• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권5호
• /
• pp.248-253
• /
• 2006

The purpose of this study is to develop a portable gait-event detection system which is necessary for the cycle-to-cycle FES(functional electrical stimulation) control of locomotion. To make the system portable, we made following modifications in the gait signal measurement system. That is, 1) to make the system wireless using Bluetooth communication, 2) to make the system small-sized and battery-powered by using low power consumption ${\mu}$ P(ATmega8535L). The gait-events were analyzed in off-line at the main computer using ANN(Artificial Neural Network). The Proposed system showed no mis-detection of the gait-events of normal subject and hemiplegia subjects. The performance of the system was better than the previous wired-system.

• 대한물리치료과학회지
• /
• 제18권3호
• /
• pp.33-39
• /
• 2011

Background : The purpose of this study was to apply cervical orthosis for temporal parameters of gait was to evaluate the effect. Methods : Seven normal adults participated in this study. Before and after applying a cervical orthosis compared to gait. Outcome measure were: general characteristics, temporal parameters of gait. General chacteristics included age, gender, height, weight. Temporal parameters included the Velocity cycle, Stride length, Step length, Cadence cycle, Initial double support time. Temporal parameters of gait, using the motion analysis system for cervical orthosis were evaluated before and after applying. The data was analyzed using SPSS 12.0 software and the Wilcoxon's signed-ranks test. Results : Velocity cycle and Step length were no significant differences(p>0.05). But Stride length, Cadence cycle, Initial double support time were significant(p<0.05). After apply Cervical orthosis in gait, Stride length and Initial double support time was decreased and Cadence cycle was increased. Conclusion : Changes in temporal of temporal parameters of gait was apply a cervical orthosis with the limitations of vision due to take effect. Therefore, Cervical orthosis does not interfere with the normal gait pattern by limiting the Range of Motion so that we consider to apply.

• 한국정밀공학회지
• /
• 제22권3호
• /
• pp.170-178
• /
• 2005

The purpose of this study is to develop a gait-event detection system, which is necessary for the cycle-to-cycle FES control of locomotion. Proposed gait event detection system consists of a signal measurement part and gait event detection part. The signal measurement was composed of the sensors and the LabVIEW program for the data acquisition and synchronization of the sensor signals. We also used a video camera and a motion capture system to get the reference gait events. Machine learning technique with ANN (artificial neural network) was adopted for automatic detection of gait events. 2 cycles of reference gait events were used as the teacher signals for ANN training and the remnants ($2\sim5$ cycles) were used fur the evaluation of the performance in gait-event detection. 14 combinations of sensor signals were used in the training and evaluation of ANN to examine the relationship between the number of sensors and the gait-event detection performance. The best combinations with minimum errors of event-detection time were 1) goniometer, foot-switch and 2) goniometer, foot-switch, accelerometer x(anterior-posterior) component. It is expected that the result of this study will be useful in the design of cycle-to-cycle FES controller.

• Journal of Information Processing Systems
• /
• 제15권4호
• /
• pp.957-966
• /
• 2019

This paper studies a novel approach to natural gait cycles based gait recognition via kernel Fisher discriminant analysis (KFDA), which can effectively calculate the features from gait sequences and accelerate the recognition process. The proposed approach firstly extracts the gait silhouettes through moving object detection and segmentation from each gait videos. Secondly, gait energy images (GEIs) are calculated for each gait videos, and used as gait features. Thirdly, KFDA method is used to refine the extracted gait features, and low-dimensional feature vectors for each gait videos can be got. The last is the nearest neighbor classifier is applied to classify. The proposed method is evaluated on the CASIA and USF gait databases, and the results show that our proposed algorithm can get better recognition effect than other existing algorithms.

• Annals of Clinical Neurophysiology
• /
• 제5권2호
• /
• pp.197-201
• /
• 2003

Background: The aim of this study is to present the basic reference data of kinematic gait analysis of normal Korean adults with 3 dimensional electrogoniometer, $Domotion^{(R)}$. Method: The basic kinematic gait parameters of hip, knee and ankle joints on the sagittal plane were obtained from 10 healthy adults with 5 repetition for each. Three-dimensional gait analysis was performed with $Domotion^{(R)}$ electrogoniometer in 10 meters long flat floor. Each data collected was processed with IBM PC equipped with gait analysis program. Results: Mean maximal hip flexion was $23.05^{\circ}{\pm}4.62^{\circ}$and mean maximal hip extension was $6.46^{\circ}{\pm}1.30^{\circ}$. Knee flexion was observed with two peak values. The first peak knee flexion was $6.50^{\circ}{\pm}2.07^{\circ}$ at 20.4% of gait cycle and the second peak flexion was $50.34^{\circ}{\pm}2.23^{\circ}$ at 75.8% of gait cycle. Mean maximum ankle dorsiflexion was $5.57^{\circ}{\pm}1.19^{\circ}$ at 44% of gait cycle and mean maximum ankle plantar flexion was $15.51^{\circ}{\pm}1.73^{\circ}$ at 68.5% of gait cycle. Conclusion: We concluded three dimensional gait analysis with electrogoniometer $Domotion^{(R)}$ offers a valid and reliable kinematic data and the application of this tools for clinical gait evaluation will be helpful in management of pathological gait.

• 대한골관절종양학회지
• /
• 제18권2호
• /
• pp.51-58
• /
• 2012

목적: 슬관절 주위에 발생한 골종양 환자에서 종양 대치물을 이용한 재건술의 결과와 보행 분석의 유용성을 알아보고자 하였다. 대상 및 방법: 2001년부터 2010년까지 슬관절 주위에 발생한 골종양에 대하여 광범위 절제술 후 종양 대치물을 이용한 재건술을 시행 받은 30명 중 7명을 대상으로 하였으며 기능적 결과 및 보행 분석 검사를 평가하였다. 결과: SF-36 점수는 신체적, 정신적 역할제한 항목에서 각각 100% (100점)으로 높은 점수를 보였으며 일반 건강상태, 신체적 기능 정도, 활력, 사회적 기능에서 낮은 점수를 나타냈다. 또한 MSTS 평가의 종합 평균 점수는 88.1% (23.8점[17-27])였다. 보행 분석 검사상 평균 보행속도 97.2 m/s, 평균 분속수 105.6 step/min, 평균 활보장 111.3 m, 평균 보장 61.5 cm, 유각기 39.8%cycle, 입각기 60.1%cycle, 평균 단하지 지지기 37.1%cycle, 평균 양하지 지지기 13.0%cycle, 평균 발 들림시기 60.7%cycle였다. 결론: 슬관절 주위 종양에 대한 광범위 절제술 후 종양 대치물을 이용한 재건술은 좋은 기능적결과를 기대할 수 있으며, 보행 분석 검사는 술후 환자의 상태를 정량적으로 평가함으로써 보행 모습 및 기능을 객관화 할 수 있는 한 방법으로 사료되며 기능적 평가 방법과 함께 치료 및 술 후 재활 계획을 세우는데 도움이 되리라 생각된다.

• 국제물리치료학회지
• /
• 제5권2호
• /
• pp.708-713
• /
• 2014

The aim of this research was to investigate how the effects of body supported treadmill training with visual feedback affect the gait factors of stroke patients. Thirty subjects (21 male, 9 female) with a diagnosis of stroke were taken to the hospital to participate in this study. The subjects received body supported treadmill training with visual feedback. The training was executed for 6 minutes, 3 times a day per week for 19 weeks after general exercise. The effects of the visual feedback in the body supported treadmill training were evaluated by measuring the average gait cycle and the average step length of the affected and unaffected. The collected data were statistically analyzed by using a paired t-test. The results of this study were a significant improvement of the average gait cycle and no statistically significant difference of the average step length. The gait cycle average had a statistically significant difference in gender, age, etiology, paretic side, and step length average. There was no statistically significant difference in infarction within etiology. Therefore, it was necessary to apply the easy and simple with the treadmill training in the rehabilitation of the stroke patients. This study will require a variety of outcome measures related to the effects of treadmill training with gait factors.

• 대한통합의학회지
• /
• 제10권1호
• /
• pp.91-99
• /
• 2022

Purpose : The goal of this study is to examine the effect of robot assisted gait training (RAGT) on the kinematic factors (temporospatial gait parameters, gait cycle ratio, and gait line length) of gait in stroke patients. Methods : The subjects of this study were 24 stroke patients selected by inclusion criteria. Participants were randomly allocated to two groups: robot assisted gait training (n=11) and general neurological physical therapy group (n=11). In the robot-assisted gait training group, robot-assisted gait training was mediated for 30 minutes a day in addition to general neurological physical therapy. The general neurological physical therapy group was mediated by general neurological physical therapy for 30 minutes a day in addition to general neurological physical therapy. The number of interventions was 5 times a week for 5 weeks. In order to compare the kinematic factors of walking between the two groups, gait analysis was performed before and after 5 weeks of training using the Zebris gait analysis system. Results : As a result of the gait analysis of the two groups, there were significant differences in temporospatial gait variables (step length, stride length, step width, step time, stride time), gait cycle ratio (swing phase, stance phase) and gait line length. However, there was no significant difference in the cadence (temporospatial gait parameters) in the robot assisted gait training group compared to general neurological physical therapy group. Conclusion : It is considered to be a useful treatment for stroke patients to promote the recovery of gait function in stroke patients. Based on the results of this study, continuous robot assisted gait training treatment is considered to have a positive effect on gait ability, the goal of stroke rehabilitation. In the future, additional studies should be conducted on many subjects of stroke patients, the kinematic factors of the legs according to the severity of stroke and treatment period, and the effect of gait training.

• 한국멀티미디어학회논문지
• /
• 제11권6호
• /
• pp.787-795
• /
• 2008

Human recognition on camera is an interesting topic in computer vision. While fingerprint and face recognition have been become common, gait is considered as a new biometric feature for distance recognition. In this paper, we propose a gait recognition algorithm based on the knee angle, 2 feet distance, walking velocity and head direction of a person who appear in camera view on one gait cycle. The background subtraction method firstly use for binary moving object extraction and then base on it we continue detect the leg region, head region and get gait features (leg angle, leg swing amplitude). Another feature, walking speed, also can be detected after a gait cycle finished. And then, we compute the errors between calculated features and stored features for recognition. This method gives good results when we performed testing using indoor and outdoor landscape in both lateral, oblique view.

• 한국정밀공학회지
• /
• 제20권1호
• /
• pp.36-42
• /
• 2003