• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 추계학술대회 논문집
• /
• pp.1166-1171
• /
• 2004

In this study, the concept of autonomous mobility is applied to a gait support mobile robot. The aim of the development of the service robot is to assist the elderly with gait rehabilitation. This study proposes an ergonomic service robot design parameter. The gait assistant path pattern is derived from analysis of the elderly gait. A lever is installed in the AMR in order to measure both the pulling force and the leading force of the elderly. The path generation of the mobile robot is developed through consideration and analysis of elderly gait patterns. The ergonomic design parameters (dimensions, action scope and working space) are determined based on moving scope of the elderly. The gait assistant mobile robot was offered the elderly guide service and internet service based on the ergonomic design parameters.

• ETRI Journal
• /
• 제33권2호
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• 대한산업공학회지
• /
• 제33권4호
• /
• pp.480-486
• /
• 2007

A gait diagnosis supporting system is necessary to evaluate the characteristics of abnormal gait of a patient in a systematic and efficient manner. The present study developed a gait diagnosis supporting system which compares abnormal gait of a patient with a reference gait data and presents abnormal gait characteristics in an organized form. Three types of diagnosis modules were developed for the spatio-temporal, kinematic and kinetic gait parameters, and a gait data for Korean normal adults was used for the reference data of the system. The system was applied to evaluate the gait pattern of three arthritis patients and the abnormal gait characteristics of them could be easily identified with a systematic and graphical presentation.

• The Journal of Korean Physical Therapy
• /
• 제32권5호
• /
• pp.283-289
• /
• 2020

Objective: The purpose of this study was to determine the force of lower extremities, the change in walking ability on the ground by applying a walking training program based on perceptual learning to improve gait capacity of chronic stroke patients. Method: This study included Twenty-four patients with chronic stroke. Using a perceptual-based gait training, the experimental group trained twice a day for 30 minutes each time, 5 times a week, for a total of 8 weeks. The control group underwent ground gait training that excluded the element of a perceptual training for 30 minutes, 5 times a week for 8 weeks. Results: In the two groups, the maximum forefoot pressure after intervention was significantly different in both the LEPGT and GGT (p<0.05). The maximum midfoot pressure was significantly different in LEPGT (p<0.05). There was a significant difference in the maximum heel pressure after intervention between the two groups (p<0.05). As a result of comparing the change in step length and stride length after intervention in the two groups, there was a significant difference between the two groups (p<0.05). Conclusion: Both gait training programs was found that gait training based on perceptual learning and ground gait training were the training for improving the functional gait of stroke patient. Perceptual learning gait training utilizing intensive perceptual awareness was the training for improving gait capacity within the period than ground gait training.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 대한의용생체공학회:의공학회지
• /
• 제26권3호
• /
• pp.145-150
• /
• 2005

A new gait detection system using both FSR (force sensing resistor) sensors and a gyrosensor was developed to detect various gait patterns. FSR sensors were put in self-designed shoe insoles and a gyrosensor was attached to the heel of a shoe. An algorithm was also developed to determine eight different gait transitions during four gait phases: heel-strike, foot-flat, heel-off and swing. The developed system was evaluated from nine heathy mans and twelve hemiplegic patients. Healthy volunteers were asked to walk in various gait patterns: level walking, fore-foot walking and stair walking. Only the level walking was performed in hemiplegic patients. The gait detection system was compared with a optical motion analysis system and the outputs of the FSR sensors. In healthy subjects, the developed system detected successfully more than $99\%$ for both level walking and fore-foot walking. For stair walking, the successful detection rate of the system was above$97\%$. In hemiplegic patients, the developed system detected approximately 98% of gait transitions. The developed gait phase detection system will be helpful not only to determine pathological gait phases but also to apply prosthetics, orthotics and functional electrical stimulation for patients with various gait disorders.

• 한국정밀공학회지
• /
• 제32권12호
• /
• pp.1065-1072
• /
• 2015

This paper is about the development of an insole sensor system that can determine the model of an exoskeleton robot for lower limb that is a multi-degree of freedom system. First, the study analyzed the kinematic model of an exoskeleton robot for the lower limb that changes according to the gait phase detection of a human. Based on the ground reaction force (GRF), which is generated when walking, to proceed with insole sensor development, the sensing type, location, and the number of sensors were selected. The center of pressure (COP) of the human foot was understood first, prior to the development of algorithm. Using the COP, an algorithm was developed that is capable of detecting the gait phase with small number of sensors. An experiment at 3 km/h speed was conducted on the developed sensor system to evaluate the developed insole sensor system and the gait phase detection algorithm.

• 한국정밀공학회지
• /
• 제21권10호
• /
• pp.196-203
• /
• 2004

In this study, a new gait phase detection system using both FSR(Force Sensing Resister) sensors and a gyrosensor was developed to detect various gait patterns. FSR sensors were put in self-designed shoe insoles and a gyrosensor was attached to the posterior aspect of a shoe. An algorithm was also developed to determine eight different gait transitions among four gait phases: heel-strike, foot-flat, heel-off and swing. The developed system was compared with the conventional gait phase detection system using only FSR sensors in various gait experiments such as level walking, fore-foot walking and stair walking. In fore-foot walking and stair walking, the developed system showed much better accuracy and reliability to detect gait phases. The developed gait phase detection system using both FSR sensors and a gyrosensor will be helpful not only to determine pathological gait phases but to apply prosthetics, orthotics and functional electrical stimulation to patients with gait disorders.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.193-195
• /
• 2006

In this study, we developed an active controlled ankle-foot orthosis(AAFO) which can control the dorsiflexion/plantarflexion of the ankle joint during gait to prevent foot drop and toe drag for paralysis patients. To prevent dropping foot after heel strike, ankle joint was actively controlled to minimize forefoot collision with the ground. It was also controlled to provide toe clearance and to help push-off during late stance. The 3D gait analysis was performed on two healthy subjects equipped with the developed AAFO to compare with the normal gait and the conventional AFO gait. In the developed AAFO gait, differently from the conventional AFO gait, significant push-off was observed during pre-swing and the maximum flexion moment during pre-swing phase was similar to that of normal gait. A remarkable dorsiflexion also occurred during initial swing. These results indicated that the developed AAFO could have certain clinical benefits to prevent foot drop for paralysis patients, compared to conventional AFOs.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2008년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.73-74
• /
• 2008

In this study, we developed a robotic gait trainer which induces the active gait training based on predefined continuous proper lower extremity joint movements. AC servo motors and linear actuators were used to control hip and knee joints of patients and the weight support system was used to support the patient's weight during the gait training. We also implemented a Gill program to set the gait training pattern with several training parameters and to confirm states of patients and the system through the visual feedback. The effectiveness of the gait training system will be determined by the long-term clinical experiments in the future. We expect that the developed robotic gait training system could be applied very practically to recover gait abilities for persons with gait disorder.