes up less space and can reduce discomfort for the patient wearing the band.
- the gait analyzing apparatus 200 may analyze the gait of the patient using a signal according to the walking of the patient received from the acceleration sensor 100.
- the gait analyzing apparatus 200 includes a receiver 210 and an analyzer 230.
- the receiver 210 receives a signal according to the walking of the patient from the acceleration sensor 100.
- the signal according to the walking of the patient may be a signal according to the walking of the patient.
- the receiver 210 receives a signal according to the walking of the patient from the acceleration sensor 100 included in the band worn on the ankle of the patient.
- the analysis unit 230 may analyze the gait of the patient using a signal according to the walking of the patient received by the receiver 210.
- the analyzer 230 preprocesses the signal according to the walking of the patient, extracts a feature from the preprocessed signal, and uses the extracted feature to calculate a correlation coefficient for the energy of the gait and the characteristics of the gait. Calculate to analyze the patient's gait.
- the analyzer 230 may include a preprocessor 231 and a feature extractor 233.
- the preprocessor 231 may perform preprocessing by removing noise from a signal according to a patient's walking.
- the preprocessor 231 may remove noise from the signal using a digital low pass filter.
- the noise may be noise in a high-frequency noise band.
- a moving average filter may be used to give an overall smoothing effect of the signal.
- the signal may be a signal according to the gait of the patient measured by the acceleration sensor 100.
- the signal can be measured by the acceleration sensor 100 included in the band worn on the left and right ankles of the patient, the signal is transmitted to the gait analysis device 200 through a network to be stored in a separate storage It may be.
- the gait analysis device 200 may be a smart phone with a gait analysis application. In this case, when the gait analysis device 200 is a smartphone, a signal may be transmitted by Bluetooth communication.
- the feature extractor 233 may extract a feature from a signal from which noise is removed by the preprocessor 231.
- the feature extractor 233 may include a feature on the time domain, a feature on the frequency domain, and an energy feature on the signal from which the noise is removed by the preprocessor 231. Can be extracted.
- the feature extractor 233 may extract a feature on a time domain by calculating a vertical component from a preprocessed signal.
- the reason for extracting the feature on the time domain is to divide a human's gait into a stance and a swinging step.
- a human gait consists of a stance and a swing. Stance refers to the foot touching the ground, and swinging refers to the foot being held up until one foot hits the ground again.
- an event that occurs at the start of a stance phase is called a heel strike
- an event that occurs at the start of a swing phase (or the end of a stance phase) is heeled off. off and / or toe off.
- the feature extractor 233 may find a heel off and / or a toe off and a heel strike point, divide the stance and the swing, and the heel off And / or compute the vertical component from the signal obtained by the acceleration sensor 100 to find the toe off and heel strike points.
- the vertical component may be calculated by Equation 1 below.
- Mx ', my' and mz ' are the mean values for the intervals sampled on each axis.
- x ', y', z ' is the acceleration signal value coming from the three-axis acceleration sensor. In this case, it is a vector value of a specific point in the sampled section, and N is the length of the sampled section.
- the characteristics of the gait such as movement time, stride length, period, speed, etc. may be calculated based on heel off and / or toe off and heel strike.
- the feature extractor 233 may extract a feature in the frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform (FFT).
- the feature extractor 233 may convert a calculated vertical component into a frequency band by using a fast Fourier transform in order to check the value of the frequency band represented by gait between normal and abnormal persons. In this case, various frequency characteristics may appear according to the walking style of the person according to the converted result.
- the feature extractor 233 may calculate an energy value of the gait to estimate a correlation coefficient of the gait of the left and right feet of the patient.
- the energy value of the gait can be calculated by Equation 2 below.
- x i is a value converted to the frequency band using the FFT
- w is the window size
- the overlapping setting so as not to miss the components of the gait according to the walking characteristics of the patient.
- the correlation may be calculated by Equation 3 below.
- x and y are the values calculated by the energy formula for the walking of the left foot and the right foot
- cov (x, y) is the covariance of x and y
- P is a correlation coefficient value of x and y.
- Figure 4 is a diagram showing the flow of the gait analysis method according to an embodiment of the present invention.
- the gait analyzing apparatus 200 receives a signal according to the gait of the patient from the acceleration sensor 100 included in the band worn on the ankle of the patient (S410).
- the gait analyzing apparatus 200 preprocesses the signal by using the signal according to the gait of the patient (S420).
- the gait analyzing apparatus 200 may perform preprocessing by removing noise from a signal according to a patient's walking. In this case, the gait analyzer 200 may remove noise from a signal using a digital low pass filter.
- the gait analyzing apparatus 200 extracts a feature from a preprocessed signal (S430).
- the gait analyzer 200 may extract a feature on a time domain and a feature on a frequency domain from a signal from which noise is removed.
- the gait analyzer 200 may extract a feature on a time domain by calculating a vertical component from a preprocessed signal. In this case, the vertical component may be calculated by Equation 1 described above.
- the gait analyzing apparatus 200 may extract a feature on the frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform (FFT).
- FFT fast Fourier transform
- the gait analyzing apparatus 200 calculates the energy of the gait using the extracted feature and calculates a correlation coefficient with respect to the gait of the gait (S440).
- the energy value of the gait may be calculated by Equation 2 described above, and the correlation may be calculated by Equation 3 described above.
- Methods according to an embodiment of the present invention may be implemented in the form of program instructions that may be implemented as an application or executed through various computer components, and may be recorded on a computer-readable recording medium.
- the computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination.
- Program instructions recorded on the computer-readable recording medium may be those specially designed and constructed for the present invention, and may be known and available to those skilled in the computer software arts.
- Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs, DVDs, and magneto-optical media such as floptical disks. media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.
- Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.
- the hardware device may be configured to operate as one or more software modules to perform the process according to the invention, and vice versa.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a device and method for analyzing a gait by using an acceleration sensor worn on an ankle. A device for analyzing a gait by using an acceleration sensor worn on an ankle according to an aspect of the present invention comprises: a reception unit for receiving a signal according to the gait of a patient from an acceleration sensor included in a band worn on the ankle of the patient; and an analysis unit for preprocessing the received signal according to the gait of the patient, extracting features from the preprocessed signal, and calculating the energy of the gait and the correlation coefficient for characteristics of the gait by using the extracted features, so as to analyze the gait of the patient.
Description
본 발명은 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치 및 방법에 관한 것으로, 더욱 상세하게는 걸음걸이에 어려움을 겪는 환자의 걸음걸이를 분석할 수 있는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치 및 방법에 관한 것이다. The present invention relates to a gait analysis device and method using an acceleration sensor worn on the ankle, more specifically gait using an acceleration sensor worn on the ankle that can analyze the gait of a patient having difficulty gait. An analysis device and method.
본 출원은 2017년 6월 15일에 출원된 한국특허출원 제10-2017-0075982호에 기초한 우선권을 주장하며, 해당 출원의 명세서 및 도면에 개시된 모든 내용은 본 출원에 원용된다.This application claims priority based on Korean Patent Application No. 10-2017-0075982 filed on June 15, 2017, and all the contents disclosed in the specification and drawings of the application are incorporated in this application.
걷기는 인간의 가장 기본적인 행동 중 하나이다. 이때, 걸음걸이는 기본적인 몸의 상태를 검사하거나 몸의 이상 징후를 찾기 위한 척도로 사용되기도 한다. 따라서, 사람의 걸음걸이를 분석함으로써 몸의 상태를 검사하거나 몸의 이상 징후를 조기에 발견할 수 있다.Walking is one of the most basic human behaviors. At this time, the gait may be used as a measure to check basic body condition or to find signs of abnormality in the body. Therefore, by analyzing a person's gait, it is possible to examine the state of the body or detect an abnormality in the body early.
이때, 걸음걸이 분석 방법은 크게 이미지 프로세싱(image processing), 플로우 센서(floor sensors) 그리고, 웨어러블 센서(wearable sensors)를 이용하게 된다. At this time, the gait analysis method uses image processing, flow sensors, and wearable sensors.
한편, 파킨슨 병과 같은 신경계질환 환자들을 대상으로 걸음걸이 특징을 추출하는 것은 매우 중요하다. 즉, 걸음걸이에 불편함을 느끼는 신경계질환 환자들이 수술을 받고 난 후의 회복 과정을 보기 위한 하나의 방법으로 걸음걸이를 분석하기도 한다.On the other hand, it is very important to extract the gait characteristics in patients with neurological diseases such as Parkinson's disease. In other words, patients with nervous system disorders who feel uncomfortable walking may analyze gait as a way to see the recovery process after surgery.
따라서, 보다 정확하게 신경계질환 환자들의 걸음걸이를 분석하기 위한 기술에 대한 연구가 필요한 실정이다. Therefore, there is a need for research on technology for more accurately analyzing the gait of patients with neurological diseases.
(특허문헌 1) 한국공개특허 제2012-0085064호(2012.07.31 공개)(Patent Document 1) Korean Patent Publication No. 2012-0085064 (2012.07.31 publication)
본 발명은 상기와 같은 문제점을 해결하기 위해 제안된 것으로서, 걸음걸이에 어려움을 겪는 환자의 발목에 가속도 센서를 부착하고, 상기 가속도 센서로부터 얻어지는 신호를 이용하여 환자의 걸음걸이를 분석할 수 있는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치 및 방법을 제공하는데 그 목적이 있다.The present invention has been proposed to solve the above problems, an ankle that is attached to the acceleration sensor to the ankle of the patient having difficulty walking, ankle that can analyze the gait of the patient using the signal obtained from the acceleration sensor It is an object of the present invention to provide a gait analysis device and method using an acceleration sensor worn on the.
본 발명의 다른 목적 및 장점들은 하기의 설명에 의해서 이해될 수 있으며, 본 발명의 일 실시 예에 의해 보다 분명하게 알게 될 것이다. 또한, 본 발명의 목적 및 장점들은 특허청구범위에 나타낸 수단 및 그 조합에 의해 실현될 수 있음을 쉽게 알 수 있을 것이다.Other objects and advantages of the present invention can be understood by the following description, and will be more clearly understood by one embodiment of the present invention. It will also be appreciated that the objects and advantages of the present invention may be realized by the means and combinations thereof indicated in the claims.
상기와 같은 목적을 달성하기 위한 본 발명의 일 측면에 따른 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치는, 환자의 발목에 착용되는 밴드에 포함되는 가속도 센서로부터 환자의 걸음걸이에 따른 신호를 수신하는 수신부; 및 상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하고, 상기 전처리된 신호에서 특징을 추출하며, 상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산함으로써 환자의 걸음걸이를 분석하는 분석부;를 포함한다.Gait analysis device using an acceleration sensor worn on the ankle according to an aspect of the present invention for achieving the above object, the signal according to the gait of the patient from the acceleration sensor included in the band worn on the patient's ankle Receiving unit for receiving; And preprocessing the signal according to the gait of the received patient, extracting a feature from the preprocessed signal, calculating the energy of the gait using the extracted feature, and calculating a correlation coefficient for the gait characteristics. Includes; an analysis unit for analyzing the gait of the.
상기 분석부는, 상기 신호에서 잡음을 제거하는 전처리부; 및 상기 잡음이 제거된 신호에서 시간 도메인 상에서의 특징, 주파수 도메인 상에서의 특징 및 에너지 특징을 추출하는 특징 추출부;를 포함한다. The analysis unit, a pre-processing unit for removing noise from the signal; And a feature extractor which extracts a feature on a time domain, a feature on a frequency domain, and an energy feature from the signal from which the noise is removed.
상기 전처리부는, 디지털 로우 패스 필터를 이용하여 상기 신호에서 잡음을 제거할 수 있다.The preprocessor may remove noise from the signal using a digital low pass filter.
상기 특징 추출부는, 상기 전처리된 신호에서 수직성분을 계산하여 시간 도메인(time domain) 상에서의 특징을 추출할 수 있다.The feature extractor may extract a feature on a time domain by calculating a vertical component from the preprocessed signal.
상기 특징 추출부는, 상기 계산된 수직성분을 고속 푸리에 변환을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인(frequency domain) 상에서의 특징을 추출할 수 있다.The feature extractor may extract a feature in a frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform.
상기 특징 추출부는, 수학식 X에 의해 걸음걸이의 에너지 값을 계산하고, 수학식 Y에 의해 걸음걸이 특성에 대한 상관계수를 계산할 수 있다.The feature extractor may calculate the energy value of the gait by Equation X, and calculate a correlation coefficient for the gait characteristic by Equation Y.
[수학식 X][Equation X]
여기서, xi는 FFT를 사용하여 주파수 대역으로 변환한 값들이고, w는 window size이다.Here, x i are values converted into a frequency band using an FFT, and w is a window size.
[수학식 Y][Equation Y]
여기서, x, y는 왼발과 오른발의 보행을 에너지 공식을 통해 계산된 값이며, 는 x, y값의 표준편차, cov(x,y)는 x, y의 공분산 값이다. P는 x, y의 상관계수 값이다.Here, x and y are the values calculated by the energy formula for the walking of the left foot and the right foot, Is the standard deviation of x and y values, and cov (x, y) is the covariance of x and y. P is a correlation coefficient value of x and y.
상기와 같은 목적을 달성하기 위한 본 발명의 다른 측면에 따른 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치에서의 걸음걸이 분석 방법은, 환자의 발목에 착용되는 밴드에 포함되는 가속도 센서로부터 환자의 걸음걸이에 따른 신호를 수신하는 단계; 상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하는 단계; 상기 전처리된 신호에서 특징을 추출하는 단계; 및 상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산하는 단계;를 포함한다.Step analysis method in the gait analysis device using an acceleration sensor worn on the ankle according to another aspect of the present invention for achieving the above object, from the acceleration sensor included in the band worn on the patient's ankle Receiving a signal according to a gait; Preprocessing the signal according to the gait of the received patient; Extracting features from the preprocessed signal; And calculating the energy of the gait using the extracted features and calculating a correlation coefficient for the characteristics of the gait.
상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하는 단계에서는, 디지털 로우 패스 필터를 이용하여 상기 신호에서 잡음을 제거할 수 있다.In the preprocessing of the signal according to the step of the patient, the digital low pass filter may be used to remove noise from the signal.
상기 전처리된 신호에서 특징을 추출하는 단계는, 상기 전처리된 신호에서 수직성분을 계산하여 시간 도메인(time domain) 상에서의 특징을 추출하는 단계; 및 상기 계산된 수직성분을 고속 푸리에 변환을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인(frequency domain) 상에서의 특징을 추출하는 단계;를 포함한다.Extracting a feature from the preprocessed signal includes: extracting a feature in a time domain by calculating a vertical component in the preprocessed signal; And extracting a feature on a frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform.
상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산하는 단계에서는, 수학식 X에 의해 걸음걸이의 에너지 값을 계산하고, 수학식 Y에 의해 걸음걸이 특성에 대한 상관계수를 계산할 수 있다.In the step of calculating the energy of the gait using the extracted feature and calculating the correlation coefficient for the characteristics of the gait, the energy value of the gait is calculated by Equation X, and the gait characteristic is calculated by Equation Y. The correlation coefficient can be calculated.
[수학식 X][Equation X]
여기서, xi는 FFT를 사용하여 주파수 대역으로 변환한 값들이고, w는 window size이다.Here, x i are values converted into a frequency band using an FFT, and w is a window size.
[수학식 Y][Equation Y]
여기서, x, y는 왼발과 오른발의 보행을 에너지 공식을 통해 계산된 값이며, 는 x, y값의 표준편차, cov(x,y)는 x, y의 공분산 값이다. P는 x, y의 상관계수 값이다.Here, x and y are the values calculated by the energy formula for the walking of the left foot and the right foot, Is the standard deviation of x and y values, and cov (x, y) is the covariance of x and y. P is a correlation coefficient value of x and y.
본 발명의 일 측면에 따르면, 소형의 가속도 센서를 이용함으로써 분석에 있어서 환자가 느끼는 불편함을 최소화할 수 있다.According to an aspect of the present invention, by using a small acceleration sensor can minimize the inconvenience that the patient feels in the analysis.
걸음걸이 분석 알고리즘을 통해 보다 정확하게 환자의 걸음걸이를 분석할 수 있다.The gait analysis algorithm can analyze the gait of the patient more accurately.
본 발명에서 얻을 수 있는 효과는 이상에서 언급한 효과로 제한되지 않으며, 언급하지 않은 또 다른 효과들은 아래의 기재로부터 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자에게 명확하게 이해될 수 있을 것이다.The effect obtained in the present invention is not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description. .
본 명세서에 첨부되는 다음의 도면들은 본 발명의 바람직한 실시 예를 예시하는 것이며, 발명을 실시하기 위한 구체적인 내용들과 함께 본 발명의 기술사상을 더욱 이해시키는 역할을 하는 것이므로, 본 발명은 그러한 도면에 기재된 사항에만 한정되어 해석되어서는 아니 된다.The following drawings attached to this specification are illustrative of the preferred embodiments of the present invention, and together with the specific details for carrying out the invention serve to further understand the technical spirit of the present invention, the present invention to such drawings It should not be construed as limited to the matters described.
도 1은 본 발명의 일 실시예에 따른 걸음걸이 분석 시스템의 개략적인 구성을 도시한 도면,1 is a view showing a schematic configuration of a gait analysis system according to an embodiment of the present invention,
도 2는 본 발명의 일 실시예에 따른 스탠스와 스윙을 도시한 도면,2 is a view showing a stance and a swing according to an embodiment of the present invention;
도 3은 본 발명의 일 실시예에 따른 걸음걸이 분석 장치의 개략적인 구성을 도시한 도면,3 is a view showing a schematic configuration of a gait analysis device according to an embodiment of the present invention,
도 4는 본 발명의 일 실시예에 따른 걸음걸이 분석 방법의 흐름을 도시한 도면이다.Figure 4 is a diagram showing the flow of the gait analysis method according to an embodiment of the present invention.
상술한 목적, 특징 및 장점은 첨부된 도면과 관련한 다음의 상세한 설명을 통하여 보다 분명해질 것이며, 그에 따라 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자가 본 발명의 기술적 사상을 용이하게 실시할 수 있을 것이다. 또한, 본 발명을 설명함에 있어서 본 발명과 관련된 공지기술에 대한 구체적인 설명이 본 발명의 요지를 불필요하게 흐릴 수 있다고 판단되는 경우에는 그 상세한 설명을 생략하기로 한다. 이하, 첨부된 도면을 참조하여 본 발명에 따른 바람직한 일 실시 예를 상세히 설명하기로 한다.The above objects, features, and advantages will become more apparent from the following detailed description taken in conjunction with the accompanying drawings, whereby those skilled in the art may easily implement the technical idea of the present invention. There will be. In addition, in describing the present invention, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention, the detailed description thereof will be omitted. Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.
명세서 전체에서, 어떤 부분이 어떤 구성요소를 “포함”한다고 할 때, 이는 특별히 반대되는 기재가 없는 한 다른 구성요소를 제외하는 것이 아니라 다른 구성 요소를 더 포함할 수 있는 것을 의미한다. 또한, 명세서에 기재된 “…부” 등의 용어는 적어도 하나의 기능이나 동작을 처리하는 단위를 의미하며, 이는 하드웨어나 소프트웨어 또는 하드웨어 및 소프트웨어의 결합으로 구현될 수 있다.Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, without excluding other components unless otherwise stated. In addition, the “…” described in the specification. “Unit” refers to a unit that processes at least one function or operation, which may be implemented in hardware or software, or a combination of hardware and software.
도 1은 본 발명의 일 실시예에 따른 걸음걸이 분석 시스템의 개략적인 구성을 도시한 도면, 도 2는 본 발명의 일 실시예에 따른 스탠스와 스윙을 도시한 도면, 도 3은 본 발명의 일 실시예에 따른 걸음걸이 분석 장치의 개략적인 구성을 도시한 도면이다. 1 is a view showing a schematic configuration of a gait analysis system according to an embodiment of the present invention, Figure 2 is a view showing a stance and a swing according to an embodiment of the present invention, Figure 3 is a view of the present invention It is a figure which shows schematic structure of the gait analyzer according to the embodiment.
도 1을 참조하면, 본 실시예에 따른 걸음걸이 분석 시스템은, 환자의 발목에 부착되는 가속도 센서(100) 및 걸음걸이 분석 장치(200)를 포함한다. 이때, 상기 환자는 파킨슨 병과 같은 신경계질환을 앓고 있는 환자일 수 있다. 상기 가속도 센서(100)와 걸음걸이 분석 장치(200)는 네트워크에 의해 연결됨에 따라, 상기 가속도 센서(100)에서 생성된 신호가 걸음걸이 분석 장치(200)로 전송될 수 있다. 이때, 상기 네트워크는 블루투스 등과 같은 무선통신일 수 있다.Referring to FIG. 1, the gait analysis system according to the present embodiment includes an acceleration sensor 100 and a gait analyzer 200 attached to an ankle of a patient. In this case, the patient may be a patient suffering from a neurological disease such as Parkinson's disease. As the acceleration sensor 100 and the gait analyzer 200 are connected by a network, a signal generated by the acceleration sensor 100 may be transmitted to the gait analyzer 200. In this case, the network may be a wireless communication such as Bluetooth.
가속도 센서(100)는 환자의 보행에 따른 신호를 획득하기 위한 것으로, 밴드 내에 포함될 수 있다. 이에 따라, 환자는 밴드를 발목에 착용함으로써, 상기 가속도 센서(100)가 환자의 발목에 부착될 수 있다. 이때, 상기 밴드는 환자의 양쪽 발목에 착용됨에 따라, 상기 밴드에 포함된 가속도 센서(100)가 환자의 보행에 따른 신호를 획득할 수 있다. 상기 환자의 보행에 따른 신호는, 환자의 걸음걸이에 따라 발생하는 신호일 수 있다. 상기 가속도 센서(100)는 3축 가속도센서, 3축 자이로스코프, 3축 지자기센서가 내장된 초소형 AHRS(Attitude Heading Reference System) 모듈일 수 있다. 상기 가속도 센서(100)는 데이터 갱신 및 출력 속도가 1000Hz까지 지원될 수 있으며, 중력성분이 제거된 순수 가속도 값을 출력할 수 있다. 본 실시예에 따른 가속도 센서(100)는 E2BOX사의 EBIMU-9DOFV2일 수 있다. 상기 가속도 센서(100)는 ASCII 출력모드, Hex(binary) 출력모드, Polling 출력 모드 등 3가지 데이터 출력모드를 포함할 수 있다. 본 실시예에서는 데이터 출력모드로 ASCII 출력모드가 사용되는 것으로 가정한다. 상기 3축 가속도 센서(100)의 동작전원은 배터리(미도시)로부터 공급되는 4.5V 전원을 사용할 수 있다. 또한, 상기 가속도 센서(100)로부터 출력되는 신호에 포함된 잡음을 제거하기 위해 센서의 내부에 설계된 Digital Low Pass Fitter를 사용할 수 있다. 한편, 상기 가속도 센서(100)는 소형이기 때문에 공간을 적게 차지하여, 밴드를 착용하는 환자에게 불편감을 덜어줄 수 있다.The acceleration sensor 100 is for acquiring a signal according to a patient's walking and may be included in a band. Accordingly, the patient may wear the band on the ankle, so that the acceleration sensor 100 may be attached to the ankle of the patient. In this case, as the band is worn on both ankles of the patient, the acceleration sensor 100 included in the band may acquire a signal according to the patient's walking. The signal according to the walking of the patient may be a signal generated according to the walking of the patient. The acceleration sensor 100 may be a very small Attitude Heading Reference System (AHRS) module having a three-axis acceleration sensor, a three-axis gyroscope, and a three-axis geomagnetic sensor. The acceleration sensor 100 may support data update and output speeds up to 1000 Hz, and output a pure acceleration value from which gravity components are removed. The acceleration sensor 100 according to the present embodiment may be EBIMU-9DOFV2 manufactured by E2BOX. The acceleration sensor 100 may include three data output modes, such as an ASCII output mode, a hex (binary) output mode, and a polling output mode. In this embodiment, it is assumed that the ASCII output mode is used as the data output mode. The operating power of the three-axis acceleration sensor 100 may use a 4.5V power supplied from a battery (not shown). In addition, a digital low pass fitter designed inside the sensor may be used to remove noise included in the signal output from the acceleration sensor 100. On the other hand, since the acceleration sensor 100 is small, it takes up less space and can reduce discomfort for the patient wearing the band.
걸음걸이 분석 장치(200)는 가속도 센서(100)로부터 수신한 환자의 보행에 따른 신호를 이용해 환자의 걸음걸이를 분석할 수 있다.The gait analyzing apparatus 200 may analyze the gait of the patient using a signal according to the walking of the patient received from the acceleration sensor 100.
도 3을 참조하면, 상기 걸음걸이 분석 장치(200)는 수신부(210) 및 분석부(230)를 포함한다.Referring to FIG. 3, the gait analyzing apparatus 200 includes a receiver 210 and an analyzer 230.
수신부(210)는 가속도 센서(100)로부터 환자의 보행에 따른 신호를 수신한다. 이때, 상기 환자의 보행에 따른 신호는, 환자의 걸음걸이에 따른 신호일 수 있다. 다시 말해, 수신부(210)는 환자의 발목에 착용되는 밴드에 포함되는 가속도 센서(100)로부터 환자의 걸음걸이에 따른 신호를 수신한다.The receiver 210 receives a signal according to the walking of the patient from the acceleration sensor 100. In this case, the signal according to the walking of the patient may be a signal according to the walking of the patient. In other words, the receiver 210 receives a signal according to the walking of the patient from the acceleration sensor 100 included in the band worn on the ankle of the patient.
분석부(230)는 상기 수신부(210)가 수신한 환자의 보행에 따른 신호를 이용해 환자의 걸음걸이를 분석할 수 있다. 상기 분석부(230)는 상기 수신한 환자의 보행에 따른 신호를 전처리하고, 상기 전처리된 신호에서 특징을 추출하며, 상기 추출된 특징을 이용해 걸음걸이의 에너지 및 걸음걸이의 특성에 대한 상관계수를 계산하여 환자의 걸음걸이를 분석할 수 있다. 이때, 상기 분석부(230)는 전처리부(231) 및 특징 추출부(233)를 포함할 수 있다.The analysis unit 230 may analyze the gait of the patient using a signal according to the walking of the patient received by the receiver 210. The analyzer 230 preprocesses the signal according to the walking of the patient, extracts a feature from the preprocessed signal, and uses the extracted feature to calculate a correlation coefficient for the energy of the gait and the characteristics of the gait. Calculate to analyze the patient's gait. In this case, the analyzer 230 may include a preprocessor 231 and a feature extractor 233.
전처리부(231)는 환자의 보행에 따른 신호에서 잡음을 제거하여 전처리를 수행할 수 있다. 이때, 상기 전처리부(231)는 디지털 로우 패스 필터(digital low pass filter)를 이용하여 신호에서 잡음을 제거할 수 있다. 한편, 상기 잡음은 고주파수 노이즈(High-frequency noise) 대역의 잡음일 수 있다. 또한, 이동 평균 필터(moving average filter)를 이용해 신호의 전반적인 스무딩 효과를 줄 수 있다. 이때, 상기 신호는 가속도 센서(100)에 의해 측정된 환자의 걸음걸이에 따른 신호일 수 있다. 상기 신호는 환자의 왼쪽과 오른쪽 발목에 착용된 밴드에 포함되는 가속도 센서(100)에 의해 측정될 수 있으며, 상기 신호는 네트워크를 통해 걸음걸이 분석 장치(200)로 전송되어 별도의 저장소에 저장될 수도 있다. 한편, 상기 걸음걸이 분석 장치(200)는 걸음걸이 분석 어플리케이션이 내장된 스마트폰일 수도 있다. 이때, 상기 걸음걸이 분석 장치(200)가 스마트폰인 경우, 블루투스 통신에 의해 신호가 전송될 수 있다.The preprocessor 231 may perform preprocessing by removing noise from a signal according to a patient's walking. In this case, the preprocessor 231 may remove noise from the signal using a digital low pass filter. The noise may be noise in a high-frequency noise band. In addition, a moving average filter may be used to give an overall smoothing effect of the signal. In this case, the signal may be a signal according to the gait of the patient measured by the acceleration sensor 100. The signal can be measured by the acceleration sensor 100 included in the band worn on the left and right ankles of the patient, the signal is transmitted to the gait analysis device 200 through a network to be stored in a separate storage It may be. On the other hand, the gait analysis device 200 may be a smart phone with a gait analysis application. In this case, when the gait analysis device 200 is a smartphone, a signal may be transmitted by Bluetooth communication.
특징 추출부(233)는 상기 전처리부(231)에 의해 잡음이 제거된 신호에서 특징을 추출할 수 있다. 자세하게, 상기 특징 추출부(233)는 상기 전처리부(231)에 의해 잡음이 제거된 신호에서 시간 도메인(time domain) 상에서의 특징, 주파수 도메인(frequency domain) 상에서의 특징 및 에너지(energy) 특징을 추출할 수 있다.The feature extractor 233 may extract a feature from a signal from which noise is removed by the preprocessor 231. In detail, the feature extractor 233 may include a feature on the time domain, a feature on the frequency domain, and an energy feature on the signal from which the noise is removed by the preprocessor 231. Can be extracted.
상기 특징 추출부(233)는 전처리된 신호에서 수직성분을 계산하여 시간 도메인 상에서의 특징을 추출할 수 있다. 이때, 시간 도메인 상에서의 특징을 추출하는 이유는 사람의 걸음걸이를 스탠스(stance : 착지)와 스윙(swing) 단계로 나누기 위함이다. 도 1에 도시된 바와 같이, 사람의 걸음걸이는 스탠스와 스윙으로 구성된다. 스탠스는 발이 지면에 닿아 있는 것을 말하고, 스윙은 한발의 발등이 다시 땅에 착지될 때까지 발이 들려있는 것을 말한다. 이때, 스탠스 단계(stance phase)의 시작 시에 발생하는 이벤트를 힐 스트라이크(heel strike)라고 하며, 스윙 단계(swing phase)의 시작(또는, 스탠스 단계의 종료)에 발생하는 이벤트를 힐 오프(heel off) 및/또는 토우 오프(toe off)라고 한다. 따라서, 상기 특징 추출부(233)는 힐 오프(heel off) 및/또는 토우 오프(toe off)와 힐 스트라이크(heel strike) 지점을 찾아, 스탠스와 스윙을 나눌 수 있으며, 상기 힐 오프(heel off) 및/또는 토우 오프(toe off)와 힐 스트라이크(heel strike) 지점을 찾기 위해 가속도 센서(100)에 의해 획득된 신호로부터 수직성분을 계산한다. 이때, 상기 수직성분은 아래의 수학식 1에 의해 계산될 수 있다.The feature extractor 233 may extract a feature on a time domain by calculating a vertical component from a preprocessed signal. At this time, the reason for extracting the feature on the time domain is to divide a human's gait into a stance and a swinging step. As shown in FIG. 1, a human gait consists of a stance and a swing. Stance refers to the foot touching the ground, and swinging refers to the foot being held up until one foot hits the ground again. In this case, an event that occurs at the start of a stance phase is called a heel strike, and an event that occurs at the start of a swing phase (or the end of a stance phase) is heeled off. off and / or toe off. Accordingly, the feature extractor 233 may find a heel off and / or a toe off and a heel strike point, divide the stance and the swing, and the heel off And / or compute the vertical component from the signal obtained by the acceleration sensor 100 to find the toe off and heel strike points. In this case, the vertical component may be calculated by Equation 1 below.
여기서, 수직 성분 벡터값 는 다음 에 대응하는 값이며 mx',my'그리고 mz'는 각축의 샘플로 추출한 구간 대한 평균값이다. 이때, x',y',z'는 3축 가속도 센서에서 나오는 가속도 신호 값이다. 이면 샘플로 추출한 구간 중의 특정 지점의 벡터값이 되며 N은 샘플로 추출한 구간의 길이이다. 에 대한 의 추정 값은 내부의 수직 성분들로 계산 된다. 을 내부의 성분들을 통해 계산된 결과라 하면, 는 추정 벡터값이다.Where vertical component vector Then Mx ', my' and mz 'are the mean values for the intervals sampled on each axis. In this case, x ', y', z 'is the acceleration signal value coming from the three-axis acceleration sensor. In this case, it is a vector value of a specific point in the sampled section, and N is the length of the sampled section. For The estimated value of It is calculated from the internal vertical components. Is the result calculated by the internal components, Is an estimated vector value.
한편, 이동시간, 보폭, 주기, 속도 등과 같은 걸음걸이의 특성은 힐 오프(heel off) 및/또는 토우 오프(toe off)와 힐 스트라이크(heel strike)를 기준으로 계산되어질 수 있다.On the other hand, the characteristics of the gait such as movement time, stride length, period, speed, etc. may be calculated based on heel off and / or toe off and heel strike.
상기 특징 추출부(233)는 계산된 수직성분을 고속 푸리에 변환(Fast Fourier Transform : FFT)을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인 상에서의 특징을 추출할 수 있다. 상기 특징 추출부(233)는 정상인과 비정상인의 걸음걸이에서 나타나는 주파수 대역의 값을 확인하기 위해 계산된 수직성분을 고속 푸리에 변환을 사용하여 주파수 대역으로 변환할 수 있다. 이때, 변환한 결과에 따라 사람의 보행 스타일에 따라서 다양한 주파수 특징이 나타날 수 있다.The feature extractor 233 may extract a feature in the frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform (FFT). The feature extractor 233 may convert a calculated vertical component into a frequency band by using a fast Fourier transform in order to check the value of the frequency band represented by gait between normal and abnormal persons. In this case, various frequency characteristics may appear according to the walking style of the person according to the converted result.
상기 특징 추출부(233)는 환자의 왼발과 오른발의 걸음걸이의 특성의 상관계수를 추정하기 위해 걸음걸이의 에너지 값을 계산할 수 있다. 이때, 상기 걸음걸이의 에너지 값은 아래의 수학식 2에 의해 계산될 수 있다.The feature extractor 233 may calculate an energy value of the gait to estimate a correlation coefficient of the gait of the left and right feet of the patient. In this case, the energy value of the gait can be calculated by Equation 2 below.
여기서, xi는 FFT를 사용하여 주파수 대역으로 변환한 값들이고, w는 window size이며, 환자의 보행 특성에 따라 걸음걸이의 성분이 누락되지 않도록 중복되게 설정한다.Here, x i is a value converted to the frequency band using the FFT, w is the window size, and the overlapping setting so as not to miss the components of the gait according to the walking characteristics of the patient.
또한, 상기 상관관계는 아래의 수학식 3에 의해 계산될 수 있다. In addition, the correlation may be calculated by Equation 3 below.
여기서, x, y는 왼발과 오른발의 보행을 에너지 공식을 통해 계산된 값이며, 는 x, y값의 표준편차, cov(x,y)는 x, y의 공분산 값이다. P는 x, y의 상관계수 값이다.Here, x and y are the values calculated by the energy formula for the walking of the left foot and the right foot, Is the standard deviation of x and y values, and cov (x, y) is the covariance of x and y. P is a correlation coefficient value of x and y.
이하, 도 4를 참조하여 상술한 바와 같은 걸음걸이 분석 장치(200)에서의 검음걸이 분석 방법에 대해 설명하기로 한다.Hereinafter, with reference to FIG. 4, the black gait analysis method in the gait analysis device 200 as described above will be described.
도 4는 본 발명의 일 실시예에 따른 걸음걸이 분석 방법의 흐름을 도시한 도면이다.Figure 4 is a diagram showing the flow of the gait analysis method according to an embodiment of the present invention.
도 4를 참조하면, 먼저, 걸음걸이 분석 장치(200)는 환자의 발목에 착용되는 밴드에 포함되는 가속도 센서(100)로부터 환자의 걸음걸이에 따른 신호를 수신한다(S410).Referring to FIG. 4, first, the gait analyzing apparatus 200 receives a signal according to the gait of the patient from the acceleration sensor 100 included in the band worn on the ankle of the patient (S410).
걸음걸이 분석 장치(200)는 수신된 환자의 걸음걸이에 따른 신호를 이용해 상기 신호를 전처리한다(S420). 상기 걸음걸이 분석 장치(200)는 환자의 보행에 따른 신호에서 잡음을 제거하여 전처리를 수행할 수 있다. 이때, 걸음걸이 분석 장치(200)는 디지털 로우 패스 필터(digital low pass filter)를 이용하여 신호에서 잡음을 제거할 수 있다.The gait analyzing apparatus 200 preprocesses the signal by using the signal according to the gait of the patient (S420). The gait analyzing apparatus 200 may perform preprocessing by removing noise from a signal according to a patient's walking. In this case, the gait analyzer 200 may remove noise from a signal using a digital low pass filter.
걸음걸이 분석 장치(200)는 전처리된 신호에서 특징을 추출한다(S430). 걸음걸이 분석 장치(200)는 잡음이 제거된 신호에서 시간 도메인(time domain) 상에서의 특징 및 주파수 도메인(frequency domain) 상에서의 특징을 추출할 수 있다. 걸음걸이 분석 장치(200)는 전처리된 신호에서 수직성분을 계산하여 시간 도메인 상에서의 특징을 추출할 수 있다. 이때, 상기 수직성분은 상술한 수학식 1에 의해 계산될 수 있다. 걸음걸이 분석 장치(200)는 계산된 수직성분을 고속 푸리에 변환(Fast Fourier Transform : FFT)을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인 상에서의 특징을 추출할 수 있다. The gait analyzing apparatus 200 extracts a feature from a preprocessed signal (S430). The gait analyzer 200 may extract a feature on a time domain and a feature on a frequency domain from a signal from which noise is removed. The gait analyzer 200 may extract a feature on a time domain by calculating a vertical component from a preprocessed signal. In this case, the vertical component may be calculated by Equation 1 described above. The gait analyzing apparatus 200 may extract a feature on the frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform (FFT).
걸음걸이 분석 장치(200)는 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산한다(S440). 이때, 상기 걸음걸이의 에너지 값은 상술한 수학식 2에 의해 계산되고, 상관관계는 상술한 수학식 3에 의해 계산될 수 있다.The gait analyzing apparatus 200 calculates the energy of the gait using the extracted feature and calculates a correlation coefficient with respect to the gait of the gait (S440). In this case, the energy value of the gait may be calculated by Equation 2 described above, and the correlation may be calculated by Equation 3 described above.
본 발명의 실시예에 따른 방법들은 애플리케이션으로 구현되거나 다양한 컴퓨터 구성요소를 통하여 수행될 수 있는 프로그램 명령어의 형태로 구현되어 컴퓨터 판독 가능한 기록 매체에 기록될 수 있다. 상기 컴퓨터 판독 가능한 기록 매체는 프로그램 명령어, 데이터 파일, 데이터 구조 등을 단독으로 또는 조합하여 포함할 수 있다. 상기 컴퓨터 판독 가능한 기록 매체에 기록되는 프로그램 명령어는, 본 발명을 위한 특별히 설계되고 구성된 것들이거니와 컴퓨터 소프트웨어 분야의 당업자에게 공지되어 사용 가능한 것일 수도 있다. 컴퓨터 판독 가능한 기록 매체의 예에는, 하드 디스크, 플로피 디스크 및 자기 테이프와 같은 자기 매체, CD-ROM, DVD와 같은 광기록 매체, 플롭티컬 디스크(floptical disk)와 같은 자기-광 매체(magneto-optical media) 및 ROM, RAM, 플래시 메모리 등과 같은 프로그램 명령어를 저장하고 수행하도록 특별히 구성된 하드웨어 장치가 포함된다. 프로그램 명령어의 예에는, 컴파일러에 의해 만들어지는 것과 같은 기계어 코드뿐만 아니라 인터프리터 등을 사용해서 컴퓨터에 의해서 실행될 수 있는 고급 언어 코드도 포함된다. 상기 하드웨어 장치는 본 발명에 따른 처리를 수행하기 위해 하나 이상의 소프트웨어 모듈로서 작동하도록 구성될 수 있으며, 그 역도 마찬가지이다.Methods according to an embodiment of the present invention may be implemented in the form of program instructions that may be implemented as an application or executed through various computer components, and may be recorded on a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the computer-readable recording medium may be those specially designed and constructed for the present invention, and may be known and available to those skilled in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs, DVDs, and magneto-optical media such as floptical disks. media) and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform the process according to the invention, and vice versa.
본 명세서는 많은 특징을 포함하는 반면, 그러한 특징은 본 발명의 범위 또는 특허청구범위를 제한하는 것으로 해석되어서는 아니 된다. 또한, 본 명세서의 개별적인 실시 예에서 설명된 특징들은 단일 실시 예에서 결합되어 구현될 수 있다. 반대로, 본 명세서의 단일 실시 예에서 설명된 다양한 특징들은 개별적으로 다양한 실시 예에서 구현되거나, 적절히 결합되어 구현될 수 있다.While this specification includes many features, such features should not be construed as limiting the scope of the invention or the claims. In addition, the features described in the individual embodiments of the present specification can be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment of the present specification can be implemented individually in various embodiments or in combination as appropriate.
도면에서 동작들이 특정한 순서로 설명되었으나, 그러한 동작들이 도시된 바와 같은 특정한 순서로 수행되는 것으로 또는 일련의 연속된 순서, 또는 원하는 결과를 얻기 위해 모든 설명된 동작이 수행되는 것으로 이해되어서는 안 된다. 특정 환경에서 멀티태스킹 및 병렬 프로세싱이 유리할 수 있다. 아울러, 상술한 실시 예에서 다양한 시스템 구성요소의 구분은 모든 실시 예에서 그러한 구분을 요구하지 않는 것으로 이해되어야 한다. 상술한 앱 구성요소 및 시스템은 일반적으로 단일 소프트웨어 제품 또는 멀티플 소프트웨어 제품에 패키지로 구현될 수 있다.Although the operations have been described in a particular order in the drawings, they should not be understood as being performed in a particular order as shown or in a sequence of successive orders, or all of the described actions being performed to obtain a desired result. Multitasking and parallel processing may be advantageous in certain circumstances. In addition, it should be understood that the division of various system components in the above-described embodiments does not require such division in all embodiments. The app components and systems described above may generally be packaged in a single software product or multiple software products.
이상에서 설명한 본 발명은, 본 발명이 속하는 기술분야에서 통상의 지식을 가진 자에게 있어 본 발명의 기술적 사상을 벗어나지 않는 범위 내에서 여러 가지 치환, 변형 및 변경이 가능하므로 전술한 실시 예 및 첨부된 도면에 의해 한정되는 것은 아니다.The present invention described above is capable of various substitutions, modifications, and changes without departing from the technical spirit of the present invention for those skilled in the art to which the present invention pertains. It is not limited by the drawing.
Claims (10)
- 환자의 발목에 착용되는 밴드에 포함되는 가속도 센서로부터 환자의 걸음걸이에 따른 신호를 수신하는 수신부; 및Receiving unit for receiving a signal according to the step of the patient from the acceleration sensor included in the band worn on the ankle of the patient; And상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하고, 상기 전처리된 신호에서 특징을 추출하며, 상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산함으로써 환자의 걸음걸이를 분석하는 분석부;를 포함하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.By preprocessing the signal according to the gait of the received patient, extracting features from the preprocessed signal, using the extracted feature to calculate the energy of the gait and calculate the correlation coefficient for the gait characteristics of the patient Gait analysis device using an acceleration sensor worn on the ankle, including; analysis unit for analyzing the gait.
- 제 1 항에 있어서,The method of claim 1,상기 분석부는,The analysis unit,상기 신호에서 잡음을 제거하는 전처리부; 및A preprocessor to remove noise from the signal; And상기 잡음이 제거된 신호에서 시간 도메인 상에서의 특징, 주파수 도메인 상에서의 특징 및 에너지 특징을 추출하는 특징 추출부;를 포함하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.A gait analysis device using an acceleration sensor worn on ankle, including; a feature extractor extracting a feature on a time domain, a feature on a frequency domain, and an energy feature from the signal from which the noise is removed.
- 제 2 항에 있어서,The method of claim 2,상기 전처리부는,The preprocessing unit,디지털 로우 패스 필터를 이용하여 상기 신호에서 잡음을 제거하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.Gait analysis device using an acceleration sensor worn on the ankle to remove noise from the signal using a digital low pass filter.
- 제 2 항에 있어서,The method of claim 2,상기 특징 추출부는,The feature extraction unit,상기 전처리된 신호에서 수직성분을 계산하여 시간 도메인(time domain) 상에서의 특징을 추출하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.A gait analysis device using an acceleration sensor worn on the ankle to extract a feature on a time domain by calculating a vertical component from the preprocessed signal.
- 제 2 항에 있어서,The method of claim 2,상기 특징 추출부는,The feature extraction unit,상기 계산된 수직성분을 고속 푸리에 변환을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인(frequency domain) 상에서의 특징을 추출하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.The gait analysis device using the acceleration sensor worn on the ankle to extract the feature on the frequency domain by converting the calculated vertical components into a frequency band using a fast Fourier transform.
- 제 2 항에 있어서,The method of claim 2,상기 특징 추출부는,The feature extraction unit,수학식 X에 의해 걸음걸이의 에너지 값을 계산하고, 수학식 Y에 의해 걸음걸이 특성에 대한 상관계수를 계산하는 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치.A gait analysis device using an acceleration sensor, which is worn on the ankle to calculate the energy value of the gait by Equation X, and calculates a correlation coefficient for the gait characteristic by Equation Y.[수학식 X][Equation X]여기서, xi는 FFT를 사용하여 주파수 대역으로 변환한 값들이고, w는 window size이다.Here, x i are values converted into a frequency band using an FFT, and w is a window size.[수학식 Y][Equation Y]여기서, x, y는 왼발과 오른발의 보행을 에너지 공식을 통해 계산된 값이며, 는 x, y값의 표준편차, cov(x,y)는 x, y의 공분산 값이다. P는 x, y의 상관계수 값이다.Here, x and y are the values calculated by the energy formula for the walking of the left foot and the right foot, Is the standard deviation of x and y values, and cov (x, y) is the covariance of x and y. P is a correlation coefficient value of x and y.
- 발목에 착용되는 가속도 센서를 이용한 걸음걸이 분석 장치에서의 걸음걸이 분석 방법에 있어서,In the gait analysis method in a gait analysis device using an acceleration sensor worn on the ankle,환자의 발목에 착용되는 밴드에 포함되는 가속도 센서로부터 환자의 걸음걸이에 따른 신호를 수신하는 단계;Receiving a signal according to the step of the patient from the acceleration sensor included in the band worn on the ankle of the patient;상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하는 단계;Preprocessing the signal according to the gait of the received patient;상기 전처리된 신호에서 특징을 추출하는 단계; 및Extracting features from the preprocessed signal; And상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산하는 단계;를 포함하는 걸음걸이 분석 방법.The step analysis method comprising the step of calculating the energy of the gait using the extracted features and calculating the correlation coefficient for the characteristics of the gait.
- 제 7 항에 있어서,The method of claim 7, wherein상기 수신된 환자의 걸음걸이에 따른 신호를 전처리하는 단계에서는,In the step of pre-processing the signal according to the step of the received patient,디지털 로우 패스 필터를 이용하여 상기 신호에서 잡음을 제거하는 걸음걸이 분석 방법.A gait analysis method for removing noise from the signal using a digital low pass filter.
- 제 7 항에 있어서,The method of claim 7, wherein상기 전처리된 신호에서 특징을 추출하는 단계는,Extracting a feature from the preprocessed signal,상기 전처리된 신호에서 수직성분을 계산하여 시간 도메인(time domain) 상에서의 특징을 추출하는 단계; 및Extracting features on a time domain by calculating vertical components in the preprocessed signal; And상기 계산된 수직성분을 고속 푸리에 변환을 사용하여 주파수 대역으로 변환함으로써 주파수 도메인(frequency domain) 상에서의 특징을 추출하는 단계;를 포함하는 걸음걸이 분석 방법.A step of extracting a feature on a frequency domain by converting the calculated vertical component into a frequency band using a fast Fourier transform.
- 제 7 항에 있어서,The method of claim 7, wherein상기 추출된 특징을 이용해 걸음걸이의 에너지를 계산하고 걸음걸이의 특성에 대한 상관계수를 계산하는 단계에서는, In the step of calculating the energy of the gait using the extracted features and calculating the correlation coefficient for the characteristics of the gait,수학식 X에 의해 걸음걸이의 에너지 값을 계산하고, 수학식 Y에 의해 걸음걸이 특성에 대한 상관계수를 계산하는 걸음걸이 분석 방법.A gait analysis method for calculating an energy value of gait by Equation X, and calculating a correlation coefficient for gait characteristics by Equation Y.[수학식 X][Equation X]여기서, xi는 FFT를 사용하여 주파수 대역으로 변환한 값들이고, w는 window size이다.Here, x i are values converted into a frequency band using an FFT, and w is a window size.[수학식 Y][Equation Y]여기서, x, y는 왼발과 오른발의 보행을 에너지 공식을 통해 계산된 값이며, 는 x, y값의 표준편차, cov(x,y)는 x, y의 공분산 값이다. P는 x, y의 상관계수 값이다.Here, x and y are the values calculated by the energy formula for the walking of the left foot and the right foot, Is the standard deviation of x and y values, and cov (x, y) is the covariance of x and y. P is a correlation coefficient value of x and y.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020170075982A KR101998465B1 (en) | 2017-06-15 | 2017-06-15 | A gait analysis device and method for neurological diseases using ankle-worn accelerometer |
KR10-2017-0075982 | 2017-06-15 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2018230787A1 true WO2018230787A1 (en) | 2018-12-20 |
Family
ID=64660291
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2017/013842 WO2018230787A1 (en) | 2017-06-15 | 2017-11-29 | Device and method for analyzing gait by using acceleration sensor worn on ankle |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR101998465B1 (en) |
WO (1) | WO2018230787A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113133761A (en) * | 2020-01-17 | 2021-07-20 | 宝成工业股份有限公司 | Method for judging left and right gait and analysis device thereof |
WO2023067694A1 (en) * | 2021-10-19 | 2023-04-27 | 日本電気株式会社 | Data generation device, learning system, estimation device, data generation method, and recording medium |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102336580B1 (en) * | 2019-10-30 | 2021-12-10 | 한국생산기술연구원 | Balance Analysis Method of Left Gait and Right Gait |
KR102421310B1 (en) * | 2020-07-21 | 2022-07-14 | 한국해양대학교 산학협력단 | Smart walking aid apparatus and method for rehabilitation of parkinson's patient |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100620118B1 (en) * | 2004-03-31 | 2006-09-13 | 학교법인 대양학원 | Walking pattern analysis apparatus and method using inertial sensor |
JP2010005033A (en) * | 2008-06-25 | 2010-01-14 | Panasonic Electric Works Co Ltd | Walking motion analyzer |
KR101053491B1 (en) * | 2009-04-07 | 2011-08-08 | (주)휴레브 | Walking Cycle Detection System and Method Using Motion Sensor |
US20130090881A1 (en) * | 2011-10-10 | 2013-04-11 | Texas Instruments Incorporated | Robust step detection using low cost mems accelerometer in mobile applications, and processing methods, apparatus and systems |
JP2015165895A (en) * | 2015-04-23 | 2015-09-24 | 株式会社東芝 | Gait analysis device and gait analysis program |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120085064A (en) | 2011-01-21 | 2012-07-31 | 주식회사 플렉스엘시디 | Wearable gait analysis apparatus and gait analysis system including the same |
-
2017
- 2017-06-15 KR KR1020170075982A patent/KR101998465B1/en active IP Right Grant
- 2017-11-29 WO PCT/KR2017/013842 patent/WO2018230787A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100620118B1 (en) * | 2004-03-31 | 2006-09-13 | 학교법인 대양학원 | Walking pattern analysis apparatus and method using inertial sensor |
JP2010005033A (en) * | 2008-06-25 | 2010-01-14 | Panasonic Electric Works Co Ltd | Walking motion analyzer |
KR101053491B1 (en) * | 2009-04-07 | 2011-08-08 | (주)휴레브 | Walking Cycle Detection System and Method Using Motion Sensor |
US20130090881A1 (en) * | 2011-10-10 | 2013-04-11 | Texas Instruments Incorporated | Robust step detection using low cost mems accelerometer in mobile applications, and processing methods, apparatus and systems |
JP2015165895A (en) * | 2015-04-23 | 2015-09-24 | 株式会社東芝 | Gait analysis device and gait analysis program |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113133761A (en) * | 2020-01-17 | 2021-07-20 | 宝成工业股份有限公司 | Method for judging left and right gait and analysis device thereof |
CN113133761B (en) * | 2020-01-17 | 2024-05-28 | 宝成工业股份有限公司 | Method for judging left and right gait and analysis device thereof |
WO2023067694A1 (en) * | 2021-10-19 | 2023-04-27 | 日本電気株式会社 | Data generation device, learning system, estimation device, data generation method, and recording medium |
Also Published As
Publication number | Publication date |
---|---|
KR101998465B1 (en) | 2019-07-09 |
KR20180136789A (en) | 2018-12-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2018230787A1 (en) | Device and method for analyzing gait by using acceleration sensor worn on ankle | |
Cola et al. | An on-node processing approach for anomaly detection in gait | |
Lee et al. | The use of a single inertial sensor to identify stride, step, and stance durations of running gait | |
WO2014204092A1 (en) | Wearable device and communication method using wearable device | |
EP1983896B1 (en) | Gait analysis | |
WO2014081154A1 (en) | Shoe insole, shoes including same, and gait correction system | |
WO2015099292A1 (en) | System and method for controlling joint angle of knee-joint type walking training robot | |
US20080146968A1 (en) | Gait analysis system | |
CN109480857B (en) | Device and method for detecting frozen gait of Parkinson disease patient | |
WO2018135692A1 (en) | Wearable device for motion recognition and control, and method for motion recognition control using same | |
EP1304072A3 (en) | Method and apparatus for the serial comparison of electrocardiograms | |
Majumder et al. | A multi-sensor approach for fall risk prediction and prevention in elderly | |
WO2018097621A1 (en) | Walking analysis system and method, and computer-readable recording medium | |
CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
KR20180026914A (en) | Method for walking assist, and device operating the same | |
US20170172519A1 (en) | Systems and techniques for estimating the severity of chronic obstructive pulmonary disease in a patient | |
WO2016126147A1 (en) | Apparatus and method for detecting snoring | |
Iervolino et al. | A wearable device for sport performance analysis and monitoring | |
Ye et al. | An adaptive method for gait event detection of gait rehabilitation robots | |
WO2018048072A1 (en) | Apparatus for eliminating motion artifacts by using ppg signal and method thereof | |
WO2017099340A1 (en) | Electronic device, signal processing method thereof, biological signal measurement system, and non-transitory computer readable recording medium | |
Boutaayamou et al. | Algorithm for temporal gait analysis using wireless foot-mounted accelerometers | |
WO2022010149A1 (en) | Method and system for generating data set relating to facial expressions, and non-transitory computer-readable recording medium | |
WO2018147654A1 (en) | Method for distinguishing pet motion and apparatus using same | |
Wu et al. | Smart shoes for obstacle detection |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17913920 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17913920 Country of ref document: EP Kind code of ref document: A1 |