• Journal of Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.333-341
• /
• 2018

In this paper, we propose an algorithm to automatically detect gait's joints. The proposed method classifies gait's types into front gait and flank gait so as to automatically detect gait's joints. And then according to classified types, the proposed applies joint extracting algorithm to input images. Firstly, we split input images into foreground image using difference images of Hue and gray-scale image of input and background one and extract gait's object. The proposed method classifies gaits into front gait and flank gait using ratio of Face's width to torso's width. Then classified gait's type, joints are detected 10 at front gait and detected 7~8 at flank gait. The proposed method is applied to the camera's input and the result shows that the proposed method automatically extracts joints.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.2
• /
• pp.17-26
• /
• 2018

In this paper, we propose a gait type classification method based on pressure sensor which reflects various terrain and velocity variations. In order to obtain stable gait classification performance, we divide the whole gait data into several steps by detecting the swing phase, and normalize each step. Then, we extract robust features for both topographic variation and speed variation by using the Null-LDA(Null-Space Linear Discriminant Analysis) method. The experimental results show that the proposed method gives a good performance of gait type classification even though there is a change in the gait velocity and the terrain.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.814-817
• /
• 2004

It is a challenging task to make the paraplegic to walk with out the assist of the caregiver. So, we have developed various type of gait orthosis for paraplegic during the five years lately. The purpose of this study ultimately is energy consumption test of serveral type gait orthosis for developing the high efficiency gait orthosis. From the experimental results, the oxygen consumption rate were 6.9$\pm$3.3ml/kg in RGO gait, 5.3$\pm$1.3ml/kg in PGO, and 6.2$\pm$3ml/kg in HGO gait. The maximum hip flexion angle were 16$^{\circ}$ in RGO , 15$^{\circ}$ in PGO, and 47.5$^{\circ}$. in HGO. As a result It was found that. Hybrid Gait Orthosis need high energy consumption more than PGO for walking, but it is small weight and strengthened muscle.

• Journal of the Korean Society of Physical Medicine
• /
• v.2 no.2
• /
• pp.161-171
• /
• 2007

Purpose : The purpose of this study was to evaluate the effect of footwear on gait in older adults. Methods : The footwear consists of loafer with fixation and mule and slipper without fixation. Twenty one female older adults voluntarily participated in this study. Each participant walked on the gait system GAITRite and measured temporal-spatial gait parameters. And the participants wore loafer, mule, slipper randomly. We measured stance time, swing time, heel-to-heel BOS, double support time, velocity, cadence, FAP as temporal-spatial gait parameters. Results : Three gait parameters showed significant difference statistically among 7 gait parameters. The stance time increased as loafer, mule, barefoot, slipper orderly. And there was a significant difference statistically (p<.05). The swing time increased as slipper, barefoot, mule, loafer orderly. And there was a significant difference statistically(p<.05). And the heel-to-heel BOS increased as barefoot, loafer, mule, slipper orderly. And there was a significant difference statistically(p<.05) according to footwear type. Conclusion : The footwear type with high stability like loafer is considered better than footwear type with low stability like mule and slipper for the elderly.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.29-38
• /
• 2022

This paper proposes a system for classifying gait types using an ensemble deep learning network for gait data measured by a smart insole equipped with multi-sensors. The gait type classification system consists of a part for normalizing the data measured by the insole, a part for extracting gait features using a deep learning network, and a part for classifying the gait type by inputting the extracted features. Two kinds of gait feature maps were extracted by independently learning networks based on CNNs and LSTMs with different characteristics. The final ensemble network classification results were obtained by combining the classification results. For the seven types of gait for adults in their 20s and 30s: walking, running, fast walking, going up and down stairs, and going up and down hills, multi-sensor data was classified into a proposed ensemble network. As a result, it was confirmed that the classification rate was higher than 90%.

• Journal of Korean Physical Therapy Science
• /
• v.9 no.1
• /
• pp.81-88
• /
• 2002

This paper presents a design and a control of a New Reciprocating Gait Orthosis and dynamic walking simulation for this system. The New Reciprocating Gait Orthosis is distinguished from other one by which has a very light-weight and a new RGO type with servo motors. The gait of a New Reciprocating Gait Orthosis depends on the constrains of mechanical kinematics and initial posture. The stability of dynamic walking is investigated by ZMP(Zero Moment Point) of the New Reciprocating Gait Orthosis. It is designed according to a human wear type and is able to accomodate itself to human environments. The joints of each leg are adopted with a good kinematic characteristics. To test of the analysis of joint kinematic properties, we did the strain stress analysis of dynamic PLS and the study of FEM with a dynamic PLS. It will be expect that the spinal card injury patients are able to train effectively with a Reciprocating Gait Orthosis. The New Reciprocating Gait Orthosis was able to keep smooth walling by the orthotic servo motors and hybrid system, make a sequence of flexion and extension of the joint during the walking. Also, the New Reciprocating Gait Orthosis turned out to be a satisfactory orthosis for walling training, for the spinal cord injury patient.

• Journal of Korean Physical Therapy Science
• /
• v.16 no.2
• /
• pp.27-37
• /
• 2009

Background: The musculoskeletal disorders with asymmetrical gait on the whole body are the most common. This study was designed to analyze that General Coordinative Manipulation Intervention Models would affect the balanced restoration of asymmetrical gait. Methods: 68 healthy volunteers(1st hypothesis: 46, 2nd hypothesis 22) participated in the two GCM intervention models, which have performed 2 times a week for 3 weeks. Digital Camera was used to measure the gait, and measurements were performed before and after the application of the each intervention model. Repeated measured ANOVA was used to determine a statistical significance. Results: The outcome of examining hypothesis is as follows: 1. The 1st hypothesis : GCM Intervention based on the coordinating the flexion type of upper body and the extension type of lower body will improve in the balanced restoration of asymmetrical gait because it offers a clear direction for treatment(p<.05). 2. The 2nd hypothesis: GCM Intervention based on the coordinating the flexion type of lower body and the extension type of upper body will improve in the balanced restoration of asymmetrical gait because it offers a clear direction for treatment(p<.05). Conclusion: GCM intervention programs on the two hypothesis groups have effects on the balanced restoration of asymmetrical gait(p<.05).

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.398-402
• /
• 1996

This paper addresses the design and the gait control of quadruped walking robot. First, we concern the mechanical and electronical(control system) hardware of walking robot, and the second is the results of experiments. The walking robot is the most suitable form to substitute fot human being. So walking robot is worthy of research. The quadruped walking robot and control system is the simplest type of walking robot, therefore we designed a small seale robot for realization of static gait. The robot is designed commpactly and its legs are constructed parallel link type and able to move freely in space. Control system consists of one upper level controller and four lower level controllers. The upper level controller plans the walking path and commands the low level controllers to follow the planned path. The main function of low level cotrollers is control of motors. Total number of motors is twealve and they operate four legs. And robot is ordered to walk and realize static wave gait.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.3
• /
• pp.123-130
• /
• 2021

PURPOSE: Robotic gait training is being used increasingly to improve the gross motor performance and gait speed. The present study examined the effectiveness of a novel end-effector type of robotic gait training (RGT) system on standing, walking, running, and jumping functions, as well as the gait speed in children with spastic cerebral palsy. METHODS: Eleven children with spastic cerebral palsy Gross Motor Function Classification System (GMFCS) levels I-III (6 males; age range, 15.09 ± 1.44 years) were examined. They underwent 24 sessions (30 minutes/sessions, one time/day, three days/week for eight consecutive weeks) of RGT. The Gross Motor Function Measure-88 D domain (GMFM D), and GMFM E were assessed with a pretest and posttest of RGT. The setting was a one-group pretest-posttest design. RESULTS: A comparison of the pre-test and post-test show that the outcomes in post-test of GMFM D (p < .01), GMFM E (p < .05), and 10MWT were improved significantly after RGT intervention. CONCLUSION: The present study provided the first evidence on the effects of an eight-weeks RGT intervention in participants with spastic CP. The outcomes of this clinical study showed that standing performance, locomotion function, and gait speed increased in after 24 sessions of the end-effector RGT system in children with spastic cerebral palsy.

• Annals of Geriatric Medicine and Research
• /
• v.21 no.1
• /
• pp.17-23
• /
• 2017

Background: In at-risk older adults, gait speed is an important factor associated with quality of life and falling risk. In this study, we assessed whether therapeutic exercise could improve gait speed. Methods: We conducted a meta-analysis to evaluate the 'best' therapeutic exercise method by analyzing each exercise in terms of intensity, type, and several gait speed indices. For the analysis, we gathered 122 papers through a database search and selected 9 (n=627) that were appropriate for the meta-analysis. Results: In 8 of the 9 included papers, gait speed improved with therapeutic exercise. Usual gait speed (n=246) improved more than maximal gait speed (n=574). A resistance program was more effective than a nonresistance program for improving maximal, but not usual, gait speed. We also found that the effects of therapeutic exercise were greater in noncommunity than in community-dwelling elderly people. Conclusion: In conclusion, therapeutic exercise was effective in improving gait speed.