Development of a Wearable Inertial Sensor-based Gait Analysis Device Using Machine Learning Algorithms -Validity of the Temporal Gait Parameter in Healthy Young Adults

설평화,유흥종,최윤철,신민용,추광재,김경신,백승윤,이용우,송창호 대한고유수용성신경근촉진법학회 2020 PNF and Movement Vol.18 No.2

Purpose: The study aims were to develop a wearable inertial sensor-based gait analysis device that uses machine learning algorithms, and to validate this novel device using temporal gait parameters. Methods: Thirty-four healthy young participants (22 male, 12 female, aged 25.76 years) with no musculoskeletal disorders were asked to walk at three different speeds. As they walked, data were simultaneously collected by a motion capture system and inertial measurement units (Reseed®). The data were sent to a machine learning algorithm adapted to the wearable inertial sensor-based gait analysis device. The validity of the newly developed instrument was assessed by comparing it to data from the motion capture system. Results: At normal speeds, intra-class correlation coefficients (ICC) for the temporal gait parameters were excellent (ICC [2, 1], 0.99∼0.99), and coefficient of variation (CV) error values were insignificant for all gait parameters (0.31∼1.08%). At slow speeds, ICCs for the temporal gait parameters were excellent (ICC [2, 1], 0.98∼0.99), and CV error values were very small for all gait parameters (0.33∼1.24%). At the fastest speeds, ICCs for temporal gait parameters were excellent (ICC [2, 1], 0.86∼0.99) but less impressive than for the other speeds. CV error values were small for all gait parameters (0.17∼5.58%). Conclusion: These results confirm that both the wearable inertial sensor-based gait analysis device and the machine learning algorithms have strong concurrent validity for temporal variables. On that basis, this novel wearable device is likely to prove useful for establishing temporal gait parameters while assessing gait.

Semantic Key Pre-Distribution Protocol For Multi-Phase Wireless Sensor Networks

Carlos Ramos,Zita Maria Almeida do Vale 사단법인 인문사회과학기술융합학회 2011 예술인문사회융합멀티미디어논문지 Vol.1 No.1

Gait is a new biometric aimed to recognize a subject by the manner in which they walk. Gait has several advantages over other biometrics, most notably that it is a non-invasive and perceivable at a distance when other biometrics are obscured. We present a new area based metric, called gait masks, which provides statistical data intimately related to the gait of the subject. Early results are promising with a recognition rate of 90% on a small database of human subjects. In addition to this, we show how gait masks can also be used on subjects other than humans to provide information about the gait cycle of the subject. In this paper, we propose a novel temporal template, called Chrono-Gait Image (CGI), to describe the spatio-temporal walking pattern for human identification by gait. The CGI temporal template encodes the temporal information among gait frames via color mapping to improve the recognition performance. Our method starts with the extraction of the contour in each gait image, followed by utilizing a color mapping function to encode each of gait contour images in the same gait sequence and compositing them to a single CGI. We also obtain the CGI-based real templates by generating CGI for each period of one gait sequence and utilize contour distortion to generate the CGI-based synthetic templates. In addition to independent recognition using either of individual templates, we combine the real and synthetic temporal templates for refining the performance of human recognition. Extensive experiments on the USF HumanID database indicate that compared with the recently published gait recognition approaches, our CGI-based approach attains better performance in gait recognition with considerable robustness to gait period detection.

신발기반형 관성센서를 이용한 전정신경염 환자의 보행 분석: 예비 연구

차준상,김동영,이혜순,김남범,이환호 대한평형의학회 2019 Research in Vestibular Science Vol.18 No.2

Objectives: Despite patients with dizziness were reported of revealing gait pro-blems, there is still lack of objective quantitative measurement of gait patterns of peripheral vestibular disorders. To demonstrate gait variability in acute uni-lateral peripheral vestibular deficit, we evaluated the differences in gait patterns between vestibular neuritis (VN) patients and healthy subjects by the use of shoe-type inertial measurement unit (IMU) with sensors mounted.Methods: Between April 2017 and January 2019, 30 patients diagnosed with uni-lateral peripheral vestibular deficit presumed to be caused by VN were enrolled in this study. The shoe-type IMU was used to analysis subjects. We assessed gait speed, cadence, stride length, stance phase, normalized stride length, normalized step length, phase coordination index and gait asymmetry of data from shoe-type IMU sensors with the walking protocol. We tested 30 healthy volunteers as con-trol group.Results: We identified spatiotemporal parameters of human gait. The gait speed of patients with VN was decreased to 3.82±0.8 compared to 4.93±1.08 in control group. In addition, there were differences in normalized stride length, normalized gait speed and related gait parameters, when comparing VN group and control group. Conclusion: Gait analysis by the use of shoe-type IMU could provide important information regarding vestibular pathophysiology in patients with VN. Gait per-formance tests can examine gait variability quantitatively. It will be taken into consideration as a vestibular function test for patients with vertigo.

A New Automatic Gait Cycle Partitioning Method and Its Application to Human Identification

Sungjun Hong,Euntai Kim 한국지능시스템학회 2017 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.17 No.2

Gait cycle partitioning is very important prior to human gait analysis such as gait modeling, gait recognition, gait feature analysis, etc. In this paper, we propose a new automatic gait cycle partitioning method based on two kinds of simple gait representation. Then, the propose method is applied to find keyframe corresponding the rest position for gait-based human identification system. To demonstrate the validity of the proposed method, the CASIA gait dataset A and the SOTON gait database are used to evaluate the recognition performance of the gait recognition system identifying subjects using the decision level fusion based on majority voting.

하지관절의 강직부위가 보행에 미치는 영향

최웅재(Choi, Woong-Jae),우병훈(Woo, Byung-Hoon) 한국체육과학회 2018 한국체육과학회지 Vol.27 No.5

The purpose of this study was to investigate the effects of the compensation effect on the other joints by inducing stiff-knee and equinus attachment by using one side lower limb brace to normal people during gait. Ten subjects were participated in the experiment(age: 26.0±6.3 yrs, height: 175.5±5.3 ㎝, weight: 69.1±6.1 ㎏). There were three condition of gait attaching position using brace(free gait, stiffe-knee gait, equinus gait). The study method adopted 3D analysis with six cameras and ground reaction force with one force-plates. The results were as follows; In angular displacement of right hip joint, equinus gait showed more flexion than other gait in RHC, LTO, RMS, RTO, LMS, and RHC1. In angular displacement of left hip joint, equinus gait showed more flexion than free gait in RHC and RHC1, and equinus gait showed more flexion than other gait in LTO, RMS, LHC, RTO and LMS. In angular displacement of left knee joint, equinus gait showed more flexion than other gait in LTO and RMS, and equinus gait showed more extension than other gait in RTO and LMS. In angular displacement of left ankle joint, equinus gait showed more plantar flexion than other gait in LTO, RMS, and LHC. In trunk tilt, equinus gait showed more forward flexion than other gait in all events. In GRF, Fx was more bigger medial and lateral force in equinus gait. Fy was more bigger only propulsion force in equinus gait. Fz was more bigger max 1 and 2 force in equinus gait.

근 긴장도 조절기법을 병행한 트레드밀 보행훈련이 만성 뇌졸중 환자의 보행능력에 미치는 영향

김동훈,김경훈 대한통합의학회 2023 대한통합의학회지 Vol.11 No.3

Purpose : Stroke patients exhibit considerable variations in gait patterns. Stroke patients generally show abnormal muscle tone and gait. This study was performed to evaluate the effects of treadmill gait training combined with muscle tone control technique (TM) on gait ability in patient with chronic stroke. Methods : A single-blind, randomized controlled trial was conducted with 36 patient with chronic stroke. They were randomly allocated 2 groups; treadmill gait training combined with muscle tone control technique group (TM group; n=18) and conservative treatment group (CG group; n=18). The TM group received 15 minutes muscle tone control technique and 15 minute treadmill gait training. In the conservative treatment group received 30 minutes conservative physical therapy. Each group performed 30 minutes a day 3 times a week for 8 weeks. The primary outcome gait ability were measured by gait measurement system (Optogait, Microgate, Italy) and 10 m walking test (10MWT). An independent t-test was used to statistically analyze the pre-test and pos-ttest gait ability results. Results : Both groups demonstrated significant improvement of outcome in gait ability during intervention period. TM group showed significant differences in gait ability as compared to the CG groups (p<.05). TM group showed significant differences in 10MWT as compared to the CG groups (p<.05). Our results showed that TM was more effective on gait ability in patients with chronic stroke. Conclusion : Our findings of this study confirmed that the treadmill gait training combined with muscle tone control technique provided significant improvements on gait ability in patient with chronic stroke. Therefore treadmill gait training combined with muscle tone control technique may positive influenced gait ability. This study will be able to be used as an intervention data for recovering gait ability in patients with chronic stroke.

보행 장애인을 위한 능동형 보행훈련 시스템 개발 및 평가

황성재,태기식,강성재,김정윤,황선홍,김한일,박시운,김영호,Hwang, S.J.,Tae, K.S.,Kang, S.J.,Kim, J.Y.,Hwang, S.H.,Kim, H.I.,Park, S.W.,Kim, Y.H. 대한의용생체공학회 2007 의공학회지 Vol.28 No.2

Modem concepts of gait rehabilitation after stroke favor a task-specific repetitive approach. In practice, the required physical effort of the therapists limits the realization of this approach. Therefore, a mechanized gait trainer enabling nonambulatory patients to have the repetitive practice of a gait-like movement without overstraining therapists was constructed. In this study, we developed an active gait training system for patients with gait disorder. This system provides joint movements to patients who cannot carry out an independent gait. It provides a normal stance-swing ratio of 60:40 using an eccentric configuration of two gears. Joint motions of the knee and the ankle were evaluated with using the 3D motion analysis system and compared with the results from the multi-body dynamics simulation. In addition, clinical investigations were also performed for low stroke patients during the 6-week gait training. Results from the dynamics simulation showed that joint movements of the knee and the ankle were affected by the gear size, the step length and the length of the foot plate, except the radius of curvature of the foot guide plate. Also, the 6-week gait training revealed relevant improvements of the gait ability in all low subjects. Functional ambulation category levels of subjects after training were 2 in three patients and 1 in a patient. The developed active gait trainer seems feasible as an adjunctive tool in gait rehabilitation after stroke.

인코더를 이용한 2축 각도 기반 보행 불균형 평가 시스템 연구

심현민(Hyeon-min Shim),김유현(Yoohyun Kim),조우형(Woo-Hyeong Cho),권장우(Jangwoo Kwon),이상민(Sangmin Lee) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.5

In this study, the gait imbalance evaluation algorithm based on two axes angle using encoder is proposed. This experiment was carried out to experiment with a healthy adult male to 10 people. The device is attached to the hip and knee joint in order to measure the angle during the gait. Normal and imbalance gait angle data were measured using an encoder attached to the hip and knee joints. Also, in order to verify the reliability of estimation of asymmetrical gait using hip and knee angle, it was compared with the result of asymmetrical gait estimation using foot pressure. SI (Symmetry Index) was used as an index for determining the gait imbalance. As a result, normal gait and 1.5cm imbalance gait were evaluation as normal gait through SI using an encoder. And imbalance gait of 3cm, 4cm, and 6cm were judge by imbalance gait. Whereas all gait experiments except normal gait were evaluation as imbalance gait through SI using the pressure. It was possible to determine both the normal gait and imbalance gait through measurement for the angle and the pressure.

가상현실환경에서 정상성인의 거울보행이 보행특성에 미치는 영향

이재호 대한통합의학회 2022 대한통합의학회지 Vol.10 No.3

Purpose : The study aims to see the effects of virtual reality and non-virtual reality in a normal person’s mirror walk on gait characteristics. Methods : Twenty male adults (Age; 27.8±5.8) took part in the study. The subjects attached reflection markers for motion analysis, and walked aware of the virtual reality environment with mirrors wearing goggles showing them virtual environments. After gait in a virtual environment, the subjects walked in a non-virtual environment with mirrors a certain distance away after taking a five minute break. To prevent the order effect cause by the experiential difference of gait order, ten subjects were chosen randomly into groups and the order was differentiated. In each gait, infrared camera was used to detect motion and the position of the markers were saved real time. Results : Comparison between virtual and non-virtual reality mirror walks showed that the movable range of leg joints (ankle, knee and hip joint), body joints (sacroiliac, atlantoaxial joint), arm joints (shoulder, wrist joint) showed meaningful differences. Temporal characteristics showed that virtual gaits speed were slower, and the cycle time and double limb support time of the gaits were longer. Furthermore, spacial characteristics showed that virtual gaits were shorter in steps length and strides length, the stride width longer and center of movement horizontally longer. Conclusion : The reduction in joint movement in virtual reality is due to adverse effects on balance and efficiency during gait. Also, the change in temporal-spatial characteristics of gait would be due to change in gait mechanisms for balance, showing that virtual gaits are more demanding than the other. However, the subject group is a normal group with no abnormality in gait ability and balance ability, and it is not clear whether the decrease in performance is the result of environment or fear. Therefore it is necessary to understand whether the subject group's improvement and fear affect the result in future studies.

Changes of Gait Variability by the Attention Demanding Task in Elderly Adults

( Sang Seok Yeo ) 대한물리치료학회 2017 대한물리치료학회지 Vol.29 No.6

Purpose: Gait variability is defined as the intrinsic fluctuations which occur during continuous gait cycles. Increased gait variability is closely associated with increased fall risk in older adults. This study investigated the influence of attention-demanding tasks on gait variability in elderly healthy adults. Methods: We recruited 15 healthy elderly adults in this study. All participants performed two cognitive tasks: a subtraction dual-task (SDT) and working memory dual-task (WMDT) during gait plus one normal gait. Using the LEGSys⁺ system, we measured the coefficient of variation (CV %=100×[standard deviation/mean]) for participants’ stride time, stride length, and stride velocity. Results: SDT gait showed significant increment of stride time variability compared with usual gait (p< 0.05), however, stride length and velocity variability did not difference between SDT gait and usual gait (p >0.05). WMDT gait showed significant increment of stride time and velocity variability compared with usual gait (p<0.05). In addition, stride time variability during WMDT gait also significantly increased compared with SDT gait (p<0.05). Conclusion: We reported that SDT and WMDT gait can induce the increment of the gait variability in elderly adults. We assume that attention demanding task based on working memory has the most influence on the interference between cognitive and gait function. Understanding the changes during dual task gait in older ages would be helpful for physical intervention strategies and improved risk assessment.